Merge tag 'perf-tools-for-v5.10-2020-11-03' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:
 "Only fixes and a sync of the headers so that the perf build is silent:

   - Fix visibility attribute in python module init code with newer gcc

   - Fix DRAM_BW_Use 0 issue for CLX/SKX in intel JSON vendor event
     files

   - Fix the build on new fedora by removing LTO compiler options when
     building perl support

   - Remove broken __no_tail_call attribute

   - Fix segfault when trying to trace events by cgroup

   - Fix crash with non-jited BPF progs

   - Increase buffer size in TUI browser, fixing format truncation

   - Fix printing of build-id for objects lacking one

   - Fix byte swapping for ino_generation field in MMAP2 perf.data
     records

   - Fix byte swapping for CGROUP perf.data records, for cross arch
     analysis of perf.data files

   - Fix the fast path of feature detection

   - Update kernel header copies"

* tag 'perf-tools-for-v5.10-2020-11-03' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (23 commits)
  tools feature: Fixup fast path feature detection
  perf tools: Add missing swap for cgroup events
  perf tools: Add missing swap for ino_generation
  perf tools: Initialize output buffer in build_id__sprintf
  perf hists browser: Increase size of 'buf' in perf_evsel__hists_browse()
  tools include UAPI: Update linux/mount.h copy
  tools headers UAPI: Update tools's copy of linux/perf_event.h
  tools kvm headers: Update KVM headers from the kernel sources
  tools UAPI: Update copy of linux/mman.h from the kernel sources
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  tools x86 headers: Update required-features.h header from the kernel
  tools x86 headers: Update cpufeatures.h headers copies
  tools headers UAPI: Update fscrypt.h copy
  tools headers UAPI: Sync drm/i915_drm.h with the kernel sources
  tools headers UAPI: Sync prctl.h with the kernel sources
  perf scripting python: Avoid declaring function pointers with a visibility attribute
  perf tools: Remove broken __no_tail_call attribute
  perf vendor events: Fix DRAM_BW_Use 0 issue for CLX/SKX
  perf trace: Fix segfault when trying to trace events by cgroup
  perf tools: Fix crash with non-jited bpf progs
  ...

tools/arch/arm64/include/uapi/asm/kvm.h

@@ -159,6 +159,21 @@ struct kvm_sync_regs {
 struct kvm_arch_memory_slot {
 };
 
+/*
+ * PMU filter structure. Describe a range of events with a particular
+ * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER.
+ */
+struct kvm_pmu_event_filter {
+	__u16	base_event;
+	__u16	nevents;
+
+#define KVM_PMU_EVENT_ALLOW	0
+#define KVM_PMU_EVENT_DENY	1
+
+	__u8	action;
+	__u8	pad[3];
+};
+
 /* for KVM_GET/SET_VCPU_EVENTS */
 struct kvm_vcpu_events {
 	struct {
@@ -242,6 +257,15 @@ struct kvm_vcpu_events {
 #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
+
+/*
+ * Only two states can be presented by the host kernel:
+ * - NOT_REQUIRED: the guest doesn't need to do anything
+ * - NOT_AVAIL: the guest isn't mitigated (it can still use SSBS if available)
+ *
+ * All the other values are deprecated. The host still accepts all
+ * values (they are ABI), but will narrow them to the above two.
+ */
 #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
@@ -329,6 +353,7 @@ struct kvm_vcpu_events {
 #define KVM_ARM_VCPU_PMU_V3_CTRL	0
 #define   KVM_ARM_VCPU_PMU_V3_IRQ	0
 #define   KVM_ARM_VCPU_PMU_V3_INIT	1
+#define   KVM_ARM_VCPU_PMU_V3_FILTER	2
 #define KVM_ARM_VCPU_TIMER_CTRL		1
 #define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER		0
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1

tools/arch/s390/include/uapi/asm/sie.h

@@ -29,7 +29,7 @@
 	{ 0x13, "SIGP conditional emergency signal" },		\
 	{ 0x15, "SIGP sense running" },				\
 	{ 0x16, "SIGP set multithreading"},			\
-	{ 0x17, "SIGP store additional status ait address"}
+	{ 0x17, "SIGP store additional status at address"}
 
 #define icpt_prog_codes						\
 	{ 0x0001, "Prog Operation" },				\

tools/arch/x86/include/asm/cpufeatures.h

@@ -96,7 +96,7 @@
 #define X86_FEATURE_SYSCALL32		( 3*32+14) /* "" syscall in IA32 userspace */
 #define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
-/* free					( 3*32+17) */
+#define X86_FEATURE_SME_COHERENT	( 3*32+17) /* "" AMD hardware-enforced cache coherency */
 #define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
 #define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
 #define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
@@ -236,6 +236,7 @@
 #define X86_FEATURE_EPT_AD		( 8*32+17) /* Intel Extended Page Table access-dirty bit */
 #define X86_FEATURE_VMCALL		( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
 #define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
+#define X86_FEATURE_SEV_ES		( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
@@ -288,6 +289,7 @@
 #define X86_FEATURE_FENCE_SWAPGS_USER	(11*32+ 4) /* "" LFENCE in user entry SWAPGS path */
 #define X86_FEATURE_FENCE_SWAPGS_KERNEL	(11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */
 #define X86_FEATURE_SPLIT_LOCK_DETECT	(11*32+ 6) /* #AC for split lock */
+#define X86_FEATURE_PER_THREAD_MBA	(11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
@@ -353,6 +355,7 @@
 #define X86_FEATURE_CLDEMOTE		(16*32+25) /* CLDEMOTE instruction */
 #define X86_FEATURE_MOVDIRI		(16*32+27) /* MOVDIRI instruction */
 #define X86_FEATURE_MOVDIR64B		(16*32+28) /* MOVDIR64B instruction */
+#define X86_FEATURE_ENQCMD		(16*32+29) /* ENQCMD and ENQCMDS instructions */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* MCA overflow recovery support */
@@ -368,6 +371,7 @@
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_SERIALIZE		(18*32+14) /* SERIALIZE instruction */
+#define X86_FEATURE_TSXLDTRK		(18*32+16) /* TSX Suspend Load Address Tracking */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_ARCH_LBR		(18*32+19) /* Intel ARCH LBR */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */

tools/arch/x86/include/asm/disabled-features.h

@@ -56,6 +56,12 @@
 # define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
 #endif
 
+#ifdef CONFIG_IOMMU_SUPPORT
+# define DISABLE_ENQCMD	0
+#else
+# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -75,7 +81,8 @@
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
-#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
+#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
+			 DISABLE_ENQCMD)
 #define DISABLED_MASK17	0
 #define DISABLED_MASK18	0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)

tools/arch/x86/include/asm/msr-index.h

@@ -257,6 +257,9 @@
 #define MSR_IA32_LASTINTFROMIP		0x000001dd
 #define MSR_IA32_LASTINTTOIP		0x000001de
 
+#define MSR_IA32_PASID			0x00000d93
+#define MSR_IA32_PASID_VALID		BIT_ULL(31)
+
 /* DEBUGCTLMSR bits (others vary by model): */
 #define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
 #define DEBUGCTLMSR_BTF_SHIFT		1
@@ -464,11 +467,15 @@
 #define MSR_AMD64_IBSOP_REG_MASK	((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
 #define MSR_AMD64_IBSCTL		0xc001103a
 #define MSR_AMD64_IBSBRTARGET		0xc001103b
+#define MSR_AMD64_ICIBSEXTDCTL		0xc001103c
 #define MSR_AMD64_IBSOPDATA4		0xc001103d
 #define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
+#define MSR_AMD64_SEV_ES_GHCB		0xc0010130
 #define MSR_AMD64_SEV			0xc0010131
 #define MSR_AMD64_SEV_ENABLED_BIT	0
+#define MSR_AMD64_SEV_ES_ENABLED_BIT	1
 #define MSR_AMD64_SEV_ENABLED		BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
+#define MSR_AMD64_SEV_ES_ENABLED	BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
 
 #define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
 
@@ -857,11 +864,14 @@
 #define MSR_CORE_PERF_FIXED_CTR0	0x00000309
 #define MSR_CORE_PERF_FIXED_CTR1	0x0000030a
 #define MSR_CORE_PERF_FIXED_CTR2	0x0000030b
+#define MSR_CORE_PERF_FIXED_CTR3	0x0000030c
 #define MSR_CORE_PERF_FIXED_CTR_CTRL	0x0000038d
 #define MSR_CORE_PERF_GLOBAL_STATUS	0x0000038e
 #define MSR_CORE_PERF_GLOBAL_CTRL	0x0000038f
 #define MSR_CORE_PERF_GLOBAL_OVF_CTRL	0x00000390
 
+#define MSR_PERF_METRICS		0x00000329
+
 /* PERF_GLOBAL_OVF_CTL bits */
 #define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT	55
 #define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI		(1ULL << MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT)

tools/arch/x86/include/asm/required-features.h

@@ -54,7 +54,7 @@
 #endif
 
 #ifdef CONFIG_X86_64
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
 /* Paravirtualized systems may not have PSE or PGE available */
 #define NEED_PSE	0
 #define NEED_PGE	0

tools/arch/x86/include/uapi/asm/kvm.h

@@ -192,6 +192,26 @@ struct kvm_msr_list {
 	__u32 indices[0];
 };
 
+/* Maximum size of any access bitmap in bytes */
+#define KVM_MSR_FILTER_MAX_BITMAP_SIZE 0x600
+
+/* for KVM_X86_SET_MSR_FILTER */
+struct kvm_msr_filter_range {
+#define KVM_MSR_FILTER_READ  (1 << 0)
+#define KVM_MSR_FILTER_WRITE (1 << 1)
+	__u32 flags;
+	__u32 nmsrs; /* number of msrs in bitmap */
+	__u32 base;  /* MSR index the bitmap starts at */
+	__u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */
+};
+
+#define KVM_MSR_FILTER_MAX_RANGES 16
+struct kvm_msr_filter {
+#define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
+#define KVM_MSR_FILTER_DEFAULT_DENY  (1 << 0)
+	__u32 flags;
+	struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
+};
 
 struct kvm_cpuid_entry {
 	__u32 function;

tools/arch/x86/include/uapi/asm/svm.h

@@ -29,6 +29,7 @@
 #define SVM_EXIT_WRITE_DR6     0x036
 #define SVM_EXIT_WRITE_DR7     0x037
 #define SVM_EXIT_EXCP_BASE     0x040
+#define SVM_EXIT_LAST_EXCP     0x05f
 #define SVM_EXIT_INTR          0x060
 #define SVM_EXIT_NMI           0x061
 #define SVM_EXIT_SMI           0x062
@@ -76,10 +77,21 @@
 #define SVM_EXIT_MWAIT_COND    0x08c
 #define SVM_EXIT_XSETBV        0x08d
 #define SVM_EXIT_RDPRU         0x08e
+#define SVM_EXIT_INVPCID       0x0a2
 #define SVM_EXIT_NPF           0x400
 #define SVM_EXIT_AVIC_INCOMPLETE_IPI		0x401
 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS	0x402
 
+/* SEV-ES software-defined VMGEXIT events */
+#define SVM_VMGEXIT_MMIO_READ			0x80000001
+#define SVM_VMGEXIT_MMIO_WRITE			0x80000002
+#define SVM_VMGEXIT_NMI_COMPLETE		0x80000003
+#define SVM_VMGEXIT_AP_HLT_LOOP			0x80000004
+#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_UNSUPPORTED_EVENT		0x8000ffff
+
 #define SVM_EXIT_ERR           -1
 
 #define SVM_EXIT_REASONS \
@@ -171,6 +183,7 @@
 	{ SVM_EXIT_MONITOR,     "monitor" }, \
 	{ SVM_EXIT_MWAIT,       "mwait" }, \
 	{ SVM_EXIT_XSETBV,      "xsetbv" }, \
+	{ SVM_EXIT_INVPCID,     "invpcid" }, \
 	{ SVM_EXIT_NPF,         "npf" }, \
 	{ SVM_EXIT_AVIC_INCOMPLETE_IPI,		"avic_incomplete_ipi" }, \
 	{ SVM_EXIT_AVIC_UNACCELERATED_ACCESS,   "avic_unaccelerated_access" }, \

tools/build/feature/test-all.c

@@ -185,7 +185,6 @@ int main(int argc, char *argv[])
 	main_test_libperl();
 	main_test_hello();
 	main_test_libelf();
-	main_test_libelf_mmap();
 	main_test_get_current_dir_name();
 	main_test_gettid();
 	main_test_glibc();

tools/include/linux/compiler-gcc.h

@@ -27,18 +27,6 @@
 #define  __pure		__attribute__((pure))
 #endif
 #define  noinline	__attribute__((noinline))
-#ifdef __has_attribute
-#if __has_attribute(disable_tail_calls)
-#define __no_tail_call	__attribute__((disable_tail_calls))
-#endif
-#endif
-#ifndef __no_tail_call
-#if GCC_VERSION > 40201
-#define __no_tail_call	__attribute__((optimize("no-optimize-sibling-calls")))
-#else
-#define __no_tail_call
-#endif
-#endif
 #ifndef __packed
 #define __packed	__attribute__((packed))
 #endif

tools/include/linux/compiler.h

@@ -47,9 +47,6 @@
 #ifndef noinline
 #define noinline
 #endif
-#ifndef __no_tail_call
-#define __no_tail_call
-#endif
 
 /* Are two types/vars the same type (ignoring qualifiers)? */
 #ifndef __same_type

tools/include/uapi/asm-generic/unistd.h

@@ -857,9 +857,11 @@ __SYSCALL(__NR_openat2, sys_openat2)
 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
 #define __NR_faccessat2 439
 __SYSCALL(__NR_faccessat2, sys_faccessat2)
+#define __NR_process_madvise 440
+__SYSCALL(__NR_process_madvise, sys_process_madvise)
 
 #undef __NR_syscalls
-#define __NR_syscalls 440
+#define __NR_syscalls 441
 
 /*
  * 32 bit systems traditionally used different

tools/include/uapi/drm/i915_drm.h

@@ -619,6 +619,12 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_PERF_REVISION	54
 
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See
+ * I915_EXEC_USE_EXTENSIONS.
+ */
+#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55
+
 /* Must be kept compact -- no holes and well documented */
 
 typedef struct drm_i915_getparam {
@@ -1046,6 +1052,38 @@ struct drm_i915_gem_exec_fence {
 	__u32 flags;
 };
 
+/**
+ * See drm_i915_gem_execbuffer_ext_timeline_fences.
+ */
+#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
+
+/**
+ * This structure describes an array of drm_syncobj and associated points for
+ * timeline variants of drm_syncobj. It is invalid to append this structure to
+ * the execbuf if I915_EXEC_FENCE_ARRAY is set.
+ */
+struct drm_i915_gem_execbuffer_ext_timeline_fences {
+	struct i915_user_extension base;
+
+	/**
+	 * Number of element in the handles_ptr & value_ptr arrays.
+	 */
+	__u64 fence_count;
+
+	/**
+	 * Pointer to an array of struct drm_i915_gem_exec_fence of length
+	 * fence_count.
+	 */
+	__u64 handles_ptr;
+
+	/**
+	 * Pointer to an array of u64 values of length fence_count. Values
+	 * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline
+	 * drm_syncobj is invalid as it turns a drm_syncobj into a binary one.
+	 */
+	__u64 values_ptr;
+};
+
 struct drm_i915_gem_execbuffer2 {
 	/**
 	 * List of gem_exec_object2 structs
@@ -1062,8 +1100,14 @@ struct drm_i915_gem_execbuffer2 {
 	__u32 num_cliprects;
 	/**
 	 * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
-	 * is not set.  If I915_EXEC_FENCE_ARRAY is set, then this is a
+	 * & I915_EXEC_USE_EXTENSIONS are not set.
-	 * struct drm_i915_gem_exec_fence *fences.
+	 *
+	 * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array
+	 * of struct drm_i915_gem_exec_fence and num_cliprects is the length
+	 * of the array.
+	 *
+	 * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a
+	 * single struct i915_user_extension and num_cliprects is 0.
 	 */
 	__u64 cliprects_ptr;
 #define I915_EXEC_RING_MASK              (0x3f)
@@ -1181,7 +1225,16 @@ struct drm_i915_gem_execbuffer2 {
  */
 #define I915_EXEC_FENCE_SUBMIT		(1 << 20)
 
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1))
+/*
+ * Setting I915_EXEC_USE_EXTENSIONS implies that
+ * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked
+ * list of i915_user_extension. Each i915_user_extension node is the base of a
+ * larger structure. The list of supported structures are listed in the
+ * drm_i915_gem_execbuffer_ext enum.
+ */
+#define I915_EXEC_USE_EXTENSIONS	(1 << 21)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1))
 
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \

tools/include/uapi/linux/fscrypt.h

@@ -45,7 +45,6 @@ struct fscrypt_policy_v1 {
 	__u8 flags;
 	__u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
 };
-#define fscrypt_policy	fscrypt_policy_v1
 
 /*
  * Process-subscribed "logon" key description prefix and payload format.
@@ -156,9 +155,9 @@ struct fscrypt_get_key_status_arg {
 	__u32 __out_reserved[13];
 };
 
-#define FS_IOC_SET_ENCRYPTION_POLICY		_IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_SET_ENCRYPTION_POLICY		_IOR('f', 19, struct fscrypt_policy_v1)
 #define FS_IOC_GET_ENCRYPTION_PWSALT		_IOW('f', 20, __u8[16])
-#define FS_IOC_GET_ENCRYPTION_POLICY		_IOW('f', 21, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_POLICY		_IOW('f', 21, struct fscrypt_policy_v1)
 #define FS_IOC_GET_ENCRYPTION_POLICY_EX		_IOWR('f', 22, __u8[9]) /* size + version */
 #define FS_IOC_ADD_ENCRYPTION_KEY		_IOWR('f', 23, struct fscrypt_add_key_arg)
 #define FS_IOC_REMOVE_ENCRYPTION_KEY		_IOWR('f', 24, struct fscrypt_remove_key_arg)
@@ -170,6 +169,7 @@ struct fscrypt_get_key_status_arg {
 
 /* old names; don't add anything new here! */
 #ifndef __KERNEL__
+#define fscrypt_policy			fscrypt_policy_v1
 #define FS_KEY_DESCRIPTOR_SIZE		FSCRYPT_KEY_DESCRIPTOR_SIZE
 #define FS_POLICY_FLAGS_PAD_4		FSCRYPT_POLICY_FLAGS_PAD_4
 #define FS_POLICY_FLAGS_PAD_8		FSCRYPT_POLICY_FLAGS_PAD_8

tools/include/uapi/linux/kvm.h

@@ -248,6 +248,8 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_IOAPIC_EOI       26
 #define KVM_EXIT_HYPERV           27
 #define KVM_EXIT_ARM_NISV         28
+#define KVM_EXIT_X86_RDMSR        29
+#define KVM_EXIT_X86_WRMSR        30
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -413,6 +415,17 @@ struct kvm_run {
 			__u64 esr_iss;
 			__u64 fault_ipa;
 		} arm_nisv;
+		/* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */
+		struct {
+			__u8 error; /* user -> kernel */
+			__u8 pad[7];
+#define KVM_MSR_EXIT_REASON_INVAL	(1 << 0)
+#define KVM_MSR_EXIT_REASON_UNKNOWN	(1 << 1)
+#define KVM_MSR_EXIT_REASON_FILTER	(1 << 2)
+			__u32 reason; /* kernel -> user */
+			__u32 index; /* kernel -> user */
+			__u64 data; /* kernel <-> user */
+		} msr;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1037,6 +1050,9 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_SMALLER_MAXPHYADDR 185
 #define KVM_CAP_S390_DIAG318 186
 #define KVM_CAP_STEAL_TIME 187
+#define KVM_CAP_X86_USER_SPACE_MSR 188
+#define KVM_CAP_X86_MSR_FILTER 189
+#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1538,6 +1554,9 @@ struct kvm_pv_cmd {
 /* Available with KVM_CAP_S390_PROTECTED */
 #define KVM_S390_PV_COMMAND		_IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
 
+/* Available with KVM_CAP_X86_MSR_FILTER */
+#define KVM_X86_SET_MSR_FILTER	_IOW(KVMIO,  0xc6, struct kvm_msr_filter)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */

tools/include/uapi/linux/mman.h

@@ -27,6 +27,7 @@
 #define MAP_HUGE_SHIFT	HUGETLB_FLAG_ENCODE_SHIFT
 #define MAP_HUGE_MASK	HUGETLB_FLAG_ENCODE_MASK
 
+#define MAP_HUGE_16KB	HUGETLB_FLAG_ENCODE_16KB
 #define MAP_HUGE_64KB	HUGETLB_FLAG_ENCODE_64KB
 #define MAP_HUGE_512KB	HUGETLB_FLAG_ENCODE_512KB
 #define MAP_HUGE_1MB	HUGETLB_FLAG_ENCODE_1MB

tools/include/uapi/linux/mount.h

@@ -16,6 +16,7 @@
 #define MS_REMOUNT	32	/* Alter flags of a mounted FS */
 #define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
 #define MS_DIRSYNC	128	/* Directory modifications are synchronous */
+#define MS_NOSYMFOLLOW	256	/* Do not follow symlinks */
 #define MS_NOATIME	1024	/* Do not update access times. */
 #define MS_NODIRATIME	2048	/* Do not update directory access times */
 #define MS_BIND		4096

tools/include/uapi/linux/perf_event.h

@@ -1196,7 +1196,7 @@ union perf_mem_data_src {
 
 #define PERF_MEM_SNOOPX_FWD	0x01 /* forward */
 /* 1 free */
-#define PERF_MEM_SNOOPX_SHIFT	38
+#define PERF_MEM_SNOOPX_SHIFT  38
 
 /* locked instruction */
 #define PERF_MEM_LOCK_NA	0x01 /* not available */

tools/include/uapi/linux/prctl.h

@@ -233,6 +233,15 @@ struct prctl_mm_map {
 #define PR_SET_TAGGED_ADDR_CTRL		55
 #define PR_GET_TAGGED_ADDR_CTRL		56
 # define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
+/* MTE tag check fault modes */
+# define PR_MTE_TCF_SHIFT		1
+# define PR_MTE_TCF_NONE		(0UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_SYNC		(1UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_ASYNC		(2UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_MASK		(3UL << PR_MTE_TCF_SHIFT)
+/* MTE tag inclusion mask */
+# define PR_MTE_TAG_SHIFT		3
+# define PR_MTE_TAG_MASK		(0xffffUL << PR_MTE_TAG_SHIFT)
 
 /* Control reclaim behavior when allocating memory */
 #define PR_SET_IO_FLUSHER		57

tools/include/uapi/linux/vhost.h

@@ -146,4 +146,8 @@
 
 /* Set event fd for config interrupt*/
 #define VHOST_VDPA_SET_CONFIG_CALL	_IOW(VHOST_VIRTIO, 0x77, int)
+
+/* Get the valid iova range */
+#define VHOST_VDPA_GET_IOVA_RANGE	_IOR(VHOST_VIRTIO, 0x78, \
+					     struct vhost_vdpa_iova_range)
 #endif

tools/perf/Makefile.config

@@ -749,6 +749,7 @@ else
   PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
   PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null)
   PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS))
+  PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS))
   PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS))
   FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 

tools/perf/arch/x86/entry/syscalls/syscall_64.tbl

@@ -361,12 +361,13 @@
 437	common	openat2			sys_openat2
 438	common	pidfd_getfd		sys_pidfd_getfd
 439	common	faccessat2		sys_faccessat2
+440	common	process_madvise		sys_process_madvise
 
 #
-# x32-specific system call numbers start at 512 to avoid cache impact
+# Due to a historical design error, certain syscalls are numbered differently
-# for native 64-bit operation. The __x32_compat_sys stubs are created
+# in x32 as compared to native x86_64.  These syscalls have numbers 512-547.
-# on-the-fly for compat_sys_*() compatibility system calls if X86_X32
+# Do not add new syscalls to this range.  Numbers 548 and above are available
-# is defined.
+# for non-x32 use.
 #
 512	x32	rt_sigaction		compat_sys_rt_sigaction
 513	x32	rt_sigreturn		compat_sys_x32_rt_sigreturn
@@ -404,3 +405,5 @@
 545	x32	execveat		compat_sys_execveat
 546	x32	preadv2			compat_sys_preadv64v2
 547	x32	pwritev2		compat_sys_pwritev64v2
+# This is the end of the legacy x32 range.  Numbers 548 and above are
+# not special and are not to be used for x32-specific syscalls.

tools/perf/builtin-trace.c

@@ -4639,9 +4639,9 @@ do_concat:
 	err = 0;
 
 	if (lists[0]) {
-		struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
+		struct option o = {
-					       "event selector. use 'perf list' to list available events",
+			.value = &trace->evlist,
-					       parse_events_option);
+		};
 		err = parse_events_option(&o, lists[0], 0);
 	}
 out:
@@ -4655,9 +4655,12 @@ static int trace__parse_cgroups(const struct option *opt, const char *str, int u
 {
 	struct trace *trace = opt->value;
 
-	if (!list_empty(&trace->evlist->core.entries))
+	if (!list_empty(&trace->evlist->core.entries)) {
-		return parse_cgroups(opt, str, unset);
+		struct option o = {
-
+			.value = &trace->evlist,
+		};
+		return parse_cgroups(&o, str, unset);
+	}
 	trace->cgroup = evlist__findnew_cgroup(trace->evlist, str);
 
 	return 0;

tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json

@@ -329,7 +329,7 @@
     },
     {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time",
         "MetricGroup": "Memory_BW;SoC",
         "MetricName": "DRAM_BW_Use"
     },

tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json

@@ -323,7 +323,7 @@
     },
     {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time",
         "MetricGroup": "Memory_BW;SoC",
         "MetricName": "DRAM_BW_Use"
     },

tools/perf/tests/dwarf-unwind.c

@@ -95,7 +95,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	return strcmp((const char *) symbol, funcs[idx]);
 }
 
-__no_tail_call noinline int test_dwarf_unwind__thread(struct thread *thread)
+noinline int test_dwarf_unwind__thread(struct thread *thread)
 {
 	struct perf_sample sample;
 	unsigned long cnt = 0;
@@ -126,7 +126,7 @@ __no_tail_call noinline int test_dwarf_unwind__thread(struct thread *thread)
 
 static int global_unwind_retval = -INT_MAX;
 
-__no_tail_call noinline int test_dwarf_unwind__compare(void *p1, void *p2)
+noinline int test_dwarf_unwind__compare(void *p1, void *p2)
 {
 	/* Any possible value should be 'thread' */
 	struct thread *thread = *(struct thread **)p1;
@@ -145,7 +145,7 @@ __no_tail_call noinline int test_dwarf_unwind__compare(void *p1, void *p2)
 	return p1 - p2;
 }
 
-__no_tail_call noinline int test_dwarf_unwind__krava_3(struct thread *thread)
+noinline int test_dwarf_unwind__krava_3(struct thread *thread)
 {
 	struct thread *array[2] = {thread, thread};
 	void *fp = &bsearch;
@@ -164,12 +164,12 @@ __no_tail_call noinline int test_dwarf_unwind__krava_3(struct thread *thread)
 	return global_unwind_retval;
 }
 
-__no_tail_call noinline int test_dwarf_unwind__krava_2(struct thread *thread)
+noinline int test_dwarf_unwind__krava_2(struct thread *thread)
 {
 	return test_dwarf_unwind__krava_3(thread);
 }
 
-__no_tail_call noinline int test_dwarf_unwind__krava_1(struct thread *thread)
+noinline int test_dwarf_unwind__krava_1(struct thread *thread)
 {
 	return test_dwarf_unwind__krava_2(thread);
 }

tools/perf/ui/browsers/hists.c

@@ -2963,7 +2963,7 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events,
 	struct popup_action actions[MAX_OPTIONS];
 	int nr_options = 0;
 	int key = -1;
-	char buf[64];
+	char buf[128];
 	int delay_secs = hbt ? hbt->refresh : 0;
 
 #define HIST_BROWSER_HELP_COMMON					\

tools/perf/util/build-id.c

@@ -102,6 +102,8 @@ int build_id__sprintf(const struct build_id *build_id, char *bf)
 	const u8 *raw = build_id->data;
 	size_t i;
 
+	bf[0] = 0x0;
+
 	for (i = 0; i < build_id->size; ++i) {
 		sprintf(bid, "%02x", *raw);
 		++raw;

tools/perf/util/hashmap.c

@@ -15,6 +15,9 @@
 /* make sure libbpf doesn't use kernel-only integer typedefs */
 #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
 
+/* prevent accidental re-addition of reallocarray() */
+#pragma GCC poison reallocarray
+
 /* start with 4 buckets */
 #define HASHMAP_MIN_CAP_BITS 2
 

tools/perf/util/hashmap.h

@@ -25,6 +25,18 @@ static inline size_t hash_bits(size_t h, int bits)
 #endif
 }
 
+/* generic C-string hashing function */
+static inline size_t str_hash(const char *s)
+{
+	size_t h = 0;
+
+	while (*s) {
+		h = h * 31 + *s;
+		s++;
+	}
+	return h;
+}
+
 typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
 typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
 

tools/perf/util/machine.c

@@ -786,11 +786,20 @@ static int machine__process_ksymbol_unregister(struct machine *machine,
 					       union perf_event *event,
 					       struct perf_sample *sample __maybe_unused)
 {
+	struct symbol *sym;
 	struct map *map;
 
 	map = maps__find(&machine->kmaps, event->ksymbol.addr);
-	if (map)
+	if (!map)
+		return 0;
+
+	if (map != machine->vmlinux_map)
 		maps__remove(&machine->kmaps, map);
+	else {
+		sym = dso__find_symbol(map->dso, map->map_ip(map, map->start));
+		if (sym)
+			dso__delete_symbol(map->dso, sym);
+	}
 
 	return 0;
 }

tools/perf/util/scripting-engines/trace-event-python.c

@@ -1592,7 +1592,6 @@ static void _free_command_line(wchar_t **command_line, int num)
 static int python_start_script(const char *script, int argc, const char **argv)
 {
 	struct tables *tables = &tables_global;
-	PyMODINIT_FUNC (*initfunc)(void);
 #if PY_MAJOR_VERSION < 3
 	const char **command_line;
 #else
@@ -1607,20 +1606,18 @@ static int python_start_script(const char *script, int argc, const char **argv)
 	FILE *fp;
 
 #if PY_MAJOR_VERSION < 3
-	initfunc = initperf_trace_context;
 	command_line = malloc((argc + 1) * sizeof(const char *));
 	command_line[0] = script;
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = argv[i - 1];
+	PyImport_AppendInittab(name, initperf_trace_context);
 #else
-	initfunc = PyInit_perf_trace_context;
 	command_line = malloc((argc + 1) * sizeof(wchar_t *));
 	command_line[0] = Py_DecodeLocale(script, NULL);
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = Py_DecodeLocale(argv[i - 1], NULL);
+	PyImport_AppendInittab(name, PyInit_perf_trace_context);
 #endif
-
-	PyImport_AppendInittab(name, initfunc);
 	Py_Initialize();
 
 #if PY_MAJOR_VERSION < 3

tools/perf/util/session.c

@@ -595,6 +595,7 @@ static void perf_event__mmap2_swap(union perf_event *event,
 	event->mmap2.maj   = bswap_32(event->mmap2.maj);
 	event->mmap2.min   = bswap_32(event->mmap2.min);
 	event->mmap2.ino   = bswap_64(event->mmap2.ino);
+	event->mmap2.ino_generation = bswap_64(event->mmap2.ino_generation);
 
 	if (sample_id_all) {
 		void *data = &event->mmap2.filename;
@@ -710,6 +711,18 @@ static void perf_event__namespaces_swap(union perf_event *event,
 		swap_sample_id_all(event, &event->namespaces.link_info[i]);
 }
 
+static void perf_event__cgroup_swap(union perf_event *event, bool sample_id_all)
+{
+	event->cgroup.id = bswap_64(event->cgroup.id);
+
+	if (sample_id_all) {
+		void *data = &event->cgroup.path;
+
+		data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
+		swap_sample_id_all(event, data);
+	}
+}
+
 static u8 revbyte(u8 b)
 {
 	int rev = (b >> 4) | ((b & 0xf) << 4);
@@ -952,6 +965,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_SWITCH]		  = perf_event__switch_swap,
 	[PERF_RECORD_SWITCH_CPU_WIDE]	  = perf_event__switch_swap,
 	[PERF_RECORD_NAMESPACES]	  = perf_event__namespaces_swap,
+	[PERF_RECORD_CGROUP]		  = perf_event__cgroup_swap,
 	[PERF_RECORD_TEXT_POKE]		  = perf_event__text_poke_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,

tools/perf/util/symbol.c

@@ -515,6 +515,13 @@ void dso__insert_symbol(struct dso *dso, struct symbol *sym)
 	}
 }
 
+void dso__delete_symbol(struct dso *dso, struct symbol *sym)
+{
+	rb_erase_cached(&sym->rb_node, &dso->symbols);
+	symbol__delete(sym);
+	dso__reset_find_symbol_cache(dso);
+}
+
 struct symbol *dso__find_symbol(struct dso *dso, u64 addr)
 {
 	if (dso->last_find_result.addr != addr || dso->last_find_result.symbol == NULL) {

tools/perf/util/symbol.h

@@ -131,6 +131,8 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map);
 
 void dso__insert_symbol(struct dso *dso,
 			struct symbol *sym);
+void dso__delete_symbol(struct dso *dso,
+			struct symbol *sym);
 
 struct symbol *dso__find_symbol(struct dso *dso, u64 addr);
 struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name);