Merge tag 'perf-tools-fixes-for-v6.3-1-2023-03-09' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Add Adrian Hunter to MAINTAINERS as a perf tools reviewer

 - Sync various tools/ copies of kernel headers with the kernel sources,
   this time trying to avoid first merging with upstream to then update
   but instead copy from upstream so that a merge is avoided and the end
   result after merging this pull request is the one expected,
   tools/perf/check-headers.sh (mostly) happy, less warnings while
   building tools/perf/

 - Fix counting when initial delay configured by setting
   perf_attr.enable_on_exec when starting workloads from the perf
   command line

 - Don't avoid emitting a PERF_RECORD_MMAP2 in 'perf inject
   --buildid-all' when that record comes with a build-id, otherwise we
   end up not being able to resolve symbols

 - Don't use comma as the CSV output separator the "stat+csv_output"
   test, as comma can appear on some tests as a modifier for an event,
   use @ instead, ditto for the JSON linter test

 - The offcpu test was looking for some bits being set on
   task_struct->prev_state without masking other bits not important for
   this specific 'perf test', fix it

* tag 'perf-tools-fixes-for-v6.3-1-2023-03-09' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf tools: Add Adrian Hunter to MAINTAINERS as a reviewer
  tools headers UAPI: Sync linux/perf_event.h with the kernel sources
  tools headers x86 cpufeatures: Sync with the kernel sources
  tools include UAPI: Sync linux/vhost.h with the kernel sources
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  tools headers kvm: Sync uapi/{asm/linux} kvm.h headers with the kernel sources
  tools include UAPI: Synchronize linux/fcntl.h with the kernel sources
  tools headers: Synchronize {linux,vdso}/bits.h with the kernel sources
  tools headers UAPI: Sync linux/prctl.h with the kernel sources
  tools headers: Update the copy of x86's mem{cpy,set}_64.S used in 'perf bench'
  perf stat: Fix counting when initial delay configured
  tools headers svm: Sync svm headers with the kernel sources
  perf test: Avoid counting commas in json linter
  perf tests stat+csv_output: Switch CSV separator to @
  perf inject: Fix --buildid-all not to eat up MMAP2
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  perf test: Fix offcpu test prev_state check

25 files changed, 154 insertions, 54 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 8d5bc223f305..150ff03b42eb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16391,6 +16391,7 @@ R:	Alexander Shishkin <alexander.shishkin@linux.intel.com>
 R:	Jiri Olsa <jolsa@kernel.org>
 R:	Namhyung Kim <namhyung@kernel.org>
 R:	Ian Rogers <irogers@google.com>
+R:	Adrian Hunter <adrian.hunter@intel.com>
 L:	linux-perf-users@vger.kernel.org
 L:	linux-kernel@vger.kernel.org
 S:	Supported
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index a7a857f1784d..f8129c624b07 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -109,6 +109,7 @@ struct kvm_regs {
 #define KVM_ARM_VCPU_SVE		4 /* enable SVE for this CPU */
 #define KVM_ARM_VCPU_PTRAUTH_ADDRESS	5 /* VCPU uses address authentication */
 #define KVM_ARM_VCPU_PTRAUTH_GENERIC	6 /* VCPU uses generic authentication */
+#define KVM_ARM_VCPU_HAS_EL2		7 /* Support nested virtualization */
 
 struct kvm_vcpu_init {
 	__u32 target;
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index b70111a75688..b89005819cd5 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS			20	   /* N 32-bit words worth of info */
+#define NCAPINTS			21	   /* N 32-bit words worth of info */
 #define NBUGINTS			1	   /* N 32-bit bug flags */
 
 /*
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index c44b56f7ffba..5dfa4fb76f4b 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -124,6 +124,7 @@
 #define DISABLED_MASK17	0
 #define DISABLED_MASK18	0
 #define DISABLED_MASK19	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20)
+#define DISABLED_MASK20	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 37ff47552bcb..ad35355ee43e 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -25,6 +25,7 @@
 #define _EFER_SVME		12 /* Enable virtualization */
 #define _EFER_LMSLE		13 /* Long Mode Segment Limit Enable */
 #define _EFER_FFXSR		14 /* Enable Fast FXSAVE/FXRSTOR */
+#define _EFER_AUTOIBRS		21 /* Enable Automatic IBRS */
 
 #define EFER_SCE		(1<<_EFER_SCE)
 #define EFER_LME		(1<<_EFER_LME)
@@ -33,6 +34,7 @@
 #define EFER_SVME		(1<<_EFER_SVME)
 #define EFER_LMSLE		(1<<_EFER_LMSLE)
 #define EFER_FFXSR		(1<<_EFER_FFXSR)
+#define EFER_AUTOIBRS		(1<<_EFER_AUTOIBRS)
 
 /* Intel MSRs. Some also available on other CPUs */
 
@@ -49,6 +51,10 @@
 #define SPEC_CTRL_RRSBA_DIS_S_SHIFT	6	   /* Disable RRSBA behavior */
 #define SPEC_CTRL_RRSBA_DIS_S		BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT)
 
+/* A mask for bits which the kernel toggles when controlling mitigations */
+#define SPEC_CTRL_MITIGATIONS_MASK	(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \
+							| SPEC_CTRL_RRSBA_DIS_S)
+
 #define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
 #define PRED_CMD_IBPB			BIT(0)	   /* Indirect Branch Prediction Barrier */
 
@@ -189,6 +195,9 @@
 #define MSR_TURBO_RATIO_LIMIT1		0x000001ae
 #define MSR_TURBO_RATIO_LIMIT2		0x000001af
 
+#define MSR_SNOOP_RSP_0			0x00001328
+#define MSR_SNOOP_RSP_1			0x00001329
+
 #define MSR_LBR_SELECT			0x000001c8
 #define MSR_LBR_TOS			0x000001c9
 
@@ -566,6 +575,26 @@
 #define MSR_AMD64_SEV_ES_ENABLED	BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
 #define MSR_AMD64_SEV_SNP_ENABLED	BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT)
 
+/* SNP feature bits enabled by the hypervisor */
+#define MSR_AMD64_SNP_VTOM			BIT_ULL(3)
+#define MSR_AMD64_SNP_REFLECT_VC		BIT_ULL(4)
+#define MSR_AMD64_SNP_RESTRICTED_INJ		BIT_ULL(5)
+#define MSR_AMD64_SNP_ALT_INJ			BIT_ULL(6)
+#define MSR_AMD64_SNP_DEBUG_SWAP		BIT_ULL(7)
+#define MSR_AMD64_SNP_PREVENT_HOST_IBS		BIT_ULL(8)
+#define MSR_AMD64_SNP_BTB_ISOLATION		BIT_ULL(9)
+#define MSR_AMD64_SNP_VMPL_SSS			BIT_ULL(10)
+#define MSR_AMD64_SNP_SECURE_TSC		BIT_ULL(11)
+#define MSR_AMD64_SNP_VMGEXIT_PARAM		BIT_ULL(12)
+#define MSR_AMD64_SNP_IBS_VIRT			BIT_ULL(14)
+#define MSR_AMD64_SNP_VMSA_REG_PROTECTION	BIT_ULL(16)
+#define MSR_AMD64_SNP_SMT_PROTECTION		BIT_ULL(17)
+
+/* SNP feature bits reserved for future use. */
+#define MSR_AMD64_SNP_RESERVED_BIT13		BIT_ULL(13)
+#define MSR_AMD64_SNP_RESERVED_BIT15		BIT_ULL(15)
+#define MSR_AMD64_SNP_RESERVED_MASK		GENMASK_ULL(63, 18)
+
 #define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
 
 /* AMD Collaborative Processor Performance Control MSRs */
@@ -1061,6 +1090,8 @@
 
 /* - AMD: */
 #define MSR_IA32_MBA_BW_BASE		0xc0000200
+#define MSR_IA32_SMBA_BW_BASE		0xc0000280
+#define MSR_IA32_EVT_CFG_BASE		0xc0000400
 
 /* MSR_IA32_VMX_MISC bits */
 #define MSR_IA32_VMX_MISC_INTEL_PT                 (1ULL << 14)
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index aff774775c67..7ba1726b71c7 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -98,6 +98,7 @@
 #define REQUIRED_MASK17	0
 #define REQUIRED_MASK18	0
 #define REQUIRED_MASK19	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20)
+#define REQUIRED_MASK20	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index e48deab8901d..7f467fe05d42 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -9,6 +9,7 @@
 
 #include <linux/types.h>
 #include <linux/ioctl.h>
+#include <linux/stddef.h>
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
@@ -507,8 +508,8 @@ struct kvm_nested_state {
 	 * KVM_{GET,PUT}_NESTED_STATE ioctl values.
 	 */
 	union {
-		struct kvm_vmx_nested_state_data vmx[0];
-		struct kvm_svm_nested_state_data svm[0];
+		__DECLARE_FLEX_ARRAY(struct kvm_vmx_nested_state_data, vmx);
+		__DECLARE_FLEX_ARRAY(struct kvm_svm_nested_state_data, svm);
 	} data;
 };
 
@@ -525,6 +526,35 @@ struct kvm_pmu_event_filter {
 #define KVM_PMU_EVENT_ALLOW 0
 #define KVM_PMU_EVENT_DENY 1
 
+#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0)
+#define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS)
+
+/*
+ * Masked event layout.
+ * Bits   Description
+ * ----   -----------
+ * 7:0    event select (low bits)
+ * 15:8   umask match
+ * 31:16  unused
+ * 35:32  event select (high bits)
+ * 36:54  unused
+ * 55     exclude bit
+ * 63:56  umask mask
+ */
+
+#define KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, exclude) \
+	(((event_select) & 0xFFULL) | (((event_select) & 0XF00ULL) << 24) | \
+	(((mask) & 0xFFULL) << 56) | \
+	(((match) & 0xFFULL) << 8) | \
+	((__u64)(!!(exclude)) << 55))
+
+#define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \
+	(GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32))
+#define KVM_PMU_MASKED_ENTRY_UMASK_MASK		(GENMASK_ULL(63, 56))
+#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH	(GENMASK_ULL(15, 8))
+#define KVM_PMU_MASKED_ENTRY_EXCLUDE		(BIT_ULL(55))
+#define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT	(56)
+
 /* for KVM_{GET,SET,HAS}_DEVICE_ATTR */
 #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */
 #define   KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
index f69c168391aa..80e1df482337 100644
--- a/tools/arch/x86/include/uapi/asm/svm.h
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -116,6 +116,12 @@
 #define SVM_VMGEXIT_AP_CREATE			1
 #define SVM_VMGEXIT_AP_DESTROY			2
 #define SVM_VMGEXIT_HV_FEATURES			0x8000fffd
+#define SVM_VMGEXIT_TERM_REQUEST		0x8000fffe
+#define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code)	\
+	/* SW_EXITINFO1[3:0] */					\
+	(((((u64)reason_set) & 0xf)) |				\
+	/* SW_EXITINFO1[11:4] */				\
+	((((u64)reason_code) & 0xff) << 4))
 #define SVM_VMGEXIT_UNSUPPORTED_EVENT		0x8000ffff
 
 /* Exit code reserved for hypervisor/software use */
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 5418e2f99834..a91ac666f758 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -7,7 +7,7 @@
 #include <asm/alternative.h>
 #include <asm/export.h>
 
-.pushsection .noinstr.text, "ax"
+.section .noinstr.text, "ax"
 
 /*
  * We build a jump to memcpy_orig by default which gets NOPped out on
@@ -42,7 +42,7 @@ SYM_TYPED_FUNC_START(__memcpy)
 SYM_FUNC_END(__memcpy)
 EXPORT_SYMBOL(__memcpy)
 
-SYM_FUNC_ALIAS_WEAK(memcpy, __memcpy)
+SYM_FUNC_ALIAS(memcpy, __memcpy)
 EXPORT_SYMBOL(memcpy)
 
 /*
@@ -183,4 +183,3 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
 	RET
 SYM_FUNC_END(memcpy_orig)
 
-.popsection
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index fc9ffd3ff3b2..6143b1a6fa2c 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -6,6 +6,8 @@
 #include <asm/alternative.h>
 #include <asm/export.h>
 
+.section .noinstr.text, "ax"
+
 /*
  * ISO C memset - set a memory block to a byte value. This function uses fast
  * string to get better performance than the original function. The code is
@@ -43,7 +45,7 @@ SYM_FUNC_START(__memset)
 SYM_FUNC_END(__memset)
 EXPORT_SYMBOL(__memset)
 
-SYM_FUNC_ALIAS_WEAK(memset, __memset)
+SYM_FUNC_ALIAS(memset, __memset)
 EXPORT_SYMBOL(memset)
 
 /*
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 87d112650dfb..7c0cf5031abe 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -6,7 +6,6 @@
 #include <vdso/bits.h>
 #include <asm/bitsperlong.h>
 
-#define BIT_ULL(nr)		(ULL(1) << (nr))
 #define BIT_MASK(nr)		(UL(1) << ((nr) % BITS_PER_LONG))
 #define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
 #define BIT_ULL_MASK(nr)	(ULL(1) << ((nr) % BITS_PER_LONG_LONG))
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 2f86b2ad6d7e..e8c07da58c9f 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -43,6 +43,7 @@
 #define F_SEAL_GROW	0x0004	/* prevent file from growing */
 #define F_SEAL_WRITE	0x0008	/* prevent writes */
 #define F_SEAL_FUTURE_WRITE	0x0010  /* prevent future writes while mapped */
+#define F_SEAL_EXEC	0x0020  /* prevent chmod modifying exec bits */
 /* (1U << 31) is reserved for signed error codes */
 
 /*
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 55155e262646..d77aef872a0a 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -583,6 +583,8 @@ struct kvm_s390_mem_op {
 		struct {
 			__u8 ar;	/* the access register number */
 			__u8 key;	/* access key, ignored if flag unset */
+			__u8 pad1[6];	/* ignored */
+			__u64 old_addr;	/* ignored if cmpxchg flag unset */
 		};
 		__u32 sida_offset; /* offset into the sida */
 		__u8 reserved[32]; /* ignored */
@@ -595,11 +597,17 @@ struct kvm_s390_mem_op {
 #define KVM_S390_MEMOP_SIDA_WRITE	3
 #define KVM_S390_MEMOP_ABSOLUTE_READ	4
 #define KVM_S390_MEMOP_ABSOLUTE_WRITE	5
+#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG	6
+
 /* flags for kvm_s390_mem_op->flags */
 #define KVM_S390_MEMOP_F_CHECK_ONLY		(1ULL << 0)
 #define KVM_S390_MEMOP_F_INJECT_EXCEPTION	(1ULL << 1)
 #define KVM_S390_MEMOP_F_SKEY_PROTECTION	(1ULL << 2)
 
+/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */
+#define KVM_S390_MEMOP_EXTENSION_CAP_BASE	(1 << 0)
+#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG	(1 << 1)
+
 /* for KVM_INTERRUPT */
 struct kvm_interrupt {
 	/* in */
@@ -1175,6 +1183,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223
 #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224
 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225
+#define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index ccb7f5dad59b..37675437b768 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -374,6 +374,7 @@ enum perf_event_read_format {
 #define PERF_ATTR_SIZE_VER5	112	/* add: aux_watermark */
 #define PERF_ATTR_SIZE_VER6	120	/* add: aux_sample_size */
 #define PERF_ATTR_SIZE_VER7	128	/* add: sig_data */
+#define PERF_ATTR_SIZE_VER8	136	/* add: config3 */
 
 /*
  * Hardware event_id to monitor via a performance monitoring event:
@@ -515,6 +516,8 @@ struct perf_event_attr {
 	 * truncated accordingly on 32 bit architectures.
 	 */
 	__u64	sig_data;
+
+	__u64	config3; /* extension of config2 */
 };
 
 /*
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index a5e06dcbba13..1312a137f7fb 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -281,6 +281,12 @@ struct prctl_mm_map {
 # define PR_SME_VL_LEN_MASK		0xffff
 # define PR_SME_VL_INHERIT		(1 << 17) /* inherit across exec */
 
+/* Memory deny write / execute */
+#define PR_SET_MDWE			65
+# define PR_MDWE_REFUSE_EXEC_GAIN	1
+
+#define PR_GET_MDWE			66
+
 #define PR_SET_VMA		0x53564d41
 # define PR_SET_VMA_ANON_NAME		0
 
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index f9f115a7c75b..92e1b700b51c 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -180,4 +180,12 @@
  */
 #define VHOST_VDPA_SUSPEND		_IO(VHOST_VIRTIO, 0x7D)
 
+/* Resume a device so it can resume processing virtqueue requests
+ *
+ * After the return of this ioctl the device will have restored all the
+ * necessary states and it is fully operational to continue processing the
+ * virtqueue descriptors.
+ */
+#define VHOST_VDPA_RESUME		_IO(VHOST_VIRTIO, 0x7E)
+
 #endif
diff --git a/tools/include/vdso/bits.h b/tools/include/vdso/bits.h
index 6d005a1f5d94..388b212088ea 100644
--- a/tools/include/vdso/bits.h
+++ b/tools/include/vdso/bits.h
@@ -5,5 +5,6 @@
 #include <vdso/const.h>
 
 #define BIT(nr)			(UL(1) << (nr))
+#define BIT_ULL(nr)		(ULL(1) << (nr))
 
 #endif	/* __VDSO_BITS_H */
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index f8182417b734..10bb1d494258 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -538,6 +538,7 @@ static int perf_event__repipe_buildid_mmap2(struct perf_tool *tool,
 			dso->hit = 1;
 		}
 		dso__put(dso);
+		perf_event__repipe(tool, event, sample, machine);
 		return 0;
 	}
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 5d18a5a6f662..fa7c40956d0f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -539,12 +539,7 @@ static int enable_counters(void)
 			return err;
 	}
 
-	/*
-	 * We need to enable counters only if:
-	 * - we don't have tracee (attaching to task or cpu)
-	 * - we have initial delay configured
-	 */
-	if (!target__none(&target)) {
+	if (!target__enable_on_exec(&target)) {
 		if (!all_counters_use_bpf)
 			evlist__enable(evsel_list);
 	}
@@ -914,7 +909,7 @@ try_again_reset:
 			return err;
 	}
 
-	if (stat_config.initial_delay) {
+	if (target.initial_delay) {
 		pr_info(EVLIST_DISABLED_MSG);
 	} else {
 		err = enable_counters();
@@ -926,8 +921,8 @@ try_again_reset:
 	if (forks)
 		evlist__start_workload(evsel_list);
 
-	if (stat_config.initial_delay > 0) {
-		usleep(stat_config.initial_delay * USEC_PER_MSEC);
+	if (target.initial_delay > 0) {
+		usleep(target.initial_delay * USEC_PER_MSEC);
 		err = enable_counters();
 		if (err)
 			return -1;
@@ -1248,7 +1243,7 @@ static struct option stat_options[] = {
 		     "aggregate counts per thread", AGGR_THREAD),
 	OPT_SET_UINT(0, "per-node", &stat_config.aggr_mode,
 		     "aggregate counts per numa node", AGGR_NODE),
-	OPT_INTEGER('D', "delay", &stat_config.initial_delay,
+	OPT_INTEGER('D', "delay", &target.initial_delay,
 		    "ms to wait before starting measurement after program start (-1: start with events disabled)"),
 	OPT_CALLBACK_NOOPT(0, "metric-only", &stat_config.metric_only, NULL,
 			"Only print computed metrics. No raw values", enable_metric_only),
diff --git a/tools/perf/tests/shell/lib/perf_json_output_lint.py b/tools/perf/tests/shell/lib/perf_json_output_lint.py
index d90f8d102eb9..97598d14e532 100644
--- a/tools/perf/tests/shell/lib/perf_json_output_lint.py
+++ b/tools/perf/tests/shell/lib/perf_json_output_lint.py
@@ -40,19 +40,6 @@ def is_counter_value(num):
   return isfloat(num) or num == '<not counted>' or num == '<not supported>'
 
 def check_json_output(expected_items):
-  if expected_items != -1:
-    for line in Lines:
-      if 'failed' not in line:
-        count = 0
-        count = line.count(',')
-        if count != expected_items and count >= 1 and count <= 3 and 'metric-value' in line:
-          # Events that generate >1 metric may have isolated metric
-          # values and possibly other prefixes like interval, core and
-          # aggregate-number.
-          continue
-        if count != expected_items:
-          raise RuntimeError(f'wrong number of fields. counted {count} expected {expected_items}'
-                             f' in \'{line}\'')
   checks = {
       'aggregate-number': lambda x: isfloat(x),
       'core': lambda x: True,
@@ -73,6 +60,16 @@ def check_json_output(expected_items):
   }
   input = '[\n' + ','.join(Lines) + '\n]'
   for item in json.loads(input):
+    if expected_items != -1:
+      count = len(item)
+      if count != expected_items and count >= 1 and count <= 4 and 'metric-value' in item:
+        # Events that generate >1 metric may have isolated metric
+        # values and possibly other prefixes like interval, core and
+        # aggregate-number.
+        pass
+      elif count != expected_items:
+        raise RuntimeError(f'wrong number of fields. counted {count} expected {expected_items}'
+                           f' in \'{item}\'')
     for key, value in item.items():
       if key not in checks:
         raise RuntimeError(f'Unexpected key: key={key} value={value}')
@@ -82,11 +79,11 @@ def check_json_output(expected_items):
 
 try:
   if args.no_args or args.system_wide or args.event:
-    expected_items = 6
-  elif args.interval or args.per_thread or args.system_wide_no_aggr:
     expected_items = 7
-  elif args.per_core or args.per_socket or args.per_node or args.per_die:
+  elif args.interval or args.per_thread or args.system_wide_no_aggr:
     expected_items = 8
+  elif args.per_core or args.per_socket or args.per_node or args.per_die:
+    expected_items = 9
   else:
     # If no option is specified, don't check the number of items.
     expected_items = -1
diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh
index b7f050aa6210..324fc9e6edd7 100755
--- a/tools/perf/tests/shell/stat+csv_output.sh
+++ b/tools/perf/tests/shell/stat+csv_output.sh
@@ -7,6 +7,7 @@
 set -e
 
 skip_test=0
+csv_sep=@
 
 function commachecker()
 {
@@ -34,7 +35,7 @@ function commachecker()
 		[ "$x" = "Failed" ] && continue
 
 		# Count the number of commas
-		x=$(echo $line | tr -d -c ',')
+		x=$(echo $line | tr -d -c $csv_sep)
 		cnt="${#x}"
 		# echo $line $cnt
 		[[ ! "$cnt" =~ $exp ]] && {
@@ -54,7 +55,7 @@ function ParanoidAndNotRoot()
 check_no_args()
 {
 	echo -n "Checking CSV output: no args "
-	perf stat -x, true 2>&1 | commachecker --no-args
+	perf stat -x$csv_sep true 2>&1 | commachecker --no-args
 	echo "[Success]"
 }
 
@@ -66,7 +67,7 @@ check_system_wide()
 		echo "[Skip] paranoid and not root"
 		return
 	fi
-	perf stat -x, -a true 2>&1 | commachecker --system-wide
+	perf stat -x$csv_sep -a true 2>&1 | commachecker --system-wide
 	echo "[Success]"
 }
 
@@ -79,14 +80,14 @@ check_system_wide_no_aggr()
 		return
 	fi
 	echo -n "Checking CSV output: system wide no aggregation "
-	perf stat -x, -A -a --no-merge true 2>&1 | commachecker --system-wide-no-aggr
+	perf stat -x$csv_sep -A -a --no-merge true 2>&1 | commachecker --system-wide-no-aggr
 	echo "[Success]"
 }
 
 check_interval()
 {
 	echo -n "Checking CSV output: interval "
-	perf stat -x, -I 1000 true 2>&1 | commachecker --interval
+	perf stat -x$csv_sep -I 1000 true 2>&1 | commachecker --interval
 	echo "[Success]"
 }
 
@@ -94,7 +95,7 @@ check_interval()
 check_event()
 {
 	echo -n "Checking CSV output: event "
-	perf stat -x, -e cpu-clock true 2>&1 | commachecker --event
+	perf stat -x$csv_sep -e cpu-clock true 2>&1 | commachecker --event
 	echo "[Success]"
 }
 
@@ -106,7 +107,7 @@ check_per_core()
 		echo "[Skip] paranoid and not root"
 		return
 	fi
-	perf stat -x, --per-core -a true 2>&1 | commachecker --per-core
+	perf stat -x$csv_sep --per-core -a true 2>&1 | commachecker --per-core
 	echo "[Success]"
 }
 
@@ -118,7 +119,7 @@ check_per_thread()
 		echo "[Skip] paranoid and not root"
 		return
 	fi
-	perf stat -x, --per-thread -a true 2>&1 | commachecker --per-thread
+	perf stat -x$csv_sep --per-thread -a true 2>&1 | commachecker --per-thread
 	echo "[Success]"
 }
 
@@ -130,7 +131,7 @@ check_per_die()
 		echo "[Skip] paranoid and not root"
 		return
 	fi
-	perf stat -x, --per-die -a true 2>&1 | commachecker --per-die
+	perf stat -x$csv_sep --per-die -a true 2>&1 | commachecker --per-die
 	echo "[Success]"
 }
 
@@ -142,7 +143,7 @@ check_per_node()
 		echo "[Skip] paranoid and not root"
 		return
 	fi
-	perf stat -x, --per-node -a true 2>&1 | commachecker --per-node
+	perf stat -x$csv_sep --per-node -a true 2>&1 | commachecker --per-node
 	echo "[Success]"
 }
 
@@ -154,7 +155,7 @@ check_per_socket()
 		echo "[Skip] paranoid and not root"
 		return
 	fi
-	perf stat -x, --per-socket -a true 2>&1 | commachecker --per-socket
+	perf stat -x$csv_sep --per-socket -a true 2>&1 | commachecker --per-socket
 	echo "[Success]"
 }
 
diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
index 38e3b287dbb2..d877a0a9731f 100644
--- a/tools/perf/util/bpf_skel/off_cpu.bpf.c
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -277,7 +277,7 @@ int on_switch(u64 *ctx)
 	else
 		prev_state = get_task_state(prev);
 
-	return off_cpu_stat(ctx, prev, next, prev_state);
+	return off_cpu_stat(ctx, prev, next, prev_state & 0xff);
 }
 
 char LICENSE[] SEC("license") = "Dual BSD/GPL";
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 534d36d26fc3..a07473703c6d 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -842,11 +842,7 @@ int create_perf_stat_counter(struct evsel *evsel,
 	if (evsel__is_group_leader(evsel)) {
 		attr->disabled = 1;
 
-		/*
-		 * In case of initial_delay we enable tracee
-		 * events manually.
-		 */
-		if (target__none(target) && !config->initial_delay)
+		if (target__enable_on_exec(target))
 			attr->enable_on_exec = 1;
 	}
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index b1c29156c560..bf1794ebc916 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -166,7 +166,6 @@ struct perf_stat_config {
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
-	int			 initial_delay;
 	unsigned int		 unit_width;
 	unsigned int		 metric_only_len;
 	int			 times;
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index daec6cba500d..880f1af7f6ad 100644
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -18,6 +18,7 @@ struct target {
 	bool	     per_thread;
 	bool	     use_bpf;
 	bool	     hybrid;
+	int	     initial_delay;
 	const char   *attr_map;
 };
 
@@ -72,6 +73,17 @@ static inline bool target__none(struct target *target)
 	return !target__has_task(target) && !target__has_cpu(target);
 }
 
+static inline bool target__enable_on_exec(struct target *target)
+{
+	/*
+	 * Normally enable_on_exec should be set if:
+	 *  1) The tracee process is forked (not attaching to existed task or cpu).
+	 *  2) And initial_delay is not configured.
+	 * Otherwise, we enable tracee events manually.
+	 */
+	return target__none(target) && !target->initial_delay;
+}
+
 static inline bool target__has_per_thread(struct target *target)
 {
 	return target->system_wide && target->per_thread;