Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf tooling updates from Ingo Molnar:
 "Tooling changes only: fixes and a few stray improvements.

  Most of the diffstat is dominated by a PowerPC related fix of system
  call trace output beautification that allows us to (again) use the
  UAPI header version and sync up with the kernel's version of PowerPC
  system call names in the arch/powerpc/kernel/syscalls/syscall.tbl
  header"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
  tools headers powerpc: Remove unistd.h
  perf powerpc: Rework syscall table generation
  perf symbols: Add 'arch_cpu_idle' to the list of kernel idle symbols
  tools include uapi: Sync linux/if_link.h copy with the kernel sources
  tools include uapi: Sync linux/vhost.h with the kernel sources
  tools include uapi: Sync linux/fs.h copy with the kernel sources
  perf beauty: Switch from using uapi/linux/fs.h to uapi/linux/mount.h
  tools include uapi: Grab a copy of linux/mount.h
  perf top: Lift restriction on using callchains without "sym" in --sort
  tools lib traceevent: Remove tep_data_event_from_type() API
  tools lib traceevent: Rename tep_is_file_bigendian() to tep_file_bigendian()
  tools lib traceevent: Changed return logic of tep_register_event_handler() API
  tools lib traceevent: Changed return logic of trace_seq_printf() and trace_seq_vprintf() APIs
  tools lib traceevent: Rename struct cmdline to struct tep_cmdline
  tools lib traceevent: Initialize host_bigendian at tep_handle allocation
  tools lib traceevent: Introduce new libtracevent API: tep_override_comm()
  perf tests: Add a test for the ARM 32-bit [vectors] page
  perf tools: Make find_vdso_map() more modular
  perf trace: Fix alignment for [continued] lines
  perf trace: Fix ')' placement in "interrupted" syscall lines
  ...

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

@@ -281,9 +281,11 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* Always save/restore FP error pointers */
+#define X86_FEATURE_WBNOINVD		(13*32+ 9) /* WBNOINVD instruction */
 #define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
 #define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
 #define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_STIBP_ALWAYS_ON	(13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */
 #define X86_FEATURE_AMD_SSBD		(13*32+24) /* "" Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 #define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */

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

@@ -16,6 +16,12 @@
 # define DISABLE_MPX	(1<<(X86_FEATURE_MPX & 31))
 #endif
 
+#ifdef CONFIG_X86_SMAP
+# define DISABLE_SMAP	0
+#else
+# define DISABLE_SMAP	(1<<(X86_FEATURE_SMAP & 31))
+#endif
+
 #ifdef CONFIG_X86_INTEL_UMIP
 # define DISABLE_UMIP	0
 #else
@@ -68,7 +74,7 @@
 #define DISABLED_MASK6	0
 #define DISABLED_MASK7	(DISABLE_PTI)
 #define DISABLED_MASK8	0
-#define DISABLED_MASK9	(DISABLE_MPX)
+#define DISABLED_MASK9	(DISABLE_MPX|DISABLE_SMAP)
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	0
 #define DISABLED_MASK12	0

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

@@ -738,9 +738,11 @@ __SYSCALL(__NR_statx,     sys_statx)
 __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
 #define __NR_rseq 293
 __SYSCALL(__NR_rseq, sys_rseq)
+#define __NR_kexec_file_load 294
+__SYSCALL(__NR_kexec_file_load,     sys_kexec_file_load)
 
 #undef __NR_syscalls
-#define __NR_syscalls 294
+#define __NR_syscalls 295
 
 /*
  * 32 bit systems traditionally used different

tools/include/uapi/drm/i915_drm.h

@@ -412,6 +412,14 @@ typedef struct drm_i915_irq_wait {
 	int irq_seq;
 } drm_i915_irq_wait_t;
 
+/*
+ * Different modes of per-process Graphics Translation Table,
+ * see I915_PARAM_HAS_ALIASING_PPGTT
+ */
+#define I915_GEM_PPGTT_NONE	0
+#define I915_GEM_PPGTT_ALIASING	1
+#define I915_GEM_PPGTT_FULL	2
+
 /* Ioctl to query kernel params:
  */
 #define I915_PARAM_IRQ_ACTIVE            1

tools/include/uapi/linux/fs.h

@@ -14,6 +14,11 @@
 #include <linux/ioctl.h>
 #include <linux/types.h>
 
+/* Use of MS_* flags within the kernel is restricted to core mount(2) code. */
+#if !defined(__KERNEL__)
+#include <linux/mount.h>
+#endif
+
 /*
  * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
  * the file limit at runtime and only root can increase the per-process
@@ -101,57 +106,6 @@ struct inodes_stat_t {
 
 #define NR_FILE  8192	/* this can well be larger on a larger system */
 
-
-/*
- * These are the fs-independent mount-flags: up to 32 flags are supported
- */
-#define MS_RDONLY	 1	/* Mount read-only */
-#define MS_NOSUID	 2	/* Ignore suid and sgid bits */
-#define MS_NODEV	 4	/* Disallow access to device special files */
-#define MS_NOEXEC	 8	/* Disallow program execution */
-#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
-#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_NOATIME	1024	/* Do not update access times. */
-#define MS_NODIRATIME	2048	/* Do not update directory access times */
-#define MS_BIND		4096
-#define MS_MOVE		8192
-#define MS_REC		16384
-#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
-				   MS_VERBOSE is deprecated. */
-#define MS_SILENT	32768
-#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
-#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
-#define MS_PRIVATE	(1<<18)	/* change to private */
-#define MS_SLAVE	(1<<19)	/* change to slave */
-#define MS_SHARED	(1<<20)	/* change to shared */
-#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
-#define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
-#define MS_I_VERSION	(1<<23) /* Update inode I_version field */
-#define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
-#define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
-
-/* These sb flags are internal to the kernel */
-#define MS_SUBMOUNT     (1<<26)
-#define MS_NOREMOTELOCK	(1<<27)
-#define MS_NOSEC	(1<<28)
-#define MS_BORN		(1<<29)
-#define MS_ACTIVE	(1<<30)
-#define MS_NOUSER	(1<<31)
-
-/*
- * Superblock flags that can be altered by MS_REMOUNT
- */
-#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
-			 MS_LAZYTIME)
-
-/*
- * Old magic mount flag and mask
- */
-#define MS_MGC_VAL 0xC0ED0000
-#define MS_MGC_MSK 0xffff0000
-
 /*
  * Structure for FS_IOC_FSGETXATTR[A] and FS_IOC_FSSETXATTR.
  */
@@ -269,7 +223,8 @@ struct fsxattr {
 #define FS_POLICY_FLAGS_PAD_16		0x02
 #define FS_POLICY_FLAGS_PAD_32		0x03
 #define FS_POLICY_FLAGS_PAD_MASK	0x03
-#define FS_POLICY_FLAGS_VALID		0x03
+#define FS_POLICY_FLAG_DIRECT_KEY	0x04	/* use master key directly */
+#define FS_POLICY_FLAGS_VALID		0x07
 
 /* Encryption algorithms */
 #define FS_ENCRYPTION_MODE_INVALID		0
@@ -281,6 +236,7 @@ struct fsxattr {
 #define FS_ENCRYPTION_MODE_AES_128_CTS		6
 #define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7 /* Removed, do not use. */
 #define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8 /* Removed, do not use. */
+#define FS_ENCRYPTION_MODE_ADIANTUM		9
 
 struct fscrypt_policy {
 	__u8 version;

tools/include/uapi/linux/if_link.h

@@ -288,6 +288,7 @@ enum {
 	IFLA_BR_MCAST_IGMP_VERSION,
 	IFLA_BR_MCAST_MLD_VERSION,
 	IFLA_BR_VLAN_STATS_PER_PORT,
+	IFLA_BR_MULTI_BOOLOPT,
 	__IFLA_BR_MAX,
 };
 
@@ -533,6 +534,7 @@ enum {
 	IFLA_VXLAN_LABEL,
 	IFLA_VXLAN_GPE,
 	IFLA_VXLAN_TTL_INHERIT,
+	IFLA_VXLAN_DF,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -542,6 +544,14 @@ struct ifla_vxlan_port_range {
 	__be16	high;
 };
 
+enum ifla_vxlan_df {
+	VXLAN_DF_UNSET = 0,
+	VXLAN_DF_SET,
+	VXLAN_DF_INHERIT,
+	__VXLAN_DF_END,
+	VXLAN_DF_MAX = __VXLAN_DF_END - 1,
+};
+
 /* GENEVE section */
 enum {
 	IFLA_GENEVE_UNSPEC,
@@ -557,10 +567,19 @@ enum {
 	IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
 	IFLA_GENEVE_LABEL,
 	IFLA_GENEVE_TTL_INHERIT,
+	IFLA_GENEVE_DF,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
 
+enum ifla_geneve_df {
+	GENEVE_DF_UNSET = 0,
+	GENEVE_DF_SET,
+	GENEVE_DF_INHERIT,
+	__GENEVE_DF_END,
+	GENEVE_DF_MAX = __GENEVE_DF_END - 1,
+};
+
 /* PPP section */
 enum {
 	IFLA_PPP_UNSPEC,

tools/include/uapi/linux/in.h

@@ -266,10 +266,14 @@ struct sockaddr_in {
 
 #define	IN_CLASSD(a)		((((long int) (a)) & 0xf0000000) == 0xe0000000)
 #define	IN_MULTICAST(a)		IN_CLASSD(a)
-#define IN_MULTICAST_NET	0xF0000000
+#define	IN_MULTICAST_NET	0xe0000000
 
-#define	IN_EXPERIMENTAL(a)	((((long int) (a)) & 0xf0000000) == 0xf0000000)
-#define	IN_BADCLASS(a)		IN_EXPERIMENTAL((a))
+#define	IN_BADCLASS(a)		((((long int) (a) ) == 0xffffffff)
+#define	IN_EXPERIMENTAL(a)	IN_BADCLASS((a))
+
+#define	IN_CLASSE(a)		((((long int) (a)) & 0xf0000000) == 0xf0000000)
+#define	IN_CLASSE_NET		0xffffffff
+#define	IN_CLASSE_NSHIFT	0
 
 /* Address to accept any incoming messages. */
 #define	INADDR_ANY		((unsigned long int) 0x00000000)

tools/include/uapi/linux/kvm.h

@@ -492,6 +492,17 @@ struct kvm_dirty_log {
 	};
 };
 
+/* for KVM_CLEAR_DIRTY_LOG */
+struct kvm_clear_dirty_log {
+	__u32 slot;
+	__u32 num_pages;
+	__u64 first_page;
+	union {
+		void __user *dirty_bitmap; /* one bit per page */
+		__u64 padding2;
+	};
+};
+
 /* for KVM_SET_SIGNAL_MASK */
 struct kvm_signal_mask {
 	__u32 len;
@@ -975,6 +986,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163
 #define KVM_CAP_EXCEPTION_PAYLOAD 164
 #define KVM_CAP_ARM_VM_IPA_SIZE 165
+#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166
+#define KVM_CAP_HYPERV_CPUID 167
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1421,6 +1434,12 @@ struct kvm_enc_region {
 #define KVM_GET_NESTED_STATE         _IOWR(KVMIO, 0xbe, struct kvm_nested_state)
 #define KVM_SET_NESTED_STATE         _IOW(KVMIO,  0xbf, struct kvm_nested_state)
 
+/* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT */
+#define KVM_CLEAR_DIRTY_LOG          _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log)
+
+/* Available with KVM_CAP_HYPERV_CPUID */
+#define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */

tools/include/uapi/linux/mount.h

+#ifndef _UAPI_LINUX_MOUNT_H
+#define _UAPI_LINUX_MOUNT_H
+
+/*
+ * These are the fs-independent mount-flags: up to 32 flags are supported
+ *
+ * Usage of these is restricted within the kernel to core mount(2) code and
+ * callers of sys_mount() only.  Filesystems should be using the SB_*
+ * equivalent instead.
+ */
+#define MS_RDONLY	 1	/* Mount read-only */
+#define MS_NOSUID	 2	/* Ignore suid and sgid bits */
+#define MS_NODEV	 4	/* Disallow access to device special files */
+#define MS_NOEXEC	 8	/* Disallow program execution */
+#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
+#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_NOATIME	1024	/* Do not update access times. */
+#define MS_NODIRATIME	2048	/* Do not update directory access times */
+#define MS_BIND		4096
+#define MS_MOVE		8192
+#define MS_REC		16384
+#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
+				   MS_VERBOSE is deprecated. */
+#define MS_SILENT	32768
+#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
+#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
+#define MS_PRIVATE	(1<<18)	/* change to private */
+#define MS_SLAVE	(1<<19)	/* change to slave */
+#define MS_SHARED	(1<<20)	/* change to shared */
+#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
+#define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
+#define MS_I_VERSION	(1<<23) /* Update inode I_version field */
+#define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
+#define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
+
+/* These sb flags are internal to the kernel */
+#define MS_SUBMOUNT     (1<<26)
+#define MS_NOREMOTELOCK	(1<<27)
+#define MS_NOSEC	(1<<28)
+#define MS_BORN		(1<<29)
+#define MS_ACTIVE	(1<<30)
+#define MS_NOUSER	(1<<31)
+
+/*
+ * Superblock flags that can be altered by MS_REMOUNT
+ */
+#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
+			 MS_LAZYTIME)
+
+/*
+ * Old magic mount flag and mask
+ */
+#define MS_MGC_VAL 0xC0ED0000
+#define MS_MGC_MSK 0xffff0000
+
+#endif /* _UAPI_LINUX_MOUNT_H */

tools/include/uapi/linux/prctl.h

@@ -220,4 +220,12 @@ struct prctl_mm_map {
 # define PR_SPEC_DISABLE		(1UL << 2)
 # define PR_SPEC_FORCE_DISABLE		(1UL << 3)
 
+/* Reset arm64 pointer authentication keys */
+#define PR_PAC_RESET_KEYS		54
+# define PR_PAC_APIAKEY			(1UL << 0)
+# define PR_PAC_APIBKEY			(1UL << 1)
+# define PR_PAC_APDAKEY			(1UL << 2)
+# define PR_PAC_APDBKEY			(1UL << 3)
+# define PR_PAC_APGAKEY			(1UL << 4)
+
 #endif /* _LINUX_PRCTL_H */

tools/include/uapi/linux/vhost.h

@@ -11,94 +11,9 @@
  * device configuration.
  */
 
+#include <linux/vhost_types.h>
 #include <linux/types.h>
-#include <linux/compiler.h>
 #include <linux/ioctl.h>
-#include <linux/virtio_config.h>
-#include <linux/virtio_ring.h>
-
-struct vhost_vring_state {
-	unsigned int index;
-	unsigned int num;
-};
-
-struct vhost_vring_file {
-	unsigned int index;
-	int fd; /* Pass -1 to unbind from file. */
-
-};
-
-struct vhost_vring_addr {
-	unsigned int index;
-	/* Option flags. */
-	unsigned int flags;
-	/* Flag values: */
-	/* Whether log address is valid. If set enables logging. */
-#define VHOST_VRING_F_LOG 0
-
-	/* Start of array of descriptors (virtually contiguous) */
-	__u64 desc_user_addr;
-	/* Used structure address. Must be 32 bit aligned */
-	__u64 used_user_addr;
-	/* Available structure address. Must be 16 bit aligned */
-	__u64 avail_user_addr;
-	/* Logging support. */
-	/* Log writes to used structure, at offset calculated from specified
-	 * address. Address must be 32 bit aligned. */
-	__u64 log_guest_addr;
-};
-
-/* no alignment requirement */
-struct vhost_iotlb_msg {
-	__u64 iova;
-	__u64 size;
-	__u64 uaddr;
-#define VHOST_ACCESS_RO      0x1
-#define VHOST_ACCESS_WO      0x2
-#define VHOST_ACCESS_RW      0x3
-	__u8 perm;
-#define VHOST_IOTLB_MISS           1
-#define VHOST_IOTLB_UPDATE         2
-#define VHOST_IOTLB_INVALIDATE     3
-#define VHOST_IOTLB_ACCESS_FAIL    4
-	__u8 type;
-};
-
-#define VHOST_IOTLB_MSG 0x1
-#define VHOST_IOTLB_MSG_V2 0x2
-
-struct vhost_msg {
-	int type;
-	union {
-		struct vhost_iotlb_msg iotlb;
-		__u8 padding[64];
-	};
-};
-
-struct vhost_msg_v2 {
-	__u32 type;
-	__u32 reserved;
-	union {
-		struct vhost_iotlb_msg iotlb;
-		__u8 padding[64];
-	};
-};
-
-struct vhost_memory_region {
-	__u64 guest_phys_addr;
-	__u64 memory_size; /* bytes */
-	__u64 userspace_addr;
-	__u64 flags_padding; /* No flags are currently specified. */
-};
-
-/* All region addresses and sizes must be 4K aligned. */
-#define VHOST_PAGE_SIZE 0x1000
-
-struct vhost_memory {
-	__u32 nregions;
-	__u32 padding;
-	struct vhost_memory_region regions[0];
-};
 
 /* ioctls */
 
@@ -186,31 +101,7 @@ struct vhost_memory {
  * device.  This can be used to stop the ring (e.g. for migration). */
 #define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file)
 
-/* Feature bits */
-/* Log all write descriptors. Can be changed while device is active. */
-#define VHOST_F_LOG_ALL 26
-/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */
-#define VHOST_NET_F_VIRTIO_NET_HDR 27
-
-/* VHOST_SCSI specific definitions */
-
-/*
- * Used by QEMU userspace to ensure a consistent vhost-scsi ABI.
- *
- * ABI Rev 0: July 2012 version starting point for v3.6-rc merge candidate +
- *            RFC-v2 vhost-scsi userspace.  Add GET_ABI_VERSION ioctl usage
- * ABI Rev 1: January 2013. Ignore vhost_tpgt filed in struct vhost_scsi_target.
- *            All the targets under vhost_wwpn can be seen and used by guset.
- */
-
-#define VHOST_SCSI_ABI_VERSION	1
-
-struct vhost_scsi_target {
-	int abi_version;
-	char vhost_wwpn[224]; /* TRANSPORT_IQN_LEN */
-	unsigned short vhost_tpgt;
-	unsigned short reserved;
-};
+/* VHOST_SCSI specific defines */
 
 #define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target)
 #define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target)

tools/lib/traceevent/event-parse-api.c

@@ -194,13 +194,13 @@ void tep_set_page_size(struct tep_handle *pevent, int _page_size)
 }
 
 /**
- * tep_is_file_bigendian - get if the file is in big endian order
+ * tep_file_bigendian - get if the file is in big endian order
  * @pevent: a handle to the tep_handle
  *
  * This returns if the file is in big endian order
  * If @pevent is NULL, 0 is returned.
  */
-int tep_is_file_bigendian(struct tep_handle *pevent)
+int tep_file_bigendian(struct tep_handle *pevent)
 {
 	if(pevent)
 		return pevent->file_bigendian;

tools/lib/traceevent/event-parse-local.h

@@ -7,7 +7,7 @@
 #ifndef _PARSE_EVENTS_INT_H
 #define _PARSE_EVENTS_INT_H
 
-struct cmdline;
+struct tep_cmdline;
 struct cmdline_list;
 struct func_map;
 struct func_list;
@@ -36,7 +36,7 @@ struct tep_handle {
 	int long_size;
 	int page_size;
 
-	struct cmdline *cmdlines;
+	struct tep_cmdline *cmdlines;
 	struct cmdline_list *cmdlist;
 	int cmdline_count;
 

tools/lib/traceevent/event-parse.c

@@ -124,15 +124,15 @@ struct tep_print_arg *alloc_arg(void)
 	return calloc(1, sizeof(struct tep_print_arg));
 }
 
-struct cmdline {
+struct tep_cmdline {
 	char *comm;
 	int pid;
 };
 
 static int cmdline_cmp(const void *a, const void *b)
 {
-	const struct cmdline *ca = a;
-	const struct cmdline *cb = b;
+	const struct tep_cmdline *ca = a;
+	const struct tep_cmdline *cb = b;
 
 	if (ca->pid < cb->pid)
 		return -1;
@@ -152,7 +152,7 @@ static int cmdline_init(struct tep_handle *pevent)
 {
 	struct cmdline_list *cmdlist = pevent->cmdlist;
 	struct cmdline_list *item;
-	struct cmdline *cmdlines;
+	struct tep_cmdline *cmdlines;
 	int i;
 
 	cmdlines = malloc(sizeof(*cmdlines) * pevent->cmdline_count);
@@ -179,8 +179,8 @@ static int cmdline_init(struct tep_handle *pevent)
 
 static const char *find_cmdline(struct tep_handle *pevent, int pid)
 {
-	const struct cmdline *comm;
-	struct cmdline key;
+	const struct tep_cmdline *comm;
+	struct tep_cmdline key;
 
 	if (!pid)
 		return "<idle>";
@@ -208,8 +208,8 @@ static const char *find_cmdline(struct tep_handle *pevent, int pid)
  */
 int tep_pid_is_registered(struct tep_handle *pevent, int pid)
 {
-	const struct cmdline *comm;
-	struct cmdline key;
+	const struct tep_cmdline *comm;
+	struct tep_cmdline key;
 
 	if (!pid)
 		return 1;
@@ -232,11 +232,13 @@ int tep_pid_is_registered(struct tep_handle *pevent, int pid)
  * we must add this pid. This is much slower than when cmdlines
  * are added before the array is initialized.
  */
-static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid)
+static int add_new_comm(struct tep_handle *pevent,
+			const char *comm, int pid, bool override)
 {
-	struct cmdline *cmdlines = pevent->cmdlines;
-	const struct cmdline *cmdline;
-	struct cmdline key;
+	struct tep_cmdline *cmdlines = pevent->cmdlines;
+	struct tep_cmdline *cmdline;
+	struct tep_cmdline key;
+	char *new_comm;
 
 	if (!pid)
 		return 0;
@@ -247,9 +249,20 @@ static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid)
 	cmdline = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
 		       sizeof(*pevent->cmdlines), cmdline_cmp);
 	if (cmdline) {
+		if (!override) {
 			errno = EEXIST;
 			return -1;
 		}
+		new_comm = strdup(comm);
+		if (!new_comm) {
+			errno = ENOMEM;
+			return -1;
+		}
+		free(cmdline->comm);
+		cmdline->comm = new_comm;
+
+		return 0;
+	}
 
 	cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (pevent->cmdline_count + 1));
 	if (!cmdlines) {
@@ -275,21 +288,13 @@ static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid)
 	return 0;
 }
 
-/**
- * tep_register_comm - register a pid / comm mapping
- * @pevent: handle for the pevent
- * @comm: the command line to register
- * @pid: the pid to map the command line to
- *
- * This adds a mapping to search for command line names with
- * a given pid. The comm is duplicated.
- */
-int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
+static int _tep_register_comm(struct tep_handle *pevent,
+			      const char *comm, int pid, bool override)
 {
 	struct cmdline_list *item;
 
 	if (pevent->cmdlines)
-		return add_new_comm(pevent, comm, pid);
+		return add_new_comm(pevent, comm, pid, override);
 
 	item = malloc(sizeof(*item));
 	if (!item)
@@ -312,6 +317,40 @@ int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
 	return 0;
 }
 
+/**
+ * tep_register_comm - register a pid / comm mapping
+ * @pevent: handle for the pevent
+ * @comm: the command line to register
+ * @pid: the pid to map the command line to
+ *
+ * This adds a mapping to search for command line names with
+ * a given pid. The comm is duplicated. If a command with the same pid
+ * already exist, -1 is returned and errno is set to EEXIST
+ */
+int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
+{
+	return _tep_register_comm(pevent, comm, pid, false);
+}
+
+/**
+ * tep_override_comm - register a pid / comm mapping
+ * @pevent: handle for the pevent
+ * @comm: the command line to register
+ * @pid: the pid to map the command line to
+ *
+ * This adds a mapping to search for command line names with
+ * a given pid. The comm is duplicated. If a command with the same pid
+ * already exist, the command string is udapted with the new one
+ */
+int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid)
+{
+	if (!pevent->cmdlines && cmdline_init(pevent)) {
+		errno = ENOMEM;
+		return -1;
+	}
+	return _tep_register_comm(pevent, comm, pid, true);
+}
+
 int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock)
 {
 	pevent->trace_clock = strdup(trace_clock);
@@ -5226,18 +5265,6 @@ int tep_data_type(struct tep_handle *pevent, struct tep_record *rec)
 	return trace_parse_common_type(pevent, rec->data);
 }
 
-/**
- * tep_data_event_from_type - find the event by a given type
- * @pevent: a handle to the pevent
- * @type: the type of the event.
- *
- * This returns the event form a given @type;
- */
-struct tep_event *tep_data_event_from_type(struct tep_handle *pevent, int type)
-{
-	return tep_find_event(pevent, type);
-}
-
 /**
  * tep_data_pid - parse the PID from record
  * @pevent: a handle to the pevent
@@ -5292,8 +5319,8 @@ const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid)
 	return comm;
 }
 
-static struct cmdline *
-pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct cmdline *next)
+static struct tep_cmdline *
+pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline *next)
 {
 	struct cmdline_list *cmdlist = (struct cmdline_list *)next;
 
@@ -5305,7 +5332,7 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct cmdline *ne
 	while (cmdlist && strcmp(cmdlist->comm, comm) != 0)
 		cmdlist = cmdlist->next;
 
-	return (struct cmdline *)cmdlist;
+	return (struct tep_cmdline *)cmdlist;
 }
 
 /**
@@ -5321,10 +5348,10 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct cmdline *ne
  * next pid.
  * Also, it does a linear search, so it may be slow.
  */
-struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
-				       struct cmdline *next)
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
+					   struct tep_cmdline *next)
 {
-	struct cmdline *cmdline;
+	struct tep_cmdline *cmdline;
 
 	/*
 	 * If the cmdlines have not been converted yet, then use
@@ -5363,7 +5390,7 @@ struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *co
  * Returns the pid for a give cmdline. If @cmdline is NULL, then
  * -1 is returned.
  */
-int tep_cmdline_pid(struct tep_handle *pevent, struct cmdline *cmdline)
+int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline)
 {
 	struct cmdline_list *cmdlist = (struct cmdline_list *)cmdline;
 
@@ -6593,6 +6620,12 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id,
  *
  * If @id is >= 0, then it is used to find the event.
  * else @sys_name and @event_name are used.
+ *
+ * Returns:
+ *  TEP_REGISTER_SUCCESS_OVERWRITE if an existing handler is overwritten
+ *  TEP_REGISTER_SUCCESS if a new handler is registered successfully
+ *  negative TEP_ERRNO_... in case of an error
+ *
  */
 int tep_register_event_handler(struct tep_handle *pevent, int id,
 			       const char *sys_name, const char *event_name,
@@ -6610,7 +6643,7 @@ int tep_register_event_handler(struct tep_handle *pevent, int id,
 
 	event->handler = func;
 	event->context = context;
-	return 0;
+	return TEP_REGISTER_SUCCESS_OVERWRITE;
 
  not_found:
 	/* Save for later use. */
@@ -6640,7 +6673,7 @@ int tep_register_event_handler(struct tep_handle *pevent, int id,
 	pevent->handlers = handle;
 	handle->context = context;
 
-	return -1;
+	return TEP_REGISTER_SUCCESS;
 }
 
 static int handle_matches(struct event_handler *handler, int id,
@@ -6723,8 +6756,10 @@ struct tep_handle *tep_alloc(void)
 {
 	struct tep_handle *pevent = calloc(1, sizeof(*pevent));
 
-	if (pevent)
+	if (pevent) {
 		pevent->ref_count = 1;
+		pevent->host_bigendian = tep_host_bigendian();
+	}
 
 	return pevent;
 }

tools/lib/traceevent/event-parse.h

@@ -432,6 +432,7 @@ int tep_set_function_resolver(struct tep_handle *pevent,
 			      tep_func_resolver_t *func, void *priv);
 void tep_reset_function_resolver(struct tep_handle *pevent);
 int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid);
+int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid);
 int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock);
 int tep_register_function(struct tep_handle *pevent, char *name,
 			  unsigned long long addr, char *mod);
@@ -484,6 +485,11 @@ int tep_print_func_field(struct trace_seq *s, const char *fmt,
 			 struct tep_event *event, const char *name,
 			 struct tep_record *record, int err);
 
+enum tep_reg_handler {
+	TEP_REGISTER_SUCCESS = 0,
+	TEP_REGISTER_SUCCESS_OVERWRITE,
+};
+
 int tep_register_event_handler(struct tep_handle *pevent, int id,
 			       const char *sys_name, const char *event_name,
 			       tep_event_handler_func func, void *context);
@@ -520,15 +526,14 @@ tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record);
 void tep_data_lat_fmt(struct tep_handle *pevent,
 		      struct trace_seq *s, struct tep_record *record);
 int tep_data_type(struct tep_handle *pevent, struct tep_record *rec);
-struct tep_event *tep_data_event_from_type(struct tep_handle *pevent, int type);
 int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec);
 int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec);
 int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec);
 const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid);
-struct cmdline;
-struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
-				       struct cmdline *next);
-int tep_cmdline_pid(struct tep_handle *pevent, struct cmdline *cmdline);
+struct tep_cmdline;
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
+					   struct tep_cmdline *next);
+int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline);
 
 void tep_print_field(struct trace_seq *s, void *data,
 		     struct tep_format_field *field);
@@ -553,7 +558,7 @@ int tep_get_long_size(struct tep_handle *pevent);
 void tep_set_long_size(struct tep_handle *pevent, int long_size);
 int tep_get_page_size(struct tep_handle *pevent);
 void tep_set_page_size(struct tep_handle *pevent, int _page_size);
-int tep_is_file_bigendian(struct tep_handle *pevent);
+int tep_file_bigendian(struct tep_handle *pevent);
 void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian);
 int tep_is_host_bigendian(struct tep_handle *pevent);
 void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian);

tools/lib/traceevent/plugin_kvm.c

@@ -389,7 +389,7 @@ static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record,
 	 * We can only use the structure if file is of the same
 	 * endianness.
 	 */
-	if (tep_is_file_bigendian(event->pevent) ==
+	if (tep_file_bigendian(event->pevent) ==
 	    tep_is_host_bigendian(event->pevent)) {
 
 		trace_seq_printf(s, "%u q%u%s %s%s %spae %snxe %swp%s%s%s",

tools/lib/traceevent/trace-seq.c

@@ -100,7 +100,8 @@ static void expand_buffer(struct trace_seq *s)
  * @fmt: printf format string
  *
  * It returns 0 if the trace oversizes the buffer's free
- * space, 1 otherwise.
+ * space, the number of characters printed, or a negative
+ * value in case of an error.
  *
  * The tracer may use either sequence operations or its own
  * copy to user routines. To simplify formating of a trace
@@ -129,9 +130,10 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 		goto try_again;
 	}
 
+	if (ret > 0)
 		s->len += ret;
 
-	return 1;
+	return ret;
 }
 
 /**
@@ -139,6 +141,10 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
  * @s: trace sequence descriptor
  * @fmt: printf format string
  *
+ * It returns 0 if the trace oversizes the buffer's free
+ * space, the number of characters printed, or a negative
+ * value in case of an error.
+ * *
  * The tracer may use either sequence operations or its own
  * copy to user routines. To simplify formating of a trace
  * trace_seq_printf is used to store strings into a special
@@ -163,9 +169,10 @@ trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
 		goto try_again;
 	}
 
+	if (ret > 0)
 		s->len += ret;
 
-	return len;
+	return ret;
 }
 
 /**

tools/perf/Makefile.perf

@@ -524,12 +524,14 @@ $(arch_errno_name_array): $(arch_errno_tbl)
 
 all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
 
+# Create python binding output directory if not already present
+_dummy := $(shell [ -d '$(OUTPUT)python' ] || mkdir -p '$(OUTPUT)python')
+
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
 	$(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \
         CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
 	  $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
-	mkdir -p $(OUTPUT)python && \
 	cp $(PYTHON_EXTBUILD_LIB)perf*.so $(OUTPUT)python/
 
 please_set_SHELL_PATH_to_a_more_modern_shell:
@@ -660,12 +662,12 @@ $(OUTPUT)perf-%: %.o $(PERFLIBS)
 	$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS)
 
 ifndef NO_PERF_READ_VDSO32
-$(OUTPUT)perf-read-vdso32: perf-read-vdso.c util/find-vdso-map.c
+$(OUTPUT)perf-read-vdso32: perf-read-vdso.c util/find-map.c
 	$(QUIET_CC)$(CC) -m32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
 endif
 
 ifndef NO_PERF_READ_VDSOX32
-$(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-vdso-map.c
+$(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-map.c
 	$(QUIET_CC)$(CC) -mx32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
 endif
 

tools/perf/arch/arm/tests/Build

 libperf-y += regs_load.o
 libperf-y += dwarf-unwind.o
+libperf-y += vectors-page.o
 
 libperf-y += arch-tests.o

tools/perf/arch/arm/tests/arch-tests.c

@@ -10,6 +10,10 @@ struct test arch_tests[] = {
 		.func = test__dwarf_unwind,
 	},
 #endif
+	{
+		.desc = "Vectors page",
+		.func = test__vectors_page,
+	},
 	{
 		.func = NULL,
 	},

tools/perf/arch/arm/tests/vectors-page.c

+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <string.h>
+#include <linux/compiler.h>
+
+#include "debug.h"
+#include "tests/tests.h"
+#include "util/find-map.c"
+
+#define VECTORS__MAP_NAME "[vectors]"
+
+int test__vectors_page(struct test *test __maybe_unused,
+		       int subtest __maybe_unused)
+{
+	void *start, *end;
+
+	if (find_map(&start, &end, VECTORS__MAP_NAME)) {
+		pr_err("%s not found, is CONFIG_KUSER_HELPERS enabled?\n",
+		       VECTORS__MAP_NAME);
+		return TEST_FAIL;
+	}
+
+	return TEST_OK;
+}

tools/perf/arch/powerpc/Makefile

@@ -14,18 +14,25 @@ PERF_HAVE_JITDUMP := 1
 out    := $(OUTPUT)arch/powerpc/include/generated/asm
 header32 := $(out)/syscalls_32.c
 header64 := $(out)/syscalls_64.c
-sysdef := $(srctree)/tools/arch/powerpc/include/uapi/asm/unistd.h
-sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls/
+syskrn := $(srctree)/arch/powerpc/kernel/syscalls/syscall.tbl
+sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls
+sysdef := $(sysprf)/syscall.tbl
 systbl := $(sysprf)/mksyscalltbl
 
 # Create output directory if not already present
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 
 $(header64): $(sysdef) $(systbl)
-	$(Q)$(SHELL) '$(systbl)' '64' '$(CC)' $(sysdef) > $@
+	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
+	(diff -B $(sysdef) $(syskrn) >/dev/null) \
+	|| echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
+	$(Q)$(SHELL) '$(systbl)' '64' $(sysdef) > $@
 
 $(header32): $(sysdef) $(systbl)
-	$(Q)$(SHELL) '$(systbl)' '32' '$(CC)' $(sysdef) > $@
+	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
+	(diff -B $(sysdef) $(syskrn) >/dev/null) \
+	|| echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
+	$(Q)$(SHELL) '$(systbl)' '32' $(sysdef) > $@
 
 clean::
 	$(call QUIET_CLEAN, powerpc) $(RM) $(header32) $(header64)

tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl

@@ -9,10 +9,9 @@
 # Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
 
 wordsize=$1
-gcc=$2
-input=$3
+SYSCALL_TBL=$2
 
-if ! test -r $input; then
+if ! test -r $SYSCALL_TBL; then
 	echo "Could not read input file" >&2
 	exit 1
 fi
@@ -20,18 +19,21 @@ fi
 create_table()
 {
 	local wordsize=$1
-	local max_nr
+	local max_nr nr abi sc discard
+	max_nr=-1
+	nr=0
 
 	echo "static const char *syscalltbl_powerpc_${wordsize}[] = {"
-	while read sc nr; do
+	while read nr abi sc discard; do
+		if [ "$max_nr" -lt "$nr" ]; then
 			printf '\t[%d] = "%s",\n' $nr $sc
 			max_nr=$nr
+		fi
 	done
 	echo '};'
 	echo "#define SYSCALLTBL_POWERPC_${wordsize}_MAX_ID $max_nr"
 }
 
-$gcc -m${wordsize} -E -dM -x c  $input	       \
-	|sed -ne 's/^#define __NR_//p' \
-	|sort -t' ' -k2 -nu	       \
+grep -E "^[[:digit:]]+[[:space:]]+(common|spu|nospu|${wordsize})" $SYSCALL_TBL \
+	|sort -k1 -n                                                           \
 	|create_table ${wordsize}

tools/perf/builtin-stat.c

@@ -561,6 +561,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 					break;
 			}
 		}
+		if (child_pid != -1)
 			wait4(child_pid, &status, 0, &stat_config.ru_data);
 
 		if (workload_exec_errno) {

tools/perf/builtin-top.c

@@ -1028,12 +1028,7 @@ static int perf_top__start_counters(struct perf_top *top)
 
 static int callchain_param__setup_sample_type(struct callchain_param *callchain)
 {
-	if (!perf_hpp_list.sym) {
-		if (callchain->enabled) {
-			ui__error("Selected -g but \"sym\" not present in --sort/-s.");
-			return -EINVAL;
-		}
-	} else if (callchain->mode != CHAIN_NONE) {
+	if (callchain->mode != CHAIN_NONE) {
 		if (callchain_register_param(callchain) < 0) {
 			ui__error("Can't register callchain params.\n");
 			return -EINVAL;

tools/perf/builtin-trace.c

@@ -1758,6 +1758,7 @@ static int trace__printf_interrupted_entry(struct trace *trace)
 {
 	struct thread_trace *ttrace;
 	size_t printed;
+	int len;
 
 	if (trace->failure_only || trace->current == NULL)
 		return 0;
@@ -1768,9 +1769,14 @@ static int trace__printf_interrupted_entry(struct trace *trace)
 		return 0;
 
 	printed  = trace__fprintf_entry_head(trace, trace->current, 0, false, ttrace->entry_time, trace->output);
-	printed += fprintf(trace->output, ")%-*s ...\n", trace->args_alignment, ttrace->entry_str);
-	ttrace->entry_pending = false;
+	printed += len = fprintf(trace->output, "%s)", ttrace->entry_str);
+
+	if (len < trace->args_alignment - 4)
+		printed += fprintf(trace->output, "%-*s", trace->args_alignment - 4 - len, " ");
 
+	printed += fprintf(trace->output, " ...\n");
+
+	ttrace->entry_pending = false;
 	++trace->nr_events_printed;
 
 	return printed;
@@ -2026,9 +2032,10 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	if (ttrace->entry_pending) {
 		printed = fprintf(trace->output, "%s", ttrace->entry_str);
 	} else {
-		fprintf(trace->output, " ... [");
+		printed += fprintf(trace->output, " ... [");
 		color_fprintf(trace->output, PERF_COLOR_YELLOW, "continued");
-		fprintf(trace->output, "]: %s()", sc->name);
+		printed += 9;
+		printed += fprintf(trace->output, "]: %s()", sc->name);
 	}
 
 	printed++; /* the closing ')' */

tools/perf/check-headers.sh

@@ -10,6 +10,7 @@ include/uapi/linux/fs.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
 include/uapi/linux/in.h
+include/uapi/linux/mount.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/prctl.h
 include/uapi/linux/sched.h
@@ -49,7 +50,6 @@ arch/parisc/include/uapi/asm/errno.h
 arch/powerpc/include/uapi/asm/errno.h
 arch/sparc/include/uapi/asm/errno.h
 arch/x86/include/uapi/asm/errno.h
-arch/powerpc/include/uapi/asm/unistd.h
 include/asm-generic/bitops/arch_hweight.h
 include/asm-generic/bitops/const_hweight.h
 include/asm-generic/bitops/__fls.h

tools/perf/perf-read-vdso.c

@@ -5,17 +5,17 @@
 #define VDSO__MAP_NAME "[vdso]"
 
 /*
- * Include definition of find_vdso_map() also used in util/vdso.c for
+ * Include definition of find_map() also used in util/vdso.c for
  * building perf.
  */
-#include "util/find-vdso-map.c"
+#include "util/find-map.c"
 
 int main(void)
 {
 	void *start, *end;
 	size_t size, written;
 
-	if (find_vdso_map(&start, &end))
+	if (find_map(&start, &end, VDSO__MAP_NAME))
 		return 1;
 
 	size = end - start;

tools/perf/tests/shell/lib/probe_vfs_getname.sh

@@ -13,7 +13,8 @@ add_probe_vfs_getname() {
 	local verbose=$1
 	if [ $had_vfs_getname -eq 1 ] ; then
 		line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/')
-		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=result->name:string"
+		perf probe -q       "vfs_getname=getname_flags:${line} pathname=result->name:string" || \
+		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:string"
 	fi
 }
 

tools/perf/tests/tests.h

@@ -119,4 +119,9 @@ int test__arch_unwind_sample(struct perf_sample *sample,
 			     struct thread *thread);
 #endif
 #endif
+
+#if defined(__arm__)
+int test__vectors_page(struct test *test, int subtest);
+#endif
+
 #endif /* TESTS_H */

tools/perf/trace/beauty/mount_flags.sh

@@ -5,11 +5,11 @@
 
 printf "static const char *mount_flags[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
-egrep $regex ${header_dir}/fs.h | egrep -v '(MSK|VERBOSE|MGC_VAL)\>' | \
+egrep $regex ${header_dir}/mount.h | egrep -v '(MSK|VERBOSE|MGC_VAL)\>' | \
 	sed -r "s/$regex/\2 \2 \1/g" | sort -n | \
 	xargs printf "\t[%s ? (ilog2(%s) + 1) : 0] = \"%s\",\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+\(1<<([[:digit:]]+)\)[[:space:]]*.*'
-egrep $regex ${header_dir}/fs.h | \
+egrep $regex ${header_dir}/mount.h | \
 	sed -r "s/$regex/\2 \1/g" | \
 	xargs printf "\t[%s + 1] = \"%s\",\n"
 printf "};\n"

tools/perf/trace/beauty/prctl_option.sh

@@ -4,7 +4,7 @@
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *prctl_options[] = {\n"
-regex='^#define[[:space:]]+PR_([GS]ET\w+)[[:space:]]*([[:xdigit:]]+).*'
+regex='^#define[[:space:]]+PR_(\w+)[[:space:]]*([[:xdigit:]]+).*'
 egrep $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort -n | xargs printf "\t[%s] = \"%s\",\n"

tools/perf/util/annotate.c

@@ -1723,15 +1723,14 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
+		 " -l -d %s %s -C \"$1\" 2>/dev/null|grep -v \"$1:\"|expand",
 		 opts->objdump_path ?: "objdump",
 		 opts->disassembler_style ? "-M " : "",
 		 opts->disassembler_style ?: "",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
 		 opts->show_asm_raw ? "" : "--no-show-raw",
-		 opts->annotate_src ? "-S" : "",
-		 symfs_filename, symfs_filename);
+		 opts->annotate_src ? "-S" : "");
 
 	if (err < 0) {
 		pr_err("Failure allocating memory for the command to run\n");
@@ -1756,7 +1755,8 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		close(stdout_fd[0]);
 		dup2(stdout_fd[1], 1);
 		close(stdout_fd[1]);
-		execl("/bin/sh", "sh", "-c", command, NULL);
+		execl("/bin/sh", "sh", "-c", command, "--", symfs_filename,
+		      NULL);
 		perror(command);
 		exit(-1);
 	}

tools/perf/util/callchain.c

@@ -766,6 +766,7 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 			cnode->cycles_count += node->branch_flags.cycles;
 			cnode->iter_count += node->nr_loop_iter;
 			cnode->iter_cycles += node->iter_cycles;
+			cnode->from_count++;
 		}
 	}
 
@@ -1345,10 +1346,10 @@ static int branch_to_str(char *bf, int bfsize,
 static int branch_from_str(char *bf, int bfsize,
 			   u64 branch_count,
 			   u64 cycles_count, u64 iter_count,
-			   u64 iter_cycles)
+			   u64 iter_cycles, u64 from_count)
 {
 	int printed = 0, i = 0;
-	u64 cycles;
+	u64 cycles, v = 0;
 
 	cycles = cycles_count / branch_count;
 	if (cycles) {
@@ -1357,15 +1358,17 @@ static int branch_from_str(char *bf, int bfsize,
 				bf + printed, bfsize - printed);
 	}
 
-	if (iter_count) {
+	if (iter_count && from_count) {
+		v = iter_count / from_count;
+		if (v) {
 			printed += count_pri64_printf(i++, "iter",
-				iter_count,
-				bf + printed, bfsize - printed);
+					v, bf + printed, bfsize - printed);
 
 			printed += count_pri64_printf(i++, "avg_cycles",
 					iter_cycles / iter_count,
 					bf + printed, bfsize - printed);
 		}
+	}
 
 	if (i)
 		printed += scnprintf(bf + printed, bfsize - printed, ")");
@@ -1377,6 +1380,7 @@ static int counts_str_build(char *bf, int bfsize,
 			     u64 branch_count, u64 predicted_count,
 			     u64 abort_count, u64 cycles_count,
 			     u64 iter_count, u64 iter_cycles,
+			     u64 from_count,
 			     struct branch_type_stat *brtype_stat)
 {
 	int printed;
@@ -1389,7 +1393,8 @@ static int counts_str_build(char *bf, int bfsize,
 				predicted_count, abort_count, brtype_stat);
 	} else {
 		printed = branch_from_str(bf, bfsize, branch_count,
-				cycles_count, iter_count, iter_cycles);
+				cycles_count, iter_count, iter_cycles,
+				from_count);
 	}
 
 	if (!printed)
@@ -1402,13 +1407,14 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
 				   u64 branch_count, u64 predicted_count,
 				   u64 abort_count, u64 cycles_count,
 				   u64 iter_count, u64 iter_cycles,
+				   u64 from_count,
 				   struct branch_type_stat *brtype_stat)
 {
 	char str[256];
 
 	counts_str_build(str, sizeof(str), branch_count,
 			 predicted_count, abort_count, cycles_count,
-			 iter_count, iter_cycles, brtype_stat);
+			 iter_count, iter_cycles, from_count, brtype_stat);
 
 	if (fp)
 		return fprintf(fp, "%s", str);
@@ -1422,6 +1428,7 @@ int callchain_list_counts__printf_value(struct callchain_list *clist,
 	u64 branch_count, predicted_count;
 	u64 abort_count, cycles_count;
 	u64 iter_count, iter_cycles;
+	u64 from_count;
 
 	branch_count = clist->branch_count;
 	predicted_count = clist->predicted_count;
@@ -1429,11 +1436,12 @@ int callchain_list_counts__printf_value(struct callchain_list *clist,
 	cycles_count = clist->cycles_count;
 	iter_count = clist->iter_count;
 	iter_cycles = clist->iter_cycles;
+	from_count = clist->from_count;
 
 	return callchain_counts_printf(fp, bf, bfsize, branch_count,
 				       predicted_count, abort_count,
 				       cycles_count, iter_count, iter_cycles,
-				       &clist->brtype_stat);
+				       from_count, &clist->brtype_stat);
 }
 
 static void free_callchain_node(struct callchain_node *node)

tools/perf/util/callchain.h

@@ -118,6 +118,7 @@ struct callchain_list {
 		bool		has_children;
 	};
 	u64			branch_count;
+	u64			from_count;
 	u64			predicted_count;
 	u64			abort_count;
 	u64			cycles_count;

tools/perf/util/find-vdso-map.c → tools/perf/util/find-map.c

 // SPDX-License-Identifier: GPL-2.0
-static int find_vdso_map(void **start, void **end)
+static int find_map(void **start, void **end, const char *name)
 {
 	FILE *maps;
 	char line[128];
@@ -7,7 +7,7 @@ static int find_vdso_map(void **start, void **end)
 
 	maps = fopen("/proc/self/maps", "r");
 	if (!maps) {
-		fprintf(stderr, "vdso: cannot open maps\n");
+		fprintf(stderr, "cannot open maps\n");
 		return -1;
 	}
 
@@ -21,8 +21,7 @@ static int find_vdso_map(void **start, void **end)
 		if (m < 0)
 			continue;
 
-		if (!strncmp(&line[m], VDSO__MAP_NAME,
-			     sizeof(VDSO__MAP_NAME) - 1))
+		if (!strncmp(&line[m], name, strlen(name)))
 			found = 1;
 	}
 

tools/perf/util/machine.c

@@ -2005,7 +2005,7 @@ static void save_iterations(struct iterations *iter,
 {
 	int i;
 
-	iter->nr_loop_iter = nr;
+	iter->nr_loop_iter++;
 	iter->cycles = 0;
 
 	for (i = 0; i < nr; i++)

tools/perf/util/strbuf.c

@@ -109,7 +109,6 @@ static int strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap)
 			return ret;
 		}
 		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap_saved);
-		va_end(ap_saved);
 		if (len > strbuf_avail(sb)) {
 			pr_debug("this should not happen, your vsnprintf is broken");
 			va_end(ap_saved);

tools/perf/util/symbol.c

@@ -614,6 +614,7 @@ int modules__parse(const char *filename, void *arg,
 static bool symbol__is_idle(const char *name)
 {
 	const char * const idle_symbols[] = {
+		"arch_cpu_idle",
 		"cpu_idle",
 		"cpu_startup_entry",
 		"intel_idle",

tools/perf/util/vdso.c

@@ -18,10 +18,10 @@
 #include "debug.h"
 
 /*
- * Include definition of find_vdso_map() also used in perf-read-vdso.c for
+ * Include definition of find_map() also used in perf-read-vdso.c for
  * building perf-read-vdso32 and perf-read-vdsox32.
  */
-#include "find-vdso-map.c"
+#include "find-map.c"
 
 #define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX"
 
@@ -76,7 +76,7 @@ static char *get_file(struct vdso_file *vdso_file)
 	if (vdso_file->found)
 		return vdso_file->temp_file_name;
 
-	if (vdso_file->error || find_vdso_map(&start, &end))
+	if (vdso_file->error || find_map(&start, &end, VDSO__MAP_NAME))
 		return NULL;
 
 	size = end - start;

tools/thermal/tmon/Makefile

@@ -6,7 +6,7 @@ VERSION = 1.0
 
 BINDIR=usr/bin
 WARNFLAGS=-Wall -Wshadow -W -Wformat -Wimplicit-function-declaration -Wimplicit-int
-override CFLAGS+= -O1 ${WARNFLAGS}
+override CFLAGS+= $(call cc-option,-O3,-O1) ${WARNFLAGS}
 # Add "-fstack-protector" only if toolchain supports it.
 override CFLAGS+= $(call cc-option,-fstack-protector-strong)
 CC?= $(CROSS_COMPILE)gcc