Merge tag 'kvmarm-5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm updates for 5.4

- New ITS translation cache
- Allow up to 512 CPUs to be supported with GICv3 (for real this time)
- Now call kvm_arch_vcpu_blocking early in the blocking sequence
- Tidy-up device mappings in S2 when DIC is available
- Clean icache invalidation on VMID rollover
- General cleanup

54 files changed, 927 insertions, 118 deletions

diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 4602464ebdfb..a4217c1a5d01 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -214,6 +214,18 @@ struct kvm_vcpu_events {
 #define KVM_REG_ARM_FW_REG(r)		(KVM_REG_ARM | KVM_REG_SIZE_U64 | \
 					 KVM_REG_ARM_FW | ((r) & 0xffff))
 #define KVM_REG_ARM_PSCI_VERSION	KVM_REG_ARM_FW_REG(0)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1	KVM_REG_ARM_FW_REG(1)
+	/* Higher values mean better protection. */
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL		0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL		1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED	2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2	KVM_REG_ARM_FW_REG(2)
+	/* Higher values mean better protection. */
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL		0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN		1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL		2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED	3
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED	(1U << 4)
 
 /* Device Control API: ARM VGIC */
 #define KVM_DEV_ARM_VGIC_GRP_ADDR	0
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index d819a3e8b552..9a507716ae2f 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -229,6 +229,16 @@ struct kvm_vcpu_events {
 #define KVM_REG_ARM_FW_REG(r)		(KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
 					 KVM_REG_ARM_FW | ((r) & 0xffff))
 #define KVM_REG_ARM_PSCI_VERSION	KVM_REG_ARM_FW_REG(0)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1	KVM_REG_ARM_FW_REG(1)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL		0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL		1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED	2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2	KVM_REG_ARM_FW_REG(2)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL		0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN		1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL		2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED	3
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED     	(1U << 4)
 
 /* SVE registers */
 #define KVM_REG_ARM64_SVE		(0x15 << KVM_REG_ARM_COPROC_SHIFT)
diff --git a/tools/arch/powerpc/include/uapi/asm/mman.h b/tools/arch/powerpc/include/uapi/asm/mman.h
index f33105bc5ca6..8601d824a9c6 100644
--- a/tools/arch/powerpc/include/uapi/asm/mman.h
+++ b/tools/arch/powerpc/include/uapi/asm/mman.h
@@ -4,12 +4,8 @@
 #define MAP_DENYWRITE	0x0800
 #define MAP_EXECUTABLE	0x1000
 #define MAP_GROWSDOWN	0x0100
-#define MAP_HUGETLB	0x40000
 #define MAP_LOCKED	0x80
-#define MAP_NONBLOCK	0x10000
 #define MAP_NORESERVE   0x40
-#define MAP_POPULATE	0x8000
-#define MAP_STACK	0x20000
 #include <uapi/asm-generic/mman-common.h>
 /* MAP_32BIT is undefined on powerpc, fix it for perf */
 #define MAP_32BIT	0
diff --git a/tools/arch/sparc/include/uapi/asm/mman.h b/tools/arch/sparc/include/uapi/asm/mman.h
index 38920eed8cbf..7b94dccc843d 100644
--- a/tools/arch/sparc/include/uapi/asm/mman.h
+++ b/tools/arch/sparc/include/uapi/asm/mman.h
@@ -4,12 +4,8 @@
 #define MAP_DENYWRITE	0x0800
 #define MAP_EXECUTABLE	0x1000
 #define MAP_GROWSDOWN	0x0200
-#define MAP_HUGETLB	0x40000
 #define MAP_LOCKED      0x100
-#define MAP_NONBLOCK	0x10000
 #define MAP_NORESERVE   0x40
-#define MAP_POPULATE	0x8000
-#define MAP_STACK	0x20000
 #include <uapi/asm-generic/mman-common.h>
 /* MAP_32BIT is undefined on sparc, fix it for perf */
 #define MAP_32BIT	0
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index d6ab5b4d15e5..503d3f42da16 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -378,10 +378,11 @@ 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_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_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1	/* unused */
@@ -432,4 +433,17 @@ struct kvm_nested_state {
 	} data;
 };
 
+/* for KVM_CAP_PMU_EVENT_FILTER */
+struct kvm_pmu_event_filter {
+	__u32 action;
+	__u32 nevents;
+	__u32 fixed_counter_bitmap;
+	__u32 flags;
+	__u32 pad[4];
+	__u64 events[0];
+};
+
+#define KVM_PMU_EVENT_ALLOW 0
+#define KVM_PMU_EVENT_DENY 1
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index d213ec5c3766..f0b0c90dd398 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -146,7 +146,6 @@
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL       2
-#define VMX_ABORT_VMCS_CORRUPTED             3
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
 
 #endif /* _UAPIVMX_H */
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index abd238d0f7a4..63b1f506ea67 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -19,15 +19,18 @@
 #define MAP_TYPE	0x0f		/* Mask for type of mapping */
 #define MAP_FIXED	0x10		/* Interpret addr exactly */
 #define MAP_ANONYMOUS	0x20		/* don't use a file */
-#ifdef CONFIG_MMAP_ALLOW_UNINITIALIZED
-# define MAP_UNINITIALIZED 0x4000000	/* For anonymous mmap, memory could be uninitialized */
-#else
-# define MAP_UNINITIALIZED 0x0		/* Don't support this flag */
-#endif
 
-/* 0x0100 - 0x80000 flags are defined in asm-generic/mman.h */
+/* 0x0100 - 0x4000 flags are defined in asm-generic/mman.h */
+#define MAP_POPULATE		0x008000	/* populate (prefault) pagetables */
+#define MAP_NONBLOCK		0x010000	/* do not block on IO */
+#define MAP_STACK		0x020000	/* give out an address that is best suited for process/thread stacks */
+#define MAP_HUGETLB		0x040000	/* create a huge page mapping */
+#define MAP_SYNC		0x080000 /* perform synchronous page faults for the mapping */
 #define MAP_FIXED_NOREPLACE	0x100000	/* MAP_FIXED which doesn't unmap underlying mapping */
 
+#define MAP_UNINITIALIZED 0x4000000	/* For anonymous mmap, memory could be
+					 * uninitialized */
+
 /*
  * Flags for mlock
  */
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
index 36c197fc44a0..406f7718f9ad 100644
--- a/tools/include/uapi/asm-generic/mman.h
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -9,13 +9,11 @@
 #define MAP_EXECUTABLE	0x1000		/* mark it as an executable */
 #define MAP_LOCKED	0x2000		/* pages are locked */
 #define MAP_NORESERVE	0x4000		/* don't check for reservations */
-#define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
-#define MAP_NONBLOCK	0x10000		/* do not block on IO */
-#define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
-#define MAP_HUGETLB	0x40000		/* create a huge page mapping */
-#define MAP_SYNC	0x80000		/* perform synchronous page faults for the mapping */
 
-/* Bits [26:31] are reserved, see mman-common.h for MAP_HUGETLB usage */
+/*
+ * Bits [26:31] are reserved, see asm-generic/hugetlb_encode.h
+ * for MAP_HUGETLB usage
+ */
 
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index a87904daf103..1be0e798e362 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -844,9 +844,15 @@ __SYSCALL(__NR_fsconfig, sys_fsconfig)
 __SYSCALL(__NR_fsmount, sys_fsmount)
 #define __NR_fspick 433
 __SYSCALL(__NR_fspick, sys_fspick)
+#define __NR_pidfd_open 434
+__SYSCALL(__NR_pidfd_open, sys_pidfd_open)
+#ifdef __ARCH_WANT_SYS_CLONE3
+#define __NR_clone3 435
+__SYSCALL(__NR_clone3, sys_clone3)
+#endif
 
 #undef __NR_syscalls
-#define __NR_syscalls 434
+#define __NR_syscalls 436
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 661d73f9a919..8a5b2f8f8eb9 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -50,6 +50,7 @@ typedef unsigned int drm_handle_t;
 
 #else /* One of the BSDs */
 
+#include <stdint.h>
 #include <sys/ioccom.h>
 #include <sys/types.h>
 typedef int8_t   __s8;
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 3a73f5316766..328d05e77d9f 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -136,6 +136,8 @@ enum drm_i915_gem_engine_class {
 struct i915_engine_class_instance {
 	__u16 engine_class; /* see enum drm_i915_gem_engine_class */
 	__u16 engine_instance;
+#define I915_ENGINE_CLASS_INVALID_NONE -1
+#define I915_ENGINE_CLASS_INVALID_VIRTUAL -2
 };
 
 /**
@@ -355,6 +357,8 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_PERF_ADD_CONFIG	0x37
 #define DRM_I915_PERF_REMOVE_CONFIG	0x38
 #define DRM_I915_QUERY			0x39
+#define DRM_I915_GEM_VM_CREATE		0x3a
+#define DRM_I915_GEM_VM_DESTROY		0x3b
 /* Must be kept compact -- no holes */
 
 #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
@@ -415,6 +419,8 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_PERF_ADD_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
 #define DRM_IOCTL_I915_PERF_REMOVE_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
 #define DRM_IOCTL_I915_QUERY			DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query)
+#define DRM_IOCTL_I915_GEM_VM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_VM_CREATE, struct drm_i915_gem_vm_control)
+#define DRM_IOCTL_I915_GEM_VM_DESTROY	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_VM_DESTROY, struct drm_i915_gem_vm_control)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -598,6 +604,12 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_MMAP_GTT_COHERENT	52
 
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports coordination of parallel
+ * execution through use of explicit fence support.
+ * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT.
+ */
+#define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53
 /* Must be kept compact -- no holes and well documented */
 
 typedef struct drm_i915_getparam {
@@ -1120,7 +1132,16 @@ struct drm_i915_gem_execbuffer2 {
  */
 #define I915_EXEC_FENCE_ARRAY   (1<<19)
 
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1))
+/*
+ * Setting I915_EXEC_FENCE_SUBMIT implies that lower_32_bits(rsvd2) represent
+ * a sync_file fd to wait upon (in a nonblocking manner) prior to executing
+ * the batch.
+ *
+ * Returns -EINVAL if the sync_file fd cannot be found.
+ */
+#define I915_EXEC_FENCE_SUBMIT		(1 << 20)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1))
 
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
@@ -1464,8 +1485,9 @@ struct drm_i915_gem_context_create_ext {
 	__u32 ctx_id; /* output: id of new context*/
 	__u32 flags;
 #define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS	(1u << 0)
+#define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE	(1u << 1)
 #define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \
-	(-(I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS << 1))
+	(-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1))
 	__u64 extensions;
 };
 
@@ -1507,6 +1529,41 @@ struct drm_i915_gem_context_param {
  * On creation, all new contexts are marked as recoverable.
  */
 #define I915_CONTEXT_PARAM_RECOVERABLE	0x8
+
+	/*
+	 * The id of the associated virtual memory address space (ppGTT) of
+	 * this context. Can be retrieved and passed to another context
+	 * (on the same fd) for both to use the same ppGTT and so share
+	 * address layouts, and avoid reloading the page tables on context
+	 * switches between themselves.
+	 *
+	 * See DRM_I915_GEM_VM_CREATE and DRM_I915_GEM_VM_DESTROY.
+	 */
+#define I915_CONTEXT_PARAM_VM		0x9
+
+/*
+ * I915_CONTEXT_PARAM_ENGINES:
+ *
+ * Bind this context to operate on this subset of available engines. Henceforth,
+ * the I915_EXEC_RING selector for DRM_IOCTL_I915_GEM_EXECBUFFER2 operates as
+ * an index into this array of engines; I915_EXEC_DEFAULT selecting engine[0]
+ * and upwards. Slots 0...N are filled in using the specified (class, instance).
+ * Use
+ *	engine_class: I915_ENGINE_CLASS_INVALID,
+ *	engine_instance: I915_ENGINE_CLASS_INVALID_NONE
+ * to specify a gap in the array that can be filled in later, e.g. by a
+ * virtual engine used for load balancing.
+ *
+ * Setting the number of engines bound to the context to 0, by passing a zero
+ * sized argument, will revert back to default settings.
+ *
+ * See struct i915_context_param_engines.
+ *
+ * Extensions:
+ *   i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE)
+ *   i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
+ */
+#define I915_CONTEXT_PARAM_ENGINES	0xa
 /* Must be kept compact -- no holes and well documented */
 
 	__u64 value;
@@ -1540,9 +1597,10 @@ struct drm_i915_gem_context_param_sseu {
 	struct i915_engine_class_instance engine;
 
 	/*
-	 * Unused for now. Must be cleared to zero.
+	 * Unknown flags must be cleared to zero.
 	 */
 	__u32 flags;
+#define I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX (1u << 0)
 
 	/*
 	 * Mask of slices to enable for the context. Valid values are a subset
@@ -1570,12 +1628,115 @@ struct drm_i915_gem_context_param_sseu {
 	__u32 rsvd;
 };
 
+/*
+ * i915_context_engines_load_balance:
+ *
+ * Enable load balancing across this set of engines.
+ *
+ * Into the I915_EXEC_DEFAULT slot [0], a virtual engine is created that when
+ * used will proxy the execbuffer request onto one of the set of engines
+ * in such a way as to distribute the load evenly across the set.
+ *
+ * The set of engines must be compatible (e.g. the same HW class) as they
+ * will share the same logical GPU context and ring.
+ *
+ * To intermix rendering with the virtual engine and direct rendering onto
+ * the backing engines (bypassing the load balancing proxy), the context must
+ * be defined to use a single timeline for all engines.
+ */
+struct i915_context_engines_load_balance {
+	struct i915_user_extension base;
+
+	__u16 engine_index;
+	__u16 num_siblings;
+	__u32 flags; /* all undefined flags must be zero */
+
+	__u64 mbz64; /* reserved for future use; must be zero */
+
+	struct i915_engine_class_instance engines[0];
+} __attribute__((packed));
+
+#define I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(name__, N__) struct { \
+	struct i915_user_extension base; \
+	__u16 engine_index; \
+	__u16 num_siblings; \
+	__u32 flags; \
+	__u64 mbz64; \
+	struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+/*
+ * i915_context_engines_bond:
+ *
+ * Constructed bonded pairs for execution within a virtual engine.
+ *
+ * All engines are equal, but some are more equal than others. Given
+ * the distribution of resources in the HW, it may be preferable to run
+ * a request on a given subset of engines in parallel to a request on a
+ * specific engine. We enable this selection of engines within a virtual
+ * engine by specifying bonding pairs, for any given master engine we will
+ * only execute on one of the corresponding siblings within the virtual engine.
+ *
+ * To execute a request in parallel on the master engine and a sibling requires
+ * coordination with a I915_EXEC_FENCE_SUBMIT.
+ */
+struct i915_context_engines_bond {
+	struct i915_user_extension base;
+
+	struct i915_engine_class_instance master;
+
+	__u16 virtual_index; /* index of virtual engine in ctx->engines[] */
+	__u16 num_bonds;
+
+	__u64 flags; /* all undefined flags must be zero */
+	__u64 mbz64[4]; /* reserved for future use; must be zero */
+
+	struct i915_engine_class_instance engines[0];
+} __attribute__((packed));
+
+#define I915_DEFINE_CONTEXT_ENGINES_BOND(name__, N__) struct { \
+	struct i915_user_extension base; \
+	struct i915_engine_class_instance master; \
+	__u16 virtual_index; \
+	__u16 num_bonds; \
+	__u64 flags; \
+	__u64 mbz64[4]; \
+	struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+struct i915_context_param_engines {
+	__u64 extensions; /* linked chain of extension blocks, 0 terminates */
+#define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */
+#define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */
+	struct i915_engine_class_instance engines[0];
+} __attribute__((packed));
+
+#define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \
+	__u64 extensions; \
+	struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
 struct drm_i915_gem_context_create_ext_setparam {
 #define I915_CONTEXT_CREATE_EXT_SETPARAM 0
 	struct i915_user_extension base;
 	struct drm_i915_gem_context_param param;
 };
 
+struct drm_i915_gem_context_create_ext_clone {
+#define I915_CONTEXT_CREATE_EXT_CLONE 1
+	struct i915_user_extension base;
+	__u32 clone_id;
+	__u32 flags;
+#define I915_CONTEXT_CLONE_ENGINES	(1u << 0)
+#define I915_CONTEXT_CLONE_FLAGS	(1u << 1)
+#define I915_CONTEXT_CLONE_SCHEDATTR	(1u << 2)
+#define I915_CONTEXT_CLONE_SSEU		(1u << 3)
+#define I915_CONTEXT_CLONE_TIMELINE	(1u << 4)
+#define I915_CONTEXT_CLONE_VM		(1u << 5)
+#define I915_CONTEXT_CLONE_UNKNOWN -(I915_CONTEXT_CLONE_VM << 1)
+	__u64 rsvd;
+};
+
 struct drm_i915_gem_context_destroy {
 	__u32 ctx_id;
 	__u32 pad;
@@ -1821,6 +1982,7 @@ struct drm_i915_perf_oa_config {
 struct drm_i915_query_item {
 	__u64 query_id;
 #define DRM_I915_QUERY_TOPOLOGY_INFO    1
+#define DRM_I915_QUERY_ENGINE_INFO	2
 /* Must be kept compact -- no holes and well documented */
 
 	/*
@@ -1919,6 +2081,47 @@ struct drm_i915_query_topology_info {
 	__u8 data[];
 };
 
+/**
+ * struct drm_i915_engine_info
+ *
+ * Describes one engine and it's capabilities as known to the driver.
+ */
+struct drm_i915_engine_info {
+	/** Engine class and instance. */
+	struct i915_engine_class_instance engine;
+
+	/** Reserved field. */
+	__u32 rsvd0;
+
+	/** Engine flags. */
+	__u64 flags;
+
+	/** Capabilities of this engine. */
+	__u64 capabilities;
+#define I915_VIDEO_CLASS_CAPABILITY_HEVC		(1 << 0)
+#define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC	(1 << 1)
+
+	/** Reserved fields. */
+	__u64 rsvd1[4];
+};
+
+/**
+ * struct drm_i915_query_engine_info
+ *
+ * Engine info query enumerates all engines known to the driver by filling in
+ * an array of struct drm_i915_engine_info structures.
+ */
+struct drm_i915_query_engine_info {
+	/** Number of struct drm_i915_engine_info structs following. */
+	__u32 num_engines;
+
+	/** MBZ */
+	__u32 rsvd[3];
+
+	/** Marker for drm_i915_engine_info structures. */
+	struct drm_i915_engine_info engines[];
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 7d113a9602f0..4a8c02cafa9a 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -695,6 +695,7 @@ enum {
 	IFLA_VF_IB_NODE_GUID,	/* VF Infiniband node GUID */
 	IFLA_VF_IB_PORT_GUID,	/* VF Infiniband port GUID */
 	IFLA_VF_VLAN_LIST,	/* nested list of vlans, option for QinQ */
+	IFLA_VF_BROADCAST,	/* VF broadcast */
 	__IFLA_VF_MAX,
 };
 
@@ -705,6 +706,10 @@ struct ifla_vf_mac {
 	__u8 mac[32]; /* MAX_ADDR_LEN */
 };
 
+struct ifla_vf_broadcast {
+	__u8 broadcast[32];
+};
+
 struct ifla_vf_vlan {
 	__u32 vf;
 	__u32 vlan; /* 0 - 4095, 0 disables VLAN filter */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index e7c67be7c15f..5e3f12d5359e 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -995,6 +995,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_SVE 170
 #define KVM_CAP_ARM_PTRAUTH_ADDRESS 171
 #define KVM_CAP_ARM_PTRAUTH_GENERIC 172
+#define KVM_CAP_PMU_EVENT_FILTER 173
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1329,6 +1330,8 @@ struct kvm_s390_ucas_mapping {
 #define KVM_PPC_GET_RMMU_INFO	  _IOW(KVMIO,  0xb0, struct kvm_ppc_rmmu_info)
 /* Available with KVM_CAP_PPC_GET_CPU_CHAR */
 #define KVM_PPC_GET_CPU_CHAR	  _IOR(KVMIO,  0xb1, struct kvm_ppc_cpu_char)
+/* Available with KVM_CAP_PMU_EVENT_FILTER */
+#define KVM_SET_PMU_EVENT_FILTER  _IOW(KVMIO,  0xb2, struct kvm_pmu_event_filter)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index ed4ee170bee2..b3105ac1381a 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -2,6 +2,8 @@
 #ifndef _UAPI_LINUX_SCHED_H
 #define _UAPI_LINUX_SCHED_H
 
+#include <linux/types.h>
+
 /*
  * cloning flags:
  */
@@ -32,6 +34,20 @@
 #define CLONE_IO		0x80000000	/* Clone io context */
 
 /*
+ * Arguments for the clone3 syscall
+ */
+struct clone_args {
+	__aligned_u64 flags;
+	__aligned_u64 pidfd;
+	__aligned_u64 child_tid;
+	__aligned_u64 parent_tid;
+	__aligned_u64 exit_signal;
+	__aligned_u64 stack;
+	__aligned_u64 stack_size;
+	__aligned_u64 tls;
+};
+
+/*
  * Scheduling policies
  */
 #define SCHED_NORMAL		0
@@ -51,9 +67,21 @@
 #define SCHED_FLAG_RESET_ON_FORK	0x01
 #define SCHED_FLAG_RECLAIM		0x02
 #define SCHED_FLAG_DL_OVERRUN		0x04
+#define SCHED_FLAG_KEEP_POLICY		0x08
+#define SCHED_FLAG_KEEP_PARAMS		0x10
+#define SCHED_FLAG_UTIL_CLAMP_MIN	0x20
+#define SCHED_FLAG_UTIL_CLAMP_MAX	0x40
+
+#define SCHED_FLAG_KEEP_ALL	(SCHED_FLAG_KEEP_POLICY | \
+				 SCHED_FLAG_KEEP_PARAMS)
+
+#define SCHED_FLAG_UTIL_CLAMP	(SCHED_FLAG_UTIL_CLAMP_MIN | \
+				 SCHED_FLAG_UTIL_CLAMP_MAX)
 
 #define SCHED_FLAG_ALL	(SCHED_FLAG_RESET_ON_FORK	| \
 			 SCHED_FLAG_RECLAIM		| \
-			 SCHED_FLAG_DL_OVERRUN)
+			 SCHED_FLAG_DL_OVERRUN		| \
+			 SCHED_FLAG_KEEP_ALL		| \
+			 SCHED_FLAG_UTIL_CLAMP)
 
 #endif /* _UAPI_LINUX_SCHED_H */
diff --git a/tools/include/uapi/linux/usbdevice_fs.h b/tools/include/uapi/linux/usbdevice_fs.h
index 964e87217be4..78efe870c2b7 100644
--- a/tools/include/uapi/linux/usbdevice_fs.h
+++ b/tools/include/uapi/linux/usbdevice_fs.h
@@ -76,6 +76,26 @@ struct usbdevfs_connectinfo {
 	unsigned char slow;
 };
 
+struct usbdevfs_conninfo_ex {
+	__u32 size;		/* Size of the structure from the kernel's */
+				/* point of view. Can be used by userspace */
+				/* to determine how much data can be       */
+				/* used/trusted.                           */
+	__u32 busnum;           /* USB bus number, as enumerated by the    */
+				/* kernel, the device is connected to.     */
+	__u32 devnum;           /* Device address on the bus.              */
+	__u32 speed;		/* USB_SPEED_* constants from ch9.h        */
+	__u8 num_ports;		/* Number of ports the device is connected */
+				/* to on the way to the root hub. It may   */
+				/* be bigger than size of 'ports' array so */
+				/* userspace can detect overflows.         */
+	__u8 ports[7];		/* List of ports on the way from the root  */
+				/* hub to the device. Current limit in     */
+				/* USB specification is 7 tiers (root hub, */
+				/* 5 intermediate hubs, device), which     */
+				/* gives at most 6 port entries.           */
+};
+
 #define USBDEVFS_URB_SHORT_NOT_OK	0x01
 #define USBDEVFS_URB_ISO_ASAP		0x02
 #define USBDEVFS_URB_BULK_CONTINUATION	0x04
@@ -137,6 +157,7 @@ struct usbdevfs_hub_portinfo {
 #define USBDEVFS_CAP_REAP_AFTER_DISCONNECT	0x10
 #define USBDEVFS_CAP_MMAP			0x20
 #define USBDEVFS_CAP_DROP_PRIVILEGES		0x40
+#define USBDEVFS_CAP_CONNINFO_EX		0x80
 
 /* USBDEVFS_DISCONNECT_CLAIM flags & struct */
 
@@ -197,5 +218,10 @@ struct usbdevfs_streams {
 #define USBDEVFS_FREE_STREAMS      _IOR('U', 29, struct usbdevfs_streams)
 #define USBDEVFS_DROP_PRIVILEGES   _IOW('U', 30, __u32)
 #define USBDEVFS_GET_SPEED         _IO('U', 31)
+/*
+ * Returns struct usbdevfs_conninfo_ex; length is variable to allow
+ * extending size of the data returned.
+ */
+#define USBDEVFS_CONNINFO_EX(len)  _IOC(_IOC_READ, 'U', 32, len)
 
 #endif /* _UAPI_LINUX_USBDEVICE_FS_H */
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 467224feb43b..d821107f55f9 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 /* Copyright (c) 2018 Facebook */
 
+#include <endian.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -419,9 +420,9 @@ done:
 
 static bool btf_check_endianness(const GElf_Ehdr *ehdr)
 {
-#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#if __BYTE_ORDER == __LITTLE_ENDIAN
 	return ehdr->e_ident[EI_DATA] == ELFDATA2LSB;
-#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+#elif __BYTE_ORDER == __BIG_ENDIAN
 	return ehdr->e_ident[EI_DATA] == ELFDATA2MSB;
 #else
 # error "Unrecognized __BYTE_ORDER__"
diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h
index 03748a742146..bae8879cdf58 100644
--- a/tools/lib/bpf/hashmap.h
+++ b/tools/lib/bpf/hashmap.h
@@ -10,6 +10,11 @@
 
 #include <stdbool.h>
 #include <stddef.h>
+#ifdef __GLIBC__
+#include <bits/wordsize.h>
+#else
+#include <bits/reg.h>
+#endif
 #include "libbpf_internal.h"
 
 static inline size_t hash_bits(size_t h, int bits)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 794dd5064ae8..2586b6cb8f34 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -20,6 +20,7 @@
 #include <inttypes.h>
 #include <string.h>
 #include <unistd.h>
+#include <endian.h>
 #include <fcntl.h>
 #include <errno.h>
 #include <asm/unistd.h>
@@ -612,10 +613,10 @@ errout:
 
 static int bpf_object__check_endianness(struct bpf_object *obj)
 {
-#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#if __BYTE_ORDER == __LITTLE_ENDIAN
 	if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB)
 		return 0;
-#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+#elif __BYTE_ORDER == __BIG_ENDIAN
 	if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB)
 		return 0;
 #else
@@ -1377,8 +1378,13 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj)
 		if (!has_datasec && kind == BTF_KIND_VAR) {
 			/* replace VAR with INT */
 			t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
-			t->size = sizeof(int);
-			*(int *)(t+1) = BTF_INT_ENC(0, 0, 32);
+			/*
+			 * using size = 1 is the safest choice, 4 will be too
+			 * big and cause kernel BTF validation failure if
+			 * original variable took less than 4 bytes
+			 */
+			t->size = 1;
+			*(int *)(t+1) = BTF_INT_ENC(0, 0, 8);
 		} else if (!has_datasec && kind == BTF_KIND_DATASEC) {
 			/* replace DATASEC with STRUCT */
 			struct btf_var_secinfo *v = (void *)(t + 1);
@@ -1500,6 +1506,12 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 			   BTF_ELF_SEC, err);
 		btf__free(obj->btf);
 		obj->btf = NULL;
+		/* btf_ext can't exist without btf, so free it as well */
+		if (obj->btf_ext) {
+			btf_ext__free(obj->btf_ext);
+			obj->btf_ext = NULL;
+		}
+
 		if (bpf_object__is_btf_mandatory(obj))
 			return err;
 	}
@@ -4507,13 +4519,13 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt,
 				     const struct perf_buffer_opts *opts)
 {
 	struct perf_buffer_params p = {};
-	struct perf_event_attr attr = {
-		.config = PERF_COUNT_SW_BPF_OUTPUT,
-		.type = PERF_TYPE_SOFTWARE,
-		.sample_type = PERF_SAMPLE_RAW,
-		.sample_period = 1,
-		.wakeup_events = 1,
-	};
+	struct perf_event_attr attr = { 0, };
+
+	attr.config = PERF_COUNT_SW_BPF_OUTPUT,
+	attr.type = PERF_TYPE_SOFTWARE;
+	attr.sample_type = PERF_SAMPLE_RAW;
+	attr.sample_period = 1;
+	attr.wakeup_events = 1;
 
 	p.attr = &attr;
 	p.sample_cb = opts ? opts->sample_cb : NULL;
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 5007b5d4fd2c..680e63066cf3 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -317,17 +317,16 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 
 static int xsk_get_max_queues(struct xsk_socket *xsk)
 {
-	struct ethtool_channels channels;
-	struct ifreq ifr;
+	struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS };
+	struct ifreq ifr = {};
 	int fd, err, ret;
 
 	fd = socket(AF_INET, SOCK_DGRAM, 0);
 	if (fd < 0)
 		return -errno;
 
-	channels.cmd = ETHTOOL_GCHANNELS;
 	ifr.ifr_data = (void *)&channels;
-	strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1);
+	memcpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1);
 	ifr.ifr_name[IFNAMSIZ - 1] = '\0';
 	err = ioctl(fd, SIOCETHTOOL, &ifr);
 	if (err && errno != EOPNOTSUPP) {
@@ -335,7 +334,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
 		goto out;
 	}
 
-	if (channels.max_combined == 0 || errno == EOPNOTSUPP)
+	if (err || channels.max_combined == 0)
 		/* If the device says it has no channels, then all traffic
 		 * is sent to a single stream, so max queues = 1.
 		 */
@@ -517,7 +516,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 		err = -errno;
 		goto out_socket;
 	}
-	strncpy(xsk->ifname, ifname, IFNAMSIZ - 1);
+	memcpy(xsk->ifname, ifname, IFNAMSIZ - 1);
 	xsk->ifname[IFNAMSIZ - 1] = '\0';
 
 	err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index 6d148a40551c..adc5a7e44b98 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -242,7 +242,7 @@ $(OUTPUT)doc.dep : $(wildcard *.txt) build-docdep.perl
 	$(PERL_PATH) ./build-docdep.perl >$@+ $(QUIET_STDERR) && \
 	mv $@+ $@
 
--include $(OUPTUT)doc.dep
+-include $(OUTPUT)doc.dep
 
 _cmds_txt = cmds-ancillaryinterrogators.txt \
 	cmds-ancillarymanipulators.txt \
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index 5f54feb19977..d030c87ed9f5 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -126,7 +126,7 @@ vendor,family,model,stepping. For example: GenuineIntel,6,69,1
 
 	HEADER_TOTAL_MEM = 10,
 
-An uint64_t with the total memory in bytes.
+An uint64_t with the total memory in kilobytes.
 
 	HEADER_CMDLINE = 11,
 
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
index a19690a17291..c8c86a0c9b79 100644
--- a/tools/perf/arch/s390/util/machine.c
+++ b/tools/perf/arch/s390/util/machine.c
@@ -6,8 +6,9 @@
 #include "machine.h"
 #include "api/fs/fs.h"
 #include "debug.h"
+#include "symbol.h"
 
-int arch__fix_module_text_start(u64 *start, const char *name)
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name)
 {
 	u64 m_start = *start;
 	char path[PATH_MAX];
@@ -17,7 +18,35 @@ int arch__fix_module_text_start(u64 *start, const char *name)
 	if (sysfs__read_ull(path, (unsigned long long *)start) < 0) {
 		pr_debug2("Using module %s start:%#lx\n", path, m_start);
 		*start = m_start;
+	} else {
+		/* Successful read of the modules segment text start address.
+		 * Calculate difference between module start address
+		 * in memory and module text segment start address.
+		 * For example module load address is 0x3ff8011b000
+		 * (from /proc/modules) and module text segment start
+		 * address is 0x3ff8011b870 (from file above).
+		 *
+		 * Adjust the module size and subtract the GOT table
+		 * size located at the beginning of the module.
+		 */
+		*size -= (*start - m_start);
 	}
 
 	return 0;
 }
+
+/* On s390 kernel text segment start is located at very low memory addresses,
+ * for example 0x10000. Modules are located at very high memory addresses,
+ * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment
+ * and beginning of first module's text segment is very big.
+ * Therefore do not fill this gap and do not assign it to the kernel dso map.
+ */
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
+		/* Last kernel symbol mapped to end of page */
+		p->end = roundup(p->end, page_size);
+	else
+		p->end = c->start;
+	pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end);
+}
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index b4e6f9e6204a..c29976eca4a8 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -355,6 +355,8 @@
 431	common	fsconfig		__x64_sys_fsconfig
 432	common	fsmount			__x64_sys_fsmount
 433	common	fspick			__x64_sys_fspick
+434	common	pidfd_open		__x64_sys_pidfd_open
+435	common	clone3			__x64_sys_clone3/ptregs
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index a640ca7aaada..513cb2f2fa32 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -379,8 +379,10 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags,
 
 	/* Allocate and initialize all memory on CPU#0: */
 	if (init_cpu0) {
-		orig_mask = bind_to_node(0);
-		bind_to_memnode(0);
+		int node = numa_node_of_cpu(0);
+
+		orig_mask = bind_to_node(node);
+		bind_to_memnode(node);
 	}
 
 	bytes = bytes0 + HPSIZE;
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 66d5a6658daf..019312810405 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -173,7 +173,7 @@ static int set_tracing_cpumask(struct cpu_map *cpumap)
 	int last_cpu;
 
 	last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1);
-	mask_size = (last_cpu + 3) / 4 + 1;
+	mask_size = last_cpu / 4 + 2; /* one more byte for EOS */
 	mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */
 
 	cpumask = malloc(mask_size);
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 1a91a197cafb..d413761621b0 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -453,6 +453,7 @@ static struct fixed {
 	{ "inst_retired.any_p", "event=0xc0" },
 	{ "cpu_clk_unhalted.ref", "event=0x0,umask=0x03" },
 	{ "cpu_clk_unhalted.thread", "event=0x3c" },
+	{ "cpu_clk_unhalted.core", "event=0x3c" },
 	{ "cpu_clk_unhalted.thread_any", "event=0x3c,any=1" },
 	{ NULL, NULL},
 };
diff --git a/tools/perf/trace/beauty/usbdevfs_ioctl.sh b/tools/perf/trace/beauty/usbdevfs_ioctl.sh
index 930b80f422e8..aa597ae53747 100755
--- a/tools/perf/trace/beauty/usbdevfs_ioctl.sh
+++ b/tools/perf/trace/beauty/usbdevfs_ioctl.sh
@@ -3,10 +3,13 @@
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
+# also as:
+# #define USBDEVFS_CONNINFO_EX(len)  _IOC(_IOC_READ, 'U', 32, len)
+
 printf "static const char *usbdevfs_ioctl_cmds[] = {\n"
-regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)[[:space:]]+_IO[WR]{0,2}\([[:space:]]*'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*"
-egrep $regex ${header_dir}/usbdevice_fs.h | egrep -v 'USBDEVFS_\w+32[[:space:]]' | \
-	sed -r "s/$regex/\2 \1/g"	| \
+regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)(\(\w+\))?[[:space:]]+_IO[CWR]{0,2}\([[:space:]]*(_IOC_\w+,[[:space:]]*)?'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*"
+egrep "$regex" ${header_dir}/usbdevice_fs.h | egrep -v 'USBDEVFS_\w+32[[:space:]]' | \
+	sed -r "s/$regex/\4 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n\n"
 printf "#if 0\n"
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index f80c51d53565..d227d74b28f8 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../string2.h"
-#include "../config.h"
-#include "../../perf.h"
+#include "../util/util.h"
+#include "../util/string2.h"
+#include "../util/config.h"
+#include "../perf.h"
 #include "libslang.h"
 #include "ui.h"
 #include "util.h"
@@ -14,7 +15,7 @@
 #include "browser.h"
 #include "helpline.h"
 #include "keysyms.h"
-#include "../color.h"
+#include "../util/color.h"
 #include <linux/ctype.h>
 #include <linux/zalloc.h>
 
diff --git a/tools/perf/ui/tui/progress.c b/tools/perf/ui/tui/progress.c
index bc134b82829d..5a24dd3ce4db 100644
--- a/tools/perf/ui/tui/progress.c
+++ b/tools/perf/ui/tui/progress.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
-#include "../cache.h"
+#include "../../util/cache.h"
 #include "../progress.h"
 #include "../libslang.h"
 #include "../ui.h"
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ac9ad2330f93..163536720149 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1122,7 +1122,7 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp)
 		goto out;
 
 	(*rawp)[0] = tmp;
-	*rawp = skip_spaces(*rawp);
+	*rawp = strim(*rawp);
 
 	return 0;
 
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 3acfbe34ebaf..39cce66b4ebc 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -751,7 +751,10 @@ size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size)
 	unsigned char *bitmap;
 	int last_cpu = cpu_map__cpu(map, map->nr - 1);
 
-	bitmap = zalloc((last_cpu + 7) / 8);
+	if (buf == NULL)
+		return 0;
+
+	bitmap = zalloc(last_cpu / 8 + 1);
 	if (bitmap == NULL) {
 		buf[0] = '\0';
 		return 0;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 20111f8da5cb..1903d7ec9797 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3559,6 +3559,13 @@ int perf_session__read_header(struct perf_session *session)
 			   data->file.path);
 	}
 
+	if (f_header.attr_size == 0) {
+		pr_err("ERROR: The %s file's attr size field is 0 which is unexpected.\n"
+		       "Was the 'perf record' command properly terminated?\n",
+		       data->file.path);
+		return -EINVAL;
+	}
+
 	nr_attrs = f_header.attrs.size / f_header.attr_size;
 	lseek(fd, f_header.attrs.offset, SEEK_SET);
 
@@ -3639,7 +3646,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
 	size += sizeof(struct perf_event_header);
 	size += ids * sizeof(u64);
 
-	ev = malloc(size);
+	ev = zalloc(size);
 
 	if (ev == NULL)
 		return -ENOMEM;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index cf826eca3aaf..83b2fbbeeb90 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1378,6 +1378,7 @@ static int machine__set_modules_path(struct machine *machine)
 	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
 }
 int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
+				u64 *size __maybe_unused,
 				const char *name __maybe_unused)
 {
 	return 0;
@@ -1389,7 +1390,7 @@ static int machine__create_module(void *arg, const char *name, u64 start,
 	struct machine *machine = arg;
 	struct map *map;
 
-	if (arch__fix_module_text_start(&start, name) < 0)
+	if (arch__fix_module_text_start(&start, &size, name) < 0)
 		return -1;
 
 	map = machine__findnew_module_map(machine, start, name);
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index f70ab98a7bde..7aa38da26427 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -222,7 +222,7 @@ struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine,
 
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename);
-int arch__fix_module_text_start(u64 *start, const char *name);
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name);
 
 int machine__load_kallsyms(struct machine *machine, const char *filename);
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 173f3378aaa0..4efde7879474 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -92,6 +92,11 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
+void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	p->end = c->start;
+}
+
 const char * __weak arch__normalize_symbol_name(const char *name)
 {
 	return name;
@@ -218,7 +223,7 @@ void symbols__fixup_end(struct rb_root_cached *symbols)
 		curr = rb_entry(nd, struct symbol, rb_node);
 
 		if (prev->end == prev->start && prev->end != curr->start)
-			prev->end = curr->start;
+			arch__symbols__fixup_end(prev, curr);
 	}
 
 	/* Last entry */
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 12755b42ea93..183f630cb5f1 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -288,6 +288,7 @@ const char *arch__normalize_symbol_name(const char *name);
 #define SYMBOL_A 0
 #define SYMBOL_B 1
 
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c);
 int arch__compare_symbol_names(const char *namea, const char *nameb);
 int arch__compare_symbol_names_n(const char *namea, const char *nameb,
 				 unsigned int n);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 873ab505ca80..590793cc5142 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -214,14 +214,24 @@ struct comm *thread__comm(const struct thread *thread)
 
 struct comm *thread__exec_comm(const struct thread *thread)
 {
-	struct comm *comm, *last = NULL;
+	struct comm *comm, *last = NULL, *second_last = NULL;
 
 	list_for_each_entry(comm, &thread->comm_list, list) {
 		if (comm->exec)
 			return comm;
+		second_last = last;
 		last = comm;
 	}
 
+	/*
+	 * 'last' with no start time might be the parent's comm of a synthesized
+	 * thread (created by processing a synthesized fork event). For a main
+	 * thread, that is very probably wrong. Prefer a later comm to avoid
+	 * that case.
+	 */
+	if (second_last && !last->start && thread->pid_ == thread->tid)
+		return second_last;
+
 	return last;
 }
 
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 11c9c62c3362..c085964e1d05 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -57,7 +57,8 @@ TEST_PROGS := test_kmod.sh \
 	test_lirc_mode2.sh \
 	test_skb_cgroup_id.sh \
 	test_flow_dissector.sh \
-	test_xdp_vlan.sh \
+	test_xdp_vlan_mode_generic.sh \
+	test_xdp_vlan_mode_native.sh \
 	test_lwt_ip_encap.sh \
 	test_tcp_check_syncookie.sh \
 	test_tc_tunnel.sh \
diff --git a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
index 5aeaa284fc47..a68062820410 100644
--- a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
+++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
@@ -41,8 +41,7 @@ int sendmsg_v6_prog(struct bpf_sock_addr *ctx)
 	}
 
 	/* Rewrite destination. */
-	if ((ctx->user_ip6[0] & 0xFFFF) == bpf_htons(0xFACE) &&
-	     ctx->user_ip6[0] >> 16 == bpf_htons(0xB00C)) {
+	if (ctx->user_ip6[0] == bpf_htonl(0xFACEB00C)) {
 		ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0);
 		ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_1);
 		ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2);
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh
index 51a3a31d1aac..bb8b0da91686 100755
--- a/tools/testing/selftests/bpf/test_xdp_vlan.sh
+++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh
@@ -1,6 +1,14 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Author: Jesper Dangaard Brouer <hawk@kernel.org>
 
-TESTNAME=xdp_vlan
+# Allow wrapper scripts to name test
+if [ -z "$TESTNAME" ]; then
+    TESTNAME=xdp_vlan
+fi
+
+# Default XDP mode
+XDP_MODE=xdpgeneric
 
 usage() {
   echo "Testing XDP + TC eBPF VLAN manipulations: $TESTNAME"
@@ -9,9 +17,23 @@ usage() {
   echo "  -v | --verbose : Verbose"
   echo "  --flush        : Flush before starting (e.g. after --interactive)"
   echo "  --interactive  : Keep netns setup running after test-run"
+  echo "  --mode=XXX     : Choose XDP mode (xdp | xdpgeneric | xdpdrv)"
   echo ""
 }
 
+valid_xdp_mode()
+{
+	local mode=$1
+
+	case "$mode" in
+		xdpgeneric | xdpdrv | xdp)
+			return 0
+			;;
+		*)
+			return 1
+	esac
+}
+
 cleanup()
 {
 	local status=$?
@@ -37,7 +59,7 @@ cleanup()
 
 # Using external program "getopt" to get --long-options
 OPTIONS=$(getopt -o hvfi: \
-    --long verbose,flush,help,interactive,debug -- "$@")
+    --long verbose,flush,help,interactive,debug,mode: -- "$@")
 if (( $? != 0 )); then
     usage
     echo "selftests: $TESTNAME [FAILED] Error calling getopt, unknown option?"
@@ -60,6 +82,11 @@ while true; do
 		cleanup
 		shift
 		;;
+	    --mode )
+		shift
+		XDP_MODE=$1
+		shift
+		;;
 	    -- )
 		shift
 		break
@@ -81,8 +108,14 @@ if [ "$EUID" -ne 0 ]; then
 	exit 1
 fi
 
-ip link set dev lo xdp off 2>/dev/null > /dev/null
-if [ $? -ne 0 ];then
+valid_xdp_mode $XDP_MODE
+if [ $? -ne 0 ]; then
+	echo "selftests: $TESTNAME [FAILED] unknown XDP mode ($XDP_MODE)"
+	exit 1
+fi
+
+ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null
+if [ $? -ne 0 ]; then
 	echo "selftests: $TESTNAME [SKIP] need ip xdp support"
 	exit 0
 fi
@@ -155,7 +188,7 @@ ip netns exec ns2 ip link set lo up
 # At this point, the hosts cannot reach each-other,
 # because ns2 are using VLAN tags on the packets.
 
-ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Okay ping fails"'
+ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Success: First ping must fail"'
 
 
 # Now we can use the test_xdp_vlan.c program to pop/push these VLAN tags
@@ -166,7 +199,7 @@ export FILE=test_xdp_vlan.o
 
 # First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change"
 export XDP_PROG=xdp_vlan_change
-ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG
+ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG
 
 # In ns1: egress use TC to add back VLAN tag 4011
 #  (del cmd)
@@ -177,8 +210,8 @@ ip netns exec ns1 tc filter add dev $DEVNS1 egress \
   prio 1 handle 1 bpf da obj $FILE sec tc_vlan_push
 
 # Now the namespaces can reach each-other, test with ping:
-ip netns exec ns2 ping -W 2 -c 3 $IPADDR1
-ip netns exec ns1 ping -W 2 -c 3 $IPADDR2
+ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1
+ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2
 
 # Second test: Replace xdp prog, that fully remove vlan header
 #
@@ -187,9 +220,9 @@ ip netns exec ns1 ping -W 2 -c 3 $IPADDR2
 # ETH_P_8021Q indication, and this cause overwriting of our changes.
 #
 export XDP_PROG=xdp_vlan_remove_outer2
-ip netns exec ns1 ip link set $DEVNS1 xdp off
-ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG
+ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE off
+ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG
 
 # Now the namespaces should still be able reach each-other, test with ping:
-ip netns exec ns2 ping -W 2 -c 3 $IPADDR1
-ip netns exec ns1 ping -W 2 -c 3 $IPADDR2
+ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1
+ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh
new file mode 100755
index 000000000000..c515326d6d59
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Exit on failure
+set -e
+
+# Wrapper script to test generic-XDP
+export TESTNAME=xdp_vlan_mode_generic
+./test_xdp_vlan.sh --mode=xdpgeneric
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh
new file mode 100755
index 000000000000..5cf7ce1f16c1
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Exit on failure
+set -e
+
+# Wrapper script to test native-XDP
+export TESTNAME=xdp_vlan_mode_native
+./test_xdp_vlan.sh --mode=xdpdrv
diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c
index b0fda2877119..d438193804b2 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_skb.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c
@@ -975,6 +975,17 @@
 	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 },
 {
+	"read gso_segs from CGROUP_SKB",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+		    offsetof(struct __sk_buff, gso_segs)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+},
+{
 	"write gso_segs from CGROUP_SKB",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index 4c223266299a..bdb69599c4bd 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -191,8 +191,7 @@ int cg_find_unified_root(char *root, size_t len)
 		strtok(NULL, delim);
 		strtok(NULL, delim);
 
-		if (strcmp(fs, "cgroup") == 0 &&
-		    strcmp(type, "cgroup2") == 0) {
+		if (strcmp(type, "cgroup2") == 0) {
 			strncpy(root, mount, len);
 			return 0;
 		}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
index 71231ad2dbfb..47315fe48d5a 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -262,7 +262,7 @@ test_mc_aware()
 
 	stop_traffic
 
-	log_test "UC performace under MC overload"
+	log_test "UC performance under MC overload"
 
 	echo "UC-only throughput  $(humanize $ucth1)"
 	echo "UC+MC throughput    $(humanize $ucth2)"
@@ -316,7 +316,7 @@ test_uc_aware()
 
 	stop_traffic
 
-	log_test "MC performace under UC overload"
+	log_test "MC performance under UC overload"
 	echo "    ingress UC throughput $(humanize ${uc_ir})"
 	echo "    egress UC throughput  $(humanize ${uc_er})"
 	echo "    sent $attempts BC ARPs, got $passes responses"
diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh
index 0a76314b4414..8b944cf042f6 100755
--- a/tools/testing/selftests/kmod/kmod.sh
+++ b/tools/testing/selftests/kmod/kmod.sh
@@ -28,7 +28,7 @@
 # override by exporting to your environment prior running this script.
 # For instance this script assumes you do not have xfs loaded upon boot.
 # If this is false, export DEFAULT_KMOD_FS="ext4" prior to running this
-# script if the filesyste module you don't have loaded upon bootup
+# script if the filesystem module you don't have loaded upon bootup
 # is ext4 instead. Refer to allow_user_defaults() for a list of user
 # override variables possible.
 #
@@ -263,7 +263,7 @@ config_get_test_result()
 config_reset()
 {
 	if ! echo -n "1" >"$DIR"/reset; then
-		echo "$0: reset shuld have worked" >&2
+		echo "$0: reset should have worked" >&2
 		exit 1
 	fi
 }
@@ -488,7 +488,7 @@ usage()
 	echo Example uses:
 	echo
 	echo "${TEST_NAME}.sh		-- executes all tests"
-	echo "${TEST_NAME}.sh -t 0008	-- Executes test ID 0008 number of times is recomended"
+	echo "${TEST_NAME}.sh -t 0008	-- Executes test ID 0008 number of times is recommended"
 	echo "${TEST_NAME}.sh -w 0008	-- Watch test ID 0008 run until an error occurs"
 	echo "${TEST_NAME}.sh -s 0008	-- Run test ID 0008 once"
 	echo "${TEST_NAME}.sh -c 0008 3	-- Run test ID 0008 three times"
diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h
index ec15c4f6af55..0ac49d91a260 100644
--- a/tools/testing/selftests/kselftest.h
+++ b/tools/testing/selftests/kselftest.h
@@ -10,6 +10,7 @@
 #ifndef __KSELFTEST_H
 #define __KSELFTEST_H
 
+#include <errno.h>
 #include <stdlib.h>
 #include <unistd.h>
 #include <stdarg.h>
@@ -81,58 +82,68 @@ static inline void ksft_print_cnts(void)
 
 static inline void ksft_print_msg(const char *msg, ...)
 {
+	int saved_errno = errno;
 	va_list args;
 
 	va_start(args, msg);
 	printf("# ");
+	errno = saved_errno;
 	vprintf(msg, args);
 	va_end(args);
 }
 
 static inline void ksft_test_result_pass(const char *msg, ...)
 {
+	int saved_errno = errno;
 	va_list args;
 
 	ksft_cnt.ksft_pass++;
 
 	va_start(args, msg);
 	printf("ok %d ", ksft_test_num());
+	errno = saved_errno;
 	vprintf(msg, args);
 	va_end(args);
 }
 
 static inline void ksft_test_result_fail(const char *msg, ...)
 {
+	int saved_errno = errno;
 	va_list args;
 
 	ksft_cnt.ksft_fail++;
 
 	va_start(args, msg);
 	printf("not ok %d ", ksft_test_num());
+	errno = saved_errno;
 	vprintf(msg, args);
 	va_end(args);
 }
 
 static inline void ksft_test_result_skip(const char *msg, ...)
 {
+	int saved_errno = errno;
 	va_list args;
 
 	ksft_cnt.ksft_xskip++;
 
 	va_start(args, msg);
 	printf("not ok %d # SKIP ", ksft_test_num());
+	errno = saved_errno;
 	vprintf(msg, args);
 	va_end(args);
 }
 
 static inline void ksft_test_result_error(const char *msg, ...)
 {
+	int saved_errno = errno;
 	va_list args;
 
 	ksft_cnt.ksft_error++;
 
 	va_start(args, msg);
 	printf("not ok %d # error ", ksft_test_num());
+	errno = saved_errno;
 	vprintf(msg, args);
 	va_end(args);
 }
@@ -152,10 +163,12 @@ static inline int ksft_exit_fail(void)
 
 static inline int ksft_exit_fail_msg(const char *msg, ...)
 {
+	int saved_errno = errno;
 	va_list args;
 
 	va_start(args, msg);
 	printf("Bail out! ");
+	errno = saved_errno;
 	vprintf(msg, args);
 	va_end(args);
 
@@ -178,10 +191,12 @@ static inline int ksft_exit_xpass(void)
 static inline int ksft_exit_skip(const char *msg, ...)
 {
 	if (msg) {
+		int saved_errno = errno;
 		va_list args;
 
 		va_start(args, msg);
 		printf("not ok %d # SKIP ", 1 + ksft_test_num());
+		errno = saved_errno;
 		vprintf(msg, args);
 		va_end(args);
 	} else {
diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh
index 30195449c63c..79b0affd21fb 100644
--- a/tools/testing/selftests/livepatch/functions.sh
+++ b/tools/testing/selftests/livepatch/functions.sh
@@ -13,6 +13,14 @@ function log() {
 	echo "$1" > /dev/kmsg
 }
 
+# skip(msg) - testing can't proceed
+#	msg - explanation
+function skip() {
+	log "SKIP: $1"
+	echo "SKIP: $1" >&2
+	exit 4
+}
+
 # die(msg) - game over, man
 #	msg - dying words
 function die() {
@@ -21,13 +29,27 @@ function die() {
 	exit 1
 }
 
-# set_dynamic_debug() - setup kernel dynamic debug
-#	TODO - push and pop this config?
+function push_dynamic_debug() {
+        DYNAMIC_DEBUG=$(grep '^kernel/livepatch' /sys/kernel/debug/dynamic_debug/control | \
+                awk -F'[: ]' '{print "file " $1 " line " $2 " " $4}')
+}
+
+function pop_dynamic_debug() {
+	if [[ -n "$DYNAMIC_DEBUG" ]]; then
+		echo -n "$DYNAMIC_DEBUG" > /sys/kernel/debug/dynamic_debug/control
+	fi
+}
+
+# set_dynamic_debug() - save the current dynamic debug config and tweak
+# 			it for the self-tests.  Set a script exit trap
+#			that restores the original config.
 function set_dynamic_debug() {
-	cat << EOF > /sys/kernel/debug/dynamic_debug/control
-file kernel/livepatch/* +p
-func klp_try_switch_task -p
-EOF
+        push_dynamic_debug
+        trap pop_dynamic_debug EXIT INT TERM HUP
+        cat <<-EOF > /sys/kernel/debug/dynamic_debug/control
+		file kernel/livepatch/* +p
+		func klp_try_switch_task -p
+		EOF
 }
 
 # loop_until(cmd) - loop a command until it is successful or $MAX_RETRIES,
@@ -43,6 +65,12 @@ function loop_until() {
 	done
 }
 
+function assert_mod() {
+	local mod="$1"
+
+	modprobe --dry-run "$mod" &>/dev/null
+}
+
 function is_livepatch_mod() {
 	local mod="$1"
 
@@ -75,6 +103,9 @@ function __load_mod() {
 function load_mod() {
 	local mod="$1"; shift
 
+	assert_mod "$mod" ||
+		skip "unable to load module ${mod}, verify CONFIG_TEST_LIVEPATCH=m and run self-tests as root"
+
 	is_livepatch_mod "$mod" &&
 		die "use load_lp() to load the livepatch module $mod"
 
@@ -88,6 +119,9 @@ function load_mod() {
 function load_lp_nowait() {
 	local mod="$1"; shift
 
+	assert_mod "$mod" ||
+		skip "unable to load module ${mod}, verify CONFIG_TEST_LIVEPATCH=m and run self-tests as root"
+
 	is_livepatch_mod "$mod" ||
 		die "module $mod is not a livepatch"
 
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 4ce0bc1612f5..c7cced739c34 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -17,7 +17,7 @@ tcp_inq
 tls
 txring_overwrite
 ip_defrag
+ipv6_flowlabel
+ipv6_flowlabel_mgr
 so_txtime
-flowlabel
-flowlabel_mgr
 tcp_fastopen_backup_key
diff --git a/tools/testing/selftests/net/forwarding/gre_multipath.sh b/tools/testing/selftests/net/forwarding/gre_multipath.sh
index cca2baa03fb8..a8d8e8b3dc81 100755
--- a/tools/testing/selftests/net/forwarding/gre_multipath.sh
+++ b/tools/testing/selftests/net/forwarding/gre_multipath.sh
@@ -93,18 +93,10 @@ sw1_create()
 	ip route add vrf v$ol1 192.0.2.16/28 \
 	   nexthop dev g1a \
 	   nexthop dev g1b
-
-	tc qdisc add dev $ul1 clsact
-	tc filter add dev $ul1 egress pref 111 prot ipv4 \
-	   flower dst_ip 192.0.2.66 action pass
-	tc filter add dev $ul1 egress pref 222 prot ipv4 \
-	   flower dst_ip 192.0.2.82 action pass
 }
 
 sw1_destroy()
 {
-	tc qdisc del dev $ul1 clsact
-
 	ip route del vrf v$ol1 192.0.2.16/28
 
 	ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146
@@ -139,10 +131,18 @@ sw2_create()
 	ip route add vrf v$ol2 192.0.2.0/28 \
 	   nexthop dev g2a \
 	   nexthop dev g2b
+
+	tc qdisc add dev $ul2 clsact
+	tc filter add dev $ul2 ingress pref 111 prot 802.1Q \
+	   flower vlan_id 111 action pass
+	tc filter add dev $ul2 ingress pref 222 prot 802.1Q \
+	   flower vlan_id 222 action pass
 }
 
 sw2_destroy()
 {
+	tc qdisc del dev $ul2 clsact
+
 	ip route del vrf v$ol2 192.0.2.0/28
 
 	ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145
@@ -187,12 +187,16 @@ setup_prepare()
 	sw1_create
 	sw2_create
 	h2_create
+
+	forwarding_enable
 }
 
 cleanup()
 {
 	pre_cleanup
 
+	forwarding_restore
+
 	h2_destroy
 	sw2_destroy
 	sw1_destroy
@@ -211,15 +215,15 @@ multipath4_test()
 	   nexthop dev g1a weight $weight1 \
 	   nexthop dev g1b weight $weight2
 
-	local t0_111=$(tc_rule_stats_get $ul1 111 egress)
-	local t0_222=$(tc_rule_stats_get $ul1 222 egress)
+	local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
 
 	ip vrf exec v$h1 \
 	   $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \
 	       -d 1msec -t udp "sp=1024,dp=0-32768"
 
-	local t1_111=$(tc_rule_stats_get $ul1 111 egress)
-	local t1_222=$(tc_rule_stats_get $ul1 222 egress)
+	local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
 
 	local d111=$((t1_111 - t0_111))
 	local d222=$((t1_222 - t0_222))
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 090fff9dbc48..4c285b6e1db8 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -25,6 +25,80 @@
 #define TLS_PAYLOAD_MAX_LEN 16384
 #define SOL_TLS 282
 
+#ifndef ENOTSUPP
+#define ENOTSUPP 524
+#endif
+
+FIXTURE(tls_basic)
+{
+	int fd, cfd;
+	bool notls;
+};
+
+FIXTURE_SETUP(tls_basic)
+{
+	struct sockaddr_in addr;
+	socklen_t len;
+	int sfd, ret;
+
+	self->notls = false;
+	len = sizeof(addr);
+
+	addr.sin_family = AF_INET;
+	addr.sin_addr.s_addr = htonl(INADDR_ANY);
+	addr.sin_port = 0;
+
+	self->fd = socket(AF_INET, SOCK_STREAM, 0);
+	sfd = socket(AF_INET, SOCK_STREAM, 0);
+
+	ret = bind(sfd, &addr, sizeof(addr));
+	ASSERT_EQ(ret, 0);
+	ret = listen(sfd, 10);
+	ASSERT_EQ(ret, 0);
+
+	ret = getsockname(sfd, &addr, &len);
+	ASSERT_EQ(ret, 0);
+
+	ret = connect(self->fd, &addr, sizeof(addr));
+	ASSERT_EQ(ret, 0);
+
+	self->cfd = accept(sfd, &addr, &len);
+	ASSERT_GE(self->cfd, 0);
+
+	close(sfd);
+
+	ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	if (ret != 0) {
+		ASSERT_EQ(errno, ENOENT);
+		self->notls = true;
+		printf("Failure setting TCP_ULP, testing without tls\n");
+		return;
+	}
+
+	ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	ASSERT_EQ(ret, 0);
+}
+
+FIXTURE_TEARDOWN(tls_basic)
+{
+	close(self->fd);
+	close(self->cfd);
+}
+
+/* Send some data through with ULP but no keys */
+TEST_F(tls_basic, base_base)
+{
+	char const *test_str = "test_read";
+	int send_len = 10;
+	char buf[10];
+
+	ASSERT_EQ(strlen(test_str) + 1, send_len);
+
+	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+	EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+};
+
 FIXTURE(tls)
 {
 	int fd, cfd;
@@ -165,6 +239,16 @@ TEST_F(tls, msg_more)
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
 
+TEST_F(tls, msg_more_unsent)
+{
+	char const *test_str = "test_read";
+	int send_len = 10;
+	char buf[10];
+
+	EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1);
+}
+
 TEST_F(tls, sendmsg_single)
 {
 	struct msghdr msg;
@@ -610,6 +694,42 @@ TEST_F(tls, recv_lowat)
 	EXPECT_EQ(memcmp(send_mem, recv_mem + 10, 5), 0);
 }
 
+TEST_F(tls, bidir)
+{
+	char const *test_str = "test_read";
+	int send_len = 10;
+	char buf[10];
+	int ret;
+
+	if (!self->notls) {
+		struct tls12_crypto_info_aes_gcm_128 tls12;
+
+		memset(&tls12, 0, sizeof(tls12));
+		tls12.info.version = TLS_1_3_VERSION;
+		tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128;
+
+		ret = setsockopt(self->fd, SOL_TLS, TLS_RX, &tls12,
+				 sizeof(tls12));
+		ASSERT_EQ(ret, 0);
+
+		ret = setsockopt(self->cfd, SOL_TLS, TLS_TX, &tls12,
+				 sizeof(tls12));
+		ASSERT_EQ(ret, 0);
+	}
+
+	ASSERT_EQ(strlen(test_str) + 1, send_len);
+
+	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+	EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+
+	memset(buf, 0, sizeof(buf));
+
+	EXPECT_EQ(send(self->cfd, test_str, send_len, 0), send_len);
+	EXPECT_NE(recv(self->fd, buf, send_len, 0), -1);
+	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+};
+
 TEST_F(tls, pollin)
 {
 	char const *test_str = "test_poll";
@@ -837,6 +957,109 @@ TEST_F(tls, control_msg)
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
 
+TEST_F(tls, shutdown)
+{
+	char const *test_str = "test_read";
+	int send_len = 10;
+	char buf[10];
+
+	ASSERT_EQ(strlen(test_str) + 1, send_len);
+
+	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+	EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+
+	shutdown(self->fd, SHUT_RDWR);
+	shutdown(self->cfd, SHUT_RDWR);
+}
+
+TEST_F(tls, shutdown_unsent)
+{
+	char const *test_str = "test_read";
+	int send_len = 10;
+
+	EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len);
+
+	shutdown(self->fd, SHUT_RDWR);
+	shutdown(self->cfd, SHUT_RDWR);
+}
+
+TEST_F(tls, shutdown_reuse)
+{
+	struct sockaddr_in addr;
+	int ret;
+
+	shutdown(self->fd, SHUT_RDWR);
+	shutdown(self->cfd, SHUT_RDWR);
+	close(self->cfd);
+
+	addr.sin_family = AF_INET;
+	addr.sin_addr.s_addr = htonl(INADDR_ANY);
+	addr.sin_port = 0;
+
+	ret = bind(self->fd, &addr, sizeof(addr));
+	EXPECT_EQ(ret, 0);
+	ret = listen(self->fd, 10);
+	EXPECT_EQ(ret, -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	ret = connect(self->fd, &addr, sizeof(addr));
+	EXPECT_EQ(ret, -1);
+	EXPECT_EQ(errno, EISCONN);
+}
+
+TEST(non_established) {
+	struct tls12_crypto_info_aes_gcm_256 tls12;
+	struct sockaddr_in addr;
+	int sfd, ret, fd;
+	socklen_t len;
+
+	len = sizeof(addr);
+
+	memset(&tls12, 0, sizeof(tls12));
+	tls12.info.version = TLS_1_2_VERSION;
+	tls12.info.cipher_type = TLS_CIPHER_AES_GCM_256;
+
+	addr.sin_family = AF_INET;
+	addr.sin_addr.s_addr = htonl(INADDR_ANY);
+	addr.sin_port = 0;
+
+	fd = socket(AF_INET, SOCK_STREAM, 0);
+	sfd = socket(AF_INET, SOCK_STREAM, 0);
+
+	ret = bind(sfd, &addr, sizeof(addr));
+	ASSERT_EQ(ret, 0);
+	ret = listen(sfd, 10);
+	ASSERT_EQ(ret, 0);
+
+	ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	EXPECT_EQ(ret, -1);
+	/* TLS ULP not supported */
+	if (errno == ENOENT)
+		return;
+	EXPECT_EQ(errno, ENOTSUPP);
+
+	ret = setsockopt(sfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	EXPECT_EQ(ret, -1);
+	EXPECT_EQ(errno, ENOTSUPP);
+
+	ret = getsockname(sfd, &addr, &len);
+	ASSERT_EQ(ret, 0);
+
+	ret = connect(fd, &addr, sizeof(addr));
+	ASSERT_EQ(ret, 0);
+
+	ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	ASSERT_EQ(ret, 0);
+
+	ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	EXPECT_EQ(ret, -1);
+	EXPECT_EQ(errno, EEXIST);
+
+	close(fd);
+	close(sfd);
+}
+
 TEST(keysizes) {
 	struct tls12_crypto_info_aes_gcm_256 tls12;
 	struct sockaddr_in addr;
diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c
index 7eaa8a3de262..b632965e60eb 100644
--- a/tools/testing/selftests/pidfd/pidfd_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_test.c
@@ -339,13 +339,9 @@ static int test_pidfd_send_signal_syscall_support(void)
 
 	ret = sys_pidfd_send_signal(pidfd, 0, NULL, 0);
 	if (ret < 0) {
-		/*
-		 * pidfd_send_signal() will currently return ENOSYS when
-		 * CONFIG_PROC_FS is not set.
-		 */
 		if (errno == ENOSYS)
 			ksft_exit_skip(
-				"%s test: pidfd_send_signal() syscall not supported (Ensure that CONFIG_PROC_FS=y is set)\n",
+				"%s test: pidfd_send_signal() syscall not supported\n",
 				test_name);
 
 		ksft_exit_fail_msg("%s test: Failed to send signal\n",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
index cc7c7d758008..6503b1ce091f 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
@@ -713,5 +713,99 @@
         "teardown": [
             "$TC actions flush action vlan"
         ]
+    },
+    {
+        "id": "294e",
+        "name": "Add batch of 32 vlan push actions with cookie",
+        "category": [
+            "actions",
+            "vlan"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action vlan",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan push protocol 802.1q id 4094 priority 7 pipe index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action vlan",
+        "matchPattern": "^[ \t]+index [0-9]+ ref",
+        "matchCount": "32",
+        "teardown": [
+            "$TC actions flush action vlan"
+        ]
+    },
+    {
+        "id": "56f7",
+        "name": "Delete batch of 32 vlan push actions",
+        "category": [
+            "actions",
+            "vlan"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action vlan",
+                0,
+                1,
+                255
+            ],
+            "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan push protocol 802.1q id 4094 priority 7 pipe index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\""
+        ],
+        "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action vlan",
+        "matchPattern": "^[ \t]+index [0-9]+ ref",
+        "matchCount": "0",
+        "teardown": []
+    },
+    {
+        "id": "759f",
+        "name": "Add batch of 32 vlan pop actions with cookie",
+        "category": [
+            "actions",
+            "vlan"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action vlan",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan pop continue index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action vlan",
+        "matchPattern": "^[ \t]+index [0-9]+ ref",
+        "matchCount": "32",
+        "teardown": [
+            "$TC actions flush action vlan"
+        ]
+    },
+    {
+        "id": "c84a",
+        "name": "Delete batch of 32 vlan pop actions",
+        "category": [
+            "actions",
+            "vlan"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action vlan",
+                0,
+                1,
+                255
+            ],
+            "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan pop index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\""
+        ],
+        "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action vlan",
+        "matchPattern": "^[ \t]+index [0-9]+ ref",
+        "matchCount": "0",
+        "teardown": []
     }
 ]
diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c
index 4602326b8f5b..a4f4d4cf22c3 100644
--- a/tools/testing/selftests/x86/test_vsyscall.c
+++ b/tools/testing/selftests/x86/test_vsyscall.c
@@ -451,7 +451,7 @@ static int test_vsys_x(void)
 		printf("[OK]\tExecuting the vsyscall page failed: #PF(0x%lx)\n",
 		       segv_err);
 	} else {
-		printf("[FAILT]\tExecution failed with the wrong error: #PF(0x%lx)\n",
+		printf("[FAIL]\tExecution failed with the wrong error: #PF(0x%lx)\n",
 		       segv_err);
 		return 1;
 	}