Merge tag 'perf-tools-fixes-for-v6.0-2022-08-19' of...

Merge tag 'perf-tools-fixes-for-v6.0-2022-08-19' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fix alignment for cpu map masks in event encoding.

 - Support reading PERF_FORMAT_LOST, perf tool counterpart for a feature
   that was added in this merge window.

 - Sync perf tools copies of kernel headers: socket, msr-index, fscrypt,
   cpufeatures, i915_drm, kvm, vhost, perf_event.

* tag 'perf-tools-fixes-for-v6.0-2022-08-19' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf tools: Support reading PERF_FORMAT_LOST
  libperf: Add a test case for read formats
  libperf: Handle read format in perf_evsel__read()
  tools headers UAPI: Sync linux/perf_event.h with the kernel sources
  tools headers UAPI: Sync x86's asm/kvm.h with the kernel sources
  tools headers UAPI: Sync KVM's vmx.h header with the kernel sources
  tools include UAPI: Sync linux/vhost.h with the kernel sources
  tools headers kvm s390: Sync headers with the kernel sources
  tools headers UAPI: Sync linux/kvm.h with the kernel sources
  tools headers UAPI: Sync drm/i915_drm.h with the kernel sources
  tools headers cpufeatures: Sync with the kernel sources
  tools headers UAPI: Sync linux/fscrypt.h with the kernel sources
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  perf beauty: Update copy of linux/socket.h with the kernel sources
  perf cpumap: Fix alignment for masks in event encoding
  perf cpumap: Compute mask size in constant time
  perf cpumap: Synthetic events and const/static
  perf cpumap: Const map for max()

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

@@ -74,6 +74,7 @@ struct kvm_s390_io_adapter_req {
 #define KVM_S390_VM_CRYPTO		2
 #define KVM_S390_VM_CPU_MODEL		3
 #define KVM_S390_VM_MIGRATION		4
+#define KVM_S390_VM_CPU_TOPOLOGY	5
 
 /* kvm attributes for mem_ctrl */
 #define KVM_S390_VM_MEM_ENABLE_CMMA	0

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

@@ -219,7 +219,7 @@
 #define X86_FEATURE_IBRS		( 7*32+25) /* Indirect Branch Restricted Speculation */
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 or above (Zen) */
+#define X86_FEATURE_ZEN			(7*32+28) /* "" CPU based on Zen microarchitecture */
 #define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 #define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
 #define X86_FEATURE_MSR_IA32_FEAT_CTL	( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
@@ -303,7 +303,7 @@
 #define X86_FEATURE_RETHUNK		(11*32+14) /* "" Use REturn THUNK */
 #define X86_FEATURE_UNRET		(11*32+15) /* "" AMD BTB untrain return */
 #define X86_FEATURE_USE_IBPB_FW		(11*32+16) /* "" Use IBPB during runtime firmware calls */
-#define X86_FEATURE_RSB_VMEXIT_LITE	(11*32+17) /* "" Fill RSB on VM-Exit when EIBRS is enabled */
+#define X86_FEATURE_RSB_VMEXIT_LITE	(11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
@@ -354,6 +354,7 @@
 #define X86_FEATURE_AVIC		(15*32+13) /* Virtual Interrupt Controller */
 #define X86_FEATURE_V_VMSAVE_VMLOAD	(15*32+15) /* Virtual VMSAVE VMLOAD */
 #define X86_FEATURE_VGIF		(15*32+16) /* Virtual GIF */
+#define X86_FEATURE_X2AVIC		(15*32+18) /* Virtual x2apic */
 #define X86_FEATURE_V_SPEC_CTRL		(15*32+20) /* Virtual SPEC_CTRL */
 #define X86_FEATURE_SVME_ADDR_CHK	(15*32+28) /* "" SVME addr check */
 
@@ -457,5 +458,6 @@
 #define X86_BUG_SRBDS			X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
 #define X86_BUG_MMIO_STALE_DATA		X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */
 #define X86_BUG_RETBLEED		X86_BUG(26) /* CPU is affected by RETBleed */
+#define X86_BUG_EIBRS_PBRSB		X86_BUG(27) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 
 #endif /* _ASM_X86_CPUFEATURES_H */

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

@@ -235,6 +235,12 @@
 #define PERF_CAP_PT_IDX			16
 
 #define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
+#define PERF_CAP_PEBS_TRAP             BIT_ULL(6)
+#define PERF_CAP_ARCH_REG              BIT_ULL(7)
+#define PERF_CAP_PEBS_FORMAT           0xf00
+#define PERF_CAP_PEBS_BASELINE         BIT_ULL(14)
+#define PERF_CAP_PEBS_MASK	(PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \
+				 PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE)
 
 #define MSR_IA32_RTIT_CTL		0x00000570
 #define RTIT_CTL_TRACEEN		BIT(0)
@@ -392,6 +398,7 @@
 #define MSR_TURBO_ACTIVATION_RATIO	0x0000064C
 
 #define MSR_PLATFORM_ENERGY_STATUS	0x0000064D
+#define MSR_SECONDARY_TURBO_RATIO_LIMIT	0x00000650
 
 #define MSR_PKG_WEIGHTED_CORE_C0_RES	0x00000658
 #define MSR_PKG_ANY_CORE_C0_RES		0x00000659
@@ -1022,6 +1029,7 @@
 #define MSR_IA32_VMX_TRUE_EXIT_CTLS      0x0000048f
 #define MSR_IA32_VMX_TRUE_ENTRY_CTLS     0x00000490
 #define MSR_IA32_VMX_VMFUNC             0x00000491
+#define MSR_IA32_VMX_PROCBASED_CTLS3	0x00000492
 
 /* VMX_BASIC bits and bitmasks */
 #define VMX_BASIC_VMCS_SIZE_SHIFT	32

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

@@ -306,7 +306,8 @@ struct kvm_pit_state {
 	struct kvm_pit_channel_state channels[3];
 };
 
-#define KVM_PIT_FLAGS_HPET_LEGACY  0x00000001
+#define KVM_PIT_FLAGS_HPET_LEGACY     0x00000001
+#define KVM_PIT_FLAGS_SPEAKER_DATA_ON 0x00000002
 
 struct kvm_pit_state2 {
 	struct kvm_pit_channel_state channels[3];
@@ -325,6 +326,7 @@ struct kvm_reinject_control {
 #define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
 #define KVM_VCPUEVENT_VALID_SMM		0x00000008
 #define KVM_VCPUEVENT_VALID_PAYLOAD	0x00000010
+#define KVM_VCPUEVENT_VALID_TRIPLE_FAULT	0x00000020
 
 /* Interrupt shadow states */
 #define KVM_X86_SHADOW_INT_MOV_SS	0x01
@@ -359,7 +361,10 @@ struct kvm_vcpu_events {
 		__u8 smm_inside_nmi;
 		__u8 latched_init;
 	} smi;
-	__u8 reserved[27];
+	struct {
+		__u8 pending;
+	} triple_fault;
+	__u8 reserved[26];
 	__u8 exception_has_payload;
 	__u64 exception_payload;
 };
@@ -434,6 +439,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_OUT_7E_INC_RIP		(1 << 3)
 #define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT	(1 << 4)
 #define KVM_X86_QUIRK_FIX_HYPERCALL_INSN	(1 << 5)
+#define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS	(1 << 6)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1

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

@@ -91,6 +91,7 @@
 #define EXIT_REASON_UMWAIT              67
 #define EXIT_REASON_TPAUSE              68
 #define EXIT_REASON_BUS_LOCK            74
+#define EXIT_REASON_NOTIFY              75
 
 #define VMX_EXIT_REASONS \
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -153,7 +154,8 @@
 	{ EXIT_REASON_XRSTORS,               "XRSTORS" }, \
 	{ EXIT_REASON_UMWAIT,                "UMWAIT" }, \
 	{ EXIT_REASON_TPAUSE,                "TPAUSE" }, \
-	{ EXIT_REASON_BUS_LOCK,              "BUS_LOCK" }
+	{ EXIT_REASON_BUS_LOCK,              "BUS_LOCK" }, \
+	{ EXIT_REASON_NOTIFY,                "NOTIFY" }
 
 #define VMX_EXIT_REASON_FLAGS \
 	{ VMX_EXIT_REASONS_FAILED_VMENTRY,	"FAILED_VMENTRY" }

tools/include/uapi/linux/fscrypt.h

@@ -27,7 +27,8 @@
 #define FSCRYPT_MODE_AES_128_CBC		5
 #define FSCRYPT_MODE_AES_128_CTS		6
 #define FSCRYPT_MODE_ADIANTUM			9
-/* If adding a mode number > 9, update FSCRYPT_MODE_MAX in fscrypt_private.h */
+#define FSCRYPT_MODE_AES_256_HCTR2		10
+/* If adding a mode number > 10, update FSCRYPT_MODE_MAX in fscrypt_private.h */
 
 /*
  * Legacy policy version; ad-hoc KDF and no key verification.

tools/include/uapi/linux/kvm.h

@@ -270,6 +270,8 @@ struct kvm_xen_exit {
 #define KVM_EXIT_X86_BUS_LOCK     33
 #define KVM_EXIT_XEN              34
 #define KVM_EXIT_RISCV_SBI        35
+#define KVM_EXIT_RISCV_CSR        36
+#define KVM_EXIT_NOTIFY           37
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -496,6 +498,18 @@ struct kvm_run {
 			unsigned long args[6];
 			unsigned long ret[2];
 		} riscv_sbi;
+		/* KVM_EXIT_RISCV_CSR */
+		struct {
+			unsigned long csr_num;
+			unsigned long new_value;
+			unsigned long write_mask;
+			unsigned long ret_value;
+		} riscv_csr;
+		/* KVM_EXIT_NOTIFY */
+		struct {
+#define KVM_NOTIFY_CONTEXT_INVALID	(1 << 0)
+			__u32 flags;
+		} notify;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1157,6 +1171,12 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_VM_TSC_CONTROL 214
 #define KVM_CAP_SYSTEM_EVENT_DATA 215
 #define KVM_CAP_ARM_SYSTEM_SUSPEND 216
+#define KVM_CAP_S390_PROTECTED_DUMP 217
+#define KVM_CAP_X86_TRIPLE_FAULT_EVENT 218
+#define KVM_CAP_X86_NOTIFY_VMEXIT 219
+#define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220
+#define KVM_CAP_S390_ZPCI_OP 221
+#define KVM_CAP_S390_CPU_TOPOLOGY 222
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1660,6 +1680,55 @@ struct kvm_s390_pv_unp {
 	__u64 tweak;
 };
 
+enum pv_cmd_dmp_id {
+	KVM_PV_DUMP_INIT,
+	KVM_PV_DUMP_CONFIG_STOR_STATE,
+	KVM_PV_DUMP_COMPLETE,
+	KVM_PV_DUMP_CPU,
+};
+
+struct kvm_s390_pv_dmp {
+	__u64 subcmd;
+	__u64 buff_addr;
+	__u64 buff_len;
+	__u64 gaddr;		/* For dump storage state */
+	__u64 reserved[4];
+};
+
+enum pv_cmd_info_id {
+	KVM_PV_INFO_VM,
+	KVM_PV_INFO_DUMP,
+};
+
+struct kvm_s390_pv_info_dump {
+	__u64 dump_cpu_buffer_len;
+	__u64 dump_config_mem_buffer_per_1m;
+	__u64 dump_config_finalize_len;
+};
+
+struct kvm_s390_pv_info_vm {
+	__u64 inst_calls_list[4];
+	__u64 max_cpus;
+	__u64 max_guests;
+	__u64 max_guest_addr;
+	__u64 feature_indication;
+};
+
+struct kvm_s390_pv_info_header {
+	__u32 id;
+	__u32 len_max;
+	__u32 len_written;
+	__u32 reserved;
+};
+
+struct kvm_s390_pv_info {
+	struct kvm_s390_pv_info_header header;
+	union {
+		struct kvm_s390_pv_info_dump dump;
+		struct kvm_s390_pv_info_vm vm;
+	};
+};
+
 enum pv_cmd_id {
 	KVM_PV_ENABLE,
 	KVM_PV_DISABLE,
@@ -1668,6 +1737,8 @@ enum pv_cmd_id {
 	KVM_PV_VERIFY,
 	KVM_PV_PREP_RESET,
 	KVM_PV_UNSHARE_ALL,
+	KVM_PV_INFO,
+	KVM_PV_DUMP,
 };
 
 struct kvm_pv_cmd {
@@ -2119,4 +2190,41 @@ struct kvm_stats_desc {
 /* Available with KVM_CAP_XSAVE2 */
 #define KVM_GET_XSAVE2		  _IOR(KVMIO,  0xcf, struct kvm_xsave)
 
+/* Available with KVM_CAP_S390_PROTECTED_DUMP */
+#define KVM_S390_PV_CPU_COMMAND	_IOWR(KVMIO, 0xd0, struct kvm_pv_cmd)
+
+/* Available with KVM_CAP_X86_NOTIFY_VMEXIT */
+#define KVM_X86_NOTIFY_VMEXIT_ENABLED		(1ULL << 0)
+#define KVM_X86_NOTIFY_VMEXIT_USER		(1ULL << 1)
+
+/* Available with KVM_CAP_S390_ZPCI_OP */
+#define KVM_S390_ZPCI_OP         _IOW(KVMIO,  0xd1, struct kvm_s390_zpci_op)
+
+struct kvm_s390_zpci_op {
+	/* in */
+	__u32 fh;               /* target device */
+	__u8  op;               /* operation to perform */
+	__u8  pad[3];
+	union {
+		/* for KVM_S390_ZPCIOP_REG_AEN */
+		struct {
+			__u64 ibv;      /* Guest addr of interrupt bit vector */
+			__u64 sb;       /* Guest addr of summary bit */
+			__u32 flags;
+			__u32 noi;      /* Number of interrupts */
+			__u8 isc;       /* Guest interrupt subclass */
+			__u8 sbo;       /* Offset of guest summary bit vector */
+			__u16 pad;
+		} reg_aen;
+		__u64 reserved[8];
+	} u;
+};
+
+/* types for kvm_s390_zpci_op->op */
+#define KVM_S390_ZPCIOP_REG_AEN                0
+#define KVM_S390_ZPCIOP_DEREG_AEN      1
+
+/* flags for kvm_s390_zpci_op->u.reg_aen.flags */
+#define KVM_S390_ZPCIOP_REGAEN_HOST    (1 << 0)
+
 #endif /* __LINUX_KVM_H */

tools/include/uapi/linux/perf_event.h

@@ -301,6 +301,7 @@ enum {
  *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
  *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		id;           } && PERF_FORMAT_ID
+ *	  { u64		lost;         } && PERF_FORMAT_LOST
  *	} && !PERF_FORMAT_GROUP
  *
  *	{ u64		nr;
@@ -308,6 +309,7 @@ enum {
  *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		value;
  *	    { u64	id;           } && PERF_FORMAT_ID
+ *	    { u64	lost;         } && PERF_FORMAT_LOST
  *	  }		cntr[nr];
  *	} && PERF_FORMAT_GROUP
  * };
@@ -317,8 +319,9 @@ enum perf_event_read_format {
 	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
 	PERF_FORMAT_ID				= 1U << 2,
 	PERF_FORMAT_GROUP			= 1U << 3,
+	PERF_FORMAT_LOST			= 1U << 4,
 
-	PERF_FORMAT_MAX = 1U << 4,		/* non-ABI */
+	PERF_FORMAT_MAX = 1U << 5,		/* non-ABI */
 };
 
 #define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */

tools/include/uapi/linux/vhost.h

@@ -171,4 +171,13 @@
 #define VHOST_VDPA_SET_GROUP_ASID	_IOW(VHOST_VIRTIO, 0x7C, \
 					     struct vhost_vring_state)
 
+/* Suspend a device so it does not process virtqueue requests anymore
+ *
+ * After the return of ioctl the device must preserve all the necessary state
+ * (the virtqueue vring base plus the possible device specific states) that is
+ * required for restoring in the future. The device must not change its
+ * configuration after that point.
+ */
+#define VHOST_VDPA_SUSPEND		_IO(VHOST_VIRTIO, 0x7D)
+
 #endif

tools/lib/perf/cpumap.c

@@ -309,7 +309,7 @@ bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
 	return perf_cpu_map__idx(cpus, cpu) != -1;
 }
 
-struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map)
+struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map)
 {
 	struct perf_cpu result = {
 		.cpu = -1

tools/lib/perf/evsel.c

@@ -305,6 +305,9 @@ int perf_evsel__read_size(struct perf_evsel *evsel)
 	if (read_format & PERF_FORMAT_ID)
 		entry += sizeof(u64);
 
+	if (read_format & PERF_FORMAT_LOST)
+		entry += sizeof(u64);
+
 	if (read_format & PERF_FORMAT_GROUP) {
 		nr = evsel->nr_members;
 		size += sizeof(u64);
@@ -314,24 +317,98 @@ int perf_evsel__read_size(struct perf_evsel *evsel)
 	return size;
 }
 
+/* This only reads values for the leader */
+static int perf_evsel__read_group(struct perf_evsel *evsel, int cpu_map_idx,
+				  int thread, struct perf_counts_values *count)
+{
+	size_t size = perf_evsel__read_size(evsel);
+	int *fd = FD(evsel, cpu_map_idx, thread);
+	u64 read_format = evsel->attr.read_format;
+	u64 *data;
+	int idx = 1;
+
+	if (fd == NULL || *fd < 0)
+		return -EINVAL;
+
+	data = calloc(1, size);
+	if (data == NULL)
+		return -ENOMEM;
+
+	if (readn(*fd, data, size) <= 0) {
+		free(data);
+		return -errno;
+	}
+
+	/*
+	 * This reads only the leader event intentionally since we don't have
+	 * perf counts values for sibling events.
+	 */
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		count->ena = data[idx++];
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		count->run = data[idx++];
+
+	/* value is always available */
+	count->val = data[idx++];
+	if (read_format & PERF_FORMAT_ID)
+		count->id = data[idx++];
+	if (read_format & PERF_FORMAT_LOST)
+		count->lost = data[idx++];
+
+	free(data);
+	return 0;
+}
+
+/*
+ * The perf read format is very flexible.  It needs to set the proper
+ * values according to the read format.
+ */
+static void perf_evsel__adjust_values(struct perf_evsel *evsel, u64 *buf,
+				      struct perf_counts_values *count)
+{
+	u64 read_format = evsel->attr.read_format;
+	int n = 0;
+
+	count->val = buf[n++];
+
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		count->ena = buf[n++];
+
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		count->run = buf[n++];
+
+	if (read_format & PERF_FORMAT_ID)
+		count->id = buf[n++];
+
+	if (read_format & PERF_FORMAT_LOST)
+		count->lost = buf[n++];
+}
+
 int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
 		     struct perf_counts_values *count)
 {
 	size_t size = perf_evsel__read_size(evsel);
 	int *fd = FD(evsel, cpu_map_idx, thread);
+	u64 read_format = evsel->attr.read_format;
+	struct perf_counts_values buf;
 
 	memset(count, 0, sizeof(*count));
 
 	if (fd == NULL || *fd < 0)
 		return -EINVAL;
 
+	if (read_format & PERF_FORMAT_GROUP)
+		return perf_evsel__read_group(evsel, cpu_map_idx, thread, count);
+
 	if (MMAP(evsel, cpu_map_idx, thread) &&
+	    !(read_format & (PERF_FORMAT_ID | PERF_FORMAT_LOST)) &&
 	    !perf_mmap__read_self(MMAP(evsel, cpu_map_idx, thread), count))
 		return 0;
 
-	if (readn(*fd, count->values, size) <= 0)
+	if (readn(*fd, buf.values, size) <= 0)
 		return -errno;
 
+	perf_evsel__adjust_values(evsel, buf.values, count);
 	return 0;
 }
 

tools/lib/perf/include/perf/cpumap.h

@@ -23,7 +23,7 @@ LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
 LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
 LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
-LIBPERF_API struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map);
+LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map);
 LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
 
 #define perf_cpu_map__for_each_cpu(cpu, idx, cpus)		\

tools/lib/perf/include/perf/event.h

@@ -6,6 +6,7 @@
 #include <linux/types.h>
 #include <linux/limits.h>
 #include <linux/bpf.h>
+#include <linux/compiler.h>
 #include <sys/types.h> /* pid_t */
 
 #define event_contains(obj, mem) ((obj).header.size > offsetof(typeof(obj), mem))
@@ -76,7 +77,7 @@ struct perf_record_lost_samples {
 };
 
 /*
- * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID
+ * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID | PERF_FORMAT_LOST
  */
 struct perf_record_read {
 	struct perf_event_header header;
@@ -85,6 +86,7 @@ struct perf_record_read {
 	__u64			 time_enabled;
 	__u64			 time_running;
 	__u64			 id;
+	__u64			 lost;
 };
 
 struct perf_record_throttle {
@@ -153,22 +155,60 @@ enum {
 	PERF_CPU_MAP__MASK = 1,
 };
 
+/*
+ * Array encoding of a perf_cpu_map where nr is the number of entries in cpu[]
+ * and each entry is a value for a CPU in the map.
+ */
 struct cpu_map_entries {
 	__u16			 nr;
 	__u16			 cpu[];
 };
 
-struct perf_record_record_cpu_map {
+/* Bitmap encoding of a perf_cpu_map where bitmap entries are 32-bit. */
+struct perf_record_mask_cpu_map32 {
+	/* Number of mask values. */
+	__u16			 nr;
+	/* Constant 4. */
+	__u16			 long_size;
+	/* Bitmap data. */
+	__u32			 mask[];
+};
+
+/* Bitmap encoding of a perf_cpu_map where bitmap entries are 64-bit. */
+struct perf_record_mask_cpu_map64 {
+	/* Number of mask values. */
 	__u16			 nr;
+	/* Constant 8. */
 	__u16			 long_size;
-	unsigned long		 mask[];
+	/* Legacy padding. */
+	char                     __pad[4];
+	/* Bitmap data. */
+	__u64			 mask[];
 };
 
-struct perf_record_cpu_map_data {
+/*
+ * 'struct perf_record_cpu_map_data' is packed as unfortunately an earlier
+ * version had unaligned data and we wish to retain file format compatibility.
+ * -irogers
+ */
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wpacked"
+#pragma GCC diagnostic ignored "-Wattributes"
+
+struct __packed perf_record_cpu_map_data {
 	__u16			 type;
-	char			 data[];
+	union {
+		/* Used when type == PERF_CPU_MAP__CPUS. */
+		struct cpu_map_entries cpus_data;
+		/* Used when type == PERF_CPU_MAP__MASK and long_size == 4. */
+		struct perf_record_mask_cpu_map32 mask32_data;
+		/* Used when type == PERF_CPU_MAP__MASK and long_size == 8. */
+		struct perf_record_mask_cpu_map64 mask64_data;
+	};
 };
 
+#pragma GCC diagnostic pop
+
 struct perf_record_cpu_map {
 	struct perf_event_header	 header;
 	struct perf_record_cpu_map_data	 data;

tools/lib/perf/include/perf/evsel.h

@@ -18,8 +18,10 @@ struct perf_counts_values {
 			uint64_t val;
 			uint64_t ena;
 			uint64_t run;
+			uint64_t id;
+			uint64_t lost;
 		};
-		uint64_t values[3];
+		uint64_t values[5];
 	};
 };
 

tools/lib/perf/tests/test-evsel.c

 // SPDX-License-Identifier: GPL-2.0
 #include <stdarg.h>
 #include <stdio.h>
+#include <string.h>
 #include <linux/perf_event.h>
+#include <linux/kernel.h>
 #include <perf/cpumap.h>
 #include <perf/threadmap.h>
 #include <perf/evsel.h>
+#include <internal/evsel.h>
 #include <internal/tests.h>
 #include "tests.h"
 
@@ -189,6 +192,163 @@ static int test_stat_user_read(int event)
 	return 0;
 }
 
+static int test_stat_read_format_single(struct perf_event_attr *attr, struct perf_thread_map *threads)
+{
+	struct perf_evsel *evsel;
+	struct perf_counts_values counts;
+	volatile int count = 0x100000;
+	int err;
+
+	evsel = perf_evsel__new(attr);
+	__T("failed to create evsel", evsel);
+
+	/* skip old kernels that don't support the format */
+	err = perf_evsel__open(evsel, NULL, threads);
+	if (err < 0)
+		return 0;
+
+	while (count--) ;
+
+	memset(&counts, -1, sizeof(counts));
+	perf_evsel__read(evsel, 0, 0, &counts);
+
+	__T("failed to read value", counts.val);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		__T("failed to read TOTAL_TIME_ENABLED", counts.ena);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		__T("failed to read TOTAL_TIME_RUNNING", counts.run);
+	if (attr->read_format & PERF_FORMAT_ID)
+		__T("failed to read ID", counts.id);
+	if (attr->read_format & PERF_FORMAT_LOST)
+		__T("failed to read LOST", counts.lost == 0);
+
+	perf_evsel__close(evsel);
+	perf_evsel__delete(evsel);
+	return 0;
+}
+
+static int test_stat_read_format_group(struct perf_event_attr *attr, struct perf_thread_map *threads)
+{
+	struct perf_evsel *leader, *member;
+	struct perf_counts_values counts;
+	volatile int count = 0x100000;
+	int err;
+
+	attr->read_format |= PERF_FORMAT_GROUP;
+	leader = perf_evsel__new(attr);
+	__T("failed to create leader", leader);
+
+	attr->read_format &= ~PERF_FORMAT_GROUP;
+	member = perf_evsel__new(attr);
+	__T("failed to create member", member);
+
+	member->leader = leader;
+	leader->nr_members = 2;
+
+	/* skip old kernels that don't support the format */
+	err = perf_evsel__open(leader, NULL, threads);
+	if (err < 0)
+		return 0;
+	err = perf_evsel__open(member, NULL, threads);
+	if (err < 0)
+		return 0;
+
+	while (count--) ;
+
+	memset(&counts, -1, sizeof(counts));
+	perf_evsel__read(leader, 0, 0, &counts);
+
+	__T("failed to read leader value", counts.val);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		__T("failed to read leader TOTAL_TIME_ENABLED", counts.ena);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		__T("failed to read leader TOTAL_TIME_RUNNING", counts.run);
+	if (attr->read_format & PERF_FORMAT_ID)
+		__T("failed to read leader ID", counts.id);
+	if (attr->read_format & PERF_FORMAT_LOST)
+		__T("failed to read leader LOST", counts.lost == 0);
+
+	memset(&counts, -1, sizeof(counts));
+	perf_evsel__read(member, 0, 0, &counts);
+
+	__T("failed to read member value", counts.val);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		__T("failed to read member TOTAL_TIME_ENABLED", counts.ena);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		__T("failed to read member TOTAL_TIME_RUNNING", counts.run);
+	if (attr->read_format & PERF_FORMAT_ID)
+		__T("failed to read member ID", counts.id);
+	if (attr->read_format & PERF_FORMAT_LOST)
+		__T("failed to read member LOST", counts.lost == 0);
+
+	perf_evsel__close(member);
+	perf_evsel__close(leader);
+	perf_evsel__delete(member);
+	perf_evsel__delete(leader);
+	return 0;
+}
+
+static int test_stat_read_format(void)
+{
+	struct perf_thread_map *threads;
+	struct perf_event_attr attr = {
+		.type	= PERF_TYPE_SOFTWARE,
+		.config	= PERF_COUNT_SW_TASK_CLOCK,
+	};
+	int err, i;
+
+#define FMT(_fmt)  PERF_FORMAT_ ## _fmt
+#define FMT_TIME  (FMT(TOTAL_TIME_ENABLED) | FMT(TOTAL_TIME_RUNNING))
+
+	uint64_t test_formats [] = {
+		0,
+		FMT_TIME,
+		FMT(ID),
+		FMT(LOST),
+		FMT_TIME | FMT(ID),
+		FMT_TIME | FMT(LOST),
+		FMT_TIME | FMT(ID) | FMT(LOST),
+		FMT(ID) | FMT(LOST),
+	};
+
+#undef FMT
+#undef FMT_TIME
+
+	threads = perf_thread_map__new_dummy();
+	__T("failed to create threads", threads);
+
+	perf_thread_map__set_pid(threads, 0, 0);
+
+	for (i = 0; i < (int)ARRAY_SIZE(test_formats); i++) {
+		attr.read_format = test_formats[i];
+		__T_VERBOSE("testing single read with read_format: %lx\n",
+			    (unsigned long)test_formats[i]);
+
+		err = test_stat_read_format_single(&attr, threads);
+		__T("failed to read single format", err == 0);
+	}
+
+	perf_thread_map__put(threads);
+
+	threads = perf_thread_map__new_array(2, NULL);
+	__T("failed to create threads", threads);
+
+	perf_thread_map__set_pid(threads, 0, 0);
+	perf_thread_map__set_pid(threads, 1, 0);
+
+	for (i = 0; i < (int)ARRAY_SIZE(test_formats); i++) {
+		attr.read_format = test_formats[i];
+		__T_VERBOSE("testing group read with read_format: %lx\n",
+			    (unsigned long)test_formats[i]);
+
+		err = test_stat_read_format_group(&attr, threads);
+		__T("failed to read group format", err == 0);
+	}
+
+	perf_thread_map__put(threads);
+	return 0;
+}
+
 int test_evsel(int argc, char **argv)
 {
 	__T_START;
@@ -200,6 +360,7 @@ int test_evsel(int argc, char **argv)
 	test_stat_thread_enable();
 	test_stat_user_read(PERF_COUNT_HW_INSTRUCTIONS);
 	test_stat_user_read(PERF_COUNT_HW_CPU_CYCLES);
+	test_stat_read_format();
 
 	__T_END;
 	return tests_failed == 0 ? 0 : -1;

tools/perf/tests/cpumap.c

@@ -17,21 +17,23 @@ static int process_event_mask(struct perf_tool *tool __maybe_unused,
 			 struct machine *machine __maybe_unused)
 {
 	struct perf_record_cpu_map *map_event = &event->cpu_map;
-	struct perf_record_record_cpu_map *mask;
 	struct perf_record_cpu_map_data *data;
 	struct perf_cpu_map *map;
 	int i;
+	unsigned int long_size;
 
 	data = &map_event->data;
 
 	TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__MASK);
 
-	mask = (struct perf_record_record_cpu_map *)data->data;
+	long_size = data->mask32_data.long_size;
 
-	TEST_ASSERT_VAL("wrong nr",   mask->nr == 1);
+	TEST_ASSERT_VAL("wrong long_size", long_size == 4 || long_size == 8);
+
+	TEST_ASSERT_VAL("wrong nr",   data->mask32_data.nr == 1);
 
 	for (i = 0; i < 20; i++) {
-		TEST_ASSERT_VAL("wrong cpu", test_bit(i, mask->mask));
+		TEST_ASSERT_VAL("wrong cpu", perf_record_cpu_map_data__test_bit(i, data));
 	}
 
 	map = cpu_map__new_data(data);
@@ -51,7 +53,6 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 			 struct machine *machine __maybe_unused)
 {
 	struct perf_record_cpu_map *map_event = &event->cpu_map;
-	struct cpu_map_entries *cpus;
 	struct perf_record_cpu_map_data *data;
 	struct perf_cpu_map *map;
 
@@ -59,11 +60,9 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 
 	TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__CPUS);
 
-	cpus = (struct cpu_map_entries *)data->data;
-
-	TEST_ASSERT_VAL("wrong nr",   cpus->nr == 2);
-	TEST_ASSERT_VAL("wrong cpu",  cpus->cpu[0] == 1);
-	TEST_ASSERT_VAL("wrong cpu",  cpus->cpu[1] == 256);
+	TEST_ASSERT_VAL("wrong nr",   data->cpus_data.nr == 2);
+	TEST_ASSERT_VAL("wrong cpu",  data->cpus_data.cpu[0] == 1);
+	TEST_ASSERT_VAL("wrong cpu",  data->cpus_data.cpu[1] == 256);
 
 	map = cpu_map__new_data(data);
 	TEST_ASSERT_VAL("wrong nr",  perf_cpu_map__nr(map) == 2);

tools/perf/tests/sample-parsing.c

@@ -86,10 +86,15 @@ static bool samples_same(const struct perf_sample *s1,
 			COMP(read.time_running);
 		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
 		if (read_format & PERF_FORMAT_GROUP) {
-			for (i = 0; i < s1->read.group.nr; i++)
-				MCOMP(read.group.values[i]);
+			for (i = 0; i < s1->read.group.nr; i++) {
+				/* FIXME: check values without LOST */
+				if (read_format & PERF_FORMAT_LOST)
+					MCOMP(read.group.values[i]);
+			}
 		} else {
 			COMP(read.one.id);
+			if (read_format & PERF_FORMAT_LOST)
+				COMP(read.one.lost);
 		}
 	}
 
@@ -263,7 +268,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 			.data	= (void *)aux_data,
 		},
 	};
-	struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
+	struct sample_read_value values[] = {{1, 5, 0}, {9, 3, 0}, {2, 7, 0}, {6, 4, 1},};
 	struct perf_sample sample_out, sample_out_endian;
 	size_t i, sz, bufsz;
 	int err, ret = -1;
@@ -286,6 +291,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 	} else {
 		sample.read.one.value = 0x08789faeb786aa87ULL;
 		sample.read.one.id    = 99;
+		sample.read.one.lost  = 1;
 	}
 
 	sz = perf_event__sample_event_size(&sample, sample_type, read_format);
@@ -370,7 +376,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
  */
 static int test__sample_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
-	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
+	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15, 20, 21, 22, 28, 29, 30, 31};
 	u64 sample_type;
 	u64 sample_regs;
 	size_t i;

tools/perf/trace/beauty/include/linux/socket.h

@@ -14,6 +14,8 @@ struct file;
 struct pid;
 struct cred;
 struct socket;
+struct sock;
+struct sk_buff;
 
 #define __sockaddr_check_size(size)	\
 	BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage)))
@@ -69,6 +71,9 @@ struct msghdr {
 	unsigned int	msg_flags;	/* flags on received message */
 	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
 	struct kiocb	*msg_iocb;	/* ptr to iocb for async requests */
+	struct ubuf_info *msg_ubuf;
+	int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb,
+			    struct iov_iter *from, size_t length);
 };
 
 struct user_msghdr {
@@ -416,10 +421,9 @@ extern int recvmsg_copy_msghdr(struct msghdr *msg,
 			       struct user_msghdr __user *umsg, unsigned flags,
 			       struct sockaddr __user **uaddr,
 			       struct iovec **iov);
-extern int __copy_msghdr_from_user(struct msghdr *kmsg,
-				   struct user_msghdr __user *umsg,
-				   struct sockaddr __user **save_addr,
-				   struct iovec __user **uiov, size_t *nsegs);
+extern int __copy_msghdr(struct msghdr *kmsg,
+			 struct user_msghdr *umsg,
+			 struct sockaddr __user **save_addr);
 
 /* helpers which do the actual work for syscalls */
 extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
@@ -428,10 +432,6 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
 extern int __sys_sendto(int fd, void __user *buff, size_t len,
 			unsigned int flags, struct sockaddr __user *addr,
 			int addr_len);
-extern int __sys_accept4_file(struct file *file, unsigned file_flags,
-			struct sockaddr __user *upeer_sockaddr,
-			 int __user *upeer_addrlen, int flags,
-			 unsigned long nofile);
 extern struct file *do_accept(struct file *file, unsigned file_flags,
 			      struct sockaddr __user *upeer_sockaddr,
 			      int __user *upeer_addrlen, int flags);

tools/perf/util/cpumap.c

@@ -22,54 +22,102 @@ static int max_node_num;
  */
 static int *cpunode_map;
 
-static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
+bool perf_record_cpu_map_data__test_bit(int i,
+					const struct perf_record_cpu_map_data *data)
+{
+	int bit_word32 = i / 32;
+	__u32 bit_mask32 = 1U << (i & 31);
+	int bit_word64 = i / 64;
+	__u64 bit_mask64 = ((__u64)1) << (i & 63);
+
+	return (data->mask32_data.long_size == 4)
+		? (bit_word32 < data->mask32_data.nr) &&
+		(data->mask32_data.mask[bit_word32] & bit_mask32) != 0
+		: (bit_word64 < data->mask64_data.nr) &&
+		(data->mask64_data.mask[bit_word64] & bit_mask64) != 0;
+}
+
+/* Read ith mask value from data into the given 64-bit sized bitmap */
+static void perf_record_cpu_map_data__read_one_mask(const struct perf_record_cpu_map_data *data,
+						    int i, unsigned long *bitmap)
+{
+#if __SIZEOF_LONG__ == 8
+	if (data->mask32_data.long_size == 4)
+		bitmap[0] = data->mask32_data.mask[i];
+	else
+		bitmap[0] = data->mask64_data.mask[i];
+#else
+	if (data->mask32_data.long_size == 4) {
+		bitmap[0] = data->mask32_data.mask[i];
+		bitmap[1] = 0;
+	} else {
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+		bitmap[0] = (unsigned long)(data->mask64_data.mask[i] >> 32);
+		bitmap[1] = (unsigned long)data->mask64_data.mask[i];
+#else
+		bitmap[0] = (unsigned long)data->mask64_data.mask[i];
+		bitmap[1] = (unsigned long)(data->mask64_data.mask[i] >> 32);
+#endif
+	}
+#endif
+}
+static struct perf_cpu_map *cpu_map__from_entries(const struct perf_record_cpu_map_data *data)
 {
 	struct perf_cpu_map *map;
 
-	map = perf_cpu_map__empty_new(cpus->nr);
+	map = perf_cpu_map__empty_new(data->cpus_data.nr);
 	if (map) {
 		unsigned i;
 
-		for (i = 0; i < cpus->nr; i++) {
+		for (i = 0; i < data->cpus_data.nr; i++) {
 			/*
 			 * Special treatment for -1, which is not real cpu number,
 			 * and we need to use (int) -1 to initialize map[i],
 			 * otherwise it would become 65535.
 			 */
-			if (cpus->cpu[i] == (u16) -1)
+			if (data->cpus_data.cpu[i] == (u16) -1)
 				map->map[i].cpu = -1;
 			else
-				map->map[i].cpu = (int) cpus->cpu[i];
+				map->map[i].cpu = (int) data->cpus_data.cpu[i];
 		}
 	}
 
 	return map;
 }
 
-static struct perf_cpu_map *cpu_map__from_mask(struct perf_record_record_cpu_map *mask)
+static struct perf_cpu_map *cpu_map__from_mask(const struct perf_record_cpu_map_data *data)
 {
+	DECLARE_BITMAP(local_copy, 64);
+	int weight = 0, mask_nr = data->mask32_data.nr;
 	struct perf_cpu_map *map;
-	int nr, nbits = mask->nr * mask->long_size * BITS_PER_BYTE;
 
-	nr = bitmap_weight(mask->mask, nbits);
+	for (int i = 0; i < mask_nr; i++) {
+		perf_record_cpu_map_data__read_one_mask(data, i, local_copy);
+		weight += bitmap_weight(local_copy, 64);
+	}
+
+	map = perf_cpu_map__empty_new(weight);
+	if (!map)
+		return NULL;
 
-	map = perf_cpu_map__empty_new(nr);
-	if (map) {
-		int cpu, i = 0;
+	for (int i = 0, j = 0; i < mask_nr; i++) {
+		int cpus_per_i = (i * data->mask32_data.long_size  * BITS_PER_BYTE);
+		int cpu;
 
-		for_each_set_bit(cpu, mask->mask, nbits)
-			map->map[i++].cpu = cpu;
+		perf_record_cpu_map_data__read_one_mask(data, i, local_copy);
+		for_each_set_bit(cpu, local_copy, 64)
+			map->map[j++].cpu = cpu + cpus_per_i;
 	}
 	return map;
 
 }
 
-struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data)
+struct perf_cpu_map *cpu_map__new_data(const struct perf_record_cpu_map_data *data)
 {
 	if (data->type == PERF_CPU_MAP__CPUS)
-		return cpu_map__from_entries((struct cpu_map_entries *)data->data);
+		return cpu_map__from_entries(data);
 	else
-		return cpu_map__from_mask((struct perf_record_record_cpu_map *)data->data);
+		return cpu_map__from_mask(data);
 }
 
 size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp)

tools/perf/util/cpumap.h

@@ -37,9 +37,11 @@ struct cpu_aggr_map {
 
 struct perf_record_cpu_map_data;
 
+bool perf_record_cpu_map_data__test_bit(int i, const struct perf_record_cpu_map_data *data);
+
 struct perf_cpu_map *perf_cpu_map__empty_new(int nr);
 
-struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data);
+struct perf_cpu_map *cpu_map__new_data(const struct perf_record_cpu_map_data *data);
 size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size);
 size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size);
 size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp);

tools/perf/util/event.h

@@ -65,7 +65,8 @@ struct stack_dump {
 
 struct sample_read_value {
 	u64 value;
-	u64 id;
+	u64 id;   /* only if PERF_FORMAT_ID */
+	u64 lost; /* only if PERF_FORMAT_LOST */
 };
 
 struct sample_read {
@@ -80,6 +81,24 @@ struct sample_read {
 	};
 };
 
+static inline size_t sample_read_value_size(u64 read_format)
+{
+	/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+	if (read_format & PERF_FORMAT_LOST)
+		return sizeof(struct sample_read_value);
+	else
+		return offsetof(struct sample_read_value, lost);
+}
+
+static inline struct sample_read_value *
+next_sample_read_value(struct sample_read_value *v, u64 read_format)
+{
+	return (void *)v + sample_read_value_size(read_format);
+}
+
+#define sample_read_group__for_each(v, nr, rf)		\
+	for (int __i = 0; __i < (int)nr; v = next_sample_read_value(v, rf), __i++)
+
 struct ip_callchain {
 	u64 nr;
 	u64 ips[];
@@ -463,10 +482,6 @@ size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FIL
 int kallsyms__get_function_start(const char *kallsyms_filename,
 				 const char *symbol_name, u64 *addr);
 
-void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max);
-void  cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map,
-			       u16 type, int max);
-
 void event_attr_init(struct perf_event_attr *attr);
 
 int perf_event_paranoid(void);

tools/perf/util/evsel.c

@@ -1541,7 +1541,7 @@ static int evsel__read_one(struct evsel *evsel, int cpu_map_idx, int thread)
 }
 
 static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread,
-			     u64 val, u64 ena, u64 run)
+			     u64 val, u64 ena, u64 run, u64 lost)
 {
 	struct perf_counts_values *count;
 
@@ -1550,6 +1550,7 @@ static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread,
 	count->val    = val;
 	count->ena    = ena;
 	count->run    = run;
+	count->lost   = lost;
 
 	perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true);
 }
@@ -1558,7 +1559,7 @@ static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int
 {
 	u64 read_format = leader->core.attr.read_format;
 	struct sample_read_value *v;
-	u64 nr, ena = 0, run = 0, i;
+	u64 nr, ena = 0, run = 0, lost = 0;
 
 	nr = *data++;
 
@@ -1571,18 +1572,18 @@ static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int
 	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
 		run = *data++;
 
-	v = (struct sample_read_value *) data;
-
-	evsel__set_count(leader, cpu_map_idx, thread, v[0].value, ena, run);
-
-	for (i = 1; i < nr; i++) {
+	v = (void *)data;
+	sample_read_group__for_each(v, nr, read_format) {
 		struct evsel *counter;
 
-		counter = evlist__id2evsel(leader->evlist, v[i].id);
+		counter = evlist__id2evsel(leader->evlist, v->id);
 		if (!counter)
 			return -EINVAL;
 
-		evsel__set_count(counter, cpu_map_idx, thread, v[i].value, ena, run);
+		if (read_format & PERF_FORMAT_LOST)
+			lost = v->lost;
+
+		evsel__set_count(counter, cpu_map_idx, thread, v->value, ena, run, lost);
 	}
 
 	return 0;
@@ -2475,8 +2476,8 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 
 			if (data->read.group.nr > max_group_nr)
 				return -EFAULT;
-			sz = data->read.group.nr *
-			     sizeof(struct sample_read_value);
+
+			sz = data->read.group.nr * sample_read_value_size(read_format);
 			OVERFLOW_CHECK(array, sz, max_size);
 			data->read.group.values =
 					(struct sample_read_value *)array;
@@ -2485,6 +2486,12 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 			OVERFLOW_CHECK_u64(array);
 			data->read.one.id = *array;
 			array++;
+
+			if (read_format & PERF_FORMAT_LOST) {
+				OVERFLOW_CHECK_u64(array);
+				data->read.one.lost = *array;
+				array++;
+			}
 		}
 	}
 

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

@@ -642,15 +642,19 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
 	return pylist;
 }
 
-static PyObject *get_sample_value_as_tuple(struct sample_read_value *value)
+static PyObject *get_sample_value_as_tuple(struct sample_read_value *value,
+					   u64 read_format)
 {
 	PyObject *t;
 
-	t = PyTuple_New(2);
+	t = PyTuple_New(3);
 	if (!t)
 		Py_FatalError("couldn't create Python tuple");
 	PyTuple_SetItem(t, 0, PyLong_FromUnsignedLongLong(value->id));
 	PyTuple_SetItem(t, 1, PyLong_FromUnsignedLongLong(value->value));
+	if (read_format & PERF_FORMAT_LOST)
+		PyTuple_SetItem(t, 2, PyLong_FromUnsignedLongLong(value->lost));
+
 	return t;
 }
 
@@ -681,12 +685,17 @@ static void set_sample_read_in_dict(PyObject *dict_sample,
 		Py_FatalError("couldn't create Python list");
 
 	if (read_format & PERF_FORMAT_GROUP) {
-		for (i = 0; i < sample->read.group.nr; i++) {
-			PyObject *t = get_sample_value_as_tuple(&sample->read.group.values[i]);
+		struct sample_read_value *v = sample->read.group.values;
+
+		i = 0;
+		sample_read_group__for_each(v, sample->read.group.nr, read_format) {
+			PyObject *t = get_sample_value_as_tuple(v, read_format);
 			PyList_SET_ITEM(values, i, t);
+			i++;
 		}
 	} else {
-		PyObject *t = get_sample_value_as_tuple(&sample->read.one);
+		PyObject *t = get_sample_value_as_tuple(&sample->read.one,
+							read_format);
 		PyList_SET_ITEM(values, 0, t);
 	}
 	pydict_set_item_string_decref(dict_sample, "values", values);

tools/perf/util/session.c

@@ -916,30 +916,30 @@ static void perf_event__cpu_map_swap(union perf_event *event,
 				     bool sample_id_all __maybe_unused)
 {
 	struct perf_record_cpu_map_data *data = &event->cpu_map.data;
-	struct cpu_map_entries *cpus;
-	struct perf_record_record_cpu_map *mask;
-	unsigned i;
 
 	data->type = bswap_16(data->type);
 
 	switch (data->type) {
 	case PERF_CPU_MAP__CPUS:
-		cpus = (struct cpu_map_entries *)data->data;
-
-		cpus->nr = bswap_16(cpus->nr);
+		data->cpus_data.nr = bswap_16(data->cpus_data.nr);
 
-		for (i = 0; i < cpus->nr; i++)
-			cpus->cpu[i] = bswap_16(cpus->cpu[i]);
+		for (unsigned i = 0; i < data->cpus_data.nr; i++)
+			data->cpus_data.cpu[i] = bswap_16(data->cpus_data.cpu[i]);
 		break;
 	case PERF_CPU_MAP__MASK:
-		mask = (struct perf_record_record_cpu_map *)data->data;
-
-		mask->nr = bswap_16(mask->nr);
-		mask->long_size = bswap_16(mask->long_size);
+		data->mask32_data.long_size = bswap_16(data->mask32_data.long_size);
 
-		switch (mask->long_size) {
-		case 4: mem_bswap_32(&mask->mask, mask->nr); break;
-		case 8: mem_bswap_64(&mask->mask, mask->nr); break;
+		switch (data->mask32_data.long_size) {
+		case 4:
+			data->mask32_data.nr = bswap_16(data->mask32_data.nr);
+			for (unsigned i = 0; i < data->mask32_data.nr; i++)
+				data->mask32_data.mask[i] = bswap_32(data->mask32_data.mask[i]);
+			break;
+		case 8:
+			data->mask64_data.nr = bswap_16(data->mask64_data.nr);
+			for (unsigned i = 0; i < data->mask64_data.nr; i++)
+				data->mask64_data.mask[i] = bswap_64(data->mask64_data.mask[i]);
+			break;
 		default:
 			pr_err("cpu_map swap: unsupported long size\n");
 		}
@@ -1283,21 +1283,25 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format)
 		       sample->read.time_running);
 
 	if (read_format & PERF_FORMAT_GROUP) {
-		u64 i;
+		struct sample_read_value *value = sample->read.group.values;
 
 		printf(".... group nr %" PRIu64 "\n", sample->read.group.nr);
 
-		for (i = 0; i < sample->read.group.nr; i++) {
-			struct sample_read_value *value;
-
-			value = &sample->read.group.values[i];
+		sample_read_group__for_each(value, sample->read.group.nr, read_format) {
 			printf("..... id %016" PRIx64
-			       ", value %016" PRIx64 "\n",
+			       ", value %016" PRIx64,
 			       value->id, value->value);
+			if (read_format & PERF_FORMAT_LOST)
+				printf(", lost %" PRIu64, value->lost);
+			printf("\n");
 		}
-	} else
-		printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n",
+	} else {
+		printf("..... id %016" PRIx64 ", value %016" PRIx64,
 			sample->read.one.id, sample->read.one.value);
+		if (read_format & PERF_FORMAT_LOST)
+			printf(", lost %" PRIu64, sample->read.one.lost);
+		printf("\n");
+	}
 }
 
 static void dump_event(struct evlist *evlist, union perf_event *event,
@@ -1411,6 +1415,9 @@ static void dump_read(struct evsel *evsel, union perf_event *event)
 
 	if (read_format & PERF_FORMAT_ID)
 		printf("... id           : %" PRI_lu64 "\n", read_event->id);
+
+	if (read_format & PERF_FORMAT_LOST)
+		printf("... lost         : %" PRI_lu64 "\n", read_event->lost);
 }
 
 static struct machine *machines__find_for_cpumode(struct machines *machines,
@@ -1479,14 +1486,14 @@ static int deliver_sample_group(struct evlist *evlist,
 				struct perf_tool *tool,
 				union  perf_event *event,
 				struct perf_sample *sample,
-				struct machine *machine)
+				struct machine *machine,
+				u64 read_format)
 {
 	int ret = -EINVAL;
-	u64 i;
+	struct sample_read_value *v = sample->read.group.values;
 
-	for (i = 0; i < sample->read.group.nr; i++) {
-		ret = deliver_sample_value(evlist, tool, event, sample,
-					   &sample->read.group.values[i],
+	sample_read_group__for_each(v, sample->read.group.nr, read_format) {
+		ret = deliver_sample_value(evlist, tool, event, sample, v,
 					   machine);
 		if (ret)
 			break;
@@ -1510,7 +1517,7 @@ static int evlist__deliver_sample(struct evlist *evlist, struct perf_tool *tool,
 	/* For PERF_SAMPLE_READ we have either single or group mode. */
 	if (read_format & PERF_FORMAT_GROUP)
 		return deliver_sample_group(evlist, tool, event, sample,
-					    machine);
+					    machine, read_format);
 	else
 		return deliver_sample_value(evlist, tool, event, sample,
 					    &sample->read.one, machine);

tools/perf/util/synthetic-events.c

@@ -1184,52 +1184,48 @@ int perf_event__synthesize_thread_map2(struct perf_tool *tool,
 	return err;
 }
 
-static void synthesize_cpus(struct cpu_map_entries *cpus,
-			    struct perf_cpu_map *map)
+static void synthesize_cpus(struct perf_record_cpu_map_data *data,
+			    const struct perf_cpu_map *map)
 {
 	int i, map_nr = perf_cpu_map__nr(map);
 
-	cpus->nr = map_nr;
+	data->cpus_data.nr = map_nr;
 
 	for (i = 0; i < map_nr; i++)
-		cpus->cpu[i] = perf_cpu_map__cpu(map, i).cpu;
+		data->cpus_data.cpu[i] = perf_cpu_map__cpu(map, i).cpu;
 }
 
-static void synthesize_mask(struct perf_record_record_cpu_map *mask,
-			    struct perf_cpu_map *map, int max)
+static void synthesize_mask(struct perf_record_cpu_map_data *data,
+			    const struct perf_cpu_map *map, int max)
 {
-	int i;
+	int idx;
+	struct perf_cpu cpu;
+
+	/* Due to padding, the 4bytes per entry mask variant is always smaller. */
+	data->mask32_data.nr = BITS_TO_U32(max);
+	data->mask32_data.long_size = 4;
 
-	mask->nr = BITS_TO_LONGS(max);
-	mask->long_size = sizeof(long);
+	perf_cpu_map__for_each_cpu(cpu, idx, map) {
+		int bit_word = cpu.cpu / 32;
+		__u32 bit_mask = 1U << (cpu.cpu & 31);
 
-	for (i = 0; i < perf_cpu_map__nr(map); i++)
-		set_bit(perf_cpu_map__cpu(map, i).cpu, mask->mask);
+		data->mask32_data.mask[bit_word] |= bit_mask;
+	}
 }
 
-static size_t cpus_size(struct perf_cpu_map *map)
+static size_t cpus_size(const struct perf_cpu_map *map)
 {
 	return sizeof(struct cpu_map_entries) + perf_cpu_map__nr(map) * sizeof(u16);
 }
 
-static size_t mask_size(struct perf_cpu_map *map, int *max)
+static size_t mask_size(const struct perf_cpu_map *map, int *max)
 {
-	int i;
-
-	*max = 0;
-
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		/* bit position of the cpu is + 1 */
-		int bit = perf_cpu_map__cpu(map, i).cpu + 1;
-
-		if (bit > *max)
-			*max = bit;
-	}
-
-	return sizeof(struct perf_record_record_cpu_map) + BITS_TO_LONGS(*max) * sizeof(long);
+	*max = perf_cpu_map__max(map).cpu;
+	return sizeof(struct perf_record_mask_cpu_map32) + BITS_TO_U32(*max) * sizeof(__u32);
 }
 
-void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max)
+static void *cpu_map_data__alloc(const struct perf_cpu_map *map, size_t *size,
+				 u16 *type, int *max)
 {
 	size_t size_cpus, size_mask;
 	bool is_dummy = perf_cpu_map__empty(map);
@@ -1258,30 +1254,31 @@ void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int
 		*type  = PERF_CPU_MAP__MASK;
 	}
 
-	*size += sizeof(struct perf_record_cpu_map_data);
+	*size += sizeof(__u16); /* For perf_record_cpu_map_data.type. */
 	*size = PERF_ALIGN(*size, sizeof(u64));
 	return zalloc(*size);
 }
 
-void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map,
-			      u16 type, int max)
+static void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data,
+				     const struct perf_cpu_map *map,
+				     u16 type, int max)
 {
 	data->type = type;
 
 	switch (type) {
 	case PERF_CPU_MAP__CPUS:
-		synthesize_cpus((struct cpu_map_entries *) data->data, map);
+		synthesize_cpus(data, map);
 		break;
 	case PERF_CPU_MAP__MASK:
-		synthesize_mask((struct perf_record_record_cpu_map *)data->data, map, max);
+		synthesize_mask(data, map, max);
 	default:
 		break;
 	}
 }
 
-static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map)
+static struct perf_record_cpu_map *cpu_map_event__new(const struct perf_cpu_map *map)
 {
-	size_t size = sizeof(struct perf_record_cpu_map);
+	size_t size = sizeof(struct perf_event_header);
 	struct perf_record_cpu_map *event;
 	int max;
 	u16 type;
@@ -1299,7 +1296,7 @@ static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map)
 }
 
 int perf_event__synthesize_cpu_map(struct perf_tool *tool,
-				   struct perf_cpu_map *map,
+				   const struct perf_cpu_map *map,
 				   perf_event__handler_t process,
 				   struct machine *machine)
 {
@@ -1432,11 +1429,12 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 			result += sizeof(u64);
 		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
 		if (read_format & PERF_FORMAT_GROUP) {
-			sz = sample->read.group.nr *
-			     sizeof(struct sample_read_value);
-			result += sz;
+			sz = sample_read_value_size(read_format);
+			result += sz * sample->read.group.nr;
 		} else {
 			result += sizeof(u64);
+			if (read_format & PERF_FORMAT_LOST)
+				result += sizeof(u64);
 		}
 	}
 
@@ -1521,6 +1519,20 @@ void __weak arch_perf_synthesize_sample_weight(const struct perf_sample *data,
 	*array = data->weight;
 }
 
+static __u64 *copy_read_group_values(__u64 *array, __u64 read_format,
+				     const struct perf_sample *sample)
+{
+	size_t sz = sample_read_value_size(read_format);
+	struct sample_read_value *v = sample->read.group.values;
+
+	sample_read_group__for_each(v, sample->read.group.nr, read_format) {
+		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+		memcpy(array, v, sz);
+		array = (void *)array + sz;
+	}
+	return array;
+}
+
 int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format,
 				  const struct perf_sample *sample)
 {
@@ -1602,13 +1614,16 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
 
 		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
 		if (read_format & PERF_FORMAT_GROUP) {
-			sz = sample->read.group.nr *
-			     sizeof(struct sample_read_value);
-			memcpy(array, sample->read.group.values, sz);
-			array = (void *)array + sz;
+			array = copy_read_group_values(array, read_format,
+						       sample);
 		} else {
 			*array = sample->read.one.id;
 			array++;
+
+			if (read_format & PERF_FORMAT_LOST) {
+				*array = sample->read.one.lost;
+				array++;
+			}
 		}
 	}
 

tools/perf/util/synthetic-events.h

@@ -46,7 +46,7 @@ typedef int (*perf_event__handler_t)(struct perf_tool *tool, union perf_event *e
 int perf_event__synthesize_attrs(struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process);
 int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process);
 int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16 misc, perf_event__handler_t process, struct machine *machine);
-int perf_event__synthesize_cpu_map(struct perf_tool *tool, struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_cpu_map(struct perf_tool *tool, const struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
 int perf_event__synthesize_event_update_name(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
 int perf_event__synthesize_event_update_scale(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);