Merge tag 'kvm-s390-master-6.0-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

PCI interpretation compile fixes

52 files changed, 1444 insertions, 512 deletions

diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 3bb134355874..316917b98707 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -75,9 +75,11 @@ struct kvm_regs {
 
 /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
 #define KVM_ARM_DEVICE_TYPE_SHIFT	0
-#define KVM_ARM_DEVICE_TYPE_MASK	(0xffff << KVM_ARM_DEVICE_TYPE_SHIFT)
+#define KVM_ARM_DEVICE_TYPE_MASK	GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \
+						KVM_ARM_DEVICE_TYPE_SHIFT)
 #define KVM_ARM_DEVICE_ID_SHIFT		16
-#define KVM_ARM_DEVICE_ID_MASK		(0xffff << KVM_ARM_DEVICE_ID_SHIFT)
+#define KVM_ARM_DEVICE_ID_MASK		GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \
+						KVM_ARM_DEVICE_ID_SHIFT)
 
 /* Supported device IDs */
 #define KVM_ARM_DEVICE_VGIC_V2		0
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 7a6b14874d65..a73cf01a1606 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -74,6 +74,7 @@ struct kvm_s390_io_adapter_req {
 #define KVM_S390_VM_CRYPTO		2
 #define KVM_S390_VM_CPU_MODEL		3
 #define KVM_S390_VM_MIGRATION		4
+#define KVM_S390_VM_CPU_TOPOLOGY	5
 
 /* kvm attributes for mem_ctrl */
 #define KVM_S390_VM_MEM_ENABLE_CMMA	0
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 8323ac5b7eee..235dc85c91c3 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -219,7 +219,7 @@
 #define X86_FEATURE_IBRS		( 7*32+25) /* Indirect Branch Restricted Speculation */
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 or above (Zen) */
+#define X86_FEATURE_ZEN			(7*32+28) /* "" CPU based on Zen microarchitecture */
 #define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 #define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
 #define X86_FEATURE_MSR_IA32_FEAT_CTL	( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
@@ -303,7 +303,7 @@
 #define X86_FEATURE_RETHUNK		(11*32+14) /* "" Use REturn THUNK */
 #define X86_FEATURE_UNRET		(11*32+15) /* "" AMD BTB untrain return */
 #define X86_FEATURE_USE_IBPB_FW		(11*32+16) /* "" Use IBPB during runtime firmware calls */
-#define X86_FEATURE_RSB_VMEXIT_LITE	(11*32+17) /* "" Fill RSB on VM-Exit when EIBRS is enabled */
+#define X86_FEATURE_RSB_VMEXIT_LITE	(11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
@@ -354,6 +354,7 @@
 #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_X2AVIC		(15*32+18) /* Virtual x2apic */
 #define X86_FEATURE_V_SPEC_CTRL		(15*32+20) /* Virtual SPEC_CTRL */
 #define X86_FEATURE_SVME_ADDR_CHK	(15*32+28) /* "" SVME addr check */
 
@@ -457,5 +458,6 @@
 #define X86_BUG_SRBDS			X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
 #define X86_BUG_MMIO_STALE_DATA		X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */
 #define X86_BUG_RETBLEED		X86_BUG(26) /* CPU is affected by RETBleed */
+#define X86_BUG_EIBRS_PBRSB		X86_BUG(27) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index e057e039173c..6674bdb096f3 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -235,6 +235,12 @@
 #define PERF_CAP_PT_IDX			16
 
 #define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
+#define PERF_CAP_PEBS_TRAP             BIT_ULL(6)
+#define PERF_CAP_ARCH_REG              BIT_ULL(7)
+#define PERF_CAP_PEBS_FORMAT           0xf00
+#define PERF_CAP_PEBS_BASELINE         BIT_ULL(14)
+#define PERF_CAP_PEBS_MASK	(PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \
+				 PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE)
 
 #define MSR_IA32_RTIT_CTL		0x00000570
 #define RTIT_CTL_TRACEEN		BIT(0)
@@ -392,6 +398,7 @@
 #define MSR_TURBO_ACTIVATION_RATIO	0x0000064C
 
 #define MSR_PLATFORM_ENERGY_STATUS	0x0000064D
+#define MSR_SECONDARY_TURBO_RATIO_LIMIT	0x00000650
 
 #define MSR_PKG_WEIGHTED_CORE_C0_RES	0x00000658
 #define MSR_PKG_ANY_CORE_C0_RES		0x00000659
@@ -1022,6 +1029,7 @@
 #define MSR_IA32_VMX_TRUE_EXIT_CTLS      0x0000048f
 #define MSR_IA32_VMX_TRUE_ENTRY_CTLS     0x00000490
 #define MSR_IA32_VMX_VMFUNC             0x00000491
+#define MSR_IA32_VMX_PROCBASED_CTLS3	0x00000492
 
 /* VMX_BASIC bits and bitmasks */
 #define VMX_BASIC_VMCS_SIZE_SHIFT	32
diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h
index fee7983a90b4..11ff975242ca 100644
--- a/tools/arch/x86/include/asm/rmwcc.h
+++ b/tools/arch/x86/include/asm/rmwcc.h
@@ -2,8 +2,6 @@
 #ifndef _TOOLS_LINUX_ASM_X86_RMWcc
 #define _TOOLS_LINUX_ASM_X86_RMWcc
 
-#ifdef CONFIG_CC_HAS_ASM_GOTO
-
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
 	asm_volatile_goto (fullop "; j" cc " %l[cc_label]"		\
@@ -20,23 +18,4 @@ cc_label:								\
 #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
 	__GEN_RMWcc(op " %1, " arg0, var, cc, vcon (val))
 
-#else /* !CONFIG_CC_HAS_ASM_GOTO */
-
-#define __GEN_RMWcc(fullop, var, cc, ...)				\
-do {									\
-	char c;								\
-	asm volatile (fullop "; set" cc " %1"				\
-			: "+m" (var), "=qm" (c)				\
-			: __VA_ARGS__ : "memory");			\
-	return c != 0;							\
-} while (0)
-
-#define GEN_UNARY_RMWcc(op, var, arg0, cc)				\
-	__GEN_RMWcc(op " " arg0, var, cc)
-
-#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
-	__GEN_RMWcc(op " %2, " arg0, var, cc, vcon (val))
-
-#endif /* CONFIG_CC_HAS_ASM_GOTO */
-
 #endif /* _TOOLS_LINUX_ASM_X86_RMWcc */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index ec53c9fa1da9..46de10a809ec 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -306,7 +306,8 @@ struct kvm_pit_state {
 	struct kvm_pit_channel_state channels[3];
 };
 
-#define KVM_PIT_FLAGS_HPET_LEGACY  0x00000001
+#define KVM_PIT_FLAGS_HPET_LEGACY     0x00000001
+#define KVM_PIT_FLAGS_SPEAKER_DATA_ON 0x00000002
 
 struct kvm_pit_state2 {
 	struct kvm_pit_channel_state channels[3];
@@ -325,6 +326,7 @@ struct kvm_reinject_control {
 #define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
 #define KVM_VCPUEVENT_VALID_SMM		0x00000008
 #define KVM_VCPUEVENT_VALID_PAYLOAD	0x00000010
+#define KVM_VCPUEVENT_VALID_TRIPLE_FAULT	0x00000020
 
 /* Interrupt shadow states */
 #define KVM_X86_SHADOW_INT_MOV_SS	0x01
@@ -359,7 +361,10 @@ struct kvm_vcpu_events {
 		__u8 smm_inside_nmi;
 		__u8 latched_init;
 	} smi;
-	__u8 reserved[27];
+	struct {
+		__u8 pending;
+	} triple_fault;
+	__u8 reserved[26];
 	__u8 exception_has_payload;
 	__u64 exception_payload;
 };
@@ -434,6 +439,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_OUT_7E_INC_RIP		(1 << 3)
 #define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT	(1 << 4)
 #define KVM_X86_QUIRK_FIX_HYPERCALL_INSN	(1 << 5)
+#define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS	(1 << 6)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index 946d761adbd3..a5faf6d88f1b 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -91,6 +91,7 @@
 #define EXIT_REASON_UMWAIT              67
 #define EXIT_REASON_TPAUSE              68
 #define EXIT_REASON_BUS_LOCK            74
+#define EXIT_REASON_NOTIFY              75
 
 #define VMX_EXIT_REASONS \
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -153,7 +154,8 @@
 	{ EXIT_REASON_XRSTORS,               "XRSTORS" }, \
 	{ EXIT_REASON_UMWAIT,                "UMWAIT" }, \
 	{ EXIT_REASON_TPAUSE,                "TPAUSE" }, \
-	{ EXIT_REASON_BUS_LOCK,              "BUS_LOCK" }
+	{ EXIT_REASON_BUS_LOCK,              "BUS_LOCK" }, \
+	{ EXIT_REASON_NOTIFY,                "NOTIFY" }
 
 #define VMX_EXIT_REASON_FLAGS \
 	{ VMX_EXIT_REASONS_FAILED_VMENTRY,	"FAILED_VMENTRY" }
diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h
index 24ae3054f304..1bdd834bdd57 100644
--- a/tools/include/linux/compiler_types.h
+++ b/tools/include/linux/compiler_types.h
@@ -36,4 +36,8 @@
 #include <linux/compiler-gcc.h>
 #endif
 
+#ifndef asm_volatile_goto
+#define asm_volatile_goto(x...) asm goto(x)
+#endif
+
 #endif /* __LINUX_COMPILER_TYPES_H */
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index b28ff5d88145..520ad2691a99 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -751,14 +751,27 @@ typedef struct drm_i915_irq_wait {
 
 /* Must be kept compact -- no holes and well documented */
 
-typedef struct drm_i915_getparam {
+/**
+ * struct drm_i915_getparam - Driver parameter query structure.
+ */
+struct drm_i915_getparam {
+	/** @param: Driver parameter to query. */
 	__s32 param;
-	/*
+
+	/**
+	 * @value: Address of memory where queried value should be put.
+	 *
 	 * WARNING: Using pointers instead of fixed-size u64 means we need to write
 	 * compat32 code. Don't repeat this mistake.
 	 */
 	int __user *value;
-} drm_i915_getparam_t;
+};
+
+/**
+ * typedef drm_i915_getparam_t - Driver parameter query structure.
+ * See struct drm_i915_getparam.
+ */
+typedef struct drm_i915_getparam drm_i915_getparam_t;
 
 /* Ioctl to set kernel params:
  */
@@ -1239,76 +1252,119 @@ struct drm_i915_gem_exec_object2 {
 	__u64 rsvd2;
 };
 
+/**
+ * struct drm_i915_gem_exec_fence - An input or output fence for the execbuf
+ * ioctl.
+ *
+ * The request will wait for input fence to signal before submission.
+ *
+ * The returned output fence will be signaled after the completion of the
+ * request.
+ */
 struct drm_i915_gem_exec_fence {
-	/**
-	 * User's handle for a drm_syncobj to wait on or signal.
-	 */
+	/** @handle: User's handle for a drm_syncobj to wait on or signal. */
 	__u32 handle;
 
+	/**
+	 * @flags: Supported flags are:
+	 *
+	 * I915_EXEC_FENCE_WAIT:
+	 * Wait for the input fence before request submission.
+	 *
+	 * I915_EXEC_FENCE_SIGNAL:
+	 * Return request completion fence as output
+	 */
+	__u32 flags;
 #define I915_EXEC_FENCE_WAIT            (1<<0)
 #define I915_EXEC_FENCE_SIGNAL          (1<<1)
 #define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SIGNAL << 1))
-	__u32 flags;
 };
 
-/*
- * See drm_i915_gem_execbuffer_ext_timeline_fences.
- */
-#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
-
-/*
+/**
+ * struct drm_i915_gem_execbuffer_ext_timeline_fences - Timeline fences
+ * for execbuf ioctl.
+ *
  * This structure describes an array of drm_syncobj and associated points for
  * timeline variants of drm_syncobj. It is invalid to append this structure to
  * the execbuf if I915_EXEC_FENCE_ARRAY is set.
  */
 struct drm_i915_gem_execbuffer_ext_timeline_fences {
+#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
+	/** @base: Extension link. See struct i915_user_extension. */
 	struct i915_user_extension base;
 
 	/**
-	 * Number of element in the handles_ptr & value_ptr arrays.
+	 * @fence_count: Number of elements in the @handles_ptr & @value_ptr
+	 * arrays.
 	 */
 	__u64 fence_count;
 
 	/**
-	 * Pointer to an array of struct drm_i915_gem_exec_fence of length
-	 * fence_count.
+	 * @handles_ptr: Pointer to an array of struct drm_i915_gem_exec_fence
+	 * of length @fence_count.
 	 */
 	__u64 handles_ptr;
 
 	/**
-	 * Pointer to an array of u64 values of length fence_count. Values
-	 * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline
-	 * drm_syncobj is invalid as it turns a drm_syncobj into a binary one.
+	 * @values_ptr: Pointer to an array of u64 values of length
+	 * @fence_count.
+	 * Values must be 0 for a binary drm_syncobj. A Value of 0 for a
+	 * timeline drm_syncobj is invalid as it turns a drm_syncobj into a
+	 * binary one.
 	 */
 	__u64 values_ptr;
 };
 
+/**
+ * struct drm_i915_gem_execbuffer2 - Structure for DRM_I915_GEM_EXECBUFFER2
+ * ioctl.
+ */
 struct drm_i915_gem_execbuffer2 {
-	/**
-	 * List of gem_exec_object2 structs
-	 */
+	/** @buffers_ptr: Pointer to a list of gem_exec_object2 structs */
 	__u64 buffers_ptr;
+
+	/** @buffer_count: Number of elements in @buffers_ptr array */
 	__u32 buffer_count;
 
-	/** Offset in the batchbuffer to start execution from. */
+	/**
+	 * @batch_start_offset: Offset in the batchbuffer to start execution
+	 * from.
+	 */
 	__u32 batch_start_offset;
-	/** Bytes used in batchbuffer from batch_start_offset */
+
+	/**
+	 * @batch_len: Length in bytes of the batch buffer, starting from the
+	 * @batch_start_offset. If 0, length is assumed to be the batch buffer
+	 * object size.
+	 */
 	__u32 batch_len;
+
+	/** @DR1: deprecated */
 	__u32 DR1;
+
+	/** @DR4: deprecated */
 	__u32 DR4;
+
+	/** @num_cliprects: See @cliprects_ptr */
 	__u32 num_cliprects;
+
 	/**
-	 * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
-	 * & I915_EXEC_USE_EXTENSIONS are not set.
+	 * @cliprects_ptr: Kernel clipping was a DRI1 misfeature.
+	 *
+	 * It is invalid to use this field if I915_EXEC_FENCE_ARRAY or
+	 * I915_EXEC_USE_EXTENSIONS flags are not set.
 	 *
 	 * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array
-	 * of struct drm_i915_gem_exec_fence and num_cliprects is the length
-	 * of the array.
+	 * of &drm_i915_gem_exec_fence and @num_cliprects is the length of the
+	 * array.
 	 *
 	 * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a
-	 * single struct i915_user_extension and num_cliprects is 0.
+	 * single &i915_user_extension and num_cliprects is 0.
 	 */
 	__u64 cliprects_ptr;
+
+	/** @flags: Execbuf flags */
+	__u64 flags;
 #define I915_EXEC_RING_MASK              (0x3f)
 #define I915_EXEC_DEFAULT                (0<<0)
 #define I915_EXEC_RENDER                 (1<<0)
@@ -1326,10 +1382,6 @@ struct drm_i915_gem_execbuffer2 {
 #define I915_EXEC_CONSTANTS_REL_GENERAL (0<<6) /* default */
 #define I915_EXEC_CONSTANTS_ABSOLUTE 	(1<<6)
 #define I915_EXEC_CONSTANTS_REL_SURFACE (2<<6) /* gen4/5 only */
-	__u64 flags;
-	__u64 rsvd1; /* now used for context info */
-	__u64 rsvd2;
-};
 
 /** Resets the SO write offset registers for transform feedback on gen7. */
 #define I915_EXEC_GEN7_SOL_RESET	(1<<8)
@@ -1432,9 +1484,23 @@ struct drm_i915_gem_execbuffer2 {
  * drm_i915_gem_execbuffer_ext enum.
  */
 #define I915_EXEC_USE_EXTENSIONS	(1 << 21)
-
 #define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1))
 
+	/** @rsvd1: Context id */
+	__u64 rsvd1;
+
+	/**
+	 * @rsvd2: in and out sync_file file descriptors.
+	 *
+	 * When I915_EXEC_FENCE_IN or I915_EXEC_FENCE_SUBMIT flag is set, the
+	 * lower 32 bits of this field will have the in sync_file fd (input).
+	 *
+	 * When I915_EXEC_FENCE_OUT flag is set, the upper 32 bits of this
+	 * field will have the out sync_file fd (output).
+	 */
+	__u64 rsvd2;
+};
+
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
 	(eb2).rsvd1 = context & I915_EXEC_CONTEXT_ID_MASK
@@ -1814,19 +1880,58 @@ struct drm_i915_gem_context_create {
 	__u32 pad;
 };
 
+/**
+ * struct drm_i915_gem_context_create_ext - Structure for creating contexts.
+ */
 struct drm_i915_gem_context_create_ext {
-	__u32 ctx_id; /* output: id of new context*/
+	/** @ctx_id: Id of the created context (output) */
+	__u32 ctx_id;
+
+	/**
+	 * @flags: Supported flags are:
+	 *
+	 * I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS:
+	 *
+	 * Extensions may be appended to this structure and driver must check
+	 * for those. See @extensions.
+	 *
+	 * I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE
+	 *
+	 * Created context will have single timeline.
+	 */
 	__u32 flags;
 #define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS	(1u << 0)
 #define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE	(1u << 1)
 #define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \
 	(-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1))
+
+	/**
+	 * @extensions: Zero-terminated chain of extensions.
+	 *
+	 * I915_CONTEXT_CREATE_EXT_SETPARAM:
+	 * Context parameter to set or query during context creation.
+	 * See struct drm_i915_gem_context_create_ext_setparam.
+	 *
+	 * I915_CONTEXT_CREATE_EXT_CLONE:
+	 * This extension has been removed. On the off chance someone somewhere
+	 * has attempted to use it, never re-use this extension number.
+	 */
 	__u64 extensions;
+#define I915_CONTEXT_CREATE_EXT_SETPARAM 0
+#define I915_CONTEXT_CREATE_EXT_CLONE 1
 };
 
+/**
+ * struct drm_i915_gem_context_param - Context parameter to set or query.
+ */
 struct drm_i915_gem_context_param {
+	/** @ctx_id: Context id */
 	__u32 ctx_id;
+
+	/** @size: Size of the parameter @value */
 	__u32 size;
+
+	/** @param: Parameter to set or query */
 	__u64 param;
 #define I915_CONTEXT_PARAM_BAN_PERIOD	0x1
 /* I915_CONTEXT_PARAM_NO_ZEROMAP has been removed.  On the off chance
@@ -1973,6 +2078,7 @@ struct drm_i915_gem_context_param {
 #define I915_CONTEXT_PARAM_PROTECTED_CONTENT    0xd
 /* Must be kept compact -- no holes and well documented */
 
+	/** @value: Context parameter value to be set or queried */
 	__u64 value;
 };
 
@@ -2371,23 +2477,29 @@ struct i915_context_param_engines {
 	struct i915_engine_class_instance engines[N__]; \
 } __attribute__((packed)) name__
 
+/**
+ * struct drm_i915_gem_context_create_ext_setparam - Context parameter
+ * to set or query during context creation.
+ */
 struct drm_i915_gem_context_create_ext_setparam {
-#define I915_CONTEXT_CREATE_EXT_SETPARAM 0
+	/** @base: Extension link. See struct i915_user_extension. */
 	struct i915_user_extension base;
+
+	/**
+	 * @param: Context parameter to set or query.
+	 * See struct drm_i915_gem_context_param.
+	 */
 	struct drm_i915_gem_context_param param;
 };
 
-/* This API has been removed.  On the off chance someone somewhere has
- * attempted to use it, never re-use this extension number.
- */
-#define I915_CONTEXT_CREATE_EXT_CLONE 1
-
 struct drm_i915_gem_context_destroy {
 	__u32 ctx_id;
 	__u32 pad;
 };
 
-/*
+/**
+ * struct drm_i915_gem_vm_control - Structure to create or destroy VM.
+ *
  * DRM_I915_GEM_VM_CREATE -
  *
  * Create a new virtual memory address space (ppGTT) for use within a context
@@ -2397,20 +2509,23 @@ struct drm_i915_gem_context_destroy {
  * The id of new VM (bound to the fd) for use with I915_CONTEXT_PARAM_VM is
  * returned in the outparam @id.
  *
- * No flags are defined, with all bits reserved and must be zero.
- *
  * An extension chain maybe provided, starting with @extensions, and terminated
  * by the @next_extension being 0. Currently, no extensions are defined.
  *
  * DRM_I915_GEM_VM_DESTROY -
  *
- * Destroys a previously created VM id, specified in @id.
+ * Destroys a previously created VM id, specified in @vm_id.
  *
  * No extensions or flags are allowed currently, and so must be zero.
  */
 struct drm_i915_gem_vm_control {
+	/** @extensions: Zero-terminated chain of extensions. */
 	__u64 extensions;
+
+	/** @flags: reserved for future usage, currently MBZ */
 	__u32 flags;
+
+	/** @vm_id: Id of the VM created or to be destroyed */
 	__u32 vm_id;
 };
 
@@ -3207,36 +3322,6 @@ struct drm_i915_gem_memory_class_instance {
  * struct drm_i915_memory_region_info - Describes one region as known to the
  * driver.
  *
- * Note that we reserve some stuff here for potential future work. As an example
- * we might want expose the capabilities for a given region, which could include
- * things like if the region is CPU mappable/accessible, what are the supported
- * mapping types etc.
- *
- * Note that to extend struct drm_i915_memory_region_info and struct
- * drm_i915_query_memory_regions in the future the plan is to do the following:
- *
- * .. code-block:: C
- *
- *	struct drm_i915_memory_region_info {
- *		struct drm_i915_gem_memory_class_instance region;
- *		union {
- *			__u32 rsvd0;
- *			__u32 new_thing1;
- *		};
- *		...
- *		union {
- *			__u64 rsvd1[8];
- *			struct {
- *				__u64 new_thing2;
- *				__u64 new_thing3;
- *				...
- *			};
- *		};
- *	};
- *
- * With this things should remain source compatible between versions for
- * userspace, even as we add new fields.
- *
  * Note this is using both struct drm_i915_query_item and struct drm_i915_query.
  * For this new query we are adding the new query id DRM_I915_QUERY_MEMORY_REGIONS
  * at &drm_i915_query_item.query_id.
@@ -3248,14 +3333,81 @@ struct drm_i915_memory_region_info {
 	/** @rsvd0: MBZ */
 	__u32 rsvd0;
 
-	/** @probed_size: Memory probed by the driver (-1 = unknown) */
+	/**
+	 * @probed_size: Memory probed by the driver
+	 *
+	 * Note that it should not be possible to ever encounter a zero value
+	 * here, also note that no current region type will ever return -1 here.
+	 * Although for future region types, this might be a possibility. The
+	 * same applies to the other size fields.
+	 */
 	__u64 probed_size;
 
-	/** @unallocated_size: Estimate of memory remaining (-1 = unknown) */
+	/**
+	 * @unallocated_size: Estimate of memory remaining
+	 *
+	 * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable accounting.
+	 * Without this (or if this is an older kernel) the value here will
+	 * always equal the @probed_size. Note this is only currently tracked
+	 * for I915_MEMORY_CLASS_DEVICE regions (for other types the value here
+	 * will always equal the @probed_size).
+	 */
 	__u64 unallocated_size;
 
-	/** @rsvd1: MBZ */
-	__u64 rsvd1[8];
+	union {
+		/** @rsvd1: MBZ */
+		__u64 rsvd1[8];
+		struct {
+			/**
+			 * @probed_cpu_visible_size: Memory probed by the driver
+			 * that is CPU accessible.
+			 *
+			 * This will be always be <= @probed_size, and the
+			 * remainder (if there is any) will not be CPU
+			 * accessible.
+			 *
+			 * On systems without small BAR, the @probed_size will
+			 * always equal the @probed_cpu_visible_size, since all
+			 * of it will be CPU accessible.
+			 *
+			 * Note this is only tracked for
+			 * I915_MEMORY_CLASS_DEVICE regions (for other types the
+			 * value here will always equal the @probed_size).
+			 *
+			 * Note that if the value returned here is zero, then
+			 * this must be an old kernel which lacks the relevant
+			 * small-bar uAPI support (including
+			 * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS), but on
+			 * such systems we should never actually end up with a
+			 * small BAR configuration, assuming we are able to load
+			 * the kernel module. Hence it should be safe to treat
+			 * this the same as when @probed_cpu_visible_size ==
+			 * @probed_size.
+			 */
+			__u64 probed_cpu_visible_size;
+
+			/**
+			 * @unallocated_cpu_visible_size: Estimate of CPU
+			 * visible memory remaining.
+			 *
+			 * Note this is only tracked for
+			 * I915_MEMORY_CLASS_DEVICE regions (for other types the
+			 * value here will always equal the
+			 * @probed_cpu_visible_size).
+			 *
+			 * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable
+			 * accounting.  Without this the value here will always
+			 * equal the @probed_cpu_visible_size. Note this is only
+			 * currently tracked for I915_MEMORY_CLASS_DEVICE
+			 * regions (for other types the value here will also
+			 * always equal the @probed_cpu_visible_size).
+			 *
+			 * If this is an older kernel the value here will be
+			 * zero, see also @probed_cpu_visible_size.
+			 */
+			__u64 unallocated_cpu_visible_size;
+		};
+	};
 };
 
 /**
@@ -3329,11 +3481,11 @@ struct drm_i915_query_memory_regions {
  * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added
  * extension support using struct i915_user_extension.
  *
- * Note that in the future we want to have our buffer flags here, at least for
- * the stuff that is immutable. Previously we would have two ioctls, one to
- * create the object with gem_create, and another to apply various parameters,
- * however this creates some ambiguity for the params which are considered
- * immutable. Also in general we're phasing out the various SET/GET ioctls.
+ * Note that new buffer flags should be added here, at least for the stuff that
+ * is immutable. Previously we would have two ioctls, one to create the object
+ * with gem_create, and another to apply various parameters, however this
+ * creates some ambiguity for the params which are considered immutable. Also in
+ * general we're phasing out the various SET/GET ioctls.
  */
 struct drm_i915_gem_create_ext {
 	/**
@@ -3341,7 +3493,6 @@ struct drm_i915_gem_create_ext {
 	 *
 	 * The (page-aligned) allocated size for the object will be returned.
 	 *
-	 *
 	 * DG2 64K min page size implications:
 	 *
 	 * On discrete platforms, starting from DG2, we have to contend with GTT
@@ -3353,7 +3504,9 @@ struct drm_i915_gem_create_ext {
 	 *
 	 * Note that the returned size here will always reflect any required
 	 * rounding up done by the kernel, i.e 4K will now become 64K on devices
-	 * such as DG2.
+	 * such as DG2. The kernel will always select the largest minimum
+	 * page-size for the set of possible placements as the value to use when
+	 * rounding up the @size.
 	 *
 	 * Special DG2 GTT address alignment requirement:
 	 *
@@ -3377,14 +3530,58 @@ struct drm_i915_gem_create_ext {
 	 * is deemed to be a good compromise.
 	 */
 	__u64 size;
+
 	/**
 	 * @handle: Returned handle for the object.
 	 *
 	 * Object handles are nonzero.
 	 */
 	__u32 handle;
-	/** @flags: MBZ */
+
+	/**
+	 * @flags: Optional flags.
+	 *
+	 * Supported values:
+	 *
+	 * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS - Signal to the kernel that
+	 * the object will need to be accessed via the CPU.
+	 *
+	 * Only valid when placing objects in I915_MEMORY_CLASS_DEVICE, and only
+	 * strictly required on configurations where some subset of the device
+	 * memory is directly visible/mappable through the CPU (which we also
+	 * call small BAR), like on some DG2+ systems. Note that this is quite
+	 * undesirable, but due to various factors like the client CPU, BIOS etc
+	 * it's something we can expect to see in the wild. See
+	 * &drm_i915_memory_region_info.probed_cpu_visible_size for how to
+	 * determine if this system applies.
+	 *
+	 * Note that one of the placements MUST be I915_MEMORY_CLASS_SYSTEM, to
+	 * ensure the kernel can always spill the allocation to system memory,
+	 * if the object can't be allocated in the mappable part of
+	 * I915_MEMORY_CLASS_DEVICE.
+	 *
+	 * Also note that since the kernel only supports flat-CCS on objects
+	 * that can *only* be placed in I915_MEMORY_CLASS_DEVICE, we therefore
+	 * don't support I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS together with
+	 * flat-CCS.
+	 *
+	 * Without this hint, the kernel will assume that non-mappable
+	 * I915_MEMORY_CLASS_DEVICE is preferred for this object. Note that the
+	 * kernel can still migrate the object to the mappable part, as a last
+	 * resort, if userspace ever CPU faults this object, but this might be
+	 * expensive, and so ideally should be avoided.
+	 *
+	 * On older kernels which lack the relevant small-bar uAPI support (see
+	 * also &drm_i915_memory_region_info.probed_cpu_visible_size),
+	 * usage of the flag will result in an error, but it should NEVER be
+	 * possible to end up with a small BAR configuration, assuming we can
+	 * also successfully load the i915 kernel module. In such cases the
+	 * entire I915_MEMORY_CLASS_DEVICE region will be CPU accessible, and as
+	 * such there are zero restrictions on where the object can be placed.
+	 */
+#define I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS (1 << 0)
 	__u32 flags;
+
 	/**
 	 * @extensions: The chain of extensions to apply to this object.
 	 *
@@ -3443,6 +3640,22 @@ struct drm_i915_gem_create_ext {
  * At which point we get the object handle in &drm_i915_gem_create_ext.handle,
  * along with the final object size in &drm_i915_gem_create_ext.size, which
  * should account for any rounding up, if required.
+ *
+ * Note that userspace has no means of knowing the current backing region
+ * for objects where @num_regions is larger than one. The kernel will only
+ * ensure that the priority order of the @regions array is honoured, either
+ * when initially placing the object, or when moving memory around due to
+ * memory pressure
+ *
+ * On Flat-CCS capable HW, compression is supported for the objects residing
+ * in I915_MEMORY_CLASS_DEVICE. When such objects (compressed) have other
+ * memory class in @regions and migrated (by i915, due to memory
+ * constraints) to the non I915_MEMORY_CLASS_DEVICE region, then i915 needs to
+ * decompress the content. But i915 doesn't have the required information to
+ * decompress the userspace compressed objects.
+ *
+ * So i915 supports Flat-CCS, on the objects which can reside only on
+ * I915_MEMORY_CLASS_DEVICE regions.
  */
 struct drm_i915_gem_create_ext_memory_regions {
 	/** @base: Extension link. See struct i915_user_extension. */
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 9f4428be3e36..a756b29afcc2 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -27,7 +27,8 @@
 #define FSCRYPT_MODE_AES_128_CBC		5
 #define FSCRYPT_MODE_AES_128_CTS		6
 #define FSCRYPT_MODE_ADIANTUM			9
-/* If adding a mode number > 9, update FSCRYPT_MODE_MAX in fscrypt_private.h */
+#define FSCRYPT_MODE_AES_256_HCTR2		10
+/* If adding a mode number > 10, update FSCRYPT_MODE_MAX in fscrypt_private.h */
 
 /*
  * Legacy policy version; ad-hoc KDF and no key verification.
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index cb6e3846d27b..eed0315a77a6 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -270,6 +270,8 @@ struct kvm_xen_exit {
 #define KVM_EXIT_X86_BUS_LOCK     33
 #define KVM_EXIT_XEN              34
 #define KVM_EXIT_RISCV_SBI        35
+#define KVM_EXIT_RISCV_CSR        36
+#define KVM_EXIT_NOTIFY           37
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -496,6 +498,18 @@ struct kvm_run {
 			unsigned long args[6];
 			unsigned long ret[2];
 		} riscv_sbi;
+		/* KVM_EXIT_RISCV_CSR */
+		struct {
+			unsigned long csr_num;
+			unsigned long new_value;
+			unsigned long write_mask;
+			unsigned long ret_value;
+		} riscv_csr;
+		/* KVM_EXIT_NOTIFY */
+		struct {
+#define KVM_NOTIFY_CONTEXT_INVALID	(1 << 0)
+			__u32 flags;
+		} notify;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1157,6 +1171,12 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_VM_TSC_CONTROL 214
 #define KVM_CAP_SYSTEM_EVENT_DATA 215
 #define KVM_CAP_ARM_SYSTEM_SUSPEND 216
+#define KVM_CAP_S390_PROTECTED_DUMP 217
+#define KVM_CAP_X86_TRIPLE_FAULT_EVENT 218
+#define KVM_CAP_X86_NOTIFY_VMEXIT 219
+#define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220
+#define KVM_CAP_S390_ZPCI_OP 221
+#define KVM_CAP_S390_CPU_TOPOLOGY 222
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1660,6 +1680,55 @@ struct kvm_s390_pv_unp {
 	__u64 tweak;
 };
 
+enum pv_cmd_dmp_id {
+	KVM_PV_DUMP_INIT,
+	KVM_PV_DUMP_CONFIG_STOR_STATE,
+	KVM_PV_DUMP_COMPLETE,
+	KVM_PV_DUMP_CPU,
+};
+
+struct kvm_s390_pv_dmp {
+	__u64 subcmd;
+	__u64 buff_addr;
+	__u64 buff_len;
+	__u64 gaddr;		/* For dump storage state */
+	__u64 reserved[4];
+};
+
+enum pv_cmd_info_id {
+	KVM_PV_INFO_VM,
+	KVM_PV_INFO_DUMP,
+};
+
+struct kvm_s390_pv_info_dump {
+	__u64 dump_cpu_buffer_len;
+	__u64 dump_config_mem_buffer_per_1m;
+	__u64 dump_config_finalize_len;
+};
+
+struct kvm_s390_pv_info_vm {
+	__u64 inst_calls_list[4];
+	__u64 max_cpus;
+	__u64 max_guests;
+	__u64 max_guest_addr;
+	__u64 feature_indication;
+};
+
+struct kvm_s390_pv_info_header {
+	__u32 id;
+	__u32 len_max;
+	__u32 len_written;
+	__u32 reserved;
+};
+
+struct kvm_s390_pv_info {
+	struct kvm_s390_pv_info_header header;
+	union {
+		struct kvm_s390_pv_info_dump dump;
+		struct kvm_s390_pv_info_vm vm;
+	};
+};
+
 enum pv_cmd_id {
 	KVM_PV_ENABLE,
 	KVM_PV_DISABLE,
@@ -1668,6 +1737,8 @@ enum pv_cmd_id {
 	KVM_PV_VERIFY,
 	KVM_PV_PREP_RESET,
 	KVM_PV_UNSHARE_ALL,
+	KVM_PV_INFO,
+	KVM_PV_DUMP,
 };
 
 struct kvm_pv_cmd {
@@ -2119,4 +2190,41 @@ struct kvm_stats_desc {
 /* Available with KVM_CAP_XSAVE2 */
 #define KVM_GET_XSAVE2		  _IOR(KVMIO,  0xcf, struct kvm_xsave)
 
+/* Available with KVM_CAP_S390_PROTECTED_DUMP */
+#define KVM_S390_PV_CPU_COMMAND	_IOWR(KVMIO, 0xd0, struct kvm_pv_cmd)
+
+/* Available with KVM_CAP_X86_NOTIFY_VMEXIT */
+#define KVM_X86_NOTIFY_VMEXIT_ENABLED		(1ULL << 0)
+#define KVM_X86_NOTIFY_VMEXIT_USER		(1ULL << 1)
+
+/* Available with KVM_CAP_S390_ZPCI_OP */
+#define KVM_S390_ZPCI_OP         _IOW(KVMIO,  0xd1, struct kvm_s390_zpci_op)
+
+struct kvm_s390_zpci_op {
+	/* in */
+	__u32 fh;               /* target device */
+	__u8  op;               /* operation to perform */
+	__u8  pad[3];
+	union {
+		/* for KVM_S390_ZPCIOP_REG_AEN */
+		struct {
+			__u64 ibv;      /* Guest addr of interrupt bit vector */
+			__u64 sb;       /* Guest addr of summary bit */
+			__u32 flags;
+			__u32 noi;      /* Number of interrupts */
+			__u8 isc;       /* Guest interrupt subclass */
+			__u8 sbo;       /* Offset of guest summary bit vector */
+			__u16 pad;
+		} reg_aen;
+		__u64 reserved[8];
+	} u;
+};
+
+/* types for kvm_s390_zpci_op->op */
+#define KVM_S390_ZPCIOP_REG_AEN                0
+#define KVM_S390_ZPCIOP_DEREG_AEN      1
+
+/* flags for kvm_s390_zpci_op->u.reg_aen.flags */
+#define KVM_S390_ZPCIOP_REGAEN_HOST    (1 << 0)
+
 #endif /* __LINUX_KVM_H */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index e2b77fbca91e..581ed4bdc062 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -301,6 +301,7 @@ enum {
  *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
  *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		id;           } && PERF_FORMAT_ID
+ *	  { u64		lost;         } && PERF_FORMAT_LOST
  *	} && !PERF_FORMAT_GROUP
  *
  *	{ u64		nr;
@@ -308,6 +309,7 @@ enum {
  *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		value;
  *	    { u64	id;           } && PERF_FORMAT_ID
+ *	    { u64	lost;         } && PERF_FORMAT_LOST
  *	  }		cntr[nr];
  *	} && PERF_FORMAT_GROUP
  * };
@@ -317,8 +319,9 @@ enum perf_event_read_format {
 	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
 	PERF_FORMAT_ID				= 1U << 2,
 	PERF_FORMAT_GROUP			= 1U << 3,
+	PERF_FORMAT_LOST			= 1U << 4,
 
-	PERF_FORMAT_MAX = 1U << 4,		/* non-ABI */
+	PERF_FORMAT_MAX = 1U << 5,		/* non-ABI */
 };
 
 #define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index cab645d4a645..f9f115a7c75b 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -171,4 +171,13 @@
 #define VHOST_VDPA_SET_GROUP_ASID	_IOW(VHOST_VIRTIO, 0x7C, \
 					     struct vhost_vring_state)
 
+/* Suspend a device so it does not process virtqueue requests anymore
+ *
+ * After the return of ioctl the device must preserve all the necessary state
+ * (the virtqueue vring base plus the possible device specific states) that is
+ * required for restoring in the future. The device must not change its
+ * configuration after that point.
+ */
+#define VHOST_VDPA_SUSPEND		_IO(VHOST_VIRTIO, 0x7D)
+
 #endif
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index 384d5e076ee4..6cd0be7c1bb4 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -309,7 +309,7 @@ bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
 	return perf_cpu_map__idx(cpus, cpu) != -1;
 }
 
-struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map)
+struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map)
 {
 	struct perf_cpu result = {
 		.cpu = -1
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index 952f3520d5c2..8ce5bbd09666 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -305,6 +305,9 @@ int perf_evsel__read_size(struct perf_evsel *evsel)
 	if (read_format & PERF_FORMAT_ID)
 		entry += sizeof(u64);
 
+	if (read_format & PERF_FORMAT_LOST)
+		entry += sizeof(u64);
+
 	if (read_format & PERF_FORMAT_GROUP) {
 		nr = evsel->nr_members;
 		size += sizeof(u64);
@@ -314,24 +317,98 @@ int perf_evsel__read_size(struct perf_evsel *evsel)
 	return size;
 }
 
+/* This only reads values for the leader */
+static int perf_evsel__read_group(struct perf_evsel *evsel, int cpu_map_idx,
+				  int thread, struct perf_counts_values *count)
+{
+	size_t size = perf_evsel__read_size(evsel);
+	int *fd = FD(evsel, cpu_map_idx, thread);
+	u64 read_format = evsel->attr.read_format;
+	u64 *data;
+	int idx = 1;
+
+	if (fd == NULL || *fd < 0)
+		return -EINVAL;
+
+	data = calloc(1, size);
+	if (data == NULL)
+		return -ENOMEM;
+
+	if (readn(*fd, data, size) <= 0) {
+		free(data);
+		return -errno;
+	}
+
+	/*
+	 * This reads only the leader event intentionally since we don't have
+	 * perf counts values for sibling events.
+	 */
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		count->ena = data[idx++];
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		count->run = data[idx++];
+
+	/* value is always available */
+	count->val = data[idx++];
+	if (read_format & PERF_FORMAT_ID)
+		count->id = data[idx++];
+	if (read_format & PERF_FORMAT_LOST)
+		count->lost = data[idx++];
+
+	free(data);
+	return 0;
+}
+
+/*
+ * The perf read format is very flexible.  It needs to set the proper
+ * values according to the read format.
+ */
+static void perf_evsel__adjust_values(struct perf_evsel *evsel, u64 *buf,
+				      struct perf_counts_values *count)
+{
+	u64 read_format = evsel->attr.read_format;
+	int n = 0;
+
+	count->val = buf[n++];
+
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		count->ena = buf[n++];
+
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		count->run = buf[n++];
+
+	if (read_format & PERF_FORMAT_ID)
+		count->id = buf[n++];
+
+	if (read_format & PERF_FORMAT_LOST)
+		count->lost = buf[n++];
+}
+
 int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
 		     struct perf_counts_values *count)
 {
 	size_t size = perf_evsel__read_size(evsel);
 	int *fd = FD(evsel, cpu_map_idx, thread);
+	u64 read_format = evsel->attr.read_format;
+	struct perf_counts_values buf;
 
 	memset(count, 0, sizeof(*count));
 
 	if (fd == NULL || *fd < 0)
 		return -EINVAL;
 
+	if (read_format & PERF_FORMAT_GROUP)
+		return perf_evsel__read_group(evsel, cpu_map_idx, thread, count);
+
 	if (MMAP(evsel, cpu_map_idx, thread) &&
+	    !(read_format & (PERF_FORMAT_ID | PERF_FORMAT_LOST)) &&
 	    !perf_mmap__read_self(MMAP(evsel, cpu_map_idx, thread), count))
 		return 0;
 
-	if (readn(*fd, count->values, size) <= 0)
+	if (readn(*fd, buf.values, size) <= 0)
 		return -errno;
 
+	perf_evsel__adjust_values(evsel, buf.values, count);
 	return 0;
 }
 
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 24de795b09bb..03aceb72a783 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -23,7 +23,7 @@ LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
 LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
 LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
-LIBPERF_API struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map);
+LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map);
 LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
 
 #define perf_cpu_map__for_each_cpu(cpu, idx, cpus)		\
diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index 556bb06798f2..93bf93a59c99 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -6,6 +6,7 @@
 #include <linux/types.h>
 #include <linux/limits.h>
 #include <linux/bpf.h>
+#include <linux/compiler.h>
 #include <sys/types.h> /* pid_t */
 
 #define event_contains(obj, mem) ((obj).header.size > offsetof(typeof(obj), mem))
@@ -76,7 +77,7 @@ struct perf_record_lost_samples {
 };
 
 /*
- * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID
+ * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID | PERF_FORMAT_LOST
  */
 struct perf_record_read {
 	struct perf_event_header header;
@@ -85,6 +86,7 @@ struct perf_record_read {
 	__u64			 time_enabled;
 	__u64			 time_running;
 	__u64			 id;
+	__u64			 lost;
 };
 
 struct perf_record_throttle {
@@ -153,22 +155,60 @@ enum {
 	PERF_CPU_MAP__MASK = 1,
 };
 
+/*
+ * Array encoding of a perf_cpu_map where nr is the number of entries in cpu[]
+ * and each entry is a value for a CPU in the map.
+ */
 struct cpu_map_entries {
 	__u16			 nr;
 	__u16			 cpu[];
 };
 
-struct perf_record_record_cpu_map {
+/* Bitmap encoding of a perf_cpu_map where bitmap entries are 32-bit. */
+struct perf_record_mask_cpu_map32 {
+	/* Number of mask values. */
+	__u16			 nr;
+	/* Constant 4. */
+	__u16			 long_size;
+	/* Bitmap data. */
+	__u32			 mask[];
+};
+
+/* Bitmap encoding of a perf_cpu_map where bitmap entries are 64-bit. */
+struct perf_record_mask_cpu_map64 {
+	/* Number of mask values. */
 	__u16			 nr;
+	/* Constant 8. */
 	__u16			 long_size;
-	unsigned long		 mask[];
+	/* Legacy padding. */
+	char                     __pad[4];
+	/* Bitmap data. */
+	__u64			 mask[];
 };
 
-struct perf_record_cpu_map_data {
+/*
+ * 'struct perf_record_cpu_map_data' is packed as unfortunately an earlier
+ * version had unaligned data and we wish to retain file format compatibility.
+ * -irogers
+ */
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wpacked"
+#pragma GCC diagnostic ignored "-Wattributes"
+
+struct __packed perf_record_cpu_map_data {
 	__u16			 type;
-	char			 data[];
+	union {
+		/* Used when type == PERF_CPU_MAP__CPUS. */
+		struct cpu_map_entries cpus_data;
+		/* Used when type == PERF_CPU_MAP__MASK and long_size == 4. */
+		struct perf_record_mask_cpu_map32 mask32_data;
+		/* Used when type == PERF_CPU_MAP__MASK and long_size == 8. */
+		struct perf_record_mask_cpu_map64 mask64_data;
+	};
 };
 
+#pragma GCC diagnostic pop
+
 struct perf_record_cpu_map {
 	struct perf_event_header	 header;
 	struct perf_record_cpu_map_data	 data;
diff --git a/tools/lib/perf/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h
index 699c0ed97d34..6f92204075c2 100644
--- a/tools/lib/perf/include/perf/evsel.h
+++ b/tools/lib/perf/include/perf/evsel.h
@@ -18,8 +18,10 @@ struct perf_counts_values {
 			uint64_t val;
 			uint64_t ena;
 			uint64_t run;
+			uint64_t id;
+			uint64_t lost;
 		};
-		uint64_t values[3];
+		uint64_t values[5];
 	};
 };
 
diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c
index 89be89afb24d..a11fc51bfb68 100644
--- a/tools/lib/perf/tests/test-evsel.c
+++ b/tools/lib/perf/tests/test-evsel.c
@@ -1,10 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdarg.h>
 #include <stdio.h>
+#include <string.h>
 #include <linux/perf_event.h>
+#include <linux/kernel.h>
 #include <perf/cpumap.h>
 #include <perf/threadmap.h>
 #include <perf/evsel.h>
+#include <internal/evsel.h>
 #include <internal/tests.h>
 #include "tests.h"
 
@@ -189,6 +192,163 @@ static int test_stat_user_read(int event)
 	return 0;
 }
 
+static int test_stat_read_format_single(struct perf_event_attr *attr, struct perf_thread_map *threads)
+{
+	struct perf_evsel *evsel;
+	struct perf_counts_values counts;
+	volatile int count = 0x100000;
+	int err;
+
+	evsel = perf_evsel__new(attr);
+	__T("failed to create evsel", evsel);
+
+	/* skip old kernels that don't support the format */
+	err = perf_evsel__open(evsel, NULL, threads);
+	if (err < 0)
+		return 0;
+
+	while (count--) ;
+
+	memset(&counts, -1, sizeof(counts));
+	perf_evsel__read(evsel, 0, 0, &counts);
+
+	__T("failed to read value", counts.val);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		__T("failed to read TOTAL_TIME_ENABLED", counts.ena);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		__T("failed to read TOTAL_TIME_RUNNING", counts.run);
+	if (attr->read_format & PERF_FORMAT_ID)
+		__T("failed to read ID", counts.id);
+	if (attr->read_format & PERF_FORMAT_LOST)
+		__T("failed to read LOST", counts.lost == 0);
+
+	perf_evsel__close(evsel);
+	perf_evsel__delete(evsel);
+	return 0;
+}
+
+static int test_stat_read_format_group(struct perf_event_attr *attr, struct perf_thread_map *threads)
+{
+	struct perf_evsel *leader, *member;
+	struct perf_counts_values counts;
+	volatile int count = 0x100000;
+	int err;
+
+	attr->read_format |= PERF_FORMAT_GROUP;
+	leader = perf_evsel__new(attr);
+	__T("failed to create leader", leader);
+
+	attr->read_format &= ~PERF_FORMAT_GROUP;
+	member = perf_evsel__new(attr);
+	__T("failed to create member", member);
+
+	member->leader = leader;
+	leader->nr_members = 2;
+
+	/* skip old kernels that don't support the format */
+	err = perf_evsel__open(leader, NULL, threads);
+	if (err < 0)
+		return 0;
+	err = perf_evsel__open(member, NULL, threads);
+	if (err < 0)
+		return 0;
+
+	while (count--) ;
+
+	memset(&counts, -1, sizeof(counts));
+	perf_evsel__read(leader, 0, 0, &counts);
+
+	__T("failed to read leader value", counts.val);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		__T("failed to read leader TOTAL_TIME_ENABLED", counts.ena);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		__T("failed to read leader TOTAL_TIME_RUNNING", counts.run);
+	if (attr->read_format & PERF_FORMAT_ID)
+		__T("failed to read leader ID", counts.id);
+	if (attr->read_format & PERF_FORMAT_LOST)
+		__T("failed to read leader LOST", counts.lost == 0);
+
+	memset(&counts, -1, sizeof(counts));
+	perf_evsel__read(member, 0, 0, &counts);
+
+	__T("failed to read member value", counts.val);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		__T("failed to read member TOTAL_TIME_ENABLED", counts.ena);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		__T("failed to read member TOTAL_TIME_RUNNING", counts.run);
+	if (attr->read_format & PERF_FORMAT_ID)
+		__T("failed to read member ID", counts.id);
+	if (attr->read_format & PERF_FORMAT_LOST)
+		__T("failed to read member LOST", counts.lost == 0);
+
+	perf_evsel__close(member);
+	perf_evsel__close(leader);
+	perf_evsel__delete(member);
+	perf_evsel__delete(leader);
+	return 0;
+}
+
+static int test_stat_read_format(void)
+{
+	struct perf_thread_map *threads;
+	struct perf_event_attr attr = {
+		.type	= PERF_TYPE_SOFTWARE,
+		.config	= PERF_COUNT_SW_TASK_CLOCK,
+	};
+	int err, i;
+
+#define FMT(_fmt)  PERF_FORMAT_ ## _fmt
+#define FMT_TIME  (FMT(TOTAL_TIME_ENABLED) | FMT(TOTAL_TIME_RUNNING))
+
+	uint64_t test_formats [] = {
+		0,
+		FMT_TIME,
+		FMT(ID),
+		FMT(LOST),
+		FMT_TIME | FMT(ID),
+		FMT_TIME | FMT(LOST),
+		FMT_TIME | FMT(ID) | FMT(LOST),
+		FMT(ID) | FMT(LOST),
+	};
+
+#undef FMT
+#undef FMT_TIME
+
+	threads = perf_thread_map__new_dummy();
+	__T("failed to create threads", threads);
+
+	perf_thread_map__set_pid(threads, 0, 0);
+
+	for (i = 0; i < (int)ARRAY_SIZE(test_formats); i++) {
+		attr.read_format = test_formats[i];
+		__T_VERBOSE("testing single read with read_format: %lx\n",
+			    (unsigned long)test_formats[i]);
+
+		err = test_stat_read_format_single(&attr, threads);
+		__T("failed to read single format", err == 0);
+	}
+
+	perf_thread_map__put(threads);
+
+	threads = perf_thread_map__new_array(2, NULL);
+	__T("failed to create threads", threads);
+
+	perf_thread_map__set_pid(threads, 0, 0);
+	perf_thread_map__set_pid(threads, 1, 0);
+
+	for (i = 0; i < (int)ARRAY_SIZE(test_formats); i++) {
+		attr.read_format = test_formats[i];
+		__T_VERBOSE("testing group read with read_format: %lx\n",
+			    (unsigned long)test_formats[i]);
+
+		err = test_stat_read_format_group(&attr, threads);
+		__T("failed to read group format", err == 0);
+	}
+
+	perf_thread_map__put(threads);
+	return 0;
+}
+
 int test_evsel(int argc, char **argv)
 {
 	__T_START;
@@ -200,6 +360,7 @@ int test_evsel(int argc, char **argv)
 	test_stat_thread_enable();
 	test_stat_user_read(PERF_COUNT_HW_INSTRUCTIONS);
 	test_stat_user_read(PERF_COUNT_HW_CPU_CYCLES);
+	test_stat_read_format();
 
 	__T_END;
 	return tests_failed == 0 ? 0 : -1;
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 91678252a9b6..e55fdf952a3a 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -162,32 +162,34 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
 
 	/*
 	 * Unfortunately these have to be hard coded because the noreturn
-	 * attribute isn't provided in ELF data.
+	 * attribute isn't provided in ELF data. Keep 'em sorted.
 	 */
 	static const char * const global_noreturns[] = {
+		"__invalid_creds",
+		"__module_put_and_kthread_exit",
+		"__reiserfs_panic",
 		"__stack_chk_fail",
-		"panic",
+		"__ubsan_handle_builtin_unreachable",
+		"cpu_bringup_and_idle",
+		"cpu_startup_entry",
 		"do_exit",
+		"do_group_exit",
 		"do_task_dead",
-		"kthread_exit",
-		"make_task_dead",
-		"__module_put_and_kthread_exit",
+		"ex_handler_msr_mce",
+		"fortify_panic",
 		"kthread_complete_and_exit",
-		"__reiserfs_panic",
+		"kthread_exit",
+		"kunit_try_catch_throw",
 		"lbug_with_loc",
-		"fortify_panic",
-		"usercopy_abort",
 		"machine_real_restart",
+		"make_task_dead",
+		"panic",
 		"rewind_stack_and_make_dead",
-		"kunit_try_catch_throw",
-		"xen_start_kernel",
-		"cpu_bringup_and_idle",
-		"do_group_exit",
+		"sev_es_terminate",
+		"snp_abort",
 		"stop_this_cpu",
-		"__invalid_creds",
-		"cpu_startup_entry",
-		"__ubsan_handle_builtin_unreachable",
-		"ex_handler_msr_mce",
+		"usercopy_abort",
+		"xen_start_kernel",
 	};
 
 	if (!func)
diff --git a/tools/perf/Documentation/intel-hybrid.txt b/tools/perf/Documentation/intel-hybrid.txt
index c9302096dc46..e7a776ad25d7 100644
--- a/tools/perf/Documentation/intel-hybrid.txt
+++ b/tools/perf/Documentation/intel-hybrid.txt
@@ -21,11 +21,6 @@ cat /sys/devices/cpu_atom/cpus
 
 It indicates cpu0-cpu15 are core cpus and cpu16-cpu23 are atom cpus.
 
-Quickstart
-
-List hybrid event
------------------
-
 As before, use perf-list to list the symbolic event.
 
 perf list
@@ -40,7 +35,6 @@ the event is belong to. Same event name but with different pmu can
 be supported.
 
 Enable hybrid event with a specific pmu
----------------------------------------
 
 To enable a core only event or atom only event, following syntax is supported:
 
@@ -53,7 +47,6 @@ For example, count the 'cycles' event on core cpus.
 	perf stat -e cpu_core/cycles/
 
 Create two events for one hardware event automatically
-------------------------------------------------------
 
 When creating one event and the event is available on both atom and core,
 two events are created automatically. One is for atom, the other is for
@@ -132,7 +125,6 @@ For perf-stat result, it displays two events:
 The first 'cycles' is core event, the second 'cycles' is atom event.
 
 Thread mode example:
---------------------
 
 perf-stat reports the scaled counts for hybrid event and with a percentage
 displayed. The percentage is the event's running time/enabling time.
@@ -176,14 +168,12 @@ perf_event_attr:
        604,097,080      cpu_atom/cycles/                                              (99.57%)
 
 perf-record:
-------------
 
 If there is no '-e' specified in perf record, on hybrid platform,
 it creates two default 'cycles' and adds them to event list. One
 is for core, the other is for atom.
 
 perf-stat:
-----------
 
 If there is no '-e' specified in perf stat, on hybrid platform,
 besides of software events, following events are created and
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 099817ef5150..0228efc96686 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -397,6 +397,9 @@ following filters are defined:
 	- abort_tx: only when the target is a hardware transaction abort
 	- cond: conditional branches
 	- save_type: save branch type during sampling in case binary is not available later
+		     For the platforms with Intel Arch LBR support (12th-Gen+ client or
+		     4th-Gen Xeon+ server), the save branch type is unconditionally enabled
+		     when the taken branch stack sampling is enabled.
 
 +
 The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.
@@ -757,8 +760,6 @@ events in data directory files. Option specified with no or empty value
 defaults to CPU layout. Masks defined or provided by the option value are
 filtered through the mask provided by -C option.
 
-include::intel-hybrid.txt[]
-
 --debuginfod[=URLs]::
 	Specify debuginfod URL to be used when cacheing perf.data binaries,
 	it follows the same syntax as the DEBUGINFOD_URLS variable, like:
@@ -778,6 +779,8 @@ include::intel-hybrid.txt[]
 	only, as of now.  So the applications built without the frame
 	pointer might see bogus addresses.
 
+include::intel-hybrid.txt[]
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 0661a1cf9855..2171f02daf59 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -265,7 +265,7 @@ endif
 # defined. get-executable-or-default fails with an error if the first argument is supplied but
 # doesn't exist.
 override PYTHON_CONFIG := $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON_AUTO))
-override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_AUTO)))
+override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_CONFIG)))
 
 grep-libs  = $(filter -l%,$(1))
 strip-libs  = $(filter-out -l%,$(1))
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 2f6cd1b8b662..a5cf243c337f 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -3355,7 +3355,8 @@ static bool schedstat_events_exposed(void)
 static int __cmd_record(int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
-	const char **rec_argv;
+	char **rec_argv;
+	const char **rec_argv_copy;
 	const char * const record_args[] = {
 		"record",
 		"-a",
@@ -3384,6 +3385,7 @@ static int __cmd_record(int argc, const char **argv)
 		ARRAY_SIZE(schedstat_args) : 0;
 
 	struct tep_event *waking_event;
+	int ret;
 
 	/*
 	 * +2 for either "-e", "sched:sched_wakeup" or
@@ -3391,14 +3393,18 @@ static int __cmd_record(int argc, const char **argv)
 	 */
 	rec_argc = ARRAY_SIZE(record_args) + 2 + schedstat_argc + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
-
 	if (rec_argv == NULL)
 		return -ENOMEM;
+	rec_argv_copy = calloc(rec_argc + 1, sizeof(char *));
+	if (rec_argv_copy == NULL) {
+		free(rec_argv);
+		return -ENOMEM;
+	}
 
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = strdup(record_args[i]);
 
-	rec_argv[i++] = "-e";
+	rec_argv[i++] = strdup("-e");
 	waking_event = trace_event__tp_format("sched", "sched_waking");
 	if (!IS_ERR(waking_event))
 		rec_argv[i++] = strdup("sched:sched_waking");
@@ -3409,11 +3415,19 @@ static int __cmd_record(int argc, const char **argv)
 		rec_argv[i++] = strdup(schedstat_args[j]);
 
 	for (j = 1; j < (unsigned int)argc; j++, i++)
-		rec_argv[i] = argv[j];
+		rec_argv[i] = strdup(argv[j]);
 
 	BUG_ON(i != rec_argc);
 
-	return cmd_record(i, rec_argv);
+	memcpy(rec_argv_copy, rec_argv, sizeof(char *) * rec_argc);
+	ret = cmd_record(rec_argc, rec_argv_copy);
+
+	for (i = 0; i < rec_argc; i++)
+		free(rec_argv[i]);
+	free(rec_argv);
+	free(rec_argv_copy);
+
+	return ret;
 }
 
 int cmd_sched(int argc, const char **argv)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7fb81a44672d..54cd29d07ca8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -826,6 +826,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	}
 
 	evlist__for_each_entry(evsel_list, counter) {
+		counter->reset_group = false;
 		if (bpf_counter__load(counter, &target))
 			return -1;
 		if (!evsel__is_bpf(counter))
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index f94929ebb54b..7ea150cdc137 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -17,21 +17,23 @@ static int process_event_mask(struct perf_tool *tool __maybe_unused,
 			 struct machine *machine __maybe_unused)
 {
 	struct perf_record_cpu_map *map_event = &event->cpu_map;
-	struct perf_record_record_cpu_map *mask;
 	struct perf_record_cpu_map_data *data;
 	struct perf_cpu_map *map;
 	int i;
+	unsigned int long_size;
 
 	data = &map_event->data;
 
 	TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__MASK);
 
-	mask = (struct perf_record_record_cpu_map *)data->data;
+	long_size = data->mask32_data.long_size;
 
-	TEST_ASSERT_VAL("wrong nr",   mask->nr == 1);
+	TEST_ASSERT_VAL("wrong long_size", long_size == 4 || long_size == 8);
+
+	TEST_ASSERT_VAL("wrong nr",   data->mask32_data.nr == 1);
 
 	for (i = 0; i < 20; i++) {
-		TEST_ASSERT_VAL("wrong cpu", test_bit(i, mask->mask));
+		TEST_ASSERT_VAL("wrong cpu", perf_record_cpu_map_data__test_bit(i, data));
 	}
 
 	map = cpu_map__new_data(data);
@@ -51,7 +53,6 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 			 struct machine *machine __maybe_unused)
 {
 	struct perf_record_cpu_map *map_event = &event->cpu_map;
-	struct cpu_map_entries *cpus;
 	struct perf_record_cpu_map_data *data;
 	struct perf_cpu_map *map;
 
@@ -59,11 +60,9 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 
 	TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__CPUS);
 
-	cpus = (struct cpu_map_entries *)data->data;
-
-	TEST_ASSERT_VAL("wrong nr",   cpus->nr == 2);
-	TEST_ASSERT_VAL("wrong cpu",  cpus->cpu[0] == 1);
-	TEST_ASSERT_VAL("wrong cpu",  cpus->cpu[1] == 256);
+	TEST_ASSERT_VAL("wrong nr",   data->cpus_data.nr == 2);
+	TEST_ASSERT_VAL("wrong cpu",  data->cpus_data.cpu[0] == 1);
+	TEST_ASSERT_VAL("wrong cpu",  data->cpus_data.cpu[1] == 256);
 
 	map = cpu_map__new_data(data);
 	TEST_ASSERT_VAL("wrong nr",  perf_cpu_map__nr(map) == 2);
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 07f2411b0ad4..20930dd48ee0 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -86,10 +86,15 @@ static bool samples_same(const struct perf_sample *s1,
 			COMP(read.time_running);
 		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
 		if (read_format & PERF_FORMAT_GROUP) {
-			for (i = 0; i < s1->read.group.nr; i++)
-				MCOMP(read.group.values[i]);
+			for (i = 0; i < s1->read.group.nr; i++) {
+				/* FIXME: check values without LOST */
+				if (read_format & PERF_FORMAT_LOST)
+					MCOMP(read.group.values[i]);
+			}
 		} else {
 			COMP(read.one.id);
+			if (read_format & PERF_FORMAT_LOST)
+				COMP(read.one.lost);
 		}
 	}
 
@@ -263,7 +268,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 			.data	= (void *)aux_data,
 		},
 	};
-	struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
+	struct sample_read_value values[] = {{1, 5, 0}, {9, 3, 0}, {2, 7, 0}, {6, 4, 1},};
 	struct perf_sample sample_out, sample_out_endian;
 	size_t i, sz, bufsz;
 	int err, ret = -1;
@@ -286,6 +291,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 	} else {
 		sample.read.one.value = 0x08789faeb786aa87ULL;
 		sample.read.one.id    = 99;
+		sample.read.one.lost  = 1;
 	}
 
 	sz = perf_event__sample_event_size(&sample, sample_type, read_format);
@@ -370,7 +376,7 @@ out_free:
  */
 static int test__sample_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
-	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
+	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15, 20, 21, 22, 28, 29, 30, 31};
 	u64 sample_type;
 	u64 sample_regs;
 	size_t i;
diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh
index 9313ef2739e0..26a51b48aee4 100755
--- a/tools/perf/tests/shell/stat.sh
+++ b/tools/perf/tests/shell/stat.sh
@@ -28,6 +28,24 @@ test_stat_record_report() {
   echo "stat record and report test [Success]"
 }
 
+test_stat_repeat_weak_groups() {
+  echo "stat repeat weak groups test"
+  if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \
+     true 2>&1 | grep -q 'seconds time elapsed'
+  then
+    echo "stat repeat weak groups test [Skipped event parsing failed]"
+    return
+  fi
+  if ! perf stat -r2 -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}:W' \
+    true > /dev/null 2>&1
+  then
+    echo "stat repeat weak groups test [Failed]"
+    err=1
+    return
+  fi
+  echo "stat repeat weak groups test [Success]"
+}
+
 test_topdown_groups() {
   # Topdown events must be grouped with the slots event first. Test that
   # parse-events reorders this.
@@ -75,6 +93,7 @@ test_topdown_weak_groups() {
 
 test_default_stat
 test_stat_record_report
+test_stat_repeat_weak_groups
 test_topdown_groups
 test_topdown_weak_groups
 exit $err
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index 17311ad9f9af..de3701a2a212 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -14,6 +14,8 @@ struct file;
 struct pid;
 struct cred;
 struct socket;
+struct sock;
+struct sk_buff;
 
 #define __sockaddr_check_size(size)	\
 	BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage)))
@@ -69,6 +71,9 @@ struct msghdr {
 	unsigned int	msg_flags;	/* flags on received message */
 	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
 	struct kiocb	*msg_iocb;	/* ptr to iocb for async requests */
+	struct ubuf_info *msg_ubuf;
+	int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb,
+			    struct iov_iter *from, size_t length);
 };
 
 struct user_msghdr {
@@ -416,10 +421,9 @@ extern int recvmsg_copy_msghdr(struct msghdr *msg,
 			       struct user_msghdr __user *umsg, unsigned flags,
 			       struct sockaddr __user **uaddr,
 			       struct iovec **iov);
-extern int __copy_msghdr_from_user(struct msghdr *kmsg,
-				   struct user_msghdr __user *umsg,
-				   struct sockaddr __user **save_addr,
-				   struct iovec __user **uiov, size_t *nsegs);
+extern int __copy_msghdr(struct msghdr *kmsg,
+			 struct user_msghdr *umsg,
+			 struct sockaddr __user **save_addr);
 
 /* helpers which do the actual work for syscalls */
 extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
@@ -428,10 +432,6 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
 extern int __sys_sendto(int fd, void __user *buff, size_t len,
 			unsigned int flags, struct sockaddr __user *addr,
 			int addr_len);
-extern int __sys_accept4_file(struct file *file, unsigned file_flags,
-			struct sockaddr __user *upeer_sockaddr,
-			 int __user *upeer_addrlen, int flags,
-			 unsigned long nofile);
 extern struct file *do_accept(struct file *file, unsigned file_flags,
 			      struct sockaddr __user *upeer_sockaddr,
 			      int __user *upeer_addrlen, int flags);
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 12b2243222b0..ae43fb88f444 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -22,54 +22,102 @@ static int max_node_num;
  */
 static int *cpunode_map;
 
-static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
+bool perf_record_cpu_map_data__test_bit(int i,
+					const struct perf_record_cpu_map_data *data)
+{
+	int bit_word32 = i / 32;
+	__u32 bit_mask32 = 1U << (i & 31);
+	int bit_word64 = i / 64;
+	__u64 bit_mask64 = ((__u64)1) << (i & 63);
+
+	return (data->mask32_data.long_size == 4)
+		? (bit_word32 < data->mask32_data.nr) &&
+		(data->mask32_data.mask[bit_word32] & bit_mask32) != 0
+		: (bit_word64 < data->mask64_data.nr) &&
+		(data->mask64_data.mask[bit_word64] & bit_mask64) != 0;
+}
+
+/* Read ith mask value from data into the given 64-bit sized bitmap */
+static void perf_record_cpu_map_data__read_one_mask(const struct perf_record_cpu_map_data *data,
+						    int i, unsigned long *bitmap)
+{
+#if __SIZEOF_LONG__ == 8
+	if (data->mask32_data.long_size == 4)
+		bitmap[0] = data->mask32_data.mask[i];
+	else
+		bitmap[0] = data->mask64_data.mask[i];
+#else
+	if (data->mask32_data.long_size == 4) {
+		bitmap[0] = data->mask32_data.mask[i];
+		bitmap[1] = 0;
+	} else {
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+		bitmap[0] = (unsigned long)(data->mask64_data.mask[i] >> 32);
+		bitmap[1] = (unsigned long)data->mask64_data.mask[i];
+#else
+		bitmap[0] = (unsigned long)data->mask64_data.mask[i];
+		bitmap[1] = (unsigned long)(data->mask64_data.mask[i] >> 32);
+#endif
+	}
+#endif
+}
+static struct perf_cpu_map *cpu_map__from_entries(const struct perf_record_cpu_map_data *data)
 {
 	struct perf_cpu_map *map;
 
-	map = perf_cpu_map__empty_new(cpus->nr);
+	map = perf_cpu_map__empty_new(data->cpus_data.nr);
 	if (map) {
 		unsigned i;
 
-		for (i = 0; i < cpus->nr; i++) {
+		for (i = 0; i < data->cpus_data.nr; i++) {
 			/*
 			 * Special treatment for -1, which is not real cpu number,
 			 * and we need to use (int) -1 to initialize map[i],
 			 * otherwise it would become 65535.
 			 */
-			if (cpus->cpu[i] == (u16) -1)
+			if (data->cpus_data.cpu[i] == (u16) -1)
 				map->map[i].cpu = -1;
 			else
-				map->map[i].cpu = (int) cpus->cpu[i];
+				map->map[i].cpu = (int) data->cpus_data.cpu[i];
 		}
 	}
 
 	return map;
 }
 
-static struct perf_cpu_map *cpu_map__from_mask(struct perf_record_record_cpu_map *mask)
+static struct perf_cpu_map *cpu_map__from_mask(const struct perf_record_cpu_map_data *data)
 {
+	DECLARE_BITMAP(local_copy, 64);
+	int weight = 0, mask_nr = data->mask32_data.nr;
 	struct perf_cpu_map *map;
-	int nr, nbits = mask->nr * mask->long_size * BITS_PER_BYTE;
 
-	nr = bitmap_weight(mask->mask, nbits);
+	for (int i = 0; i < mask_nr; i++) {
+		perf_record_cpu_map_data__read_one_mask(data, i, local_copy);
+		weight += bitmap_weight(local_copy, 64);
+	}
+
+	map = perf_cpu_map__empty_new(weight);
+	if (!map)
+		return NULL;
 
-	map = perf_cpu_map__empty_new(nr);
-	if (map) {
-		int cpu, i = 0;
+	for (int i = 0, j = 0; i < mask_nr; i++) {
+		int cpus_per_i = (i * data->mask32_data.long_size  * BITS_PER_BYTE);
+		int cpu;
 
-		for_each_set_bit(cpu, mask->mask, nbits)
-			map->map[i++].cpu = cpu;
+		perf_record_cpu_map_data__read_one_mask(data, i, local_copy);
+		for_each_set_bit(cpu, local_copy, 64)
+			map->map[j++].cpu = cpu + cpus_per_i;
 	}
 	return map;
 
 }
 
-struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data)
+struct perf_cpu_map *cpu_map__new_data(const struct perf_record_cpu_map_data *data)
 {
 	if (data->type == PERF_CPU_MAP__CPUS)
-		return cpu_map__from_entries((struct cpu_map_entries *)data->data);
+		return cpu_map__from_entries(data);
 	else
-		return cpu_map__from_mask((struct perf_record_record_cpu_map *)data->data);
+		return cpu_map__from_mask(data);
 }
 
 size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp)
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 703ae6d3386e..fa8a5acdcae1 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -37,9 +37,11 @@ struct cpu_aggr_map {
 
 struct perf_record_cpu_map_data;
 
+bool perf_record_cpu_map_data__test_bit(int i, const struct perf_record_cpu_map_data *data);
+
 struct perf_cpu_map *perf_cpu_map__empty_new(int nr);
 
-struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data);
+struct perf_cpu_map *cpu_map__new_data(const struct perf_record_cpu_map_data *data);
 size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size);
 size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size);
 size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index a7b0931d5137..12eae6917022 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -65,7 +65,8 @@ struct stack_dump {
 
 struct sample_read_value {
 	u64 value;
-	u64 id;
+	u64 id;   /* only if PERF_FORMAT_ID */
+	u64 lost; /* only if PERF_FORMAT_LOST */
 };
 
 struct sample_read {
@@ -80,6 +81,24 @@ struct sample_read {
 	};
 };
 
+static inline size_t sample_read_value_size(u64 read_format)
+{
+	/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+	if (read_format & PERF_FORMAT_LOST)
+		return sizeof(struct sample_read_value);
+	else
+		return offsetof(struct sample_read_value, lost);
+}
+
+static inline struct sample_read_value *
+next_sample_read_value(struct sample_read_value *v, u64 read_format)
+{
+	return (void *)v + sample_read_value_size(read_format);
+}
+
+#define sample_read_group__for_each(v, nr, rf)		\
+	for (int __i = 0; __i < (int)nr; v = next_sample_read_value(v, rf), __i++)
+
 struct ip_callchain {
 	u64 nr;
 	u64 ips[];
@@ -463,10 +482,6 @@ size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FIL
 int kallsyms__get_function_start(const char *kallsyms_filename,
 				 const char *symbol_name, u64 *addr);
 
-void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max);
-void  cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map,
-			       u16 type, int max);
-
 void event_attr_init(struct perf_event_attr *attr);
 
 int perf_event_paranoid(void);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 4852089e1d79..18c3eb864d55 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1541,7 +1541,7 @@ static int evsel__read_one(struct evsel *evsel, int cpu_map_idx, int thread)
 }
 
 static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread,
-			     u64 val, u64 ena, u64 run)
+			     u64 val, u64 ena, u64 run, u64 lost)
 {
 	struct perf_counts_values *count;
 
@@ -1550,6 +1550,7 @@ static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread,
 	count->val    = val;
 	count->ena    = ena;
 	count->run    = run;
+	count->lost   = lost;
 
 	perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true);
 }
@@ -1558,7 +1559,7 @@ static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int
 {
 	u64 read_format = leader->core.attr.read_format;
 	struct sample_read_value *v;
-	u64 nr, ena = 0, run = 0, i;
+	u64 nr, ena = 0, run = 0, lost = 0;
 
 	nr = *data++;
 
@@ -1571,18 +1572,18 @@ static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int
 	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
 		run = *data++;
 
-	v = (struct sample_read_value *) data;
-
-	evsel__set_count(leader, cpu_map_idx, thread, v[0].value, ena, run);
-
-	for (i = 1; i < nr; i++) {
+	v = (void *)data;
+	sample_read_group__for_each(v, nr, read_format) {
 		struct evsel *counter;
 
-		counter = evlist__id2evsel(leader->evlist, v[i].id);
+		counter = evlist__id2evsel(leader->evlist, v->id);
 		if (!counter)
 			return -EINVAL;
 
-		evsel__set_count(counter, cpu_map_idx, thread, v[i].value, ena, run);
+		if (read_format & PERF_FORMAT_LOST)
+			lost = v->lost;
+
+		evsel__set_count(counter, cpu_map_idx, thread, v->value, ena, run, lost);
 	}
 
 	return 0;
@@ -2475,8 +2476,8 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 
 			if (data->read.group.nr > max_group_nr)
 				return -EFAULT;
-			sz = data->read.group.nr *
-			     sizeof(struct sample_read_value);
+
+			sz = data->read.group.nr * sample_read_value_size(read_format);
 			OVERFLOW_CHECK(array, sz, max_size);
 			data->read.group.values =
 					(struct sample_read_value *)array;
@@ -2485,6 +2486,12 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 			OVERFLOW_CHECK_u64(array);
 			data->read.one.id = *array;
 			array++;
+
+			if (read_format & PERF_FORMAT_LOST) {
+				OVERFLOW_CHECK_u64(array);
+				data->read.one.lost = *array;
+				array++;
+			}
 		}
 	}
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 9ef2406e0ede..1f2040f36d4e 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -642,15 +642,19 @@ exit:
 	return pylist;
 }
 
-static PyObject *get_sample_value_as_tuple(struct sample_read_value *value)
+static PyObject *get_sample_value_as_tuple(struct sample_read_value *value,
+					   u64 read_format)
 {
 	PyObject *t;
 
-	t = PyTuple_New(2);
+	t = PyTuple_New(3);
 	if (!t)
 		Py_FatalError("couldn't create Python tuple");
 	PyTuple_SetItem(t, 0, PyLong_FromUnsignedLongLong(value->id));
 	PyTuple_SetItem(t, 1, PyLong_FromUnsignedLongLong(value->value));
+	if (read_format & PERF_FORMAT_LOST)
+		PyTuple_SetItem(t, 2, PyLong_FromUnsignedLongLong(value->lost));
+
 	return t;
 }
 
@@ -681,12 +685,17 @@ static void set_sample_read_in_dict(PyObject *dict_sample,
 		Py_FatalError("couldn't create Python list");
 
 	if (read_format & PERF_FORMAT_GROUP) {
-		for (i = 0; i < sample->read.group.nr; i++) {
-			PyObject *t = get_sample_value_as_tuple(&sample->read.group.values[i]);
+		struct sample_read_value *v = sample->read.group.values;
+
+		i = 0;
+		sample_read_group__for_each(v, sample->read.group.nr, read_format) {
+			PyObject *t = get_sample_value_as_tuple(v, read_format);
 			PyList_SET_ITEM(values, i, t);
+			i++;
 		}
 	} else {
-		PyObject *t = get_sample_value_as_tuple(&sample->read.one);
+		PyObject *t = get_sample_value_as_tuple(&sample->read.one,
+							read_format);
 		PyList_SET_ITEM(values, 0, t);
 	}
 	pydict_set_item_string_decref(dict_sample, "values", values);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 98e16659a149..192c9274f7ad 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -916,30 +916,30 @@ static void perf_event__cpu_map_swap(union perf_event *event,
 				     bool sample_id_all __maybe_unused)
 {
 	struct perf_record_cpu_map_data *data = &event->cpu_map.data;
-	struct cpu_map_entries *cpus;
-	struct perf_record_record_cpu_map *mask;
-	unsigned i;
 
 	data->type = bswap_16(data->type);
 
 	switch (data->type) {
 	case PERF_CPU_MAP__CPUS:
-		cpus = (struct cpu_map_entries *)data->data;
-
-		cpus->nr = bswap_16(cpus->nr);
+		data->cpus_data.nr = bswap_16(data->cpus_data.nr);
 
-		for (i = 0; i < cpus->nr; i++)
-			cpus->cpu[i] = bswap_16(cpus->cpu[i]);
+		for (unsigned i = 0; i < data->cpus_data.nr; i++)
+			data->cpus_data.cpu[i] = bswap_16(data->cpus_data.cpu[i]);
 		break;
 	case PERF_CPU_MAP__MASK:
-		mask = (struct perf_record_record_cpu_map *)data->data;
-
-		mask->nr = bswap_16(mask->nr);
-		mask->long_size = bswap_16(mask->long_size);
+		data->mask32_data.long_size = bswap_16(data->mask32_data.long_size);
 
-		switch (mask->long_size) {
-		case 4: mem_bswap_32(&mask->mask, mask->nr); break;
-		case 8: mem_bswap_64(&mask->mask, mask->nr); break;
+		switch (data->mask32_data.long_size) {
+		case 4:
+			data->mask32_data.nr = bswap_16(data->mask32_data.nr);
+			for (unsigned i = 0; i < data->mask32_data.nr; i++)
+				data->mask32_data.mask[i] = bswap_32(data->mask32_data.mask[i]);
+			break;
+		case 8:
+			data->mask64_data.nr = bswap_16(data->mask64_data.nr);
+			for (unsigned i = 0; i < data->mask64_data.nr; i++)
+				data->mask64_data.mask[i] = bswap_64(data->mask64_data.mask[i]);
+			break;
 		default:
 			pr_err("cpu_map swap: unsupported long size\n");
 		}
@@ -1283,21 +1283,25 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format)
 		       sample->read.time_running);
 
 	if (read_format & PERF_FORMAT_GROUP) {
-		u64 i;
+		struct sample_read_value *value = sample->read.group.values;
 
 		printf(".... group nr %" PRIu64 "\n", sample->read.group.nr);
 
-		for (i = 0; i < sample->read.group.nr; i++) {
-			struct sample_read_value *value;
-
-			value = &sample->read.group.values[i];
+		sample_read_group__for_each(value, sample->read.group.nr, read_format) {
 			printf("..... id %016" PRIx64
-			       ", value %016" PRIx64 "\n",
+			       ", value %016" PRIx64,
 			       value->id, value->value);
+			if (read_format & PERF_FORMAT_LOST)
+				printf(", lost %" PRIu64, value->lost);
+			printf("\n");
 		}
-	} else
-		printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n",
+	} else {
+		printf("..... id %016" PRIx64 ", value %016" PRIx64,
 			sample->read.one.id, sample->read.one.value);
+		if (read_format & PERF_FORMAT_LOST)
+			printf(", lost %" PRIu64, sample->read.one.lost);
+		printf("\n");
+	}
 }
 
 static void dump_event(struct evlist *evlist, union perf_event *event,
@@ -1411,6 +1415,9 @@ static void dump_read(struct evsel *evsel, union perf_event *event)
 
 	if (read_format & PERF_FORMAT_ID)
 		printf("... id           : %" PRI_lu64 "\n", read_event->id);
+
+	if (read_format & PERF_FORMAT_LOST)
+		printf("... lost         : %" PRI_lu64 "\n", read_event->lost);
 }
 
 static struct machine *machines__find_for_cpumode(struct machines *machines,
@@ -1479,14 +1486,14 @@ static int deliver_sample_group(struct evlist *evlist,
 				struct perf_tool *tool,
 				union  perf_event *event,
 				struct perf_sample *sample,
-				struct machine *machine)
+				struct machine *machine,
+				u64 read_format)
 {
 	int ret = -EINVAL;
-	u64 i;
+	struct sample_read_value *v = sample->read.group.values;
 
-	for (i = 0; i < sample->read.group.nr; i++) {
-		ret = deliver_sample_value(evlist, tool, event, sample,
-					   &sample->read.group.values[i],
+	sample_read_group__for_each(v, sample->read.group.nr, read_format) {
+		ret = deliver_sample_value(evlist, tool, event, sample, v,
 					   machine);
 		if (ret)
 			break;
@@ -1510,7 +1517,7 @@ static int evlist__deliver_sample(struct evlist *evlist, struct perf_tool *tool,
 	/* For PERF_SAMPLE_READ we have either single or group mode. */
 	if (read_format & PERF_FORMAT_GROUP)
 		return deliver_sample_group(evlist, tool, event, sample,
-					    machine);
+					    machine, read_format);
 	else
 		return deliver_sample_value(evlist, tool, event, sample,
 					    &sample->read.one, machine);
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 979c8cb918f7..788ce5e46470 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -1193,7 +1193,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 						  &rsd);
 		if (retiring > 0.7)
 			color = PERF_COLOR_GREEN;
-		print_metric(config, ctxp, color, "%8.1f%%", "retiring",
+		print_metric(config, ctxp, color, "%8.1f%%", "Retiring",
 				retiring * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
 		   full_td(cpu_map_idx, st, &rsd)) {
@@ -1202,7 +1202,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 						  &rsd);
 		if (fe_bound > 0.2)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "Frontend Bound",
 				fe_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
 		   full_td(cpu_map_idx, st, &rsd)) {
@@ -1211,7 +1211,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 						  &rsd);
 		if (be_bound > 0.2)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "backend bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "Backend Bound",
 				be_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
 		   full_td(cpu_map_idx, st, &rsd)) {
@@ -1220,7 +1220,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 						  &rsd);
 		if (bad_spec > 0.1)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
+		print_metric(config, ctxp, color, "%8.1f%%", "Bad Speculation",
 				bad_spec * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_HEAVY_OPS) &&
 			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1234,13 +1234,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 		if (retiring > 0.7 && heavy_ops > 0.1)
 			color = PERF_COLOR_GREEN;
-		print_metric(config, ctxp, color, "%8.1f%%", "heavy operations",
+		print_metric(config, ctxp, color, "%8.1f%%", "Heavy Operations",
 				heavy_ops * 100.);
 		if (retiring > 0.7 && light_ops > 0.6)
 			color = PERF_COLOR_GREEN;
 		else
 			color = NULL;
-		print_metric(config, ctxp, color, "%8.1f%%", "light operations",
+		print_metric(config, ctxp, color, "%8.1f%%", "Light Operations",
 				light_ops * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BR_MISPREDICT) &&
 			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1254,13 +1254,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 		if (bad_spec > 0.1 && br_mis > 0.05)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "branch mispredict",
+		print_metric(config, ctxp, color, "%8.1f%%", "Branch Mispredict",
 				br_mis * 100.);
 		if (bad_spec > 0.1 && m_clears > 0.05)
 			color = PERF_COLOR_RED;
 		else
 			color = NULL;
-		print_metric(config, ctxp, color, "%8.1f%%", "machine clears",
+		print_metric(config, ctxp, color, "%8.1f%%", "Machine Clears",
 				m_clears * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_LAT) &&
 			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1274,13 +1274,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 		if (fe_bound > 0.2 && fetch_lat > 0.15)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "fetch latency",
+		print_metric(config, ctxp, color, "%8.1f%%", "Fetch Latency",
 				fetch_lat * 100.);
 		if (fe_bound > 0.2 && fetch_bw > 0.1)
 			color = PERF_COLOR_RED;
 		else
 			color = NULL;
-		print_metric(config, ctxp, color, "%8.1f%%", "fetch bandwidth",
+		print_metric(config, ctxp, color, "%8.1f%%", "Fetch Bandwidth",
 				fetch_bw * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_MEM_BOUND) &&
 			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1294,13 +1294,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 		if (be_bound > 0.2 && mem_bound > 0.2)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "memory bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "Memory Bound",
 				mem_bound * 100.);
 		if (be_bound > 0.2 && core_bound > 0.1)
 			color = PERF_COLOR_RED;
 		else
 			color = NULL;
-		print_metric(config, ctxp, color, "%8.1f%%", "Core bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "Core Bound",
 				core_bound * 100.);
 	} else if (evsel->metric_expr) {
 		generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL,
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 2ae59c03ae77..812424dbf2d5 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -1184,52 +1184,48 @@ int perf_event__synthesize_thread_map2(struct perf_tool *tool,
 	return err;
 }
 
-static void synthesize_cpus(struct cpu_map_entries *cpus,
-			    struct perf_cpu_map *map)
+static void synthesize_cpus(struct perf_record_cpu_map_data *data,
+			    const struct perf_cpu_map *map)
 {
 	int i, map_nr = perf_cpu_map__nr(map);
 
-	cpus->nr = map_nr;
+	data->cpus_data.nr = map_nr;
 
 	for (i = 0; i < map_nr; i++)
-		cpus->cpu[i] = perf_cpu_map__cpu(map, i).cpu;
+		data->cpus_data.cpu[i] = perf_cpu_map__cpu(map, i).cpu;
 }
 
-static void synthesize_mask(struct perf_record_record_cpu_map *mask,
-			    struct perf_cpu_map *map, int max)
+static void synthesize_mask(struct perf_record_cpu_map_data *data,
+			    const struct perf_cpu_map *map, int max)
 {
-	int i;
+	int idx;
+	struct perf_cpu cpu;
+
+	/* Due to padding, the 4bytes per entry mask variant is always smaller. */
+	data->mask32_data.nr = BITS_TO_U32(max);
+	data->mask32_data.long_size = 4;
 
-	mask->nr = BITS_TO_LONGS(max);
-	mask->long_size = sizeof(long);
+	perf_cpu_map__for_each_cpu(cpu, idx, map) {
+		int bit_word = cpu.cpu / 32;
+		__u32 bit_mask = 1U << (cpu.cpu & 31);
 
-	for (i = 0; i < perf_cpu_map__nr(map); i++)
-		set_bit(perf_cpu_map__cpu(map, i).cpu, mask->mask);
+		data->mask32_data.mask[bit_word] |= bit_mask;
+	}
 }
 
-static size_t cpus_size(struct perf_cpu_map *map)
+static size_t cpus_size(const struct perf_cpu_map *map)
 {
 	return sizeof(struct cpu_map_entries) + perf_cpu_map__nr(map) * sizeof(u16);
 }
 
-static size_t mask_size(struct perf_cpu_map *map, int *max)
+static size_t mask_size(const struct perf_cpu_map *map, int *max)
 {
-	int i;
-
-	*max = 0;
-
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		/* bit position of the cpu is + 1 */
-		int bit = perf_cpu_map__cpu(map, i).cpu + 1;
-
-		if (bit > *max)
-			*max = bit;
-	}
-
-	return sizeof(struct perf_record_record_cpu_map) + BITS_TO_LONGS(*max) * sizeof(long);
+	*max = perf_cpu_map__max(map).cpu;
+	return sizeof(struct perf_record_mask_cpu_map32) + BITS_TO_U32(*max) * sizeof(__u32);
 }
 
-void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max)
+static void *cpu_map_data__alloc(const struct perf_cpu_map *map, size_t *size,
+				 u16 *type, int *max)
 {
 	size_t size_cpus, size_mask;
 	bool is_dummy = perf_cpu_map__empty(map);
@@ -1258,30 +1254,31 @@ void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int
 		*type  = PERF_CPU_MAP__MASK;
 	}
 
-	*size += sizeof(struct perf_record_cpu_map_data);
+	*size += sizeof(__u16); /* For perf_record_cpu_map_data.type. */
 	*size = PERF_ALIGN(*size, sizeof(u64));
 	return zalloc(*size);
 }
 
-void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map,
-			      u16 type, int max)
+static void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data,
+				     const struct perf_cpu_map *map,
+				     u16 type, int max)
 {
 	data->type = type;
 
 	switch (type) {
 	case PERF_CPU_MAP__CPUS:
-		synthesize_cpus((struct cpu_map_entries *) data->data, map);
+		synthesize_cpus(data, map);
 		break;
 	case PERF_CPU_MAP__MASK:
-		synthesize_mask((struct perf_record_record_cpu_map *)data->data, map, max);
+		synthesize_mask(data, map, max);
 	default:
 		break;
 	}
 }
 
-static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map)
+static struct perf_record_cpu_map *cpu_map_event__new(const struct perf_cpu_map *map)
 {
-	size_t size = sizeof(struct perf_record_cpu_map);
+	size_t size = sizeof(struct perf_event_header);
 	struct perf_record_cpu_map *event;
 	int max;
 	u16 type;
@@ -1299,7 +1296,7 @@ static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map)
 }
 
 int perf_event__synthesize_cpu_map(struct perf_tool *tool,
-				   struct perf_cpu_map *map,
+				   const struct perf_cpu_map *map,
 				   perf_event__handler_t process,
 				   struct machine *machine)
 {
@@ -1432,11 +1429,12 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 			result += sizeof(u64);
 		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
 		if (read_format & PERF_FORMAT_GROUP) {
-			sz = sample->read.group.nr *
-			     sizeof(struct sample_read_value);
-			result += sz;
+			sz = sample_read_value_size(read_format);
+			result += sz * sample->read.group.nr;
 		} else {
 			result += sizeof(u64);
+			if (read_format & PERF_FORMAT_LOST)
+				result += sizeof(u64);
 		}
 	}
 
@@ -1521,6 +1519,20 @@ void __weak arch_perf_synthesize_sample_weight(const struct perf_sample *data,
 	*array = data->weight;
 }
 
+static __u64 *copy_read_group_values(__u64 *array, __u64 read_format,
+				     const struct perf_sample *sample)
+{
+	size_t sz = sample_read_value_size(read_format);
+	struct sample_read_value *v = sample->read.group.values;
+
+	sample_read_group__for_each(v, sample->read.group.nr, read_format) {
+		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+		memcpy(array, v, sz);
+		array = (void *)array + sz;
+	}
+	return array;
+}
+
 int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format,
 				  const struct perf_sample *sample)
 {
@@ -1602,13 +1614,16 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
 
 		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
 		if (read_format & PERF_FORMAT_GROUP) {
-			sz = sample->read.group.nr *
-			     sizeof(struct sample_read_value);
-			memcpy(array, sample->read.group.values, sz);
-			array = (void *)array + sz;
+			array = copy_read_group_values(array, read_format,
+						       sample);
 		} else {
 			*array = sample->read.one.id;
 			array++;
+
+			if (read_format & PERF_FORMAT_LOST) {
+				*array = sample->read.one.lost;
+				array++;
+			}
 		}
 	}
 
diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h
index 81cb3d6af0b9..53737d1619a4 100644
--- a/tools/perf/util/synthetic-events.h
+++ b/tools/perf/util/synthetic-events.h
@@ -46,7 +46,7 @@ typedef int (*perf_event__handler_t)(struct perf_tool *tool, union perf_event *e
 int perf_event__synthesize_attrs(struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process);
 int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process);
 int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16 misc, perf_event__handler_t process, struct machine *machine);
-int perf_event__synthesize_cpu_map(struct perf_tool *tool, struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_cpu_map(struct perf_tool *tool, const struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
 int perf_event__synthesize_event_update_name(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
 int perf_event__synthesize_event_update_scale(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 10b34bb03bc1..c2064a35688b 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -12,6 +12,7 @@ TARGETS += cpu-hotplug
 TARGETS += damon
 TARGETS += drivers/dma-buf
 TARGETS += drivers/s390x/uvdevice
+TARGETS += drivers/net/bonding
 TARGETS += efivarfs
 TARGETS += exec
 TARGETS += filesystems
diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile
new file mode 100644
index 000000000000..ab6c54b12098
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for net selftests
+
+TEST_PROGS := bond-break-lacpdu-tx.sh
+
+include ../../../lib.mk
diff --git a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh
new file mode 100755
index 000000000000..47ab90596acb
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh
@@ -0,0 +1,81 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+# Regression Test:
+#   Verify LACPDUs get transmitted after setting the MAC address of
+#   the bond.
+#
+# https://bugzilla.redhat.com/show_bug.cgi?id=2020773
+#
+#       +---------+
+#       | fab-br0 |
+#       +---------+
+#            |
+#       +---------+
+#       |  fbond  |
+#       +---------+
+#        |       |
+#    +------+ +------+
+#    |veth1 | |veth2 |
+#    +------+ +------+
+#
+# We use veths instead of physical interfaces
+
+set -e
+tmp=$(mktemp -q dump.XXXXXX)
+cleanup() {
+	ip link del fab-br0 >/dev/null 2>&1 || :
+	ip link del fbond  >/dev/null 2>&1 || :
+	ip link del veth1-bond  >/dev/null 2>&1 || :
+	ip link del veth2-bond  >/dev/null 2>&1 || :
+	modprobe -r bonding  >/dev/null 2>&1 || :
+	rm -f -- ${tmp}
+}
+
+trap cleanup 0 1 2
+cleanup
+sleep 1
+
+# create the bridge
+ip link add fab-br0 address 52:54:00:3B:7C:A6 mtu 1500 type bridge \
+	forward_delay 15
+
+# create the bond
+ip link add fbond type bond mode 4 miimon 200 xmit_hash_policy 1 \
+	ad_actor_sys_prio 65535 lacp_rate fast
+
+# set bond address
+ip link set fbond address 52:54:00:3B:7C:A6
+ip link set fbond up
+
+# set again bond sysfs parameters
+ip link set fbond type bond ad_actor_sys_prio 65535
+
+# create veths
+ip link add name veth1-bond type veth peer name veth1-end
+ip link add name veth2-bond type veth peer name veth2-end
+
+# add ports
+ip link set fbond master fab-br0
+ip link set veth1-bond down master fbond
+ip link set veth2-bond down master fbond
+
+# bring up
+ip link set veth1-end up
+ip link set veth2-end up
+ip link set fab-br0 up
+ip link set fbond up
+ip addr add dev fab-br0 10.0.0.3
+
+tcpdump -n -i veth1-end -e ether proto 0x8809 >${tmp} 2>&1 &
+sleep 15
+pkill tcpdump >/dev/null 2>&1
+rc=0
+num=$(grep "packets captured" ${tmp} | awk '{print $1}')
+if test "$num" -gt 0; then
+	echo "PASS, captured ${num}"
+else
+	echo "FAIL"
+	rc=1
+fi
+exit $rc
diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config
new file mode 100644
index 000000000000..dc1c22de3c92
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/config
@@ -0,0 +1 @@
+CONFIG_BONDING=y
diff --git a/tools/testing/selftests/drivers/net/bonding/settings b/tools/testing/selftests/drivers/net/bonding/settings
new file mode 100644
index 000000000000..867e118223cd
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/settings
@@ -0,0 +1 @@
+timeout=60
diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile
index a6959df28eb0..02868ac3bc71 100644
--- a/tools/testing/selftests/landlock/Makefile
+++ b/tools/testing/selftests/landlock/Makefile
@@ -9,10 +9,13 @@ TEST_GEN_PROGS := $(src_test:.c=)
 TEST_GEN_PROGS_EXTENDED := true
 
 OVERRIDE_TARGETS := 1
+top_srcdir := ../../../..
 include ../lib.mk
 
+khdr_dir = $(top_srcdir)/usr/include
+
 $(OUTPUT)/true: true.c
 	$(LINK.c) $< $(LDLIBS) -o $@ -static
 
-$(OUTPUT)/%_test: %_test.c ../kselftest_harness.h common.h
-	$(LINK.c) $< $(LDLIBS) -o $@ -lcap
+$(OUTPUT)/%_test: %_test.c $(khdr_dir)/linux/landlock.h ../kselftest_harness.h common.h
+	$(LINK.c) $< $(LDLIBS) -o $@ -lcap -I$(khdr_dir)
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 947fc72413e9..d44c72b3abe3 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -40,6 +40,7 @@ ifeq (0,$(MAKELEVEL))
     endif
 endif
 selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST))))
+top_srcdir = $(selfdir)/../../..
 
 # The following are built by lib.mk common compile rules.
 # TEST_CUSTOM_PROGS should be used by tests that require
diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh
index d4ffebb989f8..7060bae04ec8 100755
--- a/tools/testing/selftests/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/netfilter/nft_flowtable.sh
@@ -14,13 +14,17 @@
 # nft_flowtable.sh -o8000 -l1500 -r2000
 #
 
+sfx=$(mktemp -u "XXXXXXXX")
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+nsr1="nsr1-$sfx"
+nsr2="nsr2-$sfx"
 
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 ret=0
 
-ns1in=""
-ns2in=""
+nsin=""
 ns1out=""
 ns2out=""
 
@@ -36,21 +40,19 @@ checktool (){
 checktool "nft --version" "run test without nft tool"
 checktool "ip -Version" "run test without ip tool"
 checktool "which nc" "run test without nc (netcat)"
-checktool "ip netns add nsr1" "create net namespace"
+checktool "ip netns add $nsr1" "create net namespace $nsr1"
 
-ip netns add ns1
-ip netns add ns2
-
-ip netns add nsr2
+ip netns add $ns1
+ip netns add $ns2
+ip netns add $nsr2
 
 cleanup() {
-	for i in 1 2; do
-		ip netns del ns$i
-		ip netns del nsr$i
-	done
+	ip netns del $ns1
+	ip netns del $ns2
+	ip netns del $nsr1
+	ip netns del $nsr2
 
-	rm -f "$ns1in" "$ns1out"
-	rm -f "$ns2in" "$ns2out"
+	rm -f "$nsin" "$ns1out" "$ns2out"
 
 	[ $log_netns -eq 0 ] && sysctl -q net.netfilter.nf_log_all_netns=$log_netns
 }
@@ -59,22 +61,21 @@ trap cleanup EXIT
 
 sysctl -q net.netfilter.nf_log_all_netns=1
 
-ip link add veth0 netns nsr1 type veth peer name eth0 netns ns1
-ip link add veth1 netns nsr1 type veth peer name veth0 netns nsr2
+ip link add veth0 netns $nsr1 type veth peer name eth0 netns $ns1
+ip link add veth1 netns $nsr1 type veth peer name veth0 netns $nsr2
 
-ip link add veth1 netns nsr2 type veth peer name eth0 netns ns2
+ip link add veth1 netns $nsr2 type veth peer name eth0 netns $ns2
 
 for dev in lo veth0 veth1; do
-  for i in 1 2; do
-    ip -net nsr$i link set $dev up
-  done
+    ip -net $nsr1 link set $dev up
+    ip -net $nsr2 link set $dev up
 done
 
-ip -net nsr1 addr add 10.0.1.1/24 dev veth0
-ip -net nsr1 addr add dead:1::1/64 dev veth0
+ip -net $nsr1 addr add 10.0.1.1/24 dev veth0
+ip -net $nsr1 addr add dead:1::1/64 dev veth0
 
-ip -net nsr2 addr add 10.0.2.1/24 dev veth1
-ip -net nsr2 addr add dead:2::1/64 dev veth1
+ip -net $nsr2 addr add 10.0.2.1/24 dev veth1
+ip -net $nsr2 addr add dead:2::1/64 dev veth1
 
 # set different MTUs so we need to push packets coming from ns1 (large MTU)
 # to ns2 (smaller MTU) to stack either to perform fragmentation (ip_no_pmtu_disc=1),
@@ -106,85 +107,76 @@ do
 	esac
 done
 
-if ! ip -net nsr1 link set veth0 mtu $omtu; then
+if ! ip -net $nsr1 link set veth0 mtu $omtu; then
 	exit 1
 fi
 
-ip -net ns1 link set eth0 mtu $omtu
+ip -net $ns1 link set eth0 mtu $omtu
 
-if ! ip -net nsr2 link set veth1 mtu $rmtu; then
+if ! ip -net $nsr2 link set veth1 mtu $rmtu; then
 	exit 1
 fi
 
-ip -net ns2 link set eth0 mtu $rmtu
+ip -net $ns2 link set eth0 mtu $rmtu
 
 # transfer-net between nsr1 and nsr2.
 # these addresses are not used for connections.
-ip -net nsr1 addr add 192.168.10.1/24 dev veth1
-ip -net nsr1 addr add fee1:2::1/64 dev veth1
-
-ip -net nsr2 addr add 192.168.10.2/24 dev veth0
-ip -net nsr2 addr add fee1:2::2/64 dev veth0
-
-for i in 1 2; do
-  ip netns exec nsr$i sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
-  ip netns exec nsr$i sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
-
-  ip -net ns$i link set lo up
-  ip -net ns$i link set eth0 up
-  ip -net ns$i addr add 10.0.$i.99/24 dev eth0
-  ip -net ns$i route add default via 10.0.$i.1
-  ip -net ns$i addr add dead:$i::99/64 dev eth0
-  ip -net ns$i route add default via dead:$i::1
-  if ! ip netns exec ns$i sysctl net.ipv4.tcp_no_metrics_save=1 > /dev/null; then
+ip -net $nsr1 addr add 192.168.10.1/24 dev veth1
+ip -net $nsr1 addr add fee1:2::1/64 dev veth1
+
+ip -net $nsr2 addr add 192.168.10.2/24 dev veth0
+ip -net $nsr2 addr add fee1:2::2/64 dev veth0
+
+for i in 0 1; do
+  ip netns exec $nsr1 sysctl net.ipv4.conf.veth$i.forwarding=1 > /dev/null
+  ip netns exec $nsr2 sysctl net.ipv4.conf.veth$i.forwarding=1 > /dev/null
+done
+
+for ns in $ns1 $ns2;do
+  ip -net $ns link set lo up
+  ip -net $ns link set eth0 up
+
+  if ! ip netns exec $ns sysctl net.ipv4.tcp_no_metrics_save=1 > /dev/null; then
 	echo "ERROR: Check Originator/Responder values (problem during address addition)"
 	exit 1
   fi
-
   # don't set ip DF bit for first two tests
-  ip netns exec ns$i sysctl net.ipv4.ip_no_pmtu_disc=1 > /dev/null
+  ip netns exec $ns sysctl net.ipv4.ip_no_pmtu_disc=1 > /dev/null
 done
 
-ip -net nsr1 route add default via 192.168.10.2
-ip -net nsr2 route add default via 192.168.10.1
+ip -net $ns1 addr add 10.0.1.99/24 dev eth0
+ip -net $ns2 addr add 10.0.2.99/24 dev eth0
+ip -net $ns1 route add default via 10.0.1.1
+ip -net $ns2 route add default via 10.0.2.1
+ip -net $ns1 addr add dead:1::99/64 dev eth0
+ip -net $ns2 addr add dead:2::99/64 dev eth0
+ip -net $ns1 route add default via dead:1::1
+ip -net $ns2 route add default via dead:2::1
+
+ip -net $nsr1 route add default via 192.168.10.2
+ip -net $nsr2 route add default via 192.168.10.1
 
-ip netns exec nsr1 nft -f - <<EOF
+ip netns exec $nsr1 nft -f - <<EOF
 table inet filter {
   flowtable f1 {
      hook ingress priority 0
      devices = { veth0, veth1 }
    }
 
+   counter routed_orig { }
+   counter routed_repl { }
+
    chain forward {
       type filter hook forward priority 0; policy drop;
 
       # flow offloaded? Tag ct with mark 1, so we can detect when it fails.
-      meta oif "veth1" tcp dport 12345 flow offload @f1 counter
-
-      # use packet size to trigger 'should be offloaded by now'.
-      # otherwise, if 'flow offload' expression never offloads, the
-      # test will pass.
-      tcp dport 12345 meta length gt 200 ct mark set 1 counter
+      meta oif "veth1" tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept
 
-      # this turns off flow offloading internally, so expect packets again
-      tcp flags fin,rst ct mark set 0 accept
-
-      # this allows large packets from responder, we need this as long
-      # as PMTUd is off.
-      # This rule is deleted for the last test, when we expect PMTUd
-      # to kick in and ensure all packets meet mtu requirements.
-      meta length gt $lmtu accept comment something-to-grep-for
-
-      # next line blocks connection w.o. working offload.
-      # we only do this for reverse dir, because we expect packets to
-      # enter slow path due to MTU mismatch of veth0 and veth1.
-      tcp sport 12345 ct mark 1 counter log prefix "mark failure " drop
+      # count packets supposedly offloaded as per direction.
+      ct mark 1 counter name ct direction map { original : routed_orig, reply : routed_repl } accept
 
       ct state established,related accept
 
-      # for packets that we can't offload yet, i.e. SYN (any ct that is not confirmed)
-      meta length lt 200 oif "veth1" tcp dport 12345 counter accept
-
       meta nfproto ipv4 meta l4proto icmp accept
       meta nfproto ipv6 meta l4proto icmpv6 accept
    }
@@ -197,30 +189,30 @@ if [ $? -ne 0 ]; then
 fi
 
 # test basic connectivity
-if ! ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then
-  echo "ERROR: ns1 cannot reach ns2" 1>&2
+if ! ip netns exec $ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then
+  echo "ERROR: $ns1 cannot reach ns2" 1>&2
   exit 1
 fi
 
-if ! ip netns exec ns2 ping -c 1 -q 10.0.1.99 > /dev/null; then
-  echo "ERROR: ns2 cannot reach ns1" 1>&2
+if ! ip netns exec $ns2 ping -c 1 -q 10.0.1.99 > /dev/null; then
+  echo "ERROR: $ns2 cannot reach $ns1" 1>&2
   exit 1
 fi
 
 if [ $ret -eq 0 ];then
-	echo "PASS: netns routing/connectivity: ns1 can reach ns2"
+	echo "PASS: netns routing/connectivity: $ns1 can reach $ns2"
 fi
 
-ns1in=$(mktemp)
+nsin=$(mktemp)
 ns1out=$(mktemp)
-ns2in=$(mktemp)
 ns2out=$(mktemp)
 
 make_file()
 {
 	name=$1
 
-	SIZE=$((RANDOM % (1024 * 8)))
+	SIZE=$((RANDOM % (1024 * 128)))
+	SIZE=$((SIZE + (1024 * 8)))
 	TSIZE=$((SIZE * 1024))
 
 	dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null
@@ -231,6 +223,38 @@ make_file()
 	dd if=/dev/urandom conf=notrunc of="$name" bs=1 count=$SIZE 2> /dev/null
 }
 
+check_counters()
+{
+	local what=$1
+	local ok=1
+
+	local orig=$(ip netns exec $nsr1 nft reset counter inet filter routed_orig | grep packets)
+	local repl=$(ip netns exec $nsr1 nft reset counter inet filter routed_repl | grep packets)
+
+	local orig_cnt=${orig#*bytes}
+	local repl_cnt=${repl#*bytes}
+
+	local fs=$(du -sb $nsin)
+	local max_orig=${fs%%/*}
+	local max_repl=$((max_orig/4))
+
+	if [ $orig_cnt -gt $max_orig ];then
+		echo "FAIL: $what: original counter $orig_cnt exceeds expected value $max_orig" 1>&2
+		ret=1
+		ok=0
+	fi
+
+	if [ $repl_cnt -gt $max_repl ];then
+		echo "FAIL: $what: reply counter $repl_cnt exceeds expected value $max_repl" 1>&2
+		ret=1
+		ok=0
+	fi
+
+	if [ $ok -eq 1 ]; then
+		echo "PASS: $what"
+	fi
+}
+
 check_transfer()
 {
 	in=$1
@@ -255,11 +279,11 @@ test_tcp_forwarding_ip()
 	local dstport=$4
 	local lret=0
 
-	ip netns exec $nsb nc -w 5 -l -p 12345 < "$ns2in" > "$ns2out" &
+	ip netns exec $nsb nc -w 5 -l -p 12345 < "$nsin" > "$ns2out" &
 	lpid=$!
 
 	sleep 1
-	ip netns exec $nsa nc -w 4 "$dstip" "$dstport" < "$ns1in" > "$ns1out" &
+	ip netns exec $nsa nc -w 4 "$dstip" "$dstport" < "$nsin" > "$ns1out" &
 	cpid=$!
 
 	sleep 3
@@ -274,11 +298,11 @@ test_tcp_forwarding_ip()
 
 	wait
 
-	if ! check_transfer "$ns1in" "$ns2out" "ns1 -> ns2"; then
+	if ! check_transfer "$nsin" "$ns2out" "ns1 -> ns2"; then
 		lret=1
 	fi
 
-	if ! check_transfer "$ns2in" "$ns1out" "ns1 <- ns2"; then
+	if ! check_transfer "$nsin" "$ns1out" "ns1 <- ns2"; then
 		lret=1
 	fi
 
@@ -295,41 +319,59 @@ test_tcp_forwarding()
 test_tcp_forwarding_nat()
 {
 	local lret
+	local pmtu
 
 	test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
 	lret=$?
 
+	pmtu=$3
+	what=$4
+
 	if [ $lret -eq 0 ] ; then
+		if [ $pmtu -eq 1 ] ;then
+			check_counters "flow offload for ns1/ns2 with masquerade and pmtu discovery $what"
+		else
+			echo "PASS: flow offload for ns1/ns2 with masquerade $what"
+		fi
+
 		test_tcp_forwarding_ip "$1" "$2" 10.6.6.6 1666
 		lret=$?
+		if [ $pmtu -eq 1 ] ;then
+			check_counters "flow offload for ns1/ns2 with dnat and pmtu discovery $what"
+		elif [ $lret -eq 0 ] ; then
+			echo "PASS: flow offload for ns1/ns2 with dnat $what"
+		fi
 	fi
 
 	return $lret
 }
 
-make_file "$ns1in"
-make_file "$ns2in"
+make_file "$nsin"
 
 # First test:
 # No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed.
-if test_tcp_forwarding ns1 ns2; then
+# Due to MTU mismatch in both directions, all packets (except small packets like pure
+# acks) have to be handled by normal forwarding path.  Therefore, packet counters
+# are not checked.
+if test_tcp_forwarding $ns1 $ns2; then
 	echo "PASS: flow offloaded for ns1/ns2"
 else
 	echo "FAIL: flow offload for ns1/ns2:" 1>&2
-	ip netns exec nsr1 nft list ruleset
+	ip netns exec $nsr1 nft list ruleset
 	ret=1
 fi
 
 # delete default route, i.e. ns2 won't be able to reach ns1 and
 # will depend on ns1 being masqueraded in nsr1.
 # expect ns1 has nsr1 address.
-ip -net ns2 route del default via 10.0.2.1
-ip -net ns2 route del default via dead:2::1
-ip -net ns2 route add 192.168.10.1 via 10.0.2.1
+ip -net $ns2 route del default via 10.0.2.1
+ip -net $ns2 route del default via dead:2::1
+ip -net $ns2 route add 192.168.10.1 via 10.0.2.1
 
 # Second test:
-# Same, but with NAT enabled.
-ip netns exec nsr1 nft -f - <<EOF
+# Same, but with NAT enabled.  Same as in first test: we expect normal forward path
+# to handle most packets.
+ip netns exec $nsr1 nft -f - <<EOF
 table ip nat {
    chain prerouting {
       type nat hook prerouting priority 0; policy accept;
@@ -343,47 +385,45 @@ table ip nat {
 }
 EOF
 
-if test_tcp_forwarding_nat ns1 ns2; then
-	echo "PASS: flow offloaded for ns1/ns2 with NAT"
-else
+if ! test_tcp_forwarding_nat $ns1 $ns2 0 ""; then
 	echo "FAIL: flow offload for ns1/ns2 with NAT" 1>&2
-	ip netns exec nsr1 nft list ruleset
+	ip netns exec $nsr1 nft list ruleset
 	ret=1
 fi
 
 # Third test:
-# Same as second test, but with PMTU discovery enabled.
-handle=$(ip netns exec nsr1 nft -a list table inet filter | grep something-to-grep-for | cut -d \# -f 2)
-
-if ! ip netns exec nsr1 nft delete rule inet filter forward $handle; then
-	echo "FAIL: Could not delete large-packet accept rule"
-	exit 1
-fi
-
-ip netns exec ns1 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
-ip netns exec ns2 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
-
-if test_tcp_forwarding_nat ns1 ns2; then
-	echo "PASS: flow offloaded for ns1/ns2 with NAT and pmtu discovery"
-else
+# Same as second test, but with PMTU discovery enabled. This
+# means that we expect the fastpath to handle packets as soon
+# as the endpoints adjust the packet size.
+ip netns exec $ns1 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
+ip netns exec $ns2 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
+
+# reset counters.
+# With pmtu in-place we'll also check that nft counters
+# are lower than file size and packets were forwarded via flowtable layer.
+# For earlier tests (large mtus), packets cannot be handled via flowtable
+# (except pure acks and other small packets).
+ip netns exec $nsr1 nft reset counters table inet filter >/dev/null
+
+if ! test_tcp_forwarding_nat $ns1 $ns2 1 ""; then
 	echo "FAIL: flow offload for ns1/ns2 with NAT and pmtu discovery" 1>&2
-	ip netns exec nsr1 nft list ruleset
+	ip netns exec $nsr1 nft list ruleset
 fi
 
 # Another test:
 # Add bridge interface br0 to Router1, with NAT enabled.
-ip -net nsr1 link add name br0 type bridge
-ip -net nsr1 addr flush dev veth0
-ip -net nsr1 link set up dev veth0
-ip -net nsr1 link set veth0 master br0
-ip -net nsr1 addr add 10.0.1.1/24 dev br0
-ip -net nsr1 addr add dead:1::1/64 dev br0
-ip -net nsr1 link set up dev br0
+ip -net $nsr1 link add name br0 type bridge
+ip -net $nsr1 addr flush dev veth0
+ip -net $nsr1 link set up dev veth0
+ip -net $nsr1 link set veth0 master br0
+ip -net $nsr1 addr add 10.0.1.1/24 dev br0
+ip -net $nsr1 addr add dead:1::1/64 dev br0
+ip -net $nsr1 link set up dev br0
 
-ip netns exec nsr1 sysctl net.ipv4.conf.br0.forwarding=1 > /dev/null
+ip netns exec $nsr1 sysctl net.ipv4.conf.br0.forwarding=1 > /dev/null
 
 # br0 with NAT enabled.
-ip netns exec nsr1 nft -f - <<EOF
+ip netns exec $nsr1 nft -f - <<EOF
 flush table ip nat
 table ip nat {
    chain prerouting {
@@ -398,59 +438,56 @@ table ip nat {
 }
 EOF
 
-if test_tcp_forwarding_nat ns1 ns2; then
-	echo "PASS: flow offloaded for ns1/ns2 with bridge NAT"
-else
+if ! test_tcp_forwarding_nat $ns1 $ns2 1 "on bridge"; then
 	echo "FAIL: flow offload for ns1/ns2 with bridge NAT" 1>&2
-	ip netns exec nsr1 nft list ruleset
+	ip netns exec $nsr1 nft list ruleset
 	ret=1
 fi
 
+
 # Another test:
 # Add bridge interface br0 to Router1, with NAT and VLAN.
-ip -net nsr1 link set veth0 nomaster
-ip -net nsr1 link set down dev veth0
-ip -net nsr1 link add link veth0 name veth0.10 type vlan id 10
-ip -net nsr1 link set up dev veth0
-ip -net nsr1 link set up dev veth0.10
-ip -net nsr1 link set veth0.10 master br0
-
-ip -net ns1 addr flush dev eth0
-ip -net ns1 link add link eth0 name eth0.10 type vlan id 10
-ip -net ns1 link set eth0 up
-ip -net ns1 link set eth0.10 up
-ip -net ns1 addr add 10.0.1.99/24 dev eth0.10
-ip -net ns1 route add default via 10.0.1.1
-ip -net ns1 addr add dead:1::99/64 dev eth0.10
-
-if test_tcp_forwarding_nat ns1 ns2; then
-	echo "PASS: flow offloaded for ns1/ns2 with bridge NAT and VLAN"
-else
+ip -net $nsr1 link set veth0 nomaster
+ip -net $nsr1 link set down dev veth0
+ip -net $nsr1 link add link veth0 name veth0.10 type vlan id 10
+ip -net $nsr1 link set up dev veth0
+ip -net $nsr1 link set up dev veth0.10
+ip -net $nsr1 link set veth0.10 master br0
+
+ip -net $ns1 addr flush dev eth0
+ip -net $ns1 link add link eth0 name eth0.10 type vlan id 10
+ip -net $ns1 link set eth0 up
+ip -net $ns1 link set eth0.10 up
+ip -net $ns1 addr add 10.0.1.99/24 dev eth0.10
+ip -net $ns1 route add default via 10.0.1.1
+ip -net $ns1 addr add dead:1::99/64 dev eth0.10
+
+if ! test_tcp_forwarding_nat $ns1 $ns2 1 "bridge and VLAN"; then
 	echo "FAIL: flow offload for ns1/ns2 with bridge NAT and VLAN" 1>&2
-	ip netns exec nsr1 nft list ruleset
+	ip netns exec $nsr1 nft list ruleset
 	ret=1
 fi
 
 # restore test topology (remove bridge and VLAN)
-ip -net nsr1 link set veth0 nomaster
-ip -net nsr1 link set veth0 down
-ip -net nsr1 link set veth0.10 down
-ip -net nsr1 link delete veth0.10 type vlan
-ip -net nsr1 link delete br0 type bridge
-ip -net ns1 addr flush dev eth0.10
-ip -net ns1 link set eth0.10 down
-ip -net ns1 link set eth0 down
-ip -net ns1 link delete eth0.10 type vlan
+ip -net $nsr1 link set veth0 nomaster
+ip -net $nsr1 link set veth0 down
+ip -net $nsr1 link set veth0.10 down
+ip -net $nsr1 link delete veth0.10 type vlan
+ip -net $nsr1 link delete br0 type bridge
+ip -net $ns1 addr flush dev eth0.10
+ip -net $ns1 link set eth0.10 down
+ip -net $ns1 link set eth0 down
+ip -net $ns1 link delete eth0.10 type vlan
 
 # restore address in ns1 and nsr1
-ip -net ns1 link set eth0 up
-ip -net ns1 addr add 10.0.1.99/24 dev eth0
-ip -net ns1 route add default via 10.0.1.1
-ip -net ns1 addr add dead:1::99/64 dev eth0
-ip -net ns1 route add default via dead:1::1
-ip -net nsr1 addr add 10.0.1.1/24 dev veth0
-ip -net nsr1 addr add dead:1::1/64 dev veth0
-ip -net nsr1 link set up dev veth0
+ip -net $ns1 link set eth0 up
+ip -net $ns1 addr add 10.0.1.99/24 dev eth0
+ip -net $ns1 route add default via 10.0.1.1
+ip -net $ns1 addr add dead:1::99/64 dev eth0
+ip -net $ns1 route add default via dead:1::1
+ip -net $nsr1 addr add 10.0.1.1/24 dev veth0
+ip -net $nsr1 addr add dead:1::1/64 dev veth0
+ip -net $nsr1 link set up dev veth0
 
 KEY_SHA="0x"$(ps -xaf | sha1sum | cut -d " " -f 1)
 KEY_AES="0x"$(ps -xaf | md5sum | cut -d " " -f 1)
@@ -480,23 +517,23 @@ do_esp() {
 
 }
 
-do_esp nsr1 192.168.10.1 192.168.10.2 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2
+do_esp $nsr1 192.168.10.1 192.168.10.2 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2
 
-do_esp nsr2 192.168.10.2 192.168.10.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1
+do_esp $nsr2 192.168.10.2 192.168.10.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1
 
-ip netns exec nsr1 nft delete table ip nat
+ip netns exec $nsr1 nft delete table ip nat
 
 # restore default routes
-ip -net ns2 route del 192.168.10.1 via 10.0.2.1
-ip -net ns2 route add default via 10.0.2.1
-ip -net ns2 route add default via dead:2::1
+ip -net $ns2 route del 192.168.10.1 via 10.0.2.1
+ip -net $ns2 route add default via 10.0.2.1
+ip -net $ns2 route add default via dead:2::1
 
-if test_tcp_forwarding ns1 ns2; then
-	echo "PASS: ipsec tunnel mode for ns1/ns2"
+if test_tcp_forwarding $ns1 $ns2; then
+	check_counters "ipsec tunnel mode for ns1/ns2"
 else
 	echo "FAIL: ipsec tunnel mode for ns1/ns2"
-	ip netns exec nsr1 nft list ruleset 1>&2
-	ip netns exec nsr1 cat /proc/net/xfrm_stat 1>&2
+	ip netns exec $nsr1 nft list ruleset 1>&2
+	ip netns exec $nsr1 cat /proc/net/xfrm_stat 1>&2
 fi
 
 exit $ret
diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/.gitignore b/tools/testing/selftests/powerpc/pmu/event_code_tests/.gitignore
new file mode 100644
index 000000000000..5710683da525
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/.gitignore
@@ -0,0 +1,20 @@
+blacklisted_events_test
+event_alternatives_tests_p10
+event_alternatives_tests_p9
+generic_events_valid_test
+group_constraint_cache_test
+group_constraint_l2l3_sel_test
+group_constraint_mmcra_sample_test
+group_constraint_pmc56_test
+group_constraint_pmc_count_test
+group_constraint_radix_scope_qual_test
+group_constraint_repeat_test
+group_constraint_thresh_cmp_test
+group_constraint_thresh_ctl_test
+group_constraint_thresh_sel_test
+group_constraint_unit_test
+group_pmc56_exclude_constraints_test
+hw_cache_event_type_test
+invalid_event_code_test
+reserved_bits_mmcra_sample_elig_mode_test
+reserved_bits_mmcra_thresh_ctl_test
diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/.gitignore b/tools/testing/selftests/powerpc/pmu/sampling_tests/.gitignore
index 0fce5a694684..f93b4c7c3a8a 100644
--- a/tools/testing/selftests/powerpc/pmu/sampling_tests/.gitignore
+++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/.gitignore
@@ -1,11 +1,21 @@
-mmcr0_exceptionbits_test
+bhrb_filter_map_test
+bhrb_no_crash_wo_pmu_test
+intr_regs_no_crash_wo_pmu_test
 mmcr0_cc56run_test
-mmcr0_pmccext_test
-mmcr0_pmcjce_test
+mmcr0_exceptionbits_test
 mmcr0_fc56_pmc1ce_test
 mmcr0_fc56_pmc56_test
+mmcr0_pmccext_test
+mmcr0_pmcjce_test
 mmcr1_comb_test
-mmcr2_l2l3_test
+mmcr1_sel_unit_cache_test
 mmcr2_fcs_fch_test
+mmcr2_l2l3_test
 mmcr3_src_test
+mmcra_bhrb_any_test
+mmcra_bhrb_cond_test
+mmcra_bhrb_disable_no_branch_test
+mmcra_bhrb_disable_test
+mmcra_bhrb_ind_call_test
+mmcra_thresh_cmp_test
 mmcra_thresh_marked_sample_test
diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c
index 50c5ab1aa6fa..a07896a46364 100644
--- a/tools/testing/selftests/sgx/sigstruct.c
+++ b/tools/testing/selftests/sgx/sigstruct.c
@@ -17,6 +17,12 @@
 #include "defines.h"
 #include "main.h"
 
+/*
+ * FIXME: OpenSSL 3.0 has deprecated some functions. For now just ignore
+ * the warnings.
+ */
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
+
 struct q1q2_ctx {
 	BN_CTX *bn_ctx;
 	BIGNUM *m;
diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile
index 1bea2d16d4c1..22e28b76f800 100644
--- a/tools/tracing/rtla/Makefile
+++ b/tools/tracing/rtla/Makefile
@@ -30,8 +30,8 @@ WOPTS	:= 	-Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_A
 
 TRACEFS_HEADERS	:= $$($(PKG_CONFIG) --cflags libtracefs)
 
-CFLAGS	:=	-O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS)
-LDFLAGS	:=	-ggdb
+CFLAGS	:=	-O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS)
+LDFLAGS	:=	-ggdb $(EXTRA_LDFLAGS)
 LIBS	:=	$$($(PKG_CONFIG) --libs libtracefs)
 
 SRC	:=	$(wildcard src/*.c)
@@ -61,40 +61,50 @@ endif
 LIBTRACEEVENT_MIN_VERSION = 1.5
 LIBTRACEFS_MIN_VERSION = 1.3
 
+.PHONY:	all warnings show_warnings
+all:	warnings rtla
+
 TEST_LIBTRACEEVENT = $(shell sh -c "$(PKG_CONFIG) --atleast-version $(LIBTRACEEVENT_MIN_VERSION) libtraceevent > /dev/null 2>&1 || echo n")
 ifeq ("$(TEST_LIBTRACEEVENT)", "n")
-.PHONY: warning_traceevent
-warning_traceevent:
-	@echo "********************************************"
-	@echo "** NOTICE: libtraceevent version $(LIBTRACEEVENT_MIN_VERSION) or higher not found"
-	@echo "**"
-	@echo "** Consider installing the latest libtraceevent from your"
-	@echo "** distribution, e.g., 'dnf install libtraceevent' on Fedora,"
-	@echo "** or from source:"
-	@echo "**"
-	@echo "**  https://git.kernel.org/pub/scm/libs/libtrace/libtraceevent.git/ "
-	@echo "**"
-	@echo "********************************************"
+WARNINGS = show_warnings
+MISSING_LIBS += echo "**   libtraceevent version $(LIBTRACEEVENT_MIN_VERSION) or higher";
+MISSING_PACKAGES += "libtraceevent-devel"
+MISSING_SOURCE += echo "**  https://git.kernel.org/pub/scm/libs/libtrace/libtraceevent.git/ ";
 endif
 
 TEST_LIBTRACEFS = $(shell sh -c "$(PKG_CONFIG) --atleast-version $(LIBTRACEFS_MIN_VERSION) libtracefs > /dev/null 2>&1 || echo n")
 ifeq ("$(TEST_LIBTRACEFS)", "n")
-.PHONY: warning_tracefs
-warning_tracefs:
-	@echo "********************************************"
-	@echo "** NOTICE: libtracefs version $(LIBTRACEFS_MIN_VERSION) or higher not found"
-	@echo "**"
-	@echo "** Consider installing the latest libtracefs from your"
-	@echo "** distribution, e.g., 'dnf install libtracefs' on Fedora,"
-	@echo "** or from source:"
-	@echo "**"
-	@echo "**  https://git.kernel.org/pub/scm/libs/libtrace/libtracefs.git/ "
-	@echo "**"
-	@echo "********************************************"
+WARNINGS = show_warnings
+MISSING_LIBS += echo "**   libtracefs version $(LIBTRACEFS_MIN_VERSION) or higher";
+MISSING_PACKAGES += "libtracefs-devel"
+MISSING_SOURCE += echo "**  https://git.kernel.org/pub/scm/libs/libtrace/libtracefs.git/ ";
 endif
 
-.PHONY:	all
-all:	rtla
+define show_dependencies
+	@echo "********************************************";				\
+	echo "** NOTICE: Failed build dependencies";					\
+	echo "**";									\
+	echo "** Required Libraries:";							\
+	$(MISSING_LIBS)									\
+	echo "**";									\
+	echo "** Consider installing the latest libtracefs from your";			\
+	echo "** distribution, e.g., 'dnf install $(MISSING_PACKAGES)' on Fedora,";	\
+	echo "** or from source:";							\
+	echo "**";									\
+	$(MISSING_SOURCE)								\
+	echo "**";									\
+	echo "********************************************"
+endef
+
+show_warnings:
+	$(call show_dependencies);
+
+ifneq ("$(WARNINGS)", "")
+ERROR_OUT = $(error Please add the necessary dependencies)
+
+warnings: $(WARNINGS)
+	$(ERROR_OUT)
+endif
 
 rtla: $(OBJ)
 	$(CC) -o rtla $(LDFLAGS) $(OBJ) $(LIBS)
@@ -108,9 +118,9 @@ install: doc_install
 	$(INSTALL) rtla -m 755 $(DESTDIR)$(BINDIR)
 	$(STRIP) $(DESTDIR)$(BINDIR)/rtla
 	@test ! -f $(DESTDIR)$(BINDIR)/osnoise || rm $(DESTDIR)$(BINDIR)/osnoise
-	ln -s $(DESTDIR)$(BINDIR)/rtla $(DESTDIR)$(BINDIR)/osnoise
+	ln -s rtla $(DESTDIR)$(BINDIR)/osnoise
 	@test ! -f $(DESTDIR)$(BINDIR)/timerlat || rm $(DESTDIR)$(BINDIR)/timerlat
-	ln -s $(DESTDIR)$(BINDIR)/rtla $(DESTDIR)$(BINDIR)/timerlat
+	ln -s rtla $(DESTDIR)$(BINDIR)/timerlat
 
 .PHONY: clean tarball
 clean: doc_clean
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index f3ec628f5e51..4b48af8a8309 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -892,7 +892,7 @@ int timerlat_hist_main(int argc, char *argv[])
 	return_value = 0;
 
 	if (trace_is_off(&tool->trace, &record->trace)) {
-		printf("rtla timelat hit stop tracing\n");
+		printf("rtla timerlat hit stop tracing\n");
 		if (params->trace_output) {
 			printf("  Saving trace to %s\n", params->trace_output);
 			save_trace_to_file(record->trace.inst, params->trace_output);
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
index 35452a1d45e9..334271935222 100644
--- a/tools/tracing/rtla/src/timerlat_top.c
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -687,7 +687,7 @@ int timerlat_top_main(int argc, char *argv[])
 	return_value = 0;
 
 	if (trace_is_off(&top->trace, &record->trace)) {
-		printf("rtla timelat hit stop tracing\n");
+		printf("rtla timerlat hit stop tracing\n");
 		if (params->trace_output) {
 			printf("  Saving trace to %s\n", params->trace_output);
 			save_trace_to_file(record->trace.inst, params->trace_output);