Merge branch 'master' into mm-stable

55 files changed, 1108 insertions, 504 deletions

diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index e09d6908a21d..8aa0d276a636 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -36,7 +36,7 @@
 #define MIDR_VARIANT(midr)	\
 	(((midr) & MIDR_VARIANT_MASK) >> MIDR_VARIANT_SHIFT)
 #define MIDR_IMPLEMENTOR_SHIFT	24
-#define MIDR_IMPLEMENTOR_MASK	(0xff << MIDR_IMPLEMENTOR_SHIFT)
+#define MIDR_IMPLEMENTOR_MASK	(0xffU << MIDR_IMPLEMENTOR_SHIFT)
 #define MIDR_IMPLEMENTOR(midr)	\
 	(((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT)
 
@@ -118,6 +118,10 @@
 
 #define APPLE_CPU_PART_M1_ICESTORM	0x022
 #define APPLE_CPU_PART_M1_FIRESTORM	0x023
+#define APPLE_CPU_PART_M1_ICESTORM_PRO	0x024
+#define APPLE_CPU_PART_M1_FIRESTORM_PRO	0x025
+#define APPLE_CPU_PART_M1_ICESTORM_MAX	0x028
+#define APPLE_CPU_PART_M1_FIRESTORM_MAX	0x029
 
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
@@ -164,6 +168,10 @@
 #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110)
 #define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM)
 #define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM)
+#define MIDR_APPLE_M1_ICESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_PRO)
+#define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO)
+#define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX)
+#define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX)
 
 /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
 #define MIDR_FUJITSU_ERRATUM_010001		MIDR_FUJITSU_A64FX
@@ -172,7 +180,7 @@
 
 #ifndef __ASSEMBLY__
 
-#include "sysreg.h"
+#include <asm/sysreg.h>
 
 #define read_cpuid(reg)			read_sysreg_s(SYS_ ## reg)
 
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 73e643ae94b6..03acc823838a 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -201,7 +201,7 @@
 #define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
-/* FREE!                                ( 7*32+10) */
+#define X86_FEATURE_XCOMPACTED		( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */
 #define X86_FEATURE_PTI			( 7*32+11) /* Kernel Page Table Isolation enabled */
 #define X86_FEATURE_RETPOLINE		( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_RETPOLINE_LFENCE	( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */
@@ -211,7 +211,7 @@
 #define X86_FEATURE_SSBD		( 7*32+17) /* Speculative Store Bypass Disable */
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* "" Fill RSB on context switches */
-/* FREE!                                ( 7*32+20) */
+#define X86_FEATURE_PERFMON_V2		( 7*32+20) /* AMD Performance Monitoring Version 2 */
 #define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
 #define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* "" Use IBRS during runtime firmware calls */
 #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* "" Disable Speculative Store Bypass. */
@@ -238,6 +238,7 @@
 #define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
 #define X86_FEATURE_PVUNLOCK		( 8*32+20) /* "" PV unlock function */
 #define X86_FEATURE_VCPUPREEMPT		( 8*32+21) /* "" PV vcpu_is_preempted function */
+#define X86_FEATURE_TDX_GUEST		( 8*32+22) /* Intel Trust Domain Extensions Guest */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
@@ -315,6 +316,7 @@
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 #define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
 #define X86_FEATURE_CPPC		(13*32+27) /* Collaborative Processor Performance Control */
+#define X86_FEATURE_BRS			(13*32+31) /* Branch Sampling available */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
@@ -405,6 +407,7 @@
 #define X86_FEATURE_SEV			(19*32+ 1) /* AMD Secure Encrypted Virtualization */
 #define X86_FEATURE_VM_PAGE_FLUSH	(19*32+ 2) /* "" VM Page Flush MSR is supported */
 #define X86_FEATURE_SEV_ES		(19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
+#define X86_FEATURE_V_TSC_AUX		(19*32+ 9) /* "" Virtual TSC_AUX */
 #define X86_FEATURE_SME_COHERENT	(19*32+10) /* "" AMD hardware-enforced cache coherency */
 
 /*
@@ -443,5 +446,6 @@
 #define X86_BUG_TAA			X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */
 #define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
 #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 */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 1ae0fab7d902..36369e76cc63 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -62,6 +62,12 @@
 # define DISABLE_SGX	(1 << (X86_FEATURE_SGX & 31))
 #endif
 
+#ifdef CONFIG_INTEL_TDX_GUEST
+# define DISABLE_TDX_GUEST	0
+#else
+# define DISABLE_TDX_GUEST	(1 << (X86_FEATURE_TDX_GUEST & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -73,7 +79,7 @@
 #define DISABLED_MASK5	0
 #define DISABLED_MASK6	0
 #define DISABLED_MASK7	(DISABLE_PTI)
-#define DISABLED_MASK8	0
+#define DISABLED_MASK8	(DISABLE_TDX_GUEST)
 #define DISABLED_MASK9	(DISABLE_SGX)
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	0
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 403e83b4adc8..d27e0581b777 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -116,6 +116,30 @@
 						 * Not susceptible to
 						 * TSX Async Abort (TAA) vulnerabilities.
 						 */
+#define ARCH_CAP_SBDR_SSDP_NO		BIT(13)	/*
+						 * Not susceptible to SBDR and SSDP
+						 * variants of Processor MMIO stale data
+						 * vulnerabilities.
+						 */
+#define ARCH_CAP_FBSDP_NO		BIT(14)	/*
+						 * Not susceptible to FBSDP variant of
+						 * Processor MMIO stale data
+						 * vulnerabilities.
+						 */
+#define ARCH_CAP_PSDP_NO		BIT(15)	/*
+						 * Not susceptible to PSDP variant of
+						 * Processor MMIO stale data
+						 * vulnerabilities.
+						 */
+#define ARCH_CAP_FB_CLEAR		BIT(17)	/*
+						 * VERW clears CPU fill buffer
+						 * even on MDS_NO CPUs.
+						 */
+#define ARCH_CAP_FB_CLEAR_CTRL		BIT(18)	/*
+						 * MSR_IA32_MCU_OPT_CTRL[FB_CLEAR_DIS]
+						 * bit available to control VERW
+						 * behavior.
+						 */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
@@ -133,6 +157,7 @@
 #define MSR_IA32_MCU_OPT_CTRL		0x00000123
 #define RNGDS_MITG_DIS			BIT(0)	/* SRBDS support */
 #define RTM_ALLOW			BIT(1)	/* TSX development mode */
+#define FB_CLEAR_DIS			BIT(3)	/* CPU Fill buffer clear disable */
 
 #define MSR_IA32_SYSENTER_CS		0x00000174
 #define MSR_IA32_SYSENTER_ESP		0x00000175
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index bf6e96011dfe..21614807a2cb 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -428,11 +428,12 @@ struct kvm_sync_regs {
 	struct kvm_vcpu_events events;
 };
 
-#define KVM_X86_QUIRK_LINT0_REENABLED	   (1 << 0)
-#define KVM_X86_QUIRK_CD_NW_CLEARED	   (1 << 1)
-#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE	   (1 << 2)
-#define KVM_X86_QUIRK_OUT_7E_INC_RIP	   (1 << 3)
-#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4)
+#define KVM_X86_QUIRK_LINT0_REENABLED		(1 << 0)
+#define KVM_X86_QUIRK_CD_NW_CLEARED		(1 << 1)
+#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE		(1 << 2)
+#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_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
index efa969325ede..f69c168391aa 100644
--- a/tools/arch/x86/include/uapi/asm/svm.h
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -108,6 +108,14 @@
 #define SVM_VMGEXIT_AP_JUMP_TABLE		0x80000005
 #define SVM_VMGEXIT_SET_AP_JUMP_TABLE		0
 #define SVM_VMGEXIT_GET_AP_JUMP_TABLE		1
+#define SVM_VMGEXIT_PSC				0x80000010
+#define SVM_VMGEXIT_GUEST_REQUEST		0x80000011
+#define SVM_VMGEXIT_EXT_GUEST_REQUEST		0x80000012
+#define SVM_VMGEXIT_AP_CREATION			0x80000013
+#define SVM_VMGEXIT_AP_CREATE_ON_INIT		0
+#define SVM_VMGEXIT_AP_CREATE			1
+#define SVM_VMGEXIT_AP_DESTROY			2
+#define SVM_VMGEXIT_HV_FEATURES			0x8000fffd
 #define SVM_VMGEXIT_UNSUPPORTED_EVENT		0x8000ffff
 
 /* Exit code reserved for hypervisor/software use */
@@ -218,6 +226,11 @@
 	{ SVM_VMGEXIT_NMI_COMPLETE,	"vmgexit_nmi_complete" }, \
 	{ SVM_VMGEXIT_AP_HLT_LOOP,	"vmgexit_ap_hlt_loop" }, \
 	{ SVM_VMGEXIT_AP_JUMP_TABLE,	"vmgexit_ap_jump_table" }, \
+	{ SVM_VMGEXIT_PSC,		"vmgexit_page_state_change" }, \
+	{ SVM_VMGEXIT_GUEST_REQUEST,	"vmgexit_guest_request" }, \
+	{ SVM_VMGEXIT_EXT_GUEST_REQUEST, "vmgexit_ext_guest_request" }, \
+	{ SVM_VMGEXIT_AP_CREATION,	"vmgexit_ap_creation" }, \
+	{ SVM_VMGEXIT_HV_FEATURES,	"vmgexit_hypervisor_feature" }, \
 	{ SVM_EXIT_ERR,         "invalid_guest_state" }
 
 
diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h
index 6491fa8fba6d..15b940ec1eac 100644
--- a/tools/include/linux/objtool.h
+++ b/tools/include/linux/objtool.h
@@ -143,6 +143,12 @@ struct unwind_hint {
 	.popsection
 .endm
 
+.macro STACK_FRAME_NON_STANDARD_FP func:req
+#ifdef CONFIG_FRAME_POINTER
+	STACK_FRAME_NON_STANDARD \func
+#endif
+.endm
+
 .macro ANNOTATE_NOENDBR
 .Lhere_\@:
 	.pushsection .discard.noendbr
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 05c3642aaece..a2def7b27009 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -154,25 +154,77 @@ enum i915_mocs_table_index {
 	I915_MOCS_CACHED,
 };
 
-/*
+/**
+ * enum drm_i915_gem_engine_class - uapi engine type enumeration
+ *
  * Different engines serve different roles, and there may be more than one
- * engine serving each role. enum drm_i915_gem_engine_class provides a
- * classification of the role of the engine, which may be used when requesting
- * operations to be performed on a certain subset of engines, or for providing
- * information about that group.
+ * engine serving each role.  This enum provides a classification of the role
+ * of the engine, which may be used when requesting operations to be performed
+ * on a certain subset of engines, or for providing information about that
+ * group.
  */
 enum drm_i915_gem_engine_class {
+	/**
+	 * @I915_ENGINE_CLASS_RENDER:
+	 *
+	 * Render engines support instructions used for 3D, Compute (GPGPU),
+	 * and programmable media workloads.  These instructions fetch data and
+	 * dispatch individual work items to threads that operate in parallel.
+	 * The threads run small programs (called "kernels" or "shaders") on
+	 * the GPU's execution units (EUs).
+	 */
 	I915_ENGINE_CLASS_RENDER	= 0,
+
+	/**
+	 * @I915_ENGINE_CLASS_COPY:
+	 *
+	 * Copy engines (also referred to as "blitters") support instructions
+	 * that move blocks of data from one location in memory to another,
+	 * or that fill a specified location of memory with fixed data.
+	 * Copy engines can perform pre-defined logical or bitwise operations
+	 * on the source, destination, or pattern data.
+	 */
 	I915_ENGINE_CLASS_COPY		= 1,
+
+	/**
+	 * @I915_ENGINE_CLASS_VIDEO:
+	 *
+	 * Video engines (also referred to as "bit stream decode" (BSD) or
+	 * "vdbox") support instructions that perform fixed-function media
+	 * decode and encode.
+	 */
 	I915_ENGINE_CLASS_VIDEO		= 2,
+
+	/**
+	 * @I915_ENGINE_CLASS_VIDEO_ENHANCE:
+	 *
+	 * Video enhancement engines (also referred to as "vebox") support
+	 * instructions related to image enhancement.
+	 */
 	I915_ENGINE_CLASS_VIDEO_ENHANCE	= 3,
 
-	/* should be kept compact */
+	/**
+	 * @I915_ENGINE_CLASS_COMPUTE:
+	 *
+	 * Compute engines support a subset of the instructions available
+	 * on render engines:  compute engines support Compute (GPGPU) and
+	 * programmable media workloads, but do not support the 3D pipeline.
+	 */
+	I915_ENGINE_CLASS_COMPUTE	= 4,
+
+	/* Values in this enum should be kept compact. */
 
+	/**
+	 * @I915_ENGINE_CLASS_INVALID:
+	 *
+	 * Placeholder value to represent an invalid engine class assignment.
+	 */
 	I915_ENGINE_CLASS_INVALID	= -1
 };
 
-/*
+/**
+ * struct i915_engine_class_instance - Engine class/instance identifier
+ *
  * There may be more than one engine fulfilling any role within the system.
  * Each engine of a class is given a unique instance number and therefore
  * any engine can be specified by its class:instance tuplet. APIs that allow
@@ -180,10 +232,21 @@ enum drm_i915_gem_engine_class {
  * for this identification.
  */
 struct i915_engine_class_instance {
-	__u16 engine_class; /* see enum drm_i915_gem_engine_class */
-	__u16 engine_instance;
+	/**
+	 * @engine_class:
+	 *
+	 * Engine class from enum drm_i915_gem_engine_class
+	 */
+	__u16 engine_class;
 #define I915_ENGINE_CLASS_INVALID_NONE -1
 #define I915_ENGINE_CLASS_INVALID_VIRTUAL -2
+
+	/**
+	 * @engine_instance:
+	 *
+	 * Engine instance.
+	 */
+	__u16 engine_instance;
 };
 
 /**
@@ -2657,24 +2720,65 @@ enum drm_i915_perf_record_type {
 	DRM_I915_PERF_RECORD_MAX /* non-ABI */
 };
 
-/*
+/**
+ * struct drm_i915_perf_oa_config
+ *
  * Structure to upload perf dynamic configuration into the kernel.
  */
 struct drm_i915_perf_oa_config {
-	/** String formatted like "%08x-%04x-%04x-%04x-%012x" */
+	/**
+	 * @uuid:
+	 *
+	 * String formatted like "%\08x-%\04x-%\04x-%\04x-%\012x"
+	 */
 	char uuid[36];
 
+	/**
+	 * @n_mux_regs:
+	 *
+	 * Number of mux regs in &mux_regs_ptr.
+	 */
 	__u32 n_mux_regs;
+
+	/**
+	 * @n_boolean_regs:
+	 *
+	 * Number of boolean regs in &boolean_regs_ptr.
+	 */
 	__u32 n_boolean_regs;
+
+	/**
+	 * @n_flex_regs:
+	 *
+	 * Number of flex regs in &flex_regs_ptr.
+	 */
 	__u32 n_flex_regs;
 
-	/*
-	 * These fields are pointers to tuples of u32 values (register address,
-	 * value). For example the expected length of the buffer pointed by
-	 * mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
+	/**
+	 * @mux_regs_ptr:
+	 *
+	 * Pointer to tuples of u32 values (register address, value) for mux
+	 * registers.  Expected length of buffer is (2 * sizeof(u32) *
+	 * &n_mux_regs).
 	 */
 	__u64 mux_regs_ptr;
+
+	/**
+	 * @boolean_regs_ptr:
+	 *
+	 * Pointer to tuples of u32 values (register address, value) for mux
+	 * registers.  Expected length of buffer is (2 * sizeof(u32) *
+	 * &n_boolean_regs).
+	 */
 	__u64 boolean_regs_ptr;
+
+	/**
+	 * @flex_regs_ptr:
+	 *
+	 * Pointer to tuples of u32 values (register address, value) for mux
+	 * registers.  Expected length of buffer is (2 * sizeof(u32) *
+	 * &n_flex_regs).
+	 */
 	__u64 flex_regs_ptr;
 };
 
@@ -2685,12 +2789,24 @@ struct drm_i915_perf_oa_config {
  * @data_ptr is also depends on the specific @query_id.
  */
 struct drm_i915_query_item {
-	/** @query_id: The id for this query */
+	/**
+	 * @query_id:
+	 *
+	 * The id for this query.  Currently accepted query IDs are:
+	 *  - %DRM_I915_QUERY_TOPOLOGY_INFO (see struct drm_i915_query_topology_info)
+	 *  - %DRM_I915_QUERY_ENGINE_INFO (see struct drm_i915_engine_info)
+	 *  - %DRM_I915_QUERY_PERF_CONFIG (see struct drm_i915_query_perf_config)
+	 *  - %DRM_I915_QUERY_MEMORY_REGIONS (see struct drm_i915_query_memory_regions)
+	 *  - %DRM_I915_QUERY_HWCONFIG_BLOB (see `GuC HWCONFIG blob uAPI`)
+	 *  - %DRM_I915_QUERY_GEOMETRY_SUBSLICES (see struct drm_i915_query_topology_info)
+	 */
 	__u64 query_id;
-#define DRM_I915_QUERY_TOPOLOGY_INFO    1
-#define DRM_I915_QUERY_ENGINE_INFO	2
-#define DRM_I915_QUERY_PERF_CONFIG      3
-#define DRM_I915_QUERY_MEMORY_REGIONS   4
+#define DRM_I915_QUERY_TOPOLOGY_INFO		1
+#define DRM_I915_QUERY_ENGINE_INFO		2
+#define DRM_I915_QUERY_PERF_CONFIG		3
+#define DRM_I915_QUERY_MEMORY_REGIONS		4
+#define DRM_I915_QUERY_HWCONFIG_BLOB		5
+#define DRM_I915_QUERY_GEOMETRY_SUBSLICES	6
 /* Must be kept compact -- no holes and well documented */
 
 	/**
@@ -2706,14 +2822,17 @@ struct drm_i915_query_item {
 	/**
 	 * @flags:
 	 *
-	 * When query_id == DRM_I915_QUERY_TOPOLOGY_INFO, must be 0.
+	 * When &query_id == %DRM_I915_QUERY_TOPOLOGY_INFO, must be 0.
 	 *
-	 * When query_id == DRM_I915_QUERY_PERF_CONFIG, must be one of the
+	 * When &query_id == %DRM_I915_QUERY_PERF_CONFIG, must be one of the
 	 * following:
 	 *
-	 *	- DRM_I915_QUERY_PERF_CONFIG_LIST
-	 *      - DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID
-	 *      - DRM_I915_QUERY_PERF_CONFIG_FOR_UUID
+	 *	- %DRM_I915_QUERY_PERF_CONFIG_LIST
+	 *      - %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID
+	 *      - %DRM_I915_QUERY_PERF_CONFIG_FOR_UUID
+	 *
+	 * When &query_id == %DRM_I915_QUERY_GEOMETRY_SUBSLICES must contain
+	 * a struct i915_engine_class_instance that references a render engine.
 	 */
 	__u32 flags;
 #define DRM_I915_QUERY_PERF_CONFIG_LIST          1
@@ -2771,66 +2890,112 @@ struct drm_i915_query {
 	__u64 items_ptr;
 };
 
-/*
- * Data written by the kernel with query DRM_I915_QUERY_TOPOLOGY_INFO :
- *
- * data: contains the 3 pieces of information :
- *
- * - the slice mask with one bit per slice telling whether a slice is
- *   available. The availability of slice X can be queried with the following
- *   formula :
- *
- *           (data[X / 8] >> (X % 8)) & 1
- *
- * - the subslice mask for each slice with one bit per subslice telling
- *   whether a subslice is available. Gen12 has dual-subslices, which are
- *   similar to two gen11 subslices. For gen12, this array represents dual-
- *   subslices. The availability of subslice Y in slice X can be queried
- *   with the following formula :
- *
- *           (data[subslice_offset +
- *                 X * subslice_stride +
- *                 Y / 8] >> (Y % 8)) & 1
- *
- * - the EU mask for each subslice in each slice with one bit per EU telling
- *   whether an EU is available. The availability of EU Z in subslice Y in
- *   slice X can be queried with the following formula :
+/**
+ * struct drm_i915_query_topology_info
  *
- *           (data[eu_offset +
- *                 (X * max_subslices + Y) * eu_stride +
- *                 Z / 8] >> (Z % 8)) & 1
+ * Describes slice/subslice/EU information queried by
+ * %DRM_I915_QUERY_TOPOLOGY_INFO
  */
 struct drm_i915_query_topology_info {
-	/*
+	/**
+	 * @flags:
+	 *
 	 * Unused for now. Must be cleared to zero.
 	 */
 	__u16 flags;
 
+	/**
+	 * @max_slices:
+	 *
+	 * The number of bits used to express the slice mask.
+	 */
 	__u16 max_slices;
+
+	/**
+	 * @max_subslices:
+	 *
+	 * The number of bits used to express the subslice mask.
+	 */
 	__u16 max_subslices;
+
+	/**
+	 * @max_eus_per_subslice:
+	 *
+	 * The number of bits in the EU mask that correspond to a single
+	 * subslice's EUs.
+	 */
 	__u16 max_eus_per_subslice;
 
-	/*
+	/**
+	 * @subslice_offset:
+	 *
 	 * Offset in data[] at which the subslice masks are stored.
 	 */
 	__u16 subslice_offset;
 
-	/*
+	/**
+	 * @subslice_stride:
+	 *
 	 * Stride at which each of the subslice masks for each slice are
 	 * stored.
 	 */
 	__u16 subslice_stride;
 
-	/*
+	/**
+	 * @eu_offset:
+	 *
 	 * Offset in data[] at which the EU masks are stored.
 	 */
 	__u16 eu_offset;
 
-	/*
+	/**
+	 * @eu_stride:
+	 *
 	 * Stride at which each of the EU masks for each subslice are stored.
 	 */
 	__u16 eu_stride;
 
+	/**
+	 * @data:
+	 *
+	 * Contains 3 pieces of information :
+	 *
+	 * - The slice mask with one bit per slice telling whether a slice is
+	 *   available. The availability of slice X can be queried with the
+	 *   following formula :
+	 *
+	 *   .. code:: c
+	 *
+	 *      (data[X / 8] >> (X % 8)) & 1
+	 *
+	 *   Starting with Xe_HP platforms, Intel hardware no longer has
+	 *   traditional slices so i915 will always report a single slice
+	 *   (hardcoded slicemask = 0x1) which contains all of the platform's
+	 *   subslices.  I.e., the mask here does not reflect any of the newer
+	 *   hardware concepts such as "gslices" or "cslices" since userspace
+	 *   is capable of inferring those from the subslice mask.
+	 *
+	 * - The subslice mask for each slice with one bit per subslice telling
+	 *   whether a subslice is available.  Starting with Gen12 we use the
+	 *   term "subslice" to refer to what the hardware documentation
+	 *   describes as a "dual-subslices."  The availability of subslice Y
+	 *   in slice X can be queried with the following formula :
+	 *
+	 *   .. code:: c
+	 *
+	 *      (data[subslice_offset + X * subslice_stride + Y / 8] >> (Y % 8)) & 1
+	 *
+	 * - The EU mask for each subslice in each slice, with one bit per EU
+	 *   telling whether an EU is available. The availability of EU Z in
+	 *   subslice Y in slice X can be queried with the following formula :
+	 *
+	 *   .. code:: c
+	 *
+	 *      (data[eu_offset +
+	 *            (X * max_subslices + Y) * eu_stride +
+	 *            Z / 8
+	 *       ] >> (Z % 8)) & 1
+	 */
 	__u8 data[];
 };
 
@@ -2951,52 +3116,68 @@ struct drm_i915_query_engine_info {
 	struct drm_i915_engine_info engines[];
 };
 
-/*
- * Data written by the kernel with query DRM_I915_QUERY_PERF_CONFIG.
+/**
+ * struct drm_i915_query_perf_config
+ *
+ * Data written by the kernel with query %DRM_I915_QUERY_PERF_CONFIG and
+ * %DRM_I915_QUERY_GEOMETRY_SUBSLICES.
  */
 struct drm_i915_query_perf_config {
 	union {
-		/*
-		 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets
-		 * this fields to the number of configurations available.
+		/**
+		 * @n_configs:
+		 *
+		 * When &drm_i915_query_item.flags ==
+		 * %DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets this fields to
+		 * the number of configurations available.
 		 */
 		__u64 n_configs;
 
-		/*
-		 * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID,
-		 * i915 will use the value in this field as configuration
-		 * identifier to decide what data to write into config_ptr.
+		/**
+		 * @config:
+		 *
+		 * When &drm_i915_query_item.flags ==
+		 * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID, i915 will use the
+		 * value in this field as configuration identifier to decide
+		 * what data to write into config_ptr.
 		 */
 		__u64 config;
 
-		/*
-		 * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID,
-		 * i915 will use the value in this field as configuration
-		 * identifier to decide what data to write into config_ptr.
+		/**
+		 * @uuid:
+		 *
+		 * When &drm_i915_query_item.flags ==
+		 * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID, i915 will use the
+		 * value in this field as configuration identifier to decide
+		 * what data to write into config_ptr.
 		 *
 		 * String formatted like "%08x-%04x-%04x-%04x-%012x"
 		 */
 		char uuid[36];
 	};
 
-	/*
+	/**
+	 * @flags:
+	 *
 	 * Unused for now. Must be cleared to zero.
 	 */
 	__u32 flags;
 
-	/*
-	 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 will
-	 * write an array of __u64 of configuration identifiers.
+	/**
+	 * @data:
 	 *
-	 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_DATA, i915 will
-	 * write a struct drm_i915_perf_oa_config. If the following fields of
-	 * drm_i915_perf_oa_config are set not set to 0, i915 will write into
-	 * the associated pointers the values of submitted when the
+	 * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_LIST,
+	 * i915 will write an array of __u64 of configuration identifiers.
+	 *
+	 * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_DATA,
+	 * i915 will write a struct drm_i915_perf_oa_config. If the following
+	 * fields of struct drm_i915_perf_oa_config are not set to 0, i915 will
+	 * write into the associated pointers the values of submitted when the
 	 * configuration was created :
 	 *
-	 *         - n_mux_regs
-	 *         - n_boolean_regs
-	 *         - n_flex_regs
+	 *  - &drm_i915_perf_oa_config.n_mux_regs
+	 *  - &drm_i915_perf_oa_config.n_boolean_regs
+	 *  - &drm_i915_perf_oa_config.n_flex_regs
 	 */
 	__u8 data[];
 };
@@ -3135,6 +3316,16 @@ struct drm_i915_query_memory_regions {
 };
 
 /**
+ * DOC: GuC HWCONFIG blob uAPI
+ *
+ * The GuC produces a blob with information about the current device.
+ * i915 reads this blob from GuC and makes it available via this uAPI.
+ *
+ * The format and meaning of the blob content are documented in the
+ * Programmer's Reference Manual.
+ */
+
+/**
  * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added
  * extension support using struct i915_user_extension.
  *
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index e998764f0262..a5e06dcbba13 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -272,6 +272,15 @@ struct prctl_mm_map {
 # define PR_SCHED_CORE_SCOPE_THREAD_GROUP	1
 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP	2
 
+/* arm64 Scalable Matrix Extension controls */
+/* Flag values must be in sync with SVE versions */
+#define PR_SME_SET_VL			63	/* set task vector length */
+# define PR_SME_SET_VL_ONEXEC		(1 << 18) /* defer effect until exec */
+#define PR_SME_GET_VL			64	/* get task vector length */
+/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */
+# define PR_SME_VL_LEN_MASK		0xffff
+# define PR_SME_VL_INHERIT		(1 << 17) /* inherit across exec */
+
 #define PR_SET_VMA		0x53564d41
 # define PR_SET_VMA_ANON_NAME		0
 
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index 5d99e7c242a2..cab645d4a645 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -89,11 +89,6 @@
 
 /* Set or get vhost backend capability */
 
-/* Use message type V2 */
-#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1
-/* IOTLB can accept batching hints */
-#define VHOST_BACKEND_F_IOTLB_BATCH  0x2
-
 #define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64)
 #define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64)
 
@@ -150,11 +145,30 @@
 /* Get the valid iova range */
 #define VHOST_VDPA_GET_IOVA_RANGE	_IOR(VHOST_VIRTIO, 0x78, \
 					     struct vhost_vdpa_iova_range)
-
 /* Get the config size */
 #define VHOST_VDPA_GET_CONFIG_SIZE	_IOR(VHOST_VIRTIO, 0x79, __u32)
 
 /* Get the count of all virtqueues */
 #define VHOST_VDPA_GET_VQS_COUNT	_IOR(VHOST_VIRTIO, 0x80, __u32)
 
+/* Get the number of virtqueue groups. */
+#define VHOST_VDPA_GET_GROUP_NUM	_IOR(VHOST_VIRTIO, 0x81, __u32)
+
+/* Get the number of address spaces. */
+#define VHOST_VDPA_GET_AS_NUM		_IOR(VHOST_VIRTIO, 0x7A, unsigned int)
+
+/* Get the group for a virtqueue: read index, write group in num,
+ * The virtqueue index is stored in the index field of
+ * vhost_vring_state. The group for this specific virtqueue is
+ * returned via num field of vhost_vring_state.
+ */
+#define VHOST_VDPA_GET_VRING_GROUP	_IOWR(VHOST_VIRTIO, 0x7B,	\
+					      struct vhost_vring_state)
+/* Set the ASID for a virtqueue group. The group index is stored in
+ * the index field of vhost_vring_state, the ASID associated with this
+ * group is stored at num field of vhost_vring_state.
+ */
+#define VHOST_VDPA_SET_GROUP_ASID	_IOW(VHOST_VIRTIO, 0x7C, \
+					     struct vhost_vring_state)
+
 #endif
diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index 5a5bd74f55bd..9c366b3a676d 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -1646,7 +1646,8 @@ Press any other key to refresh statistics immediately.
                          .format(values))
             if len(pids) > 1:
                 sys.exit('Error: Multiple processes found (pids: {}). Use "-p"'
-                         ' to specify the desired pid'.format(" ".join(pids)))
+                         ' to specify the desired pid'
+                         .format(" ".join(map(str, pids))))
             namespace.pid = pids[0]
 
     argparser = argparse.ArgumentParser(description=description_text,
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index c1d58673f6ef..952f3520d5c2 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -149,23 +149,30 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 			int fd, group_fd, *evsel_fd;
 
 			evsel_fd = FD(evsel, idx, thread);
-			if (evsel_fd == NULL)
-				return -EINVAL;
+			if (evsel_fd == NULL) {
+				err = -EINVAL;
+				goto out;
+			}
 
 			err = get_group_fd(evsel, idx, thread, &group_fd);
 			if (err < 0)
-				return err;
+				goto out;
 
 			fd = sys_perf_event_open(&evsel->attr,
 						 threads->map[thread].pid,
 						 cpu, group_fd, 0);
 
-			if (fd < 0)
-				return -errno;
+			if (fd < 0) {
+				err = -errno;
+				goto out;
+			}
 
 			*evsel_fd = fd;
 		}
 	}
+out:
+	if (err)
+		perf_evsel__close(evsel);
 
 	return err;
 }
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index a75bf11585b5..54d4e508a092 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -891,7 +891,9 @@ static int copy_kcore_dir(struct perf_inject *inject)
 	if (ret < 0)
 		return ret;
 	pr_debug("%s\n", cmd);
-	return system(cmd);
+	ret = system(cmd);
+	free(cmd);
+	return ret;
 }
 
 static int output_fd(struct perf_inject *inject)
@@ -916,7 +918,7 @@ static int __cmd_inject(struct perf_inject *inject)
 		inject->tool.tracing_data = perf_event__repipe_tracing_data;
 	}
 
-	output_data_offset = session->header.data_offset;
+	output_data_offset = perf_session__data_offset(session->evlist);
 
 	if (inject->build_id_all) {
 		inject->tool.mmap	  = perf_event__repipe_buildid_mmap;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 4ce87a8eb7d7..d2ecd4d29624 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2586,6 +2586,8 @@ int cmd_stat(int argc, const char **argv)
 	if (evlist__initialize_ctlfd(evsel_list, stat_config.ctl_fd, stat_config.ctl_fd_ack))
 		goto out;
 
+	/* Enable ignoring missing threads when -p option is defined. */
+	evlist__first(evsel_list)->ignore_missing_thread = target.pid;
 	status = 0;
 	for (run_idx = 0; forever || run_idx < stat_config.run_count; run_idx++) {
 		if (stat_config.run_count != 1 && verbose > 0)
diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c
index d1ebb5561e5b..6f921db33cf9 100644
--- a/tools/perf/tests/bp_account.c
+++ b/tools/perf/tests/bp_account.c
@@ -151,11 +151,21 @@ static int detect_ioctl(void)
 static int detect_share(int wp_cnt, int bp_cnt)
 {
 	struct perf_event_attr attr;
-	int i, fd[wp_cnt + bp_cnt], ret;
+	int i, *fd = NULL, ret = -1;
+
+	if (wp_cnt + bp_cnt == 0)
+		return 0;
+
+	fd = malloc(sizeof(int) * (wp_cnt + bp_cnt));
+	if (!fd)
+		return -1;
 
 	for (i = 0; i < wp_cnt; i++) {
 		fd[i] = wp_event((void *)&the_var, &attr);
-		TEST_ASSERT_VAL("failed to create wp\n", fd[i] != -1);
+		if (fd[i] == -1) {
+			pr_err("failed to create wp\n");
+			goto out;
+		}
 	}
 
 	for (; i < (bp_cnt + wp_cnt); i++) {
@@ -166,9 +176,11 @@ static int detect_share(int wp_cnt, int bp_cnt)
 
 	ret = i != (bp_cnt + wp_cnt);
 
+out:
 	while (i--)
 		close(fd[i]);
 
+	free(fd);
 	return ret;
 }
 
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index d54c5371c6a6..5c0032fe93ae 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -97,6 +97,8 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
 	ret |= test(ctx, "2.2 > 2.2", 0);
 	ret |= test(ctx, "2.2 < 1.1", 0);
 	ret |= test(ctx, "1.1 > 2.2", 0);
+	ret |= test(ctx, "1.1e10 < 1.1e100", 1);
+	ret |= test(ctx, "1.1e2 > 1.1e-2", 1);
 
 	if (ret) {
 		expr__ctx_free(ctx);
diff --git a/tools/perf/tests/shell/lib/perf_csv_output_lint.py b/tools/perf/tests/shell/lib/perf_csv_output_lint.py
deleted file mode 100644
index 714f283cfb1b..000000000000
--- a/tools/perf/tests/shell/lib/perf_csv_output_lint.py
+++ /dev/null
@@ -1,48 +0,0 @@
-#!/usr/bin/python
-# SPDX-License-Identifier: GPL-2.0
-
-import argparse
-import sys
-
-# Basic sanity check of perf CSV output as specified in the man page.
-# Currently just checks the number of fields per line in output.
-
-ap = argparse.ArgumentParser()
-ap.add_argument('--no-args', action='store_true')
-ap.add_argument('--interval', action='store_true')
-ap.add_argument('--system-wide-no-aggr', action='store_true')
-ap.add_argument('--system-wide', action='store_true')
-ap.add_argument('--event', action='store_true')
-ap.add_argument('--per-core', action='store_true')
-ap.add_argument('--per-thread', action='store_true')
-ap.add_argument('--per-die', action='store_true')
-ap.add_argument('--per-node', action='store_true')
-ap.add_argument('--per-socket', action='store_true')
-ap.add_argument('--separator', default=',', nargs='?')
-args = ap.parse_args()
-
-Lines = sys.stdin.readlines()
-
-def check_csv_output(exp):
-  for line in Lines:
-    if 'failed' not in line:
-      count = line.count(args.separator)
-      if count != exp:
-        sys.stdout.write(''.join(Lines))
-        raise RuntimeError(f'wrong number of fields. expected {exp} in {line}')
-
-try:
-  if args.no_args or args.system_wide or args.event:
-    expected_items = 6
-  elif args.interval or args.per_thread or args.system_wide_no_aggr:
-    expected_items = 7
-  elif args.per_core or args.per_socket or args.per_node or args.per_die:
-    expected_items = 8
-  else:
-    ap.print_help()
-    raise RuntimeError('No checking option specified')
-  check_csv_output(expected_items)
-
-except:
-  sys.stdout.write('Test failed for input: ' + ''.join(Lines))
-  raise
diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh
index 983220ef3cb4..38c26f3ef4c1 100755
--- a/tools/perf/tests/shell/stat+csv_output.sh
+++ b/tools/perf/tests/shell/stat+csv_output.sh
@@ -6,20 +6,41 @@
 
 set -e
 
-pythonchecker=$(dirname $0)/lib/perf_csv_output_lint.py
-if [ "x$PYTHON" == "x" ]
-then
-	if which python3 > /dev/null
-	then
-		PYTHON=python3
-	elif which python > /dev/null
-	then
-		PYTHON=python
-	else
-		echo Skipping test, python not detected please set environment variable PYTHON.
-		exit 2
-	fi
-fi
+function commachecker()
+{
+	local -i cnt=0 exp=0
+
+	case "$1"
+	in "--no-args")		exp=6
+	;; "--system-wide")	exp=6
+	;; "--event")		exp=6
+	;; "--interval")	exp=7
+	;; "--per-thread")	exp=7
+	;; "--system-wide-no-aggr")	exp=7
+				[ $(uname -m) = "s390x" ] && exp=6
+	;; "--per-core")	exp=8
+	;; "--per-socket")	exp=8
+	;; "--per-node")	exp=8
+	;; "--per-die")		exp=8
+	esac
+
+	while read line
+	do
+		# Check for lines beginning with Failed
+		x=${line:0:6}
+		[ "$x" = "Failed" ] && continue
+
+		# Count the number of commas
+		x=$(echo $line | tr -d -c ',')
+		cnt="${#x}"
+		# echo $line $cnt
+		[ "$cnt" -ne "$exp" ] && {
+			echo "wrong number of fields. expected $exp in $line" 1>&2
+			exit 1;
+		}
+	done
+	return 0
+}
 
 # Return true if perf_event_paranoid is > $1 and not running as root.
 function ParanoidAndNotRoot()
@@ -30,7 +51,7 @@ function ParanoidAndNotRoot()
 check_no_args()
 {
 	echo -n "Checking CSV output: no args "
-	perf stat -x, true 2>&1 | $PYTHON $pythonchecker --no-args
+	perf stat -x, true 2>&1 | commachecker --no-args
 	echo "[Success]"
 }
 
@@ -42,7 +63,7 @@ check_system_wide()
 		echo "[Skip] paranoid and not root"
 		return
 	fi
-	perf stat -x, -a true 2>&1 | $PYTHON $pythonchecker --system-wide
+	perf stat -x, -a true 2>&1 | commachecker --system-wide
 	echo "[Success]"
 }
 
@@ -55,14 +76,14 @@ check_system_wide_no_aggr()
 		return
 	fi
 	echo -n "Checking CSV output: system wide no aggregation "
-	perf stat -x, -A -a --no-merge true 2>&1 | $PYTHON $pythonchecker --system-wide-no-aggr
+	perf stat -x, -A -a --no-merge true 2>&1 | commachecker --system-wide-no-aggr
 	echo "[Success]"
 }
 
 check_interval()
 {
 	echo -n "Checking CSV output: interval "
-	perf stat -x, -I 1000 true 2>&1 | $PYTHON $pythonchecker --interval
+	perf stat -x, -I 1000 true 2>&1 | commachecker --interval
 	echo "[Success]"
 }
 
@@ -70,7 +91,7 @@ check_interval()
 check_event()
 {
 	echo -n "Checking CSV output: event "
-	perf stat -x, -e cpu-clock true 2>&1 | $PYTHON $pythonchecker --event
+	perf stat -x, -e cpu-clock true 2>&1 | commachecker --event
 	echo "[Success]"
 }
 
@@ -82,7 +103,7 @@ check_per_core()
 		echo "[Skip] paranoid and not root"
 		return
 	fi
-	perf stat -x, --per-core -a true 2>&1 | $PYTHON $pythonchecker --per-core
+	perf stat -x, --per-core -a true 2>&1 | commachecker --per-core
 	echo "[Success]"
 }
 
@@ -94,7 +115,7 @@ check_per_thread()
 		echo "[Skip] paranoid and not root"
 		return
 	fi
-	perf stat -x, --per-thread -a true 2>&1 | $PYTHON $pythonchecker --per-thread
+	perf stat -x, --per-thread -a true 2>&1 | commachecker --per-thread
 	echo "[Success]"
 }
 
@@ -106,7 +127,7 @@ check_per_die()
 		echo "[Skip] paranoid and not root"
 		return
 	fi
-	perf stat -x, --per-die -a true 2>&1 | $PYTHON $pythonchecker --per-die
+	perf stat -x, --per-die -a true 2>&1 | commachecker --per-die
 	echo "[Success]"
 }
 
@@ -118,7 +139,7 @@ check_per_node()
 		echo "[Skip] paranoid and not root"
 		return
 	fi
-	perf stat -x, --per-node -a true 2>&1 | $PYTHON $pythonchecker --per-node
+	perf stat -x, --per-node -a true 2>&1 | commachecker --per-node
 	echo "[Success]"
 }
 
@@ -130,7 +151,7 @@ check_per_socket()
 		echo "[Skip] paranoid and not root"
 		return
 	fi
-	perf stat -x, --per-socket -a true 2>&1 | $PYTHON $pythonchecker --per-socket
+	perf stat -x, --per-socket -a true 2>&1 | commachecker --per-socket
 	echo "[Success]"
 }
 
diff --git a/tools/perf/tests/shell/test_arm_callgraph_fp.sh b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
index 6ffbb27afaba..ec108d45d3c6 100755
--- a/tools/perf/tests/shell/test_arm_callgraph_fp.sh
+++ b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
@@ -43,7 +43,7 @@ CFLAGS="-g -O0 -fno-inline -fno-omit-frame-pointer"
 cc $CFLAGS $TEST_PROGRAM_SOURCE -o $TEST_PROGRAM || exit 1
 
 # Add a 1 second delay to skip samples that are not in the leaf() function
-perf record -o $PERF_DATA --call-graph fp -e cycles//u -D 1000 -- $TEST_PROGRAM 2> /dev/null &
+perf record -o $PERF_DATA --call-graph fp -e cycles//u -D 1000 --user-callchains -- $TEST_PROGRAM 2> /dev/null &
 PID=$!
 
 echo " + Recording (PID=$PID)..."
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index d23a9e322ff5..0b4f61b6cc6b 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -115,7 +115,7 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 	 * physical_package_id will be set to -1. Hence skip this
 	 * test if physical_package_id returns -1 for cpu from perf_cpu_map.
 	 */
-	if (strncmp(session->header.env.arch, "powerpc", 7)) {
+	if (!strncmp(session->header.env.arch, "ppc64le", 7)) {
 		if (cpu__get_socket_id(perf_cpu_map__cpu(map, 0)) == -1)
 			return TEST_SKIP;
 	}
diff --git a/tools/perf/trace/beauty/arch_errno_names.sh b/tools/perf/trace/beauty/arch_errno_names.sh
index 2c5f72fa8108..37c53bac5f56 100755
--- a/tools/perf/trace/beauty/arch_errno_names.sh
+++ b/tools/perf/trace/beauty/arch_errno_names.sh
@@ -33,23 +33,13 @@ create_errno_lookup_func()
 	local arch=$(arch_string "$1")
 	local nr name
 
-	cat <<EoFuncBegin
-static const char *errno_to_name__$arch(int err)
-{
-	switch (err) {
-EoFuncBegin
+	printf "static const char *errno_to_name__%s(int err)\n{\n\tswitch (err) {\n" $arch
 
 	while read name nr; do
 		printf '\tcase %d: return "%s";\n' $nr $name
 	done
 
-	cat <<EoFuncEnd
-	default:
-		return "(unknown)";
-	}
-}
-
-EoFuncEnd
+	printf '\tdefault: return "(unknown)";\n\t}\n}\n'
 }
 
 process_arch()
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index 6f85f5d957ef..17311ad9f9af 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -50,6 +50,9 @@ struct linger {
 struct msghdr {
 	void		*msg_name;	/* ptr to socket address structure */
 	int		msg_namelen;	/* size of socket address structure */
+
+	int		msg_inq;	/* output, data left in socket */
+
 	struct iov_iter	msg_iter;	/* data */
 
 	/*
@@ -62,8 +65,9 @@ struct msghdr {
 		void __user	*msg_control_user;
 	};
 	bool		msg_control_is_user : 1;
-	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
+	bool		msg_get_inq : 1;/* return INQ after receive */
 	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 */
 };
 
@@ -434,6 +438,7 @@ extern struct file *do_accept(struct file *file, unsigned file_flags,
 extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 			 int __user *upeer_addrlen, int flags);
 extern int __sys_socket(int family, int type, int protocol);
+extern struct file *__sys_socket_file(int family, int type, int protocol);
 extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
 extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr,
 			      int addrlen, int file_flags);
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 1a80151baed9..d040406f3314 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -387,26 +387,16 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,
 	return arm_spe_deliver_synth_event(spe, speq, event, &sample);
 }
 
-#define SPE_MEM_TYPE	(ARM_SPE_L1D_ACCESS | ARM_SPE_L1D_MISS | \
-			 ARM_SPE_LLC_ACCESS | ARM_SPE_LLC_MISS | \
-			 ARM_SPE_REMOTE_ACCESS)
-
-static bool arm_spe__is_memory_event(enum arm_spe_sample_type type)
-{
-	if (type & SPE_MEM_TYPE)
-		return true;
-
-	return false;
-}
-
 static u64 arm_spe__synth_data_source(const struct arm_spe_record *record)
 {
 	union perf_mem_data_src	data_src = { 0 };
 
 	if (record->op == ARM_SPE_LD)
 		data_src.mem_op = PERF_MEM_OP_LOAD;
-	else
+	else if (record->op == ARM_SPE_ST)
 		data_src.mem_op = PERF_MEM_OP_STORE;
+	else
+		return 0;
 
 	if (record->type & (ARM_SPE_LLC_ACCESS | ARM_SPE_LLC_MISS)) {
 		data_src.mem_lvl = PERF_MEM_LVL_L3;
@@ -510,7 +500,11 @@ static int arm_spe_sample(struct arm_spe_queue *speq)
 			return err;
 	}
 
-	if (spe->sample_memory && arm_spe__is_memory_event(record->type)) {
+	/*
+	 * When data_src is zero it means the record is not a memory operation,
+	 * skip to synthesize memory sample for this case.
+	 */
+	if (spe->sample_memory && data_src) {
 		err = arm_spe__synth_mem_sample(speq, spe->memory_id, data_src);
 		if (err)
 			return err;
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 82f3d46bea70..328668f38c69 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -872,6 +872,30 @@ out_free:
 	return err;
 }
 
+static int filename__read_build_id_ns(const char *filename,
+				      struct build_id *bid,
+				      struct nsinfo *nsi)
+{
+	struct nscookie nsc;
+	int ret;
+
+	nsinfo__mountns_enter(nsi, &nsc);
+	ret = filename__read_build_id(filename, bid);
+	nsinfo__mountns_exit(&nsc);
+
+	return ret;
+}
+
+static bool dso__build_id_mismatch(struct dso *dso, const char *name)
+{
+	struct build_id bid;
+
+	if (filename__read_build_id_ns(name, &bid, dso->nsinfo) < 0)
+		return false;
+
+	return !dso__build_id_equal(dso, &bid);
+}
+
 static int dso__cache_build_id(struct dso *dso, struct machine *machine,
 			       void *priv __maybe_unused)
 {
@@ -886,6 +910,10 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine,
 		is_kallsyms = true;
 		name = machine->mmap_name;
 	}
+
+	if (!is_kallsyms && dso__build_id_mismatch(dso, name))
+		return 0;
+
 	return build_id_cache__add_b(&dso->bid, name, dso->nsinfo,
 				     is_kallsyms, is_vdso);
 }
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
index 0a13eb20c814..4dc8edbfd9ce 100644
--- a/tools/perf/util/expr.l
+++ b/tools/perf/util/expr.l
@@ -91,7 +91,7 @@ static int literal(yyscan_t scanner)
 }
 %}
 
-number		([0-9]+\.?[0-9]*|[0-9]*\.?[0-9]+)
+number		([0-9]+\.?[0-9]*|[0-9]*\.?[0-9]+)(e-?[0-9]+)?
 
 sch		[-,=]
 spec		\\{sch}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 53332da100e8..6ad629db63b7 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3686,6 +3686,20 @@ int perf_session__write_header(struct perf_session *session,
 	return perf_session__do_write_header(session, evlist, fd, at_exit, NULL);
 }
 
+size_t perf_session__data_offset(const struct evlist *evlist)
+{
+	struct evsel *evsel;
+	size_t data_offset;
+
+	data_offset = sizeof(struct perf_file_header);
+	evlist__for_each_entry(evlist, evsel) {
+		data_offset += evsel->core.ids * sizeof(u64);
+	}
+	data_offset += evlist->core.nr_entries * sizeof(struct perf_file_attr);
+
+	return data_offset;
+}
+
 int perf_session__inject_header(struct perf_session *session,
 				struct evlist *evlist,
 				int fd,
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 08563c1f1bff..56916dabce7b 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -136,6 +136,8 @@ int perf_session__inject_header(struct perf_session *session,
 				int fd,
 				struct feat_copier *fc);
 
+size_t perf_session__data_offset(const struct evlist *evlist);
+
 void perf_header__set_feat(struct perf_header *header, int feat);
 void perf_header__clear_feat(struct perf_header *header, int feat);
 bool perf_header__has_feat(const struct perf_header *header, int feat);
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index ee8fcfa115e5..8f7baeabc5cf 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -1372,6 +1372,7 @@ static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu,
 
 	*out_evlist = NULL;
 	if (!metric_no_merge || hashmap__size(ids->ids) == 0) {
+		bool added_event = false;
 		int i;
 		/*
 		 * We may fail to share events between metrics because a tool
@@ -1393,8 +1394,16 @@ static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu,
 				if (!tmp)
 					return -ENOMEM;
 				ids__insert(ids->ids, tmp);
+				added_event = true;
 			}
 		}
+		if (!added_event && hashmap__size(ids->ids) == 0) {
+			char *tmp = strdup("duration_time");
+
+			if (!tmp)
+				return -ENOMEM;
+			ids__insert(ids->ids, tmp);
+		}
 	}
 	ret = metricgroup__build_event_string(&events, ids, modifier,
 					      has_constraint);
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 37622699c91a..6e5b8cce47bf 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -174,7 +174,7 @@ static int elf_section_address_and_offset(int fd, const char *name, u64 *address
 	Elf *elf;
 	GElf_Ehdr ehdr;
 	GElf_Shdr shdr;
-	int ret;
+	int ret = -1;
 
 	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
 	if (elf == NULL)
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
index 83ef55e3caa4..2974b44f80fa 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
@@ -121,24 +121,24 @@ static void kprobe_multi_link_api_subtest(void)
 })
 
 	GET_ADDR("bpf_fentry_test1", addrs[0]);
-	GET_ADDR("bpf_fentry_test2", addrs[1]);
-	GET_ADDR("bpf_fentry_test3", addrs[2]);
-	GET_ADDR("bpf_fentry_test4", addrs[3]);
-	GET_ADDR("bpf_fentry_test5", addrs[4]);
-	GET_ADDR("bpf_fentry_test6", addrs[5]);
-	GET_ADDR("bpf_fentry_test7", addrs[6]);
+	GET_ADDR("bpf_fentry_test3", addrs[1]);
+	GET_ADDR("bpf_fentry_test4", addrs[2]);
+	GET_ADDR("bpf_fentry_test5", addrs[3]);
+	GET_ADDR("bpf_fentry_test6", addrs[4]);
+	GET_ADDR("bpf_fentry_test7", addrs[5]);
+	GET_ADDR("bpf_fentry_test2", addrs[6]);
 	GET_ADDR("bpf_fentry_test8", addrs[7]);
 
 #undef GET_ADDR
 
-	cookies[0] = 1;
-	cookies[1] = 2;
-	cookies[2] = 3;
-	cookies[3] = 4;
-	cookies[4] = 5;
-	cookies[5] = 6;
-	cookies[6] = 7;
-	cookies[7] = 8;
+	cookies[0] = 1; /* bpf_fentry_test1 */
+	cookies[1] = 2; /* bpf_fentry_test3 */
+	cookies[2] = 3; /* bpf_fentry_test4 */
+	cookies[3] = 4; /* bpf_fentry_test5 */
+	cookies[4] = 5; /* bpf_fentry_test6 */
+	cookies[5] = 6; /* bpf_fentry_test7 */
+	cookies[6] = 7; /* bpf_fentry_test2 */
+	cookies[7] = 8; /* bpf_fentry_test8 */
 
 	opts.kprobe_multi.addrs = (const unsigned long *) &addrs;
 	opts.kprobe_multi.cnt = ARRAY_SIZE(addrs);
@@ -149,14 +149,14 @@ static void kprobe_multi_link_api_subtest(void)
 	if (!ASSERT_GE(link1_fd, 0, "link1_fd"))
 		goto cleanup;
 
-	cookies[0] = 8;
-	cookies[1] = 7;
-	cookies[2] = 6;
-	cookies[3] = 5;
-	cookies[4] = 4;
-	cookies[5] = 3;
-	cookies[6] = 2;
-	cookies[7] = 1;
+	cookies[0] = 8; /* bpf_fentry_test1 */
+	cookies[1] = 7; /* bpf_fentry_test3 */
+	cookies[2] = 6; /* bpf_fentry_test4 */
+	cookies[3] = 5; /* bpf_fentry_test5 */
+	cookies[4] = 4; /* bpf_fentry_test6 */
+	cookies[5] = 3; /* bpf_fentry_test7 */
+	cookies[6] = 2; /* bpf_fentry_test2 */
+	cookies[7] = 1; /* bpf_fentry_test8 */
 
 	opts.kprobe_multi.flags = BPF_F_KPROBE_MULTI_RETURN;
 	prog_fd = bpf_program__fd(skel->progs.test_kretprobe);
@@ -181,12 +181,12 @@ static void kprobe_multi_attach_api_subtest(void)
 	struct kprobe_multi *skel = NULL;
 	const char *syms[8] = {
 		"bpf_fentry_test1",
-		"bpf_fentry_test2",
 		"bpf_fentry_test3",
 		"bpf_fentry_test4",
 		"bpf_fentry_test5",
 		"bpf_fentry_test6",
 		"bpf_fentry_test7",
+		"bpf_fentry_test2",
 		"bpf_fentry_test8",
 	};
 	__u64 cookies[8];
@@ -198,14 +198,14 @@ static void kprobe_multi_attach_api_subtest(void)
 	skel->bss->pid = getpid();
 	skel->bss->test_cookie = true;
 
-	cookies[0] = 1;
-	cookies[1] = 2;
-	cookies[2] = 3;
-	cookies[3] = 4;
-	cookies[4] = 5;
-	cookies[5] = 6;
-	cookies[6] = 7;
-	cookies[7] = 8;
+	cookies[0] = 1; /* bpf_fentry_test1 */
+	cookies[1] = 2; /* bpf_fentry_test3 */
+	cookies[2] = 3; /* bpf_fentry_test4 */
+	cookies[3] = 4; /* bpf_fentry_test5 */
+	cookies[4] = 5; /* bpf_fentry_test6 */
+	cookies[5] = 6; /* bpf_fentry_test7 */
+	cookies[6] = 7; /* bpf_fentry_test2 */
+	cookies[7] = 8; /* bpf_fentry_test8 */
 
 	opts.syms = syms;
 	opts.cnt = ARRAY_SIZE(syms);
@@ -216,14 +216,14 @@ static void kprobe_multi_attach_api_subtest(void)
 	if (!ASSERT_OK_PTR(link1, "bpf_program__attach_kprobe_multi_opts"))
 		goto cleanup;
 
-	cookies[0] = 8;
-	cookies[1] = 7;
-	cookies[2] = 6;
-	cookies[3] = 5;
-	cookies[4] = 4;
-	cookies[5] = 3;
-	cookies[6] = 2;
-	cookies[7] = 1;
+	cookies[0] = 8; /* bpf_fentry_test1 */
+	cookies[1] = 7; /* bpf_fentry_test3 */
+	cookies[2] = 6; /* bpf_fentry_test4 */
+	cookies[3] = 5; /* bpf_fentry_test5 */
+	cookies[4] = 4; /* bpf_fentry_test6 */
+	cookies[5] = 3; /* bpf_fentry_test7 */
+	cookies[6] = 2; /* bpf_fentry_test2 */
+	cookies[7] = 1; /* bpf_fentry_test8 */
 
 	opts.retprobe = true;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index 586dc52d6fb9..5b93d5d0bd93 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -364,6 +364,9 @@ static int get_syms(char ***symsp, size_t *cntp)
 			continue;
 		if (!strncmp(name, "rcu_", 4))
 			continue;
+		if (!strncmp(name, "__ftrace_invalid_address__",
+			     sizeof("__ftrace_invalid_address__") - 1))
+			continue;
 		err = hashmap__add(map, name, NULL);
 		if (err) {
 			free(name);
diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index c4da87ec3ba4..19c70880cfb3 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -831,6 +831,59 @@ out:
 	bpf_object__close(obj);
 }
 
+#include "tailcall_bpf2bpf6.skel.h"
+
+/* Tail call counting works even when there is data on stack which is
+ * not aligned to 8 bytes.
+ */
+static void test_tailcall_bpf2bpf_6(void)
+{
+	struct tailcall_bpf2bpf6 *obj;
+	int err, map_fd, prog_fd, main_fd, data_fd, i, val;
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1,
+	);
+
+	obj = tailcall_bpf2bpf6__open_and_load();
+	if (!ASSERT_OK_PTR(obj, "open and load"))
+		return;
+
+	main_fd = bpf_program__fd(obj->progs.entry);
+	if (!ASSERT_GE(main_fd, 0, "entry prog fd"))
+		goto out;
+
+	map_fd = bpf_map__fd(obj->maps.jmp_table);
+	if (!ASSERT_GE(map_fd, 0, "jmp_table map fd"))
+		goto out;
+
+	prog_fd = bpf_program__fd(obj->progs.classifier_0);
+	if (!ASSERT_GE(prog_fd, 0, "classifier_0 prog fd"))
+		goto out;
+
+	i = 0;
+	err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+	if (!ASSERT_OK(err, "jmp_table map update"))
+		goto out;
+
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "entry prog test run");
+	ASSERT_EQ(topts.retval, 0, "tailcall retval");
+
+	data_fd = bpf_map__fd(obj->maps.bss);
+	if (!ASSERT_GE(map_fd, 0, "bss map fd"))
+		goto out;
+
+	i = 0;
+	err = bpf_map_lookup_elem(data_fd, &i, &val);
+	ASSERT_OK(err, "bss map lookup");
+	ASSERT_EQ(val, 1, "done flag is set");
+
+out:
+	tailcall_bpf2bpf6__destroy(obj);
+}
+
 void test_tailcalls(void)
 {
 	if (test__start_subtest("tailcall_1"))
@@ -855,4 +908,6 @@ void test_tailcalls(void)
 		test_tailcall_bpf2bpf_4(false);
 	if (test__start_subtest("tailcall_bpf2bpf_5"))
 		test_tailcall_bpf2bpf_4(true);
+	if (test__start_subtest("tailcall_bpf2bpf_6"))
+		test_tailcall_bpf2bpf_6();
 }
diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi.c b/tools/testing/selftests/bpf/progs/kprobe_multi.c
index 93510f4f0f3a..08f95a8155d1 100644
--- a/tools/testing/selftests/bpf/progs/kprobe_multi.c
+++ b/tools/testing/selftests/bpf/progs/kprobe_multi.c
@@ -54,21 +54,21 @@ static void kprobe_multi_check(void *ctx, bool is_return)
 
 	if (is_return) {
 		SET(kretprobe_test1_result, &bpf_fentry_test1, 8);
-		SET(kretprobe_test2_result, &bpf_fentry_test2, 7);
-		SET(kretprobe_test3_result, &bpf_fentry_test3, 6);
-		SET(kretprobe_test4_result, &bpf_fentry_test4, 5);
-		SET(kretprobe_test5_result, &bpf_fentry_test5, 4);
-		SET(kretprobe_test6_result, &bpf_fentry_test6, 3);
-		SET(kretprobe_test7_result, &bpf_fentry_test7, 2);
+		SET(kretprobe_test2_result, &bpf_fentry_test2, 2);
+		SET(kretprobe_test3_result, &bpf_fentry_test3, 7);
+		SET(kretprobe_test4_result, &bpf_fentry_test4, 6);
+		SET(kretprobe_test5_result, &bpf_fentry_test5, 5);
+		SET(kretprobe_test6_result, &bpf_fentry_test6, 4);
+		SET(kretprobe_test7_result, &bpf_fentry_test7, 3);
 		SET(kretprobe_test8_result, &bpf_fentry_test8, 1);
 	} else {
 		SET(kprobe_test1_result, &bpf_fentry_test1, 1);
-		SET(kprobe_test2_result, &bpf_fentry_test2, 2);
-		SET(kprobe_test3_result, &bpf_fentry_test3, 3);
-		SET(kprobe_test4_result, &bpf_fentry_test4, 4);
-		SET(kprobe_test5_result, &bpf_fentry_test5, 5);
-		SET(kprobe_test6_result, &bpf_fentry_test6, 6);
-		SET(kprobe_test7_result, &bpf_fentry_test7, 7);
+		SET(kprobe_test2_result, &bpf_fentry_test2, 7);
+		SET(kprobe_test3_result, &bpf_fentry_test3, 2);
+		SET(kprobe_test4_result, &bpf_fentry_test4, 3);
+		SET(kprobe_test5_result, &bpf_fentry_test5, 4);
+		SET(kprobe_test6_result, &bpf_fentry_test6, 5);
+		SET(kprobe_test7_result, &bpf_fentry_test7, 6);
 		SET(kprobe_test8_result, &bpf_fentry_test8, 8);
 	}
 
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c
new file mode 100644
index 000000000000..41ce83da78e8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#define __unused __attribute__((unused))
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+int done = 0;
+
+SEC("tc")
+int classifier_0(struct __sk_buff *skb __unused)
+{
+	done = 1;
+	return 0;
+}
+
+static __noinline
+int subprog_tail(struct __sk_buff *skb)
+{
+	/* Don't propagate the constant to the caller */
+	volatile int ret = 1;
+
+	bpf_tail_call_static(skb, &jmp_table, 0);
+	return ret;
+}
+
+SEC("tc")
+int entry(struct __sk_buff *skb)
+{
+	/* Have data on stack which size is not a multiple of 8 */
+	volatile char arr[1] = {};
+
+	return subprog_tail(skb);
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/dma/Makefile b/tools/testing/selftests/dma/Makefile
index aa8e8b5b3864..cd8c5ece1cba 100644
--- a/tools/testing/selftests/dma/Makefile
+++ b/tools/testing/selftests/dma/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 CFLAGS += -I../../../../usr/include/
+CFLAGS += -I../../../../include/
 
 TEST_GEN_PROGS := dma_map_benchmark
 
diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c
index c3b3c09e995e..5c997f17fcbd 100644
--- a/tools/testing/selftests/dma/dma_map_benchmark.c
+++ b/tools/testing/selftests/dma/dma_map_benchmark.c
@@ -10,8 +10,8 @@
 #include <unistd.h>
 #include <sys/ioctl.h>
 #include <sys/mman.h>
-#include <linux/map_benchmark.h>
 #include <linux/types.h>
+#include <linux/map_benchmark.h>
 
 #define NSEC_PER_MSEC	1000000L
 
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 81470a99ed1c..22423c871ed6 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -37,11 +37,38 @@ ifeq ($(ARCH),riscv)
 	UNAME_M := riscv
 endif
 
-LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c
-LIBKVM_x86_64 = lib/x86_64/apic.c lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S
-LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c lib/aarch64/handlers.S lib/aarch64/spinlock.c lib/aarch64/gic.c lib/aarch64/gic_v3.c lib/aarch64/vgic.c
-LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
-LIBKVM_riscv = lib/riscv/processor.c lib/riscv/ucall.c
+LIBKVM += lib/assert.c
+LIBKVM += lib/elf.c
+LIBKVM += lib/guest_modes.c
+LIBKVM += lib/io.c
+LIBKVM += lib/kvm_util.c
+LIBKVM += lib/perf_test_util.c
+LIBKVM += lib/rbtree.c
+LIBKVM += lib/sparsebit.c
+LIBKVM += lib/test_util.c
+
+LIBKVM_x86_64 += lib/x86_64/apic.c
+LIBKVM_x86_64 += lib/x86_64/handlers.S
+LIBKVM_x86_64 += lib/x86_64/perf_test_util.c
+LIBKVM_x86_64 += lib/x86_64/processor.c
+LIBKVM_x86_64 += lib/x86_64/svm.c
+LIBKVM_x86_64 += lib/x86_64/ucall.c
+LIBKVM_x86_64 += lib/x86_64/vmx.c
+
+LIBKVM_aarch64 += lib/aarch64/gic.c
+LIBKVM_aarch64 += lib/aarch64/gic_v3.c
+LIBKVM_aarch64 += lib/aarch64/handlers.S
+LIBKVM_aarch64 += lib/aarch64/processor.c
+LIBKVM_aarch64 += lib/aarch64/spinlock.c
+LIBKVM_aarch64 += lib/aarch64/ucall.c
+LIBKVM_aarch64 += lib/aarch64/vgic.c
+
+LIBKVM_s390x += lib/s390x/diag318_test_handler.c
+LIBKVM_s390x += lib/s390x/processor.c
+LIBKVM_s390x += lib/s390x/ucall.c
+
+LIBKVM_riscv += lib/riscv/processor.c
+LIBKVM_riscv += lib/riscv/ucall.c
 
 TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test
 TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
@@ -173,12 +200,13 @@ LDFLAGS += -pthread $(no-pie-option) $(pgste-option)
 # $(TEST_GEN_PROGS) starts with $(OUTPUT)/
 include ../lib.mk
 
-STATIC_LIBS := $(OUTPUT)/libkvm.a
 LIBKVM_C := $(filter %.c,$(LIBKVM))
 LIBKVM_S := $(filter %.S,$(LIBKVM))
 LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
 LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
-EXTRA_CLEAN += $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(STATIC_LIBS) cscope.*
+LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)
+
+EXTRA_CLEAN += $(LIBKVM_OBJS) cscope.*
 
 x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
 $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
@@ -187,13 +215,8 @@ $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
 $(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
-LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)
-$(OUTPUT)/libkvm.a: $(LIBKVM_OBJS)
-	$(AR) crs $@ $^
-
 x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
-all: $(STATIC_LIBS)
-$(TEST_GEN_PROGS): $(STATIC_LIBS)
+$(TEST_GEN_PROGS): $(LIBKVM_OBJS)
 
 cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib ..
 cscope:
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 7b47ae4f952e..d60a34cdfaee 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -336,8 +336,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 static void help(char *name)
 {
 	puts("");
-	printf("usage: %s [-h] [-i iterations] [-p offset] [-g]"
-	       "[-m mode] [-b vcpu bytes] [-v vcpus] [-o] [-s mem type]"
+	printf("usage: %s [-h] [-i iterations] [-p offset] [-g] "
+	       "[-m mode] [-n] [-b vcpu bytes] [-v vcpus] [-o] [-s mem type]"
 	       "[-x memslots]\n", name);
 	puts("");
 	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
@@ -351,6 +351,7 @@ static void help(char *name)
 	printf(" -p: specify guest physical test memory offset\n"
 	       "     Warning: a low offset can conflict with the loaded test code.\n");
 	guest_modes_help();
+	printf(" -n: Run the vCPUs in nested mode (L2)\n");
 	printf(" -b: specify the size of the memory region which should be\n"
 	       "     dirtied by each vCPU. e.g. 10M or 3G.\n"
 	       "     (default: 1G)\n");
@@ -387,7 +388,7 @@ int main(int argc, char *argv[])
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "ghi:p:m:b:f:v:os:x:")) != -1) {
+	while ((opt = getopt(argc, argv, "ghi:p:m:nb:f:v:os:x:")) != -1) {
 		switch (opt) {
 		case 'g':
 			dirty_log_manual_caps = 0;
@@ -401,6 +402,9 @@ int main(int argc, char *argv[])
 		case 'm':
 			guest_modes_cmdline(optarg);
 			break;
+		case 'n':
+			perf_test_args.nested = true;
+			break;
 		case 'b':
 			guest_percpu_mem_size = parse_size(optarg);
 			break;
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index a86f953d8d36..d822cb670f1c 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -30,10 +30,15 @@ struct perf_test_vcpu_args {
 
 struct perf_test_args {
 	struct kvm_vm *vm;
+	/* The starting address and size of the guest test region. */
 	uint64_t gpa;
+	uint64_t size;
 	uint64_t guest_page_size;
 	int wr_fract;
 
+	/* Run vCPUs in L2 instead of L1, if the architecture supports it. */
+	bool nested;
+
 	struct perf_test_vcpu_args vcpu_args[KVM_MAX_VCPUS];
 };
 
@@ -49,5 +54,9 @@ void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract);
 
 void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *));
 void perf_test_join_vcpu_threads(int vcpus);
+void perf_test_guest_code(uint32_t vcpu_id);
+
+uint64_t perf_test_nested_pages(int nr_vcpus);
+void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus);
 
 #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index d0d51adec76e..6ce185449259 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -482,13 +482,23 @@ void vcpu_set_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
 struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
 void vm_xsave_req_perm(int bit);
 
-enum x86_page_size {
-	X86_PAGE_SIZE_4K = 0,
-	X86_PAGE_SIZE_2M,
-	X86_PAGE_SIZE_1G,
+enum pg_level {
+	PG_LEVEL_NONE,
+	PG_LEVEL_4K,
+	PG_LEVEL_2M,
+	PG_LEVEL_1G,
+	PG_LEVEL_512G,
+	PG_LEVEL_NUM
 };
-void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
-		   enum x86_page_size page_size);
+
+#define PG_LEVEL_SHIFT(_level) ((_level - 1) * 9 + 12)
+#define PG_LEVEL_SIZE(_level) (1ull << PG_LEVEL_SHIFT(_level))
+
+#define PG_SIZE_4K PG_LEVEL_SIZE(PG_LEVEL_4K)
+#define PG_SIZE_2M PG_LEVEL_SIZE(PG_LEVEL_2M)
+#define PG_SIZE_1G PG_LEVEL_SIZE(PG_LEVEL_1G)
+
+void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level);
 
 /*
  * Basic CPU control in CR0
@@ -505,9 +515,6 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 #define X86_CR0_CD          (1UL<<30) /* Cache Disable */
 #define X86_CR0_PG          (1UL<<31) /* Paging */
 
-/* VMX_EPT_VPID_CAP bits */
-#define VMX_EPT_VPID_CAP_AD_BITS       (1ULL << 21)
-
 #define XSTATE_XTILE_CFG_BIT		17
 #define XSTATE_XTILE_DATA_BIT		18
 
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 583ceb0d1457..cc3604f8f1d3 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -96,6 +96,9 @@
 #define VMX_MISC_PREEMPTION_TIMER_RATE_MASK	0x0000001f
 #define VMX_MISC_SAVE_EFER_LMA			0x00000020
 
+#define VMX_EPT_VPID_CAP_1G_PAGES		0x00020000
+#define VMX_EPT_VPID_CAP_AD_BITS		0x00200000
+
 #define EXIT_REASON_FAILED_VMENTRY	0x80000000
 #define EXIT_REASON_EXCEPTION_NMI	0
 #define EXIT_REASON_EXTERNAL_INTERRUPT	1
@@ -606,6 +609,7 @@ bool load_vmcs(struct vmx_pages *vmx);
 
 bool nested_vmx_supported(void);
 void nested_vmx_check_supported(void);
+bool ept_1g_pages_supported(void);
 
 void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
 		   uint64_t nested_paddr, uint64_t paddr);
@@ -613,6 +617,8 @@ void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
 		 uint64_t nested_paddr, uint64_t paddr, uint64_t size);
 void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
 			uint32_t memslot);
+void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm,
+			    uint64_t addr, uint64_t size);
 void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
 		  uint32_t eptp_memslot);
 void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm);
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
index e0b0164e9af8..be1d9728c4ce 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
@@ -73,20 +73,19 @@ void ucall_uninit(struct kvm_vm *vm)
 
 void ucall(uint64_t cmd, int nargs, ...)
 {
-	struct ucall uc = {
-		.cmd = cmd,
-	};
+	struct ucall uc = {};
 	va_list va;
 	int i;
 
+	WRITE_ONCE(uc.cmd, cmd);
 	nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS;
 
 	va_start(va, nargs);
 	for (i = 0; i < nargs; ++i)
-		uc.args[i] = va_arg(va, uint64_t);
+		WRITE_ONCE(uc.args[i], va_arg(va, uint64_t));
 	va_end(va);
 
-	*ucall_exit_mmio_addr = (vm_vaddr_t)&uc;
+	WRITE_ONCE(*ucall_exit_mmio_addr, (vm_vaddr_t)&uc);
 }
 
 uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 722df3a28791..f989ff91f022 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -40,7 +40,7 @@ static bool all_vcpu_threads_running;
  * Continuously write to the first 8 bytes of each page in the
  * specified region.
  */
-static void guest_code(uint32_t vcpu_id)
+void perf_test_guest_code(uint32_t vcpu_id)
 {
 	struct perf_test_args *pta = &perf_test_args;
 	struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_id];
@@ -108,8 +108,9 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 {
 	struct perf_test_args *pta = &perf_test_args;
 	struct kvm_vm *vm;
-	uint64_t guest_num_pages;
+	uint64_t guest_num_pages, slot0_pages = DEFAULT_GUEST_PHY_PAGES;
 	uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src);
+	uint64_t region_end_gfn;
 	int i;
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
@@ -135,33 +136,53 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 		    slots);
 
 	/*
+	 * If using nested, allocate extra pages for the nested page tables and
+	 * in-memory data structures.
+	 */
+	if (pta->nested)
+		slot0_pages += perf_test_nested_pages(vcpus);
+
+	/*
 	 * Pass guest_num_pages to populate the page tables for test memory.
 	 * The memory is also added to memslot 0, but that's a benign side
 	 * effect as KVM allows aliasing HVAs in meslots.
 	 */
-	vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES,
-				  guest_num_pages, 0, guest_code, NULL);
+	vm = vm_create_with_vcpus(mode, vcpus, slot0_pages, guest_num_pages, 0,
+				  perf_test_guest_code, NULL);
 
 	pta->vm = vm;
 
+	/* Put the test region at the top guest physical memory. */
+	region_end_gfn = vm_get_max_gfn(vm) + 1;
+
+#ifdef __x86_64__
+	/*
+	 * When running vCPUs in L2, restrict the test region to 48 bits to
+	 * avoid needing 5-level page tables to identity map L2.
+	 */
+	if (pta->nested)
+		region_end_gfn = min(region_end_gfn, (1UL << 48) / pta->guest_page_size);
+#endif
 	/*
 	 * If there should be more memory in the guest test region than there
 	 * can be pages in the guest, it will definitely cause problems.
 	 */
-	TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
+	TEST_ASSERT(guest_num_pages < region_end_gfn,
 		    "Requested more guest memory than address space allows.\n"
 		    "    guest pages: %" PRIx64 " max gfn: %" PRIx64
 		    " vcpus: %d wss: %" PRIx64 "]\n",
-		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
+		    guest_num_pages, region_end_gfn - 1, vcpus,
 		    vcpu_memory_bytes);
 
-	pta->gpa = (vm_get_max_gfn(vm) - guest_num_pages) * pta->guest_page_size;
+	pta->gpa = (region_end_gfn - guest_num_pages) * pta->guest_page_size;
 	pta->gpa = align_down(pta->gpa, backing_src_pagesz);
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
 	pta->gpa = align_down(pta->gpa, 1 << 20);
 #endif
-	pr_info("guest physical test memory offset: 0x%lx\n", pta->gpa);
+	pta->size = guest_num_pages * pta->guest_page_size;
+	pr_info("guest physical test memory: [0x%lx, 0x%lx)\n",
+		pta->gpa, pta->gpa + pta->size);
 
 	/* Add extra memory slots for testing */
 	for (i = 0; i < slots; i++) {
@@ -178,6 +199,11 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 
 	perf_test_setup_vcpus(vm, vcpus, vcpu_memory_bytes, partition_vcpu_memory_access);
 
+	if (pta->nested) {
+		pr_info("Configuring vCPUs to run in L2 (nested).\n");
+		perf_test_setup_nested(vm, vcpus);
+	}
+
 	ucall_init(vm, NULL);
 
 	/* Export the shared variables to the guest. */
@@ -198,6 +224,17 @@ void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract)
 	sync_global_to_guest(vm, perf_test_args);
 }
 
+uint64_t __weak perf_test_nested_pages(int nr_vcpus)
+{
+	return 0;
+}
+
+void __weak perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus)
+{
+	pr_info("%s() not support on this architecture, skipping.\n", __func__);
+	exit(KSFT_SKIP);
+}
+
 static void *vcpu_thread_main(void *data)
 {
 	struct vcpu_thread *vcpu = data;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c b/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c
new file mode 100644
index 000000000000..e258524435a0
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * x86_64-specific extensions to perf_test_util.c.
+ *
+ * Copyright (C) 2022, Google, Inc.
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "perf_test_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+#include "vmx.h"
+
+void perf_test_l2_guest_code(uint64_t vcpu_id)
+{
+	perf_test_guest_code(vcpu_id);
+	vmcall();
+}
+
+extern char perf_test_l2_guest_entry[];
+__asm__(
+"perf_test_l2_guest_entry:"
+"	mov (%rsp), %rdi;"
+"	call perf_test_l2_guest_code;"
+"	ud2;"
+);
+
+static void perf_test_l1_guest_code(struct vmx_pages *vmx, uint64_t vcpu_id)
+{
+#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	unsigned long *rsp;
+
+	GUEST_ASSERT(vmx->vmcs_gpa);
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx));
+	GUEST_ASSERT(load_vmcs(vmx));
+	GUEST_ASSERT(ept_1g_pages_supported());
+
+	rsp = &l2_guest_stack[L2_GUEST_STACK_SIZE - 1];
+	*rsp = vcpu_id;
+	prepare_vmcs(vmx, perf_test_l2_guest_entry, rsp);
+
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+	GUEST_DONE();
+}
+
+uint64_t perf_test_nested_pages(int nr_vcpus)
+{
+	/*
+	 * 513 page tables is enough to identity-map 256 TiB of L2 with 1G
+	 * pages and 4-level paging, plus a few pages per-vCPU for data
+	 * structures such as the VMCS.
+	 */
+	return 513 + 10 * nr_vcpus;
+}
+
+void perf_test_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm)
+{
+	uint64_t start, end;
+
+	prepare_eptp(vmx, vm, 0);
+
+	/*
+	 * Identity map the first 4G and the test region with 1G pages so that
+	 * KVM can shadow the EPT12 with the maximum huge page size supported
+	 * by the backing source.
+	 */
+	nested_identity_map_1g(vmx, vm, 0, 0x100000000ULL);
+
+	start = align_down(perf_test_args.gpa, PG_SIZE_1G);
+	end = align_up(perf_test_args.gpa + perf_test_args.size, PG_SIZE_1G);
+	nested_identity_map_1g(vmx, vm, start, end - start);
+}
+
+void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus)
+{
+	struct vmx_pages *vmx, *vmx0 = NULL;
+	struct kvm_regs regs;
+	vm_vaddr_t vmx_gva;
+	int vcpu_id;
+
+	nested_vmx_check_supported();
+
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+		vmx = vcpu_alloc_vmx(vm, &vmx_gva);
+
+		if (vcpu_id == 0) {
+			perf_test_setup_ept(vmx, vm);
+			vmx0 = vmx;
+		} else {
+			/* Share the same EPT table across all vCPUs. */
+			vmx->eptp = vmx0->eptp;
+			vmx->eptp_hva = vmx0->eptp_hva;
+			vmx->eptp_gpa = vmx0->eptp_gpa;
+		}
+
+		/*
+		 * Override the vCPU to run perf_test_l1_guest_code() which will
+		 * bounce it into L2 before calling perf_test_guest_code().
+		 */
+		vcpu_regs_get(vm, vcpu_id, &regs);
+		regs.rip = (unsigned long) perf_test_l1_guest_code;
+		vcpu_regs_set(vm, vcpu_id, &regs);
+		vcpu_args_set(vm, vcpu_id, 2, vmx_gva, vcpu_id);
+	}
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 33ea5e9955d9..ead7011ee8f6 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -158,7 +158,7 @@ static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr,
 			  int level)
 {
 	uint64_t *page_table = addr_gpa2hva(vm, pt_pfn << vm->page_shift);
-	int index = vaddr >> (vm->page_shift + level * 9) & 0x1ffu;
+	int index = (vaddr >> PG_LEVEL_SHIFT(level)) & 0x1ffu;
 
 	return &page_table[index];
 }
@@ -167,14 +167,14 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
 				       uint64_t pt_pfn,
 				       uint64_t vaddr,
 				       uint64_t paddr,
-				       int level,
-				       enum x86_page_size page_size)
+				       int current_level,
+				       int target_level)
 {
-	uint64_t *pte = virt_get_pte(vm, pt_pfn, vaddr, level);
+	uint64_t *pte = virt_get_pte(vm, pt_pfn, vaddr, current_level);
 
 	if (!(*pte & PTE_PRESENT_MASK)) {
 		*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK;
-		if (level == page_size)
+		if (current_level == target_level)
 			*pte |= PTE_LARGE_MASK | (paddr & PHYSICAL_PAGE_MASK);
 		else
 			*pte |= vm_alloc_page_table(vm) & PHYSICAL_PAGE_MASK;
@@ -184,20 +184,19 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
 		 * a hugepage at this level, and that there isn't a hugepage at
 		 * this level.
 		 */
-		TEST_ASSERT(level != page_size,
+		TEST_ASSERT(current_level != target_level,
 			    "Cannot create hugepage at level: %u, vaddr: 0x%lx\n",
-			    page_size, vaddr);
+			    current_level, vaddr);
 		TEST_ASSERT(!(*pte & PTE_LARGE_MASK),
 			    "Cannot create page table at level: %u, vaddr: 0x%lx\n",
-			    level, vaddr);
+			    current_level, vaddr);
 	}
 	return pte;
 }
 
-void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
-		   enum x86_page_size page_size)
+void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
 {
-	const uint64_t pg_size = 1ull << ((page_size * 9) + 12);
+	const uint64_t pg_size = PG_LEVEL_SIZE(level);
 	uint64_t *pml4e, *pdpe, *pde;
 	uint64_t *pte;
 
@@ -222,20 +221,20 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 	 * early if a hugepage was created.
 	 */
 	pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift,
-				      vaddr, paddr, 3, page_size);
+				      vaddr, paddr, PG_LEVEL_512G, level);
 	if (*pml4e & PTE_LARGE_MASK)
 		return;
 
-	pdpe = virt_create_upper_pte(vm, PTE_GET_PFN(*pml4e), vaddr, paddr, 2, page_size);
+	pdpe = virt_create_upper_pte(vm, PTE_GET_PFN(*pml4e), vaddr, paddr, PG_LEVEL_1G, level);
 	if (*pdpe & PTE_LARGE_MASK)
 		return;
 
-	pde = virt_create_upper_pte(vm, PTE_GET_PFN(*pdpe), vaddr, paddr, 1, page_size);
+	pde = virt_create_upper_pte(vm, PTE_GET_PFN(*pdpe), vaddr, paddr, PG_LEVEL_2M, level);
 	if (*pde & PTE_LARGE_MASK)
 		return;
 
 	/* Fill in page table entry. */
-	pte = virt_get_pte(vm, PTE_GET_PFN(*pde), vaddr, 0);
+	pte = virt_get_pte(vm, PTE_GET_PFN(*pde), vaddr, PG_LEVEL_4K);
 	TEST_ASSERT(!(*pte & PTE_PRESENT_MASK),
 		    "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr);
 	*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK);
@@ -243,7 +242,7 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 
 void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
 {
-	__virt_pg_map(vm, vaddr, paddr, X86_PAGE_SIZE_4K);
+	__virt_pg_map(vm, vaddr, paddr, PG_LEVEL_4K);
 }
 
 static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid,
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index d089d8b850b5..b77a01d0a271 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -198,6 +198,16 @@ bool load_vmcs(struct vmx_pages *vmx)
 	return true;
 }
 
+static bool ept_vpid_cap_supported(uint64_t mask)
+{
+	return rdmsr(MSR_IA32_VMX_EPT_VPID_CAP) & mask;
+}
+
+bool ept_1g_pages_supported(void)
+{
+	return ept_vpid_cap_supported(VMX_EPT_VPID_CAP_1G_PAGES);
+}
+
 /*
  * Initialize the control fields to the most basic settings possible.
  */
@@ -215,7 +225,7 @@ static inline void init_vmcs_control_fields(struct vmx_pages *vmx)
 		struct eptPageTablePointer eptp = {
 			.memory_type = VMX_BASIC_MEM_TYPE_WB,
 			.page_walk_length = 3, /* + 1 */
-			.ad_enabled = !!(rdmsr(MSR_IA32_VMX_EPT_VPID_CAP) & VMX_EPT_VPID_CAP_AD_BITS),
+			.ad_enabled = ept_vpid_cap_supported(VMX_EPT_VPID_CAP_AD_BITS),
 			.address = vmx->eptp_gpa >> PAGE_SHIFT_4K,
 		};
 
@@ -392,80 +402,93 @@ void nested_vmx_check_supported(void)
 	}
 }
 
-void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
-		   uint64_t nested_paddr, uint64_t paddr)
+static void nested_create_pte(struct kvm_vm *vm,
+			      struct eptPageTableEntry *pte,
+			      uint64_t nested_paddr,
+			      uint64_t paddr,
+			      int current_level,
+			      int target_level)
+{
+	if (!pte->readable) {
+		pte->writable = true;
+		pte->readable = true;
+		pte->executable = true;
+		pte->page_size = (current_level == target_level);
+		if (pte->page_size)
+			pte->address = paddr >> vm->page_shift;
+		else
+			pte->address = vm_alloc_page_table(vm) >> vm->page_shift;
+	} else {
+		/*
+		 * Entry already present.  Assert that the caller doesn't want
+		 * a hugepage at this level, and that there isn't a hugepage at
+		 * this level.
+		 */
+		TEST_ASSERT(current_level != target_level,
+			    "Cannot create hugepage at level: %u, nested_paddr: 0x%lx\n",
+			    current_level, nested_paddr);
+		TEST_ASSERT(!pte->page_size,
+			    "Cannot create page table at level: %u, nested_paddr: 0x%lx\n",
+			    current_level, nested_paddr);
+	}
+}
+
+
+void __nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+		     uint64_t nested_paddr, uint64_t paddr, int target_level)
 {
-	uint16_t index[4];
-	struct eptPageTableEntry *pml4e;
+	const uint64_t page_size = PG_LEVEL_SIZE(target_level);
+	struct eptPageTableEntry *pt = vmx->eptp_hva, *pte;
+	uint16_t index;
 
 	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
 		    "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
 
-	TEST_ASSERT((nested_paddr % vm->page_size) == 0,
+	TEST_ASSERT((nested_paddr >> 48) == 0,
+		    "Nested physical address 0x%lx requires 5-level paging",
+		    nested_paddr);
+	TEST_ASSERT((nested_paddr % page_size) == 0,
 		    "Nested physical address not on page boundary,\n"
-		    "  nested_paddr: 0x%lx vm->page_size: 0x%x",
-		    nested_paddr, vm->page_size);
+		    "  nested_paddr: 0x%lx page_size: 0x%lx",
+		    nested_paddr, page_size);
 	TEST_ASSERT((nested_paddr >> vm->page_shift) <= vm->max_gfn,
 		    "Physical address beyond beyond maximum supported,\n"
 		    "  nested_paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
 		    paddr, vm->max_gfn, vm->page_size);
-	TEST_ASSERT((paddr % vm->page_size) == 0,
+	TEST_ASSERT((paddr % page_size) == 0,
 		    "Physical address not on page boundary,\n"
-		    "  paddr: 0x%lx vm->page_size: 0x%x",
-		    paddr, vm->page_size);
+		    "  paddr: 0x%lx page_size: 0x%lx",
+		    paddr, page_size);
 	TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
 		    "Physical address beyond beyond maximum supported,\n"
 		    "  paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
 		    paddr, vm->max_gfn, vm->page_size);
 
-	index[0] = (nested_paddr >> 12) & 0x1ffu;
-	index[1] = (nested_paddr >> 21) & 0x1ffu;
-	index[2] = (nested_paddr >> 30) & 0x1ffu;
-	index[3] = (nested_paddr >> 39) & 0x1ffu;
-
-	/* Allocate page directory pointer table if not present. */
-	pml4e = vmx->eptp_hva;
-	if (!pml4e[index[3]].readable) {
-		pml4e[index[3]].address = vm_alloc_page_table(vm) >> vm->page_shift;
-		pml4e[index[3]].writable = true;
-		pml4e[index[3]].readable = true;
-		pml4e[index[3]].executable = true;
-	}
+	for (int level = PG_LEVEL_512G; level >= PG_LEVEL_4K; level--) {
+		index = (nested_paddr >> PG_LEVEL_SHIFT(level)) & 0x1ffu;
+		pte = &pt[index];
 
-	/* Allocate page directory table if not present. */
-	struct eptPageTableEntry *pdpe;
-	pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
-	if (!pdpe[index[2]].readable) {
-		pdpe[index[2]].address = vm_alloc_page_table(vm) >> vm->page_shift;
-		pdpe[index[2]].writable = true;
-		pdpe[index[2]].readable = true;
-		pdpe[index[2]].executable = true;
-	}
+		nested_create_pte(vm, pte, nested_paddr, paddr, level, target_level);
 
-	/* Allocate page table if not present. */
-	struct eptPageTableEntry *pde;
-	pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
-	if (!pde[index[1]].readable) {
-		pde[index[1]].address = vm_alloc_page_table(vm) >> vm->page_shift;
-		pde[index[1]].writable = true;
-		pde[index[1]].readable = true;
-		pde[index[1]].executable = true;
-	}
+		if (pte->page_size)
+			break;
 
-	/* Fill in page table entry. */
-	struct eptPageTableEntry *pte;
-	pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
-	pte[index[0]].address = paddr >> vm->page_shift;
-	pte[index[0]].writable = true;
-	pte[index[0]].readable = true;
-	pte[index[0]].executable = true;
+		pt = addr_gpa2hva(vm, pte->address * vm->page_size);
+	}
 
 	/*
 	 * For now mark these as accessed and dirty because the only
 	 * testcase we have needs that.  Can be reconsidered later.
 	 */
-	pte[index[0]].accessed = true;
-	pte[index[0]].dirty = true;
+	pte->accessed = true;
+	pte->dirty = true;
+
+}
+
+void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+		   uint64_t nested_paddr, uint64_t paddr)
+{
+	__nested_pg_map(vmx, vm, nested_paddr, paddr, PG_LEVEL_4K);
 }
 
 /*
@@ -476,7 +499,7 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
  *   nested_paddr - Nested guest physical address to map
  *   paddr - VM Physical Address
  *   size - The size of the range to map
- *   eptp_memslot - Memory region slot for new virtual translation tables
+ *   level - The level at which to map the range
  *
  * Output Args: None
  *
@@ -485,22 +508,29 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
  * Within the VM given by vm, creates a nested guest translation for the
  * page range starting at nested_paddr to the page range starting at paddr.
  */
-void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
-		uint64_t nested_paddr, uint64_t paddr, uint64_t size)
+void __nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+		  uint64_t nested_paddr, uint64_t paddr, uint64_t size,
+		  int level)
 {
-	size_t page_size = vm->page_size;
+	size_t page_size = PG_LEVEL_SIZE(level);
 	size_t npages = size / page_size;
 
 	TEST_ASSERT(nested_paddr + size > nested_paddr, "Vaddr overflow");
 	TEST_ASSERT(paddr + size > paddr, "Paddr overflow");
 
 	while (npages--) {
-		nested_pg_map(vmx, vm, nested_paddr, paddr);
+		__nested_pg_map(vmx, vm, nested_paddr, paddr, level);
 		nested_paddr += page_size;
 		paddr += page_size;
 	}
 }
 
+void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+		uint64_t nested_paddr, uint64_t paddr, uint64_t size)
+{
+	__nested_map(vmx, vm, nested_paddr, paddr, size, PG_LEVEL_4K);
+}
+
 /* Prepare an identity extended page table that maps all the
  * physical pages in VM.
  */
@@ -525,6 +555,13 @@ void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
 	}
 }
 
+/* Identity map a region with 1GiB Pages. */
+void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm,
+			    uint64_t addr, uint64_t size)
+{
+	__nested_map(vmx, vm, addr, addr, size, PG_LEVEL_1G);
+}
+
 void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
 		  uint32_t eptp_memslot)
 {
diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c
index 3875c4b23a04..15f046e19cb2 100644
--- a/tools/testing/selftests/kvm/max_guest_memory_test.c
+++ b/tools/testing/selftests/kvm/max_guest_memory_test.c
@@ -244,7 +244,7 @@ int main(int argc, char *argv[])
 #ifdef __x86_64__
 		/* Identity map memory in the guest using 1gb pages. */
 		for (i = 0; i < slot_size; i += size_1gb)
-			__virt_pg_map(vm, gpa + i, gpa + i, X86_PAGE_SIZE_1G);
+			__virt_pg_map(vm, gpa + i, gpa + i, PG_LEVEL_1G);
 #else
 		for (i = 0; i < slot_size; i += vm_get_page_size(vm))
 			virt_pg_map(vm, gpa + i, gpa + i);
diff --git a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
index da2325fcad87..bdecd532f935 100644
--- a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
+++ b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
@@ -35,7 +35,7 @@ static void mmu_role_test(u32 *cpuid_reg, u32 evil_cpuid_val)
 	run = vcpu_state(vm, VCPU_ID);
 
 	/* Map 1gb page without a backing memlot. */
-	__virt_pg_map(vm, MMIO_GPA, MMIO_GPA, X86_PAGE_SIZE_1G);
+	__virt_pg_map(vm, MMIO_GPA, MMIO_GPA, PG_LEVEL_1G);
 
 	r = _vcpu_run(vm, VCPU_ID);
 
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 2a2d240cdc1b..1a5cc3cd97ec 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -7,10 +7,31 @@ else ifneq ($(filter -%,$(LLVM)),)
 LLVM_SUFFIX := $(LLVM)
 endif
 
-CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX)
+CLANG_TARGET_FLAGS_arm          := arm-linux-gnueabi
+CLANG_TARGET_FLAGS_arm64        := aarch64-linux-gnu
+CLANG_TARGET_FLAGS_hexagon      := hexagon-linux-musl
+CLANG_TARGET_FLAGS_m68k         := m68k-linux-gnu
+CLANG_TARGET_FLAGS_mips         := mipsel-linux-gnu
+CLANG_TARGET_FLAGS_powerpc      := powerpc64le-linux-gnu
+CLANG_TARGET_FLAGS_riscv        := riscv64-linux-gnu
+CLANG_TARGET_FLAGS_s390         := s390x-linux-gnu
+CLANG_TARGET_FLAGS_x86          := x86_64-linux-gnu
+CLANG_TARGET_FLAGS              := $(CLANG_TARGET_FLAGS_$(ARCH))
+
+ifeq ($(CROSS_COMPILE),)
+ifeq ($(CLANG_TARGET_FLAGS),)
+$(error Specify CROSS_COMPILE or add '--target=' option to lib.mk
+else
+CLANG_FLAGS     += --target=$(CLANG_TARGET_FLAGS)
+endif # CLANG_TARGET_FLAGS
+else
+CLANG_FLAGS     += --target=$(notdir $(CROSS_COMPILE:%-=%))
+endif # CROSS_COMPILE
+
+CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX) $(CLANG_FLAGS) -fintegrated-as
 else
 CC := $(CROSS_COMPILE)gcc
-endif
+endif # LLVM
 
 ifeq (0,$(MAKELEVEL))
     ifeq ($(OUTPUT),)
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index b984f8c8d523..a29f79618934 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -37,4 +37,3 @@ gro
 ioam6_parser
 toeplitz
 cmsg_sender
-bind_bhash_test
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 464df13831f2..7ea54af55490 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -59,7 +59,6 @@ TEST_GEN_FILES += toeplitz
 TEST_GEN_FILES += cmsg_sender
 TEST_GEN_FILES += stress_reuseport_listen
 TEST_PROGS += test_vxlan_vnifiltering.sh
-TEST_GEN_FILES += bind_bhash_test
 
 TEST_FILES := settings
 
@@ -70,5 +69,4 @@ include bpf/Makefile
 
 $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
 $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread
-$(OUTPUT)/bind_bhash_test: LDLIBS += -lpthread
 $(OUTPUT)/tcp_inq: LDLIBS += -lpthread
diff --git a/tools/testing/selftests/net/bind_bhash_test.c b/tools/testing/selftests/net/bind_bhash_test.c
deleted file mode 100644
index 252e73754e76..000000000000
--- a/tools/testing/selftests/net/bind_bhash_test.c
+++ /dev/null
@@ -1,119 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * This times how long it takes to bind to a port when the port already
- * has multiple sockets in its bhash table.
- *
- * In the setup(), we populate the port's bhash table with
- * MAX_THREADS * MAX_CONNECTIONS number of entries.
- */
-
-#include <unistd.h>
-#include <stdio.h>
-#include <netdb.h>
-#include <pthread.h>
-
-#define MAX_THREADS 600
-#define MAX_CONNECTIONS 40
-
-static const char *bind_addr = "::1";
-static const char *port;
-
-static int fd_array[MAX_THREADS][MAX_CONNECTIONS];
-
-static int bind_socket(int opt, const char *addr)
-{
-	struct addrinfo *res, hint = {};
-	int sock_fd, reuse = 1, err;
-
-	sock_fd = socket(AF_INET6, SOCK_STREAM, 0);
-	if (sock_fd < 0) {
-		perror("socket fd err");
-		return -1;
-	}
-
-	hint.ai_family = AF_INET6;
-	hint.ai_socktype = SOCK_STREAM;
-
-	err = getaddrinfo(addr, port, &hint, &res);
-	if (err) {
-		perror("getaddrinfo failed");
-		return -1;
-	}
-
-	if (opt) {
-		err = setsockopt(sock_fd, SOL_SOCKET, opt, &reuse, sizeof(reuse));
-		if (err) {
-			perror("setsockopt failed");
-			return -1;
-		}
-	}
-
-	err = bind(sock_fd, res->ai_addr, res->ai_addrlen);
-	if (err) {
-		perror("failed to bind to port");
-		return -1;
-	}
-
-	return sock_fd;
-}
-
-static void *setup(void *arg)
-{
-	int sock_fd, i;
-	int *array = (int *)arg;
-
-	for (i = 0; i < MAX_CONNECTIONS; i++) {
-		sock_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, bind_addr);
-		if (sock_fd < 0)
-			return NULL;
-		array[i] = sock_fd;
-	}
-
-	return NULL;
-}
-
-int main(int argc, const char *argv[])
-{
-	int listener_fd, sock_fd, i, j;
-	pthread_t tid[MAX_THREADS];
-	clock_t begin, end;
-
-	if (argc != 2) {
-		printf("Usage: listener <port>\n");
-		return -1;
-	}
-
-	port = argv[1];
-
-	listener_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, bind_addr);
-	if (listen(listener_fd, 100) < 0) {
-		perror("listen failed");
-		return -1;
-	}
-
-	/* Set up threads to populate the bhash table entry for the port */
-	for (i = 0; i < MAX_THREADS; i++)
-		pthread_create(&tid[i], NULL, setup, fd_array[i]);
-
-	for (i = 0; i < MAX_THREADS; i++)
-		pthread_join(tid[i], NULL);
-
-	begin = clock();
-
-	/* Bind to the same port on a different address */
-	sock_fd  = bind_socket(0, "2001:0db8:0:f101::1");
-
-	end = clock();
-
-	printf("time spent = %f\n", (double)(end - begin) / CLOCKS_PER_SEC);
-
-	/* clean up */
-	close(sock_fd);
-	close(listener_fd);
-	for (i = 0; i < MAX_THREADS; i++) {
-		for (j = 0; i < MAX_THREADS; i++)
-			close(fd_array[i][j]);
-	}
-
-	return 0;
-}
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 54701c8b0cd7..03b586760164 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -70,6 +70,10 @@ NSB_LO_IP6=2001:db8:2::2
 NL_IP=172.17.1.1
 NL_IP6=2001:db8:4::1
 
+# multicast and broadcast addresses
+MCAST_IP=224.0.0.1
+BCAST_IP=255.255.255.255
+
 MD5_PW=abc123
 MD5_WRONG_PW=abc1234
 
@@ -308,6 +312,9 @@ addr2str()
 	127.0.0.1) echo "loopback";;
 	::1) echo "IPv6 loopback";;
 
+	${BCAST_IP}) echo "broadcast";;
+	${MCAST_IP}) echo "multicast";;
+
 	${NSA_IP})	echo "ns-A IP";;
 	${NSA_IP6})	echo "ns-A IPv6";;
 	${NSA_LO_IP})	echo "ns-A loopback IP";;
@@ -1793,12 +1800,33 @@ ipv4_addr_bind_novrf()
 	done
 
 	#
-	# raw socket with nonlocal bind
+	# tests for nonlocal bind
 	#
 	a=${NL_IP}
 	log_start
-	run_cmd nettest -s -R -P icmp -f -l ${a} -I ${NSA_DEV} -b
-	log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address after device bind"
+	run_cmd nettest -s -R -f -l ${a} -b
+	log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address"
+
+	log_start
+	run_cmd nettest -s -f -l ${a} -b
+	log_test_addr ${a} $? 0 "TCP socket bind to nonlocal address"
+
+	log_start
+	run_cmd nettest -s -D -P icmp -f -l ${a} -b
+	log_test_addr ${a} $? 0 "ICMP socket bind to nonlocal address"
+
+	#
+	# check that ICMP sockets cannot bind to broadcast and multicast addresses
+	#
+	a=${BCAST_IP}
+	log_start
+	run_cmd nettest -s -D -P icmp -l ${a} -b
+	log_test_addr ${a} $? 1 "ICMP socket bind to broadcast address"
+
+	a=${MCAST_IP}
+	log_start
+	run_cmd nettest -s -D -P icmp -l ${a} -b
+	log_test_addr ${a} $? 1 "ICMP socket bind to multicast address"
 
 	#
 	# tcp sockets
@@ -1850,13 +1878,34 @@ ipv4_addr_bind_vrf()
 	log_test_addr ${a} $? 1 "Raw socket bind to out of scope address after VRF bind"
 
 	#
-	# raw socket with nonlocal bind
+	# tests for nonlocal bind
 	#
 	a=${NL_IP}
 	log_start
-	run_cmd nettest -s -R -P icmp -f -l ${a} -I ${VRF} -b
+	run_cmd nettest -s -R -f -l ${a} -I ${VRF} -b
 	log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address after VRF bind"
 
+	log_start
+	run_cmd nettest -s -f -l ${a} -I ${VRF} -b
+	log_test_addr ${a} $? 0 "TCP socket bind to nonlocal address after VRF bind"
+
+	log_start
+	run_cmd nettest -s -D -P icmp -f -l ${a} -I ${VRF} -b
+	log_test_addr ${a} $? 0 "ICMP socket bind to nonlocal address after VRF bind"
+
+	#
+	# check that ICMP sockets cannot bind to broadcast and multicast addresses
+	#
+	a=${BCAST_IP}
+	log_start
+	run_cmd nettest -s -D -P icmp -l ${a} -I ${VRF} -b
+	log_test_addr ${a} $? 1 "ICMP socket bind to broadcast address after VRF bind"
+
+	a=${MCAST_IP}
+	log_start
+	run_cmd nettest -s -D -P icmp -l ${a} -I ${VRF} -b
+	log_test_addr ${a} $? 1 "ICMP socket bind to multicast address after VRF bind"
+
 	#
 	# tcp sockets
 	#
@@ -1889,10 +1938,12 @@ ipv4_addr_bind()
 
 	log_subsection "No VRF"
 	setup
+	set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null
 	ipv4_addr_bind_novrf
 
 	log_subsection "With VRF"
 	setup "yes"
+	set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null
 	ipv4_addr_bind_vrf
 }
 
diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh
index b35010cc7f6a..a6991877e50c 100755
--- a/tools/testing/selftests/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/netfilter/nft_concat_range.sh
@@ -31,7 +31,7 @@ BUGS="flush_remove_add reload"
 
 # List of possible paths to pktgen script from kernel tree for performance tests
 PKTGEN_SCRIPT_PATHS="
-	../../../samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh
+	../../../../samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh
 	pktgen/pktgen_bench_xmit_mode_netif_receive.sh"
 
 # Definition of set types:
diff --git a/tools/testing/selftests/vm/ksm_tests.c b/tools/testing/selftests/vm/ksm_tests.c
index 2fcf24312da8..f5e4e0bbd081 100644
--- a/tools/testing/selftests/vm/ksm_tests.c
+++ b/tools/testing/selftests/vm/ksm_tests.c
@@ -54,6 +54,7 @@ static int ksm_write_sysfs(const char *file_path, unsigned long val)
 	}
 	if (fprintf(f, "%lu", val) < 0) {
 		perror("fprintf");
+		fclose(f);
 		return 1;
 	}
 	fclose(f);
@@ -72,6 +73,7 @@ static int ksm_read_sysfs(const char *file_path, unsigned long *val)
 	}
 	if (fscanf(f, "%lu", val) != 1) {
 		perror("fscanf");
+		fclose(f);
 		return 1;
 	}
 	fclose(f);