diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index f35eb72739c0..9de8780ac8d9 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -646,10 +646,12 @@ struct perf_event_mmap_page {
  *
  *   PERF_RECORD_MISC_MMAP_DATA  - PERF_RECORD_MMAP* events
  *   PERF_RECORD_MISC_COMM_EXEC  - PERF_RECORD_COMM event
+ *   PERF_RECORD_MISC_FORK_EXEC  - PERF_RECORD_FORK event (perf internal)
  *   PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
  */
 #define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
+#define PERF_RECORD_MISC_FORK_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
  * These PERF_RECORD_MISC_* flags below are safely reused
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8c490130c4fb..84530ab358c3 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -750,7 +750,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event)
 	/*
 	 * Do not update time when cgroup is not active
 	 */
-       if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
+	if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
 		__update_cgrp_time(event->cgrp);
 }
 
diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
index 5072cbd15c82..dae1584cf017 100644
--- a/tools/arch/arm64/include/uapi/asm/unistd.h
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -16,5 +16,6 @@
  */
 
 #define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_NEW_STAT
 
 #include <asm-generic/unistd.h>
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 1b32b56a03d3..8c876c166ef2 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -634,6 +634,7 @@ struct kvm_ppc_cpu_char {
 
 #define KVM_REG_PPC_DEC_EXPIRY	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
 #define KVM_REG_PPC_ONLINE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
+#define KVM_REG_PPC_PTCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc0)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 9a50f02b9894..16511d97e8dc 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -160,6 +160,8 @@ struct kvm_s390_vm_cpu_subfunc {
 #define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW	1
 #define KVM_S390_VM_CRYPTO_DISABLE_AES_KW	2
 #define KVM_S390_VM_CRYPTO_DISABLE_DEA_KW	3
+#define KVM_S390_VM_CRYPTO_ENABLE_APIE		4
+#define KVM_S390_VM_CRYPTO_DISABLE_APIE		5
 
 /* kvm attributes for migration mode */
 #define KVM_S390_VM_MIGRATION_STOP	0
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 8a6eff9c27f3..dabfcf7c3941 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -300,10 +300,7 @@ struct kvm_vcpu_events {
 		__u8 injected;
 		__u8 nr;
 		__u8 has_error_code;
-		union {
-			__u8 pad;
-			__u8 pending;
-		};
+		__u8 pending;
 		__u32 error_code;
 	} exception;
 	struct {
@@ -387,6 +384,7 @@ struct kvm_sync_regs {
 
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
+#define KVM_STATE_NESTED_EVMCS		0x00000004
 
 #define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_SMM_VMXON	0x00000002
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index df4bedb9b01c..538546edbfbd 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -242,10 +242,12 @@ __SYSCALL(__NR_tee, sys_tee)
 /* fs/stat.c */
 #define __NR_readlinkat 78
 __SYSCALL(__NR_readlinkat, sys_readlinkat)
+#if defined(__ARCH_WANT_NEW_STAT) || defined(__ARCH_WANT_STAT64)
 #define __NR3264_fstatat 79
 __SC_3264(__NR3264_fstatat, sys_fstatat64, sys_newfstatat)
 #define __NR3264_fstat 80
 __SC_3264(__NR3264_fstat, sys_fstat64, sys_newfstat)
+#endif
 
 /* fs/sync.c */
 #define __NR_sync 81
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
new file mode 100644
index 000000000000..a441ea1bfe6d
--- /dev/null
+++ b/tools/include/uapi/linux/fs.h
@@ -0,0 +1,393 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_FS_H
+#define _UAPI_LINUX_FS_H
+
+/*
+ * This file has definitions for some important file table structures
+ * and constants and structures used by various generic file system
+ * ioctl's.  Please do not make any changes in this file before
+ * sending patches for review to linux-fsdevel@vger.kernel.org and
+ * linux-api@vger.kernel.org.
+ */
+
+#include <linux/limits.h>
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/*
+ * 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
+ * nr_file rlimit, so it's safe to set up a ridiculously high absolute
+ * upper limit on files-per-process.
+ *
+ * Some programs (notably those using select()) may have to be 
+ * recompiled to take full advantage of the new limits..  
+ */
+
+/* Fixed constants first: */
+#undef NR_OPEN
+#define INR_OPEN_CUR 1024	/* Initial setting for nfile rlimits */
+#define INR_OPEN_MAX 4096	/* Hard limit for nfile rlimits */
+
+#define BLOCK_SIZE_BITS 10
+#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
+
+#define SEEK_SET	0	/* seek relative to beginning of file */
+#define SEEK_CUR	1	/* seek relative to current file position */
+#define SEEK_END	2	/* seek relative to end of file */
+#define SEEK_DATA	3	/* seek to the next data */
+#define SEEK_HOLE	4	/* seek to the next hole */
+#define SEEK_MAX	SEEK_HOLE
+
+#define RENAME_NOREPLACE	(1 << 0)	/* Don't overwrite target */
+#define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
+#define RENAME_WHITEOUT		(1 << 2)	/* Whiteout source */
+
+struct file_clone_range {
+	__s64 src_fd;
+	__u64 src_offset;
+	__u64 src_length;
+	__u64 dest_offset;
+};
+
+struct fstrim_range {
+	__u64 start;
+	__u64 len;
+	__u64 minlen;
+};
+
+/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
+#define FILE_DEDUPE_RANGE_SAME		0
+#define FILE_DEDUPE_RANGE_DIFFERS	1
+
+/* from struct btrfs_ioctl_file_extent_same_info */
+struct file_dedupe_range_info {
+	__s64 dest_fd;		/* in - destination file */
+	__u64 dest_offset;	/* in - start of extent in destination */
+	__u64 bytes_deduped;	/* out - total # of bytes we were able
+				 * to dedupe from this file. */
+	/* status of this dedupe operation:
+	 * < 0 for error
+	 * == FILE_DEDUPE_RANGE_SAME if dedupe succeeds
+	 * == FILE_DEDUPE_RANGE_DIFFERS if data differs
+	 */
+	__s32 status;		/* out - see above description */
+	__u32 reserved;		/* must be zero */
+};
+
+/* from struct btrfs_ioctl_file_extent_same_args */
+struct file_dedupe_range {
+	__u64 src_offset;	/* in - start of extent in source */
+	__u64 src_length;	/* in - length of extent */
+	__u16 dest_count;	/* in - total elements in info array */
+	__u16 reserved1;	/* must be zero */
+	__u32 reserved2;	/* must be zero */
+	struct file_dedupe_range_info info[0];
+};
+
+/* And dynamically-tunable limits and defaults: */
+struct files_stat_struct {
+	unsigned long nr_files;		/* read only */
+	unsigned long nr_free_files;	/* read only */
+	unsigned long max_files;		/* tunable */
+};
+
+struct inodes_stat_t {
+	long nr_inodes;
+	long nr_unused;
+	long dummy[5];		/* padding for sysctl ABI compatibility */
+};
+
+
+#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.
+ */
+struct fsxattr {
+	__u32		fsx_xflags;	/* xflags field value (get/set) */
+	__u32		fsx_extsize;	/* extsize field value (get/set)*/
+	__u32		fsx_nextents;	/* nextents field value (get)	*/
+	__u32		fsx_projid;	/* project identifier (get/set) */
+	__u32		fsx_cowextsize;	/* CoW extsize field value (get/set)*/
+	unsigned char	fsx_pad[8];
+};
+
+/*
+ * Flags for the fsx_xflags field
+ */
+#define FS_XFLAG_REALTIME	0x00000001	/* data in realtime volume */
+#define FS_XFLAG_PREALLOC	0x00000002	/* preallocated file extents */
+#define FS_XFLAG_IMMUTABLE	0x00000008	/* file cannot be modified */
+#define FS_XFLAG_APPEND		0x00000010	/* all writes append */
+#define FS_XFLAG_SYNC		0x00000020	/* all writes synchronous */
+#define FS_XFLAG_NOATIME	0x00000040	/* do not update access time */
+#define FS_XFLAG_NODUMP		0x00000080	/* do not include in backups */
+#define FS_XFLAG_RTINHERIT	0x00000100	/* create with rt bit set */
+#define FS_XFLAG_PROJINHERIT	0x00000200	/* create with parents projid */
+#define FS_XFLAG_NOSYMLINKS	0x00000400	/* disallow symlink creation */
+#define FS_XFLAG_EXTSIZE	0x00000800	/* extent size allocator hint */
+#define FS_XFLAG_EXTSZINHERIT	0x00001000	/* inherit inode extent size */
+#define FS_XFLAG_NODEFRAG	0x00002000	/* do not defragment */
+#define FS_XFLAG_FILESTREAM	0x00004000	/* use filestream allocator */
+#define FS_XFLAG_DAX		0x00008000	/* use DAX for IO */
+#define FS_XFLAG_COWEXTSIZE	0x00010000	/* CoW extent size allocator hint */
+#define FS_XFLAG_HASATTR	0x80000000	/* no DIFLAG for this	*/
+
+/* the read-only stuff doesn't really belong here, but any other place is
+   probably as bad and I don't want to create yet another include file. */
+
+#define BLKROSET   _IO(0x12,93)	/* set device read-only (0 = read-write) */
+#define BLKROGET   _IO(0x12,94)	/* get read-only status (0 = read_write) */
+#define BLKRRPART  _IO(0x12,95)	/* re-read partition table */
+#define BLKGETSIZE _IO(0x12,96)	/* return device size /512 (long *arg) */
+#define BLKFLSBUF  _IO(0x12,97)	/* flush buffer cache */
+#define BLKRASET   _IO(0x12,98)	/* set read ahead for block device */
+#define BLKRAGET   _IO(0x12,99)	/* get current read ahead setting */
+#define BLKFRASET  _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */
+#define BLKFRAGET  _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */
+#define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */
+#define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */
+#define BLKSSZGET  _IO(0x12,104)/* get block device sector size */
+#if 0
+#define BLKPG      _IO(0x12,105)/* See blkpg.h */
+
+/* Some people are morons.  Do not use sizeof! */
+
+#define BLKELVGET  _IOR(0x12,106,size_t)/* elevator get */
+#define BLKELVSET  _IOW(0x12,107,size_t)/* elevator set */
+/* This was here just to show that the number is taken -
+   probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */
+#endif
+/* A jump here: 108-111 have been used for various private purposes. */
+#define BLKBSZGET  _IOR(0x12,112,size_t)
+#define BLKBSZSET  _IOW(0x12,113,size_t)
+#define BLKGETSIZE64 _IOR(0x12,114,size_t)	/* return device size in bytes (u64 *arg) */
+#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup)
+#define BLKTRACESTART _IO(0x12,116)
+#define BLKTRACESTOP _IO(0x12,117)
+#define BLKTRACETEARDOWN _IO(0x12,118)
+#define BLKDISCARD _IO(0x12,119)
+#define BLKIOMIN _IO(0x12,120)
+#define BLKIOOPT _IO(0x12,121)
+#define BLKALIGNOFF _IO(0x12,122)
+#define BLKPBSZGET _IO(0x12,123)
+#define BLKDISCARDZEROES _IO(0x12,124)
+#define BLKSECDISCARD _IO(0x12,125)
+#define BLKROTATIONAL _IO(0x12,126)
+#define BLKZEROOUT _IO(0x12,127)
+/*
+ * A jump here: 130-131 are reserved for zoned block devices
+ * (see uapi/linux/blkzoned.h)
+ */
+
+#define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
+#define FIBMAP	   _IO(0x00,1)	/* bmap access */
+#define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */
+#define FIFREEZE	_IOWR('X', 119, int)	/* Freeze */
+#define FITHAW		_IOWR('X', 120, int)	/* Thaw */
+#define FITRIM		_IOWR('X', 121, struct fstrim_range)	/* Trim */
+#define FICLONE		_IOW(0x94, 9, int)
+#define FICLONERANGE	_IOW(0x94, 13, struct file_clone_range)
+#define FIDEDUPERANGE	_IOWR(0x94, 54, struct file_dedupe_range)
+
+#define FSLABEL_MAX 256	/* Max chars for the interface; each fs may differ */
+
+#define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
+#define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
+#define	FS_IOC_GETVERSION		_IOR('v', 1, long)
+#define	FS_IOC_SETVERSION		_IOW('v', 2, long)
+#define FS_IOC_FIEMAP			_IOWR('f', 11, struct fiemap)
+#define FS_IOC32_GETFLAGS		_IOR('f', 1, int)
+#define FS_IOC32_SETFLAGS		_IOW('f', 2, int)
+#define FS_IOC32_GETVERSION		_IOR('v', 1, int)
+#define FS_IOC32_SETVERSION		_IOW('v', 2, int)
+#define FS_IOC_FSGETXATTR		_IOR('X', 31, struct fsxattr)
+#define FS_IOC_FSSETXATTR		_IOW('X', 32, struct fsxattr)
+#define FS_IOC_GETFSLABEL		_IOR(0x94, 49, char[FSLABEL_MAX])
+#define FS_IOC_SETFSLABEL		_IOW(0x94, 50, char[FSLABEL_MAX])
+
+/*
+ * File system encryption support
+ */
+/* Policy provided via an ioctl on the topmost directory */
+#define FS_KEY_DESCRIPTOR_SIZE	8
+
+#define FS_POLICY_FLAGS_PAD_4		0x00
+#define FS_POLICY_FLAGS_PAD_8		0x01
+#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
+
+/* Encryption algorithms */
+#define FS_ENCRYPTION_MODE_INVALID		0
+#define FS_ENCRYPTION_MODE_AES_256_XTS		1
+#define FS_ENCRYPTION_MODE_AES_256_GCM		2
+#define FS_ENCRYPTION_MODE_AES_256_CBC		3
+#define FS_ENCRYPTION_MODE_AES_256_CTS		4
+#define FS_ENCRYPTION_MODE_AES_128_CBC		5
+#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. */
+
+struct fscrypt_policy {
+	__u8 version;
+	__u8 contents_encryption_mode;
+	__u8 filenames_encryption_mode;
+	__u8 flags;
+	__u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
+};
+
+#define FS_IOC_SET_ENCRYPTION_POLICY	_IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_PWSALT	_IOW('f', 20, __u8[16])
+#define FS_IOC_GET_ENCRYPTION_POLICY	_IOW('f', 21, struct fscrypt_policy)
+
+/* Parameters for passing an encryption key into the kernel keyring */
+#define FS_KEY_DESC_PREFIX		"fscrypt:"
+#define FS_KEY_DESC_PREFIX_SIZE		8
+
+/* Structure that userspace passes to the kernel keyring */
+#define FS_MAX_KEY_SIZE			64
+
+struct fscrypt_key {
+	__u32 mode;
+	__u8 raw[FS_MAX_KEY_SIZE];
+	__u32 size;
+};
+
+/*
+ * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
+ *
+ * Note: for historical reasons, these flags were originally used and
+ * defined for use by ext2/ext3, and then other file systems started
+ * using these flags so they wouldn't need to write their own version
+ * of chattr/lsattr (which was shipped as part of e2fsprogs).  You
+ * should think twice before trying to use these flags in new
+ * contexts, or trying to assign these flags, since they are used both
+ * as the UAPI and the on-disk encoding for ext2/3/4.  Also, we are
+ * almost out of 32-bit flags.  :-)
+ *
+ * We have recently hoisted FS_IOC_FSGETXATTR / FS_IOC_FSSETXATTR from
+ * XFS to the generic FS level interface.  This uses a structure that
+ * has padding and hence has more room to grow, so it may be more
+ * appropriate for many new use cases.
+ *
+ * Please do not change these flags or interfaces before checking with
+ * linux-fsdevel@vger.kernel.org and linux-api@vger.kernel.org.
+ */
+#define	FS_SECRM_FL			0x00000001 /* Secure deletion */
+#define	FS_UNRM_FL			0x00000002 /* Undelete */
+#define	FS_COMPR_FL			0x00000004 /* Compress file */
+#define FS_SYNC_FL			0x00000008 /* Synchronous updates */
+#define FS_IMMUTABLE_FL			0x00000010 /* Immutable file */
+#define FS_APPEND_FL			0x00000020 /* writes to file may only append */
+#define FS_NODUMP_FL			0x00000040 /* do not dump file */
+#define FS_NOATIME_FL			0x00000080 /* do not update atime */
+/* Reserved for compression usage... */
+#define FS_DIRTY_FL			0x00000100
+#define FS_COMPRBLK_FL			0x00000200 /* One or more compressed clusters */
+#define FS_NOCOMP_FL			0x00000400 /* Don't compress */
+/* End compression flags --- maybe not all used */
+#define FS_ENCRYPT_FL			0x00000800 /* Encrypted file */
+#define FS_BTREE_FL			0x00001000 /* btree format dir */
+#define FS_INDEX_FL			0x00001000 /* hash-indexed directory */
+#define FS_IMAGIC_FL			0x00002000 /* AFS directory */
+#define FS_JOURNAL_DATA_FL		0x00004000 /* Reserved for ext3 */
+#define FS_NOTAIL_FL			0x00008000 /* file tail should not be merged */
+#define FS_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
+#define FS_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
+#define FS_HUGE_FILE_FL			0x00040000 /* Reserved for ext4 */
+#define FS_EXTENT_FL			0x00080000 /* Extents */
+#define FS_EA_INODE_FL			0x00200000 /* Inode used for large EA */
+#define FS_EOFBLOCKS_FL			0x00400000 /* Reserved for ext4 */
+#define FS_NOCOW_FL			0x00800000 /* Do not cow file */
+#define FS_INLINE_DATA_FL		0x10000000 /* Reserved for ext4 */
+#define FS_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
+#define FS_RESERVED_FL			0x80000000 /* reserved for ext2 lib */
+
+#define FS_FL_USER_VISIBLE		0x0003DFFF /* User visible flags */
+#define FS_FL_USER_MODIFIABLE		0x000380FF /* User modifiable flags */
+
+
+#define SYNC_FILE_RANGE_WAIT_BEFORE	1
+#define SYNC_FILE_RANGE_WRITE		2
+#define SYNC_FILE_RANGE_WAIT_AFTER	4
+
+/*
+ * Flags for preadv2/pwritev2:
+ */
+
+typedef int __bitwise __kernel_rwf_t;
+
+/* high priority request, poll if possible */
+#define RWF_HIPRI	((__force __kernel_rwf_t)0x00000001)
+
+/* per-IO O_DSYNC */
+#define RWF_DSYNC	((__force __kernel_rwf_t)0x00000002)
+
+/* per-IO O_SYNC */
+#define RWF_SYNC	((__force __kernel_rwf_t)0x00000004)
+
+/* per-IO, return -EAGAIN if operation would block */
+#define RWF_NOWAIT	((__force __kernel_rwf_t)0x00000008)
+
+/* per-IO O_APPEND */
+#define RWF_APPEND	((__force __kernel_rwf_t)0x00000010)
+
+/* mask of flags supported by the kernel */
+#define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
+			 RWF_APPEND)
+
+#endif /* _UAPI_LINUX_FS_H */
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 58faab897201..1debfa42cba1 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -287,6 +287,7 @@ enum {
 	IFLA_BR_MCAST_STATS_ENABLED,
 	IFLA_BR_MCAST_IGMP_VERSION,
 	IFLA_BR_MCAST_MLD_VERSION,
+	IFLA_BR_VLAN_STATS_PER_PORT,
 	__IFLA_BR_MAX,
 };
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 2875ce85b322..2b7a652c9fa4 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -420,13 +420,19 @@ struct kvm_run {
 struct kvm_coalesced_mmio_zone {
 	__u64 addr;
 	__u32 size;
-	__u32 pad;
+	union {
+		__u32 pad;
+		__u32 pio;
+	};
 };
 
 struct kvm_coalesced_mmio {
 	__u64 phys_addr;
 	__u32 len;
-	__u32 pad;
+	union {
+		__u32 pad;
+		__u32 pio;
+	};
 	__u8  data[8];
 };
 
@@ -751,6 +757,15 @@ struct kvm_ppc_resize_hpt {
 
 #define KVM_S390_SIE_PAGE_OFFSET 1
 
+/*
+ * On arm64, machine type can be used to request the physical
+ * address size for the VM. Bits[7-0] are reserved for the guest
+ * PA size shift (i.e, log2(PA_Size)). For backward compatibility,
+ * value 0 implies the default IPA size, 40bits.
+ */
+#define KVM_VM_TYPE_ARM_IPA_SIZE_MASK	0xffULL
+#define KVM_VM_TYPE_ARM_IPA_SIZE(x)		\
+	((x) & KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
 /*
  * ioctls for /dev/kvm fds:
  */
@@ -958,6 +973,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_HYPERV_SEND_IPI 161
 #define KVM_CAP_COALESCED_PIO 162
 #define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163
+#define KVM_CAP_EXCEPTION_PAYLOAD 164
+#define KVM_CAP_ARM_VM_IPA_SIZE 165
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index bfd5938fede6..d0f515d53299 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -28,7 +28,9 @@
 #define MAP_HUGE_2MB	HUGETLB_FLAG_ENCODE_2MB
 #define MAP_HUGE_8MB	HUGETLB_FLAG_ENCODE_8MB
 #define MAP_HUGE_16MB	HUGETLB_FLAG_ENCODE_16MB
+#define MAP_HUGE_32MB	HUGETLB_FLAG_ENCODE_32MB
 #define MAP_HUGE_256MB	HUGETLB_FLAG_ENCODE_256MB
+#define MAP_HUGE_512MB	HUGETLB_FLAG_ENCODE_512MB
 #define MAP_HUGE_1GB	HUGETLB_FLAG_ENCODE_1GB
 #define MAP_HUGE_2GB	HUGETLB_FLAG_ENCODE_2GB
 #define MAP_HUGE_16GB	HUGETLB_FLAG_ENCODE_16GB
diff --git a/tools/include/uapi/linux/netlink.h b/tools/include/uapi/linux/netlink.h
index 776bc92e9118..486ed1f0c0bc 100644
--- a/tools/include/uapi/linux/netlink.h
+++ b/tools/include/uapi/linux/netlink.h
@@ -155,6 +155,7 @@ enum nlmsgerr_attrs {
 #define NETLINK_LIST_MEMBERSHIPS	9
 #define NETLINK_CAP_ACK			10
 #define NETLINK_EXT_ACK			11
+#define NETLINK_DUMP_STRICT_CHK		12
 
 struct nl_pktinfo {
 	__u32	group;
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index f35eb72739c0..9de8780ac8d9 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -646,10 +646,12 @@ struct perf_event_mmap_page {
  *
  *   PERF_RECORD_MISC_MMAP_DATA  - PERF_RECORD_MMAP* events
  *   PERF_RECORD_MISC_COMM_EXEC  - PERF_RECORD_COMM event
+ *   PERF_RECORD_MISC_FORK_EXEC  - PERF_RECORD_FORK event (perf internal)
  *   PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
  */
 #define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
+#define PERF_RECORD_MISC_FORK_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
  * These PERF_RECORD_MISC_* flags below are safely reused
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index ed0a120d4f08..404d4b9ffe76 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -752,7 +752,7 @@ struct snd_timer_info {
 #define SNDRV_TIMER_PSFLG_EARLY_EVENT	(1<<2)	/* write early event to the poll queue */
 
 struct snd_timer_params {
-	unsigned int flags;		/* flags - SNDRV_MIXER_PSFLG_* */
+	unsigned int flags;		/* flags - SNDRV_TIMER_PSFLG_* */
 	unsigned int ticks;		/* requested resolution in ticks */
 	unsigned int queue_size;	/* total size of queue (32-1024) */
 	unsigned int reserved0;		/* reserved, was: failure locations */
diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index cb7154eccbdc..dbb9efbf718a 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -116,6 +116,7 @@ static int get_value(struct parse_opt_ctx_t *p,
 		case OPTION_INTEGER:
 		case OPTION_UINTEGER:
 		case OPTION_LONG:
+		case OPTION_ULONG:
 		case OPTION_U64:
 		default:
 			break;
@@ -166,6 +167,7 @@ static int get_value(struct parse_opt_ctx_t *p,
 		case OPTION_INTEGER:
 		case OPTION_UINTEGER:
 		case OPTION_LONG:
+		case OPTION_ULONG:
 		case OPTION_U64:
 		default:
 			break;
@@ -295,6 +297,22 @@ static int get_value(struct parse_opt_ctx_t *p,
 			return opterror(opt, "expects a numerical value", flags);
 		return 0;
 
+	case OPTION_ULONG:
+		if (unset) {
+			*(unsigned long *)opt->value = 0;
+			return 0;
+		}
+		if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+			*(unsigned long *)opt->value = opt->defval;
+			return 0;
+		}
+		if (get_arg(p, opt, flags, &arg))
+			return -1;
+		*(unsigned long *)opt->value = strtoul(arg, (char **)&s, 10);
+		if (*s)
+			return opterror(opt, "expects a numerical value", flags);
+		return 0;
+
 	case OPTION_U64:
 		if (unset) {
 			*(u64 *)opt->value = 0;
@@ -703,6 +721,7 @@ static void print_option_help(const struct option *opts, int full)
 	case OPTION_ARGUMENT:
 		break;
 	case OPTION_LONG:
+	case OPTION_ULONG:
 	case OPTION_U64:
 	case OPTION_INTEGER:
 	case OPTION_UINTEGER:
diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h
index 92fdbe1519f6..6ca2a8bfe716 100644
--- a/tools/lib/subcmd/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -25,6 +25,7 @@ enum parse_opt_type {
 	OPTION_STRING,
 	OPTION_INTEGER,
 	OPTION_LONG,
+	OPTION_ULONG,
 	OPTION_CALLBACK,
 	OPTION_U64,
 	OPTION_UINTEGER,
@@ -133,6 +134,7 @@ struct option {
 #define OPT_INTEGER(s, l, v, h)     { .type = OPTION_INTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
 #define OPT_UINTEGER(s, l, v, h)    { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) }
 #define OPT_LONG(s, l, v, h)        { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
+#define OPT_ULONG(s, l, v, h)        { .type = OPTION_ULONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned long *), .help = (h) }
 #define OPT_U64(s, l, v, h)         { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
 #define OPT_STRING(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h) }
 #define OPT_STRING_OPTARG(s, l, v, a, h, d) \
diff --git a/tools/perf/Documentation/build-xed.txt b/tools/perf/Documentation/build-xed.txt
new file mode 100644
index 000000000000..6222c1e7231f
--- /dev/null
+++ b/tools/perf/Documentation/build-xed.txt
@@ -0,0 +1,19 @@
+
+For --xed the xed tool is needed. Here is how to install it:
+
+  $ git clone https://github.com/intelxed/mbuild.git mbuild
+  $ git clone https://github.com/intelxed/xed
+  $ cd xed
+  $ ./mfile.py --share
+  $ ./mfile.py examples
+  $ sudo ./mfile.py --prefix=/usr/local install
+  $ sudo ldconfig
+  $ sudo cp obj/examples/xed /usr/local/bin
+
+Basic xed testing:
+
+  $ xed | head -3
+  ERROR: required argument(s) were missing
+  Copyright (C) 2017, Intel Corporation. All rights reserved.
+  XED version: [v10.0-328-g7d62c8c49b7b]
+  $
diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index 76971d2e4164..115eaacc455f 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -106,7 +106,7 @@ in transaction, respectively.
 While it is possible to create scripts to analyze the data, an alternative
 approach is available to export the data to a sqlite or postgresql database.
 Refer to script export-to-sqlite.py or export-to-postgresql.py for more details,
-and to script call-graph-from-sql.py for an example of using the database.
+and to script exported-sql-viewer.py for an example of using the database.
 
 There is also script intel-pt-events.py which provides an example of how to
 unpack the raw data for power events and PTWRITE.
diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index a3abe04c779d..c2182cbabde3 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -11,10 +11,11 @@
 		l	synthesize last branch entries (use with i or x)
 		s       skip initial number of events
 
-	The default is all events i.e. the same as --itrace=ibxwpe
+	The default is all events i.e. the same as --itrace=ibxwpe,
+	except for perf script where it is --itrace=ce
 
-	In addition, the period (default 100000) for instructions events
-	can be specified in units of:
+	In addition, the period (default 100000, except for perf script where it is 1)
+	for instructions events can be specified in units of:
 
 		i	instructions
 		t	ticks
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index afdafe2110a1..a2b37ce48094 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -383,6 +383,24 @@ include::itrace.txt[]
 	will be printed. Each entry has function name and file/line. Enabled by
 	default, disable with --no-inline.
 
+--insn-trace::
+	Show instruction stream for intel_pt traces. Combine with --xed to
+	show disassembly.
+
+--xed::
+	Run xed disassembler on output. Requires installing the xed disassembler.
+
+--call-trace::
+	Show call stream for intel_pt traces. The CPUs are interleaved, but
+	can be filtered with -C.
+
+--call-ret-trace::
+	Show call and return stream for intel_pt traces.
+
+--graph-function::
+	For itrace only show specified functions and their callees for
+	itrace. Multiple functions can be separated by comma.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 114fda12aa49..808b664343c9 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -242,6 +242,16 @@ Default is to monitor all CPUS.
 --hierarchy::
 	Enable hierarchy output.
 
+--overwrite::
+	Enable this to use just the most recent records, which helps in high core count
+	machines such as Knights Landing/Mill, but right now is disabled by default as
+	the pausing used in this technique is leading to loss of metadata events such
+	as PERF_RECORD_MMAP which makes 'perf top' unable to resolve samples, leading
+	to lots of unknown samples appearing on the UI. Enable this if you are in such
+	machines and profiling a workload that doesn't creates short lived threads and/or
+	doesn't uses many executable mmap operations. Work is being planed to solve
+	this situation, till then, this will remain disabled by default.
+
 --force::
 	Don't do ownership validation.
 
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 115db9e06ecd..e113450503d2 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -171,6 +171,11 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --kernel-syscall-graph::
 	 Show the kernel callchains on the syscall exit path.
 
+--max-events=N::
+	Stop after processing N events. Note that strace-like events are considered
+	only at exit time or when a syscall is interrupted, i.e. in those cases this
+	option is equivalent to the number of lines printed.
+
 --max-stack::
         Set the stack depth limit when parsing the callchain, anything
         beyond the specified depth will be ignored. Note that at this point
@@ -238,6 +243,68 @@ Trace syscalls, major and minor pagefaults:
   As you can see, there was major pagefault in python process, from
   CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so.
 
+Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
+
+  $ perf trace -e open* --max-events 4
+  [root@jouet perf]# trace -e open* --max-events 4
+  2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
+  2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
+  3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
+  4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
+  $
+
+Trace the first minor page fault when running a workload:
+
+  # perf trace -F min --max-stack=7 --max-events 1 sleep 1
+     0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
+                                       __clear_user ([kernel.kallsyms])
+                                       load_elf_binary ([kernel.kallsyms])
+                                       search_binary_handler ([kernel.kallsyms])
+                                       __do_execve_file.isra.33 ([kernel.kallsyms])
+                                       __x64_sys_execve ([kernel.kallsyms])
+                                       do_syscall_64 ([kernel.kallsyms])
+                                       entry_SYSCALL_64 ([kernel.kallsyms])
+  #
+
+Trace the next min page page fault to take place on the first CPU:
+
+  # perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
+     0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
+                                       js::gc::FreeSpan::initAsEmpty (inlined)
+                                       js::gc::Arena::setAsNotAllocated (inlined)
+                                       js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
+                                       js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
+                                       js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
+                                       JSThinInlineString::new_<(js::AllowGC)1> (inlined)
+                                       AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
+                                       js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
+                                       [0x18b26e6bc2bd] (/tmp/perf-17136.map)
+  #
+
+Trace the next two sched:sched_switch events, four block:*_plug events, the
+next block:*_unplug and the next three net:*dev_queue events, this last one
+with a backtrace of at most 16 entries, system wide:
+
+  # perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
+     0.000 :0/0 sched:sched_switch:swapper/2:0 [120] S ==> rcu_sched:10 [120]
+     0.015 rcu_sched/10 sched:sched_switch:rcu_sched:10 [120] R ==> swapper/2:0 [120]
+   254.198 irq/50-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=66
+                                       __dev_queue_xmit ([kernel.kallsyms])
+   273.977 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=78
+                                       __dev_queue_xmit ([kernel.kallsyms])
+   274.007 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ff00 len=78
+                                       __dev_queue_xmit ([kernel.kallsyms])
+  2930.140 kworker/u16:58/2722 block:block_plug:[kworker/u16:58]
+  2930.162 kworker/u16:58/2722 block:block_unplug:[kworker/u16:58] 1
+  4466.094 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
+  8050.123 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
+  8050.271 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
+  #
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script[1]
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 2f3bf025e305..3ccb4f0bf088 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -1,4 +1,5 @@
 include ../scripts/Makefile.include
+include ../scripts/Makefile.arch
 
 # The default target of this Makefile is...
 all:
@@ -385,6 +386,8 @@ export INSTALL SHELL_PATH
 SHELL = $(SHELL_PATH)
 
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
+asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
+arch_asm_uapi_dir := $(srctree)/tools/arch/$(ARCH)/include/uapi/asm/
 
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
@@ -460,6 +463,18 @@ madvise_behavior_tbl := $(srctree)/tools/perf/trace/beauty/madvise_behavior.sh
 $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_tbl)
 	$(Q)$(SHELL) '$(madvise_behavior_tbl)' $(madvise_hdr_dir) > $@
 
+mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c
+mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh
+
+$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(arch_asm_uapi_dir)/mman.h $(mmap_flags_tbl)
+	$(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
+
+mount_flags_array := $(beauty_outdir)/mount_flags_array.c
+mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
+
+$(mount_flags_array): $(linux_uapi_dir)/fs.h $(mount_flags_tbl)
+	$(Q)$(SHELL) '$(mount_flags_tbl)' $(linux_uapi_dir) > $@
+
 prctl_option_array := $(beauty_outdir)/prctl_option_array.c
 prctl_hdr_dir := $(srctree)/tools/include/uapi/linux/
 prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh
@@ -577,6 +592,8 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(socket_ipproto_array) \
 	$(vhost_virtio_ioctl_array) \
 	$(madvise_behavior_array) \
+	$(mmap_flags_array) \
+	$(mount_flags_array) \
 	$(perf_ioctl_array) \
 	$(prctl_option_array) \
 	$(arch_errno_name_array)
@@ -863,6 +880,8 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
 		$(OUTPUT)pmu-events/pmu-events.c \
 		$(OUTPUT)$(madvise_behavior_array) \
+		$(OUTPUT)$(mmap_flags_array) \
+		$(OUTPUT)$(mount_flags_array) \
 		$(OUTPUT)$(drm_ioctl_array) \
 		$(OUTPUT)$(pkey_alloc_access_rights_array) \
 		$(OUTPUT)$(sndrv_ctl_ioctl_array) \
diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
index 2dbb8cade048..c88fd32563eb 100755
--- a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
+++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
@@ -23,7 +23,7 @@ create_table_from_c()
 {
 	local sc nr last_sc
 
-	create_table_exe=`mktemp /tmp/create-table-XXXXXX`
+	create_table_exe=`mktemp ${TMPDIR:-/tmp}/create-table-XXXXXX`
 
 	{
 
diff --git a/tools/perf/arch/sparc/Makefile b/tools/perf/arch/sparc/Makefile
index 7fbca175099e..275dea7ff59a 100644
--- a/tools/perf/arch/sparc/Makefile
+++ b/tools/perf/arch/sparc/Makefile
@@ -1,3 +1,5 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
+
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/sparc/annotate/instructions.c b/tools/perf/arch/sparc/annotate/instructions.c
new file mode 100644
index 000000000000..2614c010c235
--- /dev/null
+++ b/tools/perf/arch/sparc/annotate/instructions.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+
+static int is_branch_cond(const char *cond)
+{
+	if (cond[0] == '\0')
+		return 1;
+
+	if (cond[0] == 'a' && cond[1] == '\0')
+		return 1;
+
+	if (cond[0] == 'c' &&
+	    (cond[1] == 'c' || cond[1] == 's') &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'e' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 'q' && cond[2] == '\0')))
+		return 1;
+
+	if (cond[0] == 'g' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 't' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == 'u' && cond[3] == '\0')))
+		return 1;
+
+	if (cond[0] == 'l' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 't' && cond[2] == '\0') ||
+	     (cond[1] == 'u' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == 'u' && cond[3] == '\0')))
+		return 1;
+
+	if (cond[0] == 'n' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 'e' && cond[2] == '\0') ||
+	     (cond[1] == 'z' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == 'g' && cond[3] == '\0')))
+		return 1;
+
+	if (cond[0] == 'b' &&
+	    cond[1] == 'p' &&
+	    cond[2] == 'o' &&
+	    cond[3] == 's' &&
+	    cond[4] == '\0')
+		return 1;
+
+	if (cond[0] == 'v' &&
+	    (cond[1] == 'c' || cond[1] == 's') &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'b' &&
+	    cond[1] == 'z' &&
+	    cond[2] == '\0')
+		return 1;
+
+	return 0;
+}
+
+static int is_branch_reg_cond(const char *cond)
+{
+	if ((cond[0] == 'n' || cond[0] == 'l') &&
+	    cond[1] == 'z' &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'z' &&
+	    cond[1] == '\0')
+		return 1;
+
+	if ((cond[0] == 'g' || cond[0] == 'l') &&
+	    cond[1] == 'e' &&
+	    cond[2] == 'z' &&
+	    cond[3] == '\0')
+		return 1;
+
+	if (cond[0] == 'g' &&
+	    cond[1] == 'z' &&
+	    cond[2] == '\0')
+		return 1;
+
+	return 0;
+}
+
+static int is_branch_float_cond(const char *cond)
+{
+	if (cond[0] == '\0')
+		return 1;
+
+	if ((cond[0] == 'a' || cond[0] == 'e' ||
+	     cond[0] == 'z' || cond[0] == 'g' ||
+	     cond[0] == 'l' || cond[0] == 'n' ||
+	     cond[0] == 'o' || cond[0] == 'u') &&
+	    cond[1] == '\0')
+		return 1;
+
+	if (((cond[0] == 'g' && cond[1] == 'e') ||
+	     (cond[0] == 'l' && (cond[1] == 'e' ||
+				 cond[1] == 'g')) ||
+	     (cond[0] == 'n' && (cond[1] == 'e' ||
+				 cond[1] == 'z')) ||
+	     (cond[0] == 'u' && (cond[1] == 'e' ||
+				 cond[1] == 'g' ||
+				 cond[1] == 'l'))) &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'u' &&
+	    (cond[1] == 'g' || cond[1] == 'l') &&
+	    cond[2] == 'e' &&
+	    cond[3] == '\0')
+		return 1;
+
+	return 0;
+}
+
+static struct ins_ops *sparc__associate_instruction_ops(struct arch *arch, const char *name)
+{
+	struct ins_ops *ops = NULL;
+
+	if (!strcmp(name, "call") ||
+	    !strcmp(name, "jmp") ||
+	    !strcmp(name, "jmpl")) {
+		ops = &call_ops;
+	} else if (!strcmp(name, "ret") ||
+		   !strcmp(name, "retl") ||
+		   !strcmp(name, "return")) {
+		ops = &ret_ops;
+	} else if (!strcmp(name, "mov")) {
+		ops = &mov_ops;
+	} else {
+		if (name[0] == 'c' &&
+		    (name[1] == 'w' || name[1] == 'x'))
+			name += 2;
+
+		if (name[0] == 'b') {
+			const char *cond = name + 1;
+
+			if (cond[0] == 'r') {
+				if (is_branch_reg_cond(cond + 1))
+					ops = &jump_ops;
+			} else if (is_branch_cond(cond)) {
+				ops = &jump_ops;
+			}
+		} else if (name[0] == 'f' && name[1] == 'b') {
+			if (is_branch_float_cond(name + 2))
+				ops = &jump_ops;
+		}
+	}
+
+	if (ops)
+		arch__associate_ins_ops(arch, name, ops);
+
+	return ops;
+}
+
+static int sparc__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
+{
+	if (!arch->initialized) {
+		arch->initialized = true;
+		arch->associate_instruction_ops = sparc__associate_instruction_ops;
+		arch->objdump.comment_char = '#';
+	}
+
+	return 0;
+}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0980dfe3396b..10cf889c6d75 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -592,6 +592,9 @@ static void record__init_features(struct record *rec)
 	if (!rec->opts.full_auxtrace)
 		perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
 
+	if (!(rec->opts.use_clockid && rec->opts.clockid_res_ns))
+		perf_header__clear_feat(&session->header, HEADER_CLOCKID);
+
 	perf_header__clear_feat(&session->header, HEADER_STAT);
 }
 
@@ -897,6 +900,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	record__init_features(rec);
 
+	if (rec->opts.use_clockid && rec->opts.clockid_res_ns)
+		session->header.env.clockid_res_ns = rec->opts.clockid_res_ns;
+
 	if (forks) {
 		err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
 						    argv, data->is_pipe,
@@ -1337,6 +1343,19 @@ static const struct clockid_map clockids[] = {
 	CLOCKID_END,
 };
 
+static int get_clockid_res(clockid_t clk_id, u64 *res_ns)
+{
+	struct timespec res;
+
+	*res_ns = 0;
+	if (!clock_getres(clk_id, &res))
+		*res_ns = res.tv_nsec + res.tv_sec * NSEC_PER_SEC;
+	else
+		pr_warning("WARNING: Failed to determine specified clock resolution.\n");
+
+	return 0;
+}
+
 static int parse_clockid(const struct option *opt, const char *str, int unset)
 {
 	struct record_opts *opts = (struct record_opts *)opt->value;
@@ -1360,7 +1379,7 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
 
 	/* if its a number, we're done */
 	if (sscanf(str, "%d", &opts->clockid) == 1)
-		return 0;
+		return get_clockid_res(opts->clockid, &opts->clockid_res_ns);
 
 	/* allow a "CLOCK_" prefix to the name */
 	if (!strncasecmp(str, "CLOCK_", 6))
@@ -1369,7 +1388,8 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
 	for (cm = clockids; cm->name; cm++) {
 		if (!strcasecmp(str, cm->name)) {
 			opts->clockid = cm->clockid;
-			return 0;
+			return get_clockid_res(opts->clockid,
+					       &opts->clockid_res_ns);
 		}
 	}
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 4da5e32b9e03..b5bc85bd0bbe 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -44,6 +44,7 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <unistd.h>
+#include <subcmd/pager.h>
 
 #include "sane_ctype.h"
 
@@ -912,7 +913,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
 
 static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 			    struct perf_insn *x, u8 *inbuf, int len,
-			    int insn, FILE *fp)
+			    int insn, FILE *fp, int *total_cycles)
 {
 	int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t#%s%s%s%s", ip,
 			      dump_insn(x, ip, inbuf, len, NULL),
@@ -921,7 +922,8 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 			      en->flags.in_tx ? " INTX" : "",
 			      en->flags.abort ? " ABORT" : "");
 	if (en->flags.cycles) {
-		printed += fprintf(fp, " %d cycles", en->flags.cycles);
+		*total_cycles += en->flags.cycles;
+		printed += fprintf(fp, " %d cycles [%d]", en->flags.cycles, *total_cycles);
 		if (insn)
 			printed += fprintf(fp, " %.2f IPC", (float)insn / en->flags.cycles);
 	}
@@ -978,6 +980,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 	u8 buffer[MAXBB];
 	unsigned off;
 	struct symbol *lastsym = NULL;
+	int total_cycles = 0;
 
 	if (!(br && br->nr))
 		return 0;
@@ -998,7 +1001,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 		printed += ip__fprintf_sym(br->entries[nr - 1].from, thread,
 					   x.cpumode, x.cpu, &lastsym, attr, fp);
 		printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
-					    &x, buffer, len, 0, fp);
+					    &x, buffer, len, 0, fp, &total_cycles);
 	}
 
 	/* Print all blocks */
@@ -1026,7 +1029,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 
 			printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
 			if (ip == end) {
-				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp);
+				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp,
+							    &total_cycles);
 				break;
 			} else {
 				printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip,
@@ -1104,6 +1108,35 @@ out:
 	return printed;
 }
 
+static const char *resolve_branch_sym(struct perf_sample *sample,
+				      struct perf_evsel *evsel,
+				      struct thread *thread,
+				      struct addr_location *al,
+				      u64 *ip)
+{
+	struct addr_location addr_al;
+	struct perf_event_attr *attr = &evsel->attr;
+	const char *name = NULL;
+
+	if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
+		if (sample_addr_correlates_sym(attr)) {
+			thread__resolve(thread, &addr_al, sample);
+			if (addr_al.sym)
+				name = addr_al.sym->name;
+			else
+				*ip = sample->addr;
+		} else {
+			*ip = sample->addr;
+		}
+	} else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
+		if (al->sym)
+			name = al->sym->name;
+		else
+			*ip = sample->ip;
+	}
+	return name;
+}
+
 static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 					   struct perf_evsel *evsel,
 					   struct thread *thread,
@@ -1111,7 +1144,6 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	size_t depth = thread_stack__depth(thread);
-	struct addr_location addr_al;
 	const char *name = NULL;
 	static int spacing;
 	int len = 0;
@@ -1125,22 +1157,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 	if (thread->ts && sample->flags & PERF_IP_FLAG_RETURN)
 		depth += 1;
 
-	if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
-		if (sample_addr_correlates_sym(attr)) {
-			thread__resolve(thread, &addr_al, sample);
-			if (addr_al.sym)
-				name = addr_al.sym->name;
-			else
-				ip = sample->addr;
-		} else {
-			ip = sample->addr;
-		}
-	} else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
-		if (al->sym)
-			name = al->sym->name;
-		else
-			ip = sample->ip;
-	}
+	name = resolve_branch_sym(sample, evsel, thread, al, &ip);
 
 	if (PRINT_FIELD(DSO) && !(PRINT_FIELD(IP) || PRINT_FIELD(ADDR))) {
 		dlen += fprintf(fp, "(");
@@ -1646,6 +1663,47 @@ static void perf_sample__fprint_metric(struct perf_script *script,
 	}
 }
 
+static bool show_event(struct perf_sample *sample,
+		       struct perf_evsel *evsel,
+		       struct thread *thread,
+		       struct addr_location *al)
+{
+	int depth = thread_stack__depth(thread);
+
+	if (!symbol_conf.graph_function)
+		return true;
+
+	if (thread->filter) {
+		if (depth <= thread->filter_entry_depth) {
+			thread->filter = false;
+			return false;
+		}
+		return true;
+	} else {
+		const char *s = symbol_conf.graph_function;
+		u64 ip;
+		const char *name = resolve_branch_sym(sample, evsel, thread, al,
+				&ip);
+		unsigned nlen;
+
+		if (!name)
+			return false;
+		nlen = strlen(name);
+		while (*s) {
+			unsigned len = strcspn(s, ",");
+			if (nlen == len && !strncmp(name, s, len)) {
+				thread->filter = true;
+				thread->filter_entry_depth = depth;
+				return true;
+			}
+			s += len;
+			if (*s == ',')
+				s++;
+		}
+		return false;
+	}
+}
+
 static void process_event(struct perf_script *script,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
 			  struct addr_location *al,
@@ -1660,6 +1718,9 @@ static void process_event(struct perf_script *script,
 	if (output[type].fields == 0)
 		return;
 
+	if (!show_event(sample, evsel, thread, al))
+		return;
+
 	++es->samples;
 
 	perf_sample__fprintf_start(sample, thread, evsel,
@@ -1737,6 +1798,9 @@ static void process_event(struct perf_script *script,
 
 	if (PRINT_FIELD(METRIC))
 		perf_sample__fprint_metric(script, thread, evsel, sample, fp);
+
+	if (verbose)
+		fflush(fp);
 }
 
 static struct scripting_ops	*scripting_ops;
@@ -3100,6 +3164,44 @@ static int perf_script__process_auxtrace_info(struct perf_session *session,
 #define perf_script__process_auxtrace_info 0
 #endif
 
+static int parse_insn_trace(const struct option *opt __maybe_unused,
+			    const char *str __maybe_unused,
+			    int unset __maybe_unused)
+{
+	parse_output_fields(NULL, "+insn,-event,-period", 0);
+	itrace_parse_synth_opts(opt, "i0ns", 0);
+	nanosecs = true;
+	return 0;
+}
+
+static int parse_xed(const struct option *opt __maybe_unused,
+		     const char *str __maybe_unused,
+		     int unset __maybe_unused)
+{
+	force_pager("xed -F insn: -A -64 | less");
+	return 0;
+}
+
+static int parse_call_trace(const struct option *opt __maybe_unused,
+			    const char *str __maybe_unused,
+			    int unset __maybe_unused)
+{
+	parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0);
+	itrace_parse_synth_opts(opt, "cewp", 0);
+	nanosecs = true;
+	return 0;
+}
+
+static int parse_callret_trace(const struct option *opt __maybe_unused,
+			    const char *str __maybe_unused,
+			    int unset __maybe_unused)
+{
+	parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent,+flags", 0);
+	itrace_parse_synth_opts(opt, "crewp", 0);
+	nanosecs = true;
+	return 0;
+}
+
 int cmd_script(int argc, const char **argv)
 {
 	bool show_full_info = false;
@@ -3109,7 +3211,10 @@ int cmd_script(int argc, const char **argv)
 	char *rec_script_path = NULL;
 	char *rep_script_path = NULL;
 	struct perf_session *session;
-	struct itrace_synth_opts itrace_synth_opts = { .set = false, };
+	struct itrace_synth_opts itrace_synth_opts = {
+		.set = false,
+		.default_no_sample = true,
+	};
 	char *script_path = NULL;
 	const char **__argv;
 	int i, j, err = 0;
@@ -3184,6 +3289,16 @@ int cmd_script(int argc, const char **argv)
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
 		   "only consider these symbols"),
+	OPT_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, NULL,
+			"Decode instructions from itrace", parse_insn_trace),
+	OPT_CALLBACK_OPTARG(0, "xed", NULL, NULL, NULL,
+			"Run xed disassembler on output", parse_xed),
+	OPT_CALLBACK_OPTARG(0, "call-trace", &itrace_synth_opts, NULL, NULL,
+			"Decode calls from from itrace", parse_call_trace),
+	OPT_CALLBACK_OPTARG(0, "call-ret-trace", &itrace_synth_opts, NULL, NULL,
+			"Decode calls and returns from itrace", parse_callret_trace),
+	OPT_STRING(0, "graph-function", &symbol_conf.graph_function, "symbol[,symbol...]",
+			"Only print symbols and callees with --call-trace/--call-ret-trace"),
 	OPT_STRING(0, "stop-bt", &symbol_conf.bt_stop_list_str, "symbol[,symbol...]",
 		   "Stop display of callgraph at these symbols"),
 	OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
@@ -3417,8 +3532,10 @@ int cmd_script(int argc, const char **argv)
 		exit(-1);
 	}
 
-	if (!script_name)
+	if (!script_name) {
 		setup_pager();
+		use_browser = 0;
+	}
 
 	session = perf_session__new(&data, false, &script.tool);
 	if (session == NULL)
@@ -3439,7 +3556,8 @@ int cmd_script(int argc, const char **argv)
 	script.session = session;
 	script__setup_sample_type(&script);
 
-	if (output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT)
+	if ((output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT) ||
+	    symbol_conf.graph_function)
 		itrace_synth_opts.thread_stack = true;
 
 	session->itrace_synth_opts = &itrace_synth_opts;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index b86aba1c8028..d1028d7755bb 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -409,6 +409,28 @@ static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
 	return leader;
 }
 
+static bool is_target_alive(struct target *_target,
+			    struct thread_map *threads)
+{
+	struct stat st;
+	int i;
+
+	if (!target__has_task(_target))
+		return true;
+
+	for (i = 0; i < threads->nr; i++) {
+		char path[PATH_MAX];
+
+		scnprintf(path, PATH_MAX, "%s/%d", procfs__mountpoint(),
+			  threads->map[i].pid);
+
+		if (!stat(path, &st))
+			return true;
+	}
+
+	return false;
+}
+
 static int __run_perf_stat(int argc, const char **argv, int run_idx)
 {
 	int interval = stat_config.interval;
@@ -579,6 +601,8 @@ try_again:
 		enable_counters();
 		while (!done) {
 			nanosleep(&ts, NULL);
+			if (!is_target_alive(&target, evsel_list->threads))
+				break;
 			if (timeout)
 				break;
 			if (interval) {
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index d21d8751e749..b2838de13de0 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1134,11 +1134,6 @@ static int __cmd_top(struct perf_top *top)
         if (!target__none(&opts->target))
                 perf_evlist__enable(top->evlist);
 
-	/* Wait for a minimal set of events before starting the snapshot */
-	perf_evlist__poll(top->evlist, 100);
-
-	perf_top__mmap_read(top);
-
 	ret = -1;
 	if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
 							    display_thread), top)) {
@@ -1156,6 +1151,11 @@ static int __cmd_top(struct perf_top *top)
 		}
 	}
 
+	/* Wait for a minimal set of events before starting the snapshot */
+	perf_evlist__poll(top->evlist, 100);
+
+	perf_top__mmap_read(top);
+
 	while (!done) {
 		u64 hits = top->samples;
 
@@ -1257,7 +1257,14 @@ int cmd_top(int argc, const char **argv)
 				.uses_mmap   = true,
 			},
 			.proc_map_timeout    = 500,
-			.overwrite	= 1,
+			/*
+			 * FIXME: This will lose PERF_RECORD_MMAP and other metadata
+			 * when we pause, fix that and reenable. Probably using a
+			 * separate evlist with a dummy event, i.e. a non-overwrite
+			 * ring buffer just for metadata events, while PERF_RECORD_SAMPLE
+			 * stays in overwrite mode. -acme
+			 * */
+			.overwrite	= 0,
 		},
 		.max_stack	     = sysctl__max_stack(),
 		.annotation_opts     = annotation__default_options,
@@ -1372,6 +1379,8 @@ int cmd_top(int argc, const char **argv)
 		    "Show raw trace event output (do not use print fmt or plugins)"),
 	OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
 		    "Show entries in a hierarchy"),
+	OPT_BOOLEAN(0, "overwrite", &top.record_opts.overwrite,
+		    "Use a backward ring buffer, default: no"),
 	OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"),
 	OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize,
 			"number of thread to run event synthesize"),
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 90289f31dd87..dc8a6c4986ce 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -89,6 +89,8 @@ struct trace {
 	u64			base_time;
 	FILE			*output;
 	unsigned long		nr_events;
+	unsigned long		nr_events_printed;
+	unsigned long		max_events;
 	struct strlist		*ev_qualifier;
 	struct {
 		size_t		nr;
@@ -612,6 +614,7 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
 
 struct syscall_arg_fmt {
 	size_t	   (*scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
+	unsigned long (*mask_val)(struct syscall_arg *arg, unsigned long val);
 	void	   *parm;
 	const char *name;
 	bool	   show_zero;
@@ -723,6 +726,10 @@ static struct syscall_fmt {
 	  .arg = { [0] = { .scnprintf = SCA_HEX,	/* addr */ },
 		   [2] = { .scnprintf = SCA_MMAP_PROT,	/* prot */ },
 		   [3] = { .scnprintf = SCA_MMAP_FLAGS,	/* flags */ }, }, },
+	{ .name	    = "mount",
+	  .arg = { [0] = { .scnprintf = SCA_FILENAME, /* dev_name */ },
+		   [3] = { .scnprintf = SCA_MOUNT_FLAGS, /* flags */
+			   .mask_val  = SCAMV_MOUNT_FLAGS, /* flags */ }, }, },
 	{ .name	    = "mprotect",
 	  .arg = { [0] = { .scnprintf = SCA_HEX,	/* start */ },
 		   [2] = { .scnprintf = SCA_MMAP_PROT,	/* prot */ }, }, },
@@ -832,7 +839,8 @@ static struct syscall_fmt {
 	  .arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
 	{ .name	    = "tkill",
 	  .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
-	{ .name     = "umount2", .alias = "umount", },
+	{ .name     = "umount2", .alias = "umount",
+	  .arg = { [0] = { .scnprintf = SCA_FILENAME, /* name */ }, }, },
 	{ .name	    = "uname", .alias = "newuname", },
 	{ .name	    = "unlinkat",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
@@ -856,6 +864,18 @@ static struct syscall_fmt *syscall_fmt__find(const char *name)
 	return bsearch(name, syscall_fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp);
 }
 
+static struct syscall_fmt *syscall_fmt__find_by_alias(const char *alias)
+{
+	int i, nmemb = ARRAY_SIZE(syscall_fmts);
+
+	for (i = 0; i < nmemb; ++i) {
+		if (syscall_fmts[i].alias && strcmp(syscall_fmts[i].alias, alias) == 0)
+			return &syscall_fmts[i];
+	}
+
+	return NULL;
+}
+
 /*
  * is_exit: is this "exit" or "exit_group"?
  * is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter.
@@ -1485,6 +1505,19 @@ static size_t syscall__scnprintf_name(struct syscall *sc, char *bf, size_t size,
 	return scnprintf(bf, size, "arg%d: ", arg->idx);
 }
 
+/*
+ * Check if the value is in fact zero, i.e. mask whatever needs masking, such
+ * as mount 'flags' argument that needs ignoring some magic flag, see comment
+ * in tools/perf/trace/beauty/mount_flags.c
+ */
+static unsigned long syscall__mask_val(struct syscall *sc, struct syscall_arg *arg, unsigned long val)
+{
+	if (sc->arg_fmt && sc->arg_fmt[arg->idx].mask_val)
+		return sc->arg_fmt[arg->idx].mask_val(arg, val);
+
+	return val;
+}
+
 static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size,
 				     struct syscall_arg *arg, unsigned long val)
 {
@@ -1533,6 +1566,11 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
 				continue;
 
 			val = syscall_arg__val(&arg, arg.idx);
+			/*
+			 * Some syscall args need some mask, most don't and
+			 * return val untouched.
+			 */
+			val = syscall__mask_val(sc, &arg, val);
 
 			/*
  			 * Suppress this argument if its value is zero and
@@ -1664,6 +1702,8 @@ static int trace__printf_interrupted_entry(struct trace *trace)
 	printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str);
 	ttrace->entry_pending = false;
 
+	++trace->nr_events_printed;
+
 	return printed;
 }
 
@@ -1810,12 +1850,14 @@ static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evse
 	int max_stack = evsel->attr.sample_max_stack ?
 			evsel->attr.sample_max_stack :
 			trace->max_stack;
+	int err;
 
-	if (machine__resolve(trace->host, &al, sample) < 0 ||
-	    thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack))
+	if (machine__resolve(trace->host, &al, sample) < 0)
 		return -1;
 
-	return 0;
+	err = thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack);
+	addr_location__put(&al);
+	return err;
 }
 
 static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sample)
@@ -1940,6 +1982,13 @@ errno_print: {
 
 	fputc('\n', trace->output);
 
+	/*
+	 * We only consider an 'event' for the sake of --max-events a non-filtered
+	 * sys_enter + sys_exit and other tracepoint events.
+	 */
+	if (++trace->nr_events_printed == trace->max_events && trace->max_events != ULONG_MAX)
+		interrupted = true;
+
 	if (callchain_ret > 0)
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
@@ -2072,14 +2121,25 @@ static void bpf_output__fprintf(struct trace *trace,
 {
 	binary__fprintf(sample->raw_data, sample->raw_size, 8,
 			bpf_output__printer, NULL, trace->output);
+	++trace->nr_events_printed;
 }
 
 static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 				union perf_event *event __maybe_unused,
 				struct perf_sample *sample)
 {
-	struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+	struct thread *thread;
 	int callchain_ret = 0;
+	/*
+	 * Check if we called perf_evsel__disable(evsel) due to, for instance,
+	 * this event's max_events having been hit and this is an entry coming
+	 * from the ring buffer that we should discard, since the max events
+	 * have already been considered/printed.
+	 */
+	if (evsel->disabled)
+		return 0;
+
+	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 
 	if (sample->callchain) {
 		callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
@@ -2127,6 +2187,12 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 			event_format__fprintf(evsel->tp_format, sample->cpu,
 					      sample->raw_data, sample->raw_size,
 					      trace->output);
+			++trace->nr_events_printed;
+
+			if (evsel->max_events != ULONG_MAX && ++evsel->nr_events_printed == evsel->max_events) {
+				perf_evsel__disable(evsel);
+				perf_evsel__close(evsel);
+			}
 		}
 	}
 
@@ -2137,8 +2203,8 @@ newline:
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
 		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
-	thread__put(thread);
 out:
+	thread__put(thread);
 	return 0;
 }
 
@@ -2225,6 +2291,8 @@ static int trace__pgfault(struct trace *trace,
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
 		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
+
+	++trace->nr_events_printed;
 out:
 	err = 0;
 out_put:
@@ -2402,6 +2470,9 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st
 		tracepoint_handler handler = evsel->handler;
 		handler(trace, evsel, event, sample);
 	}
+
+	if (trace->nr_events_printed >= trace->max_events && trace->max_events != ULONG_MAX)
+		interrupted = true;
 }
 
 static int trace__add_syscall_newtp(struct trace *trace)
@@ -2706,7 +2777,7 @@ next_event:
 		int timeout = done ? 100 : -1;
 
 		if (!draining && perf_evlist__poll(evlist, timeout) > 0) {
-			if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP) == 0)
+			if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP | POLLNVAL) == 0)
 				draining = true;
 
 			goto again;
@@ -3138,6 +3209,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 	int len = strlen(str) + 1, err = -1, list, idx;
 	char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
 	char group_name[PATH_MAX];
+	struct syscall_fmt *fmt;
 
 	if (strace_groups_dir == NULL)
 		return -1;
@@ -3155,12 +3227,19 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 		if (syscalltbl__id(trace->sctbl, s) >= 0 ||
 		    syscalltbl__strglobmatch_first(trace->sctbl, s, &idx) >= 0) {
 			list = 1;
+			goto do_concat;
+		}
+
+		fmt = syscall_fmt__find_by_alias(s);
+		if (fmt != NULL) {
+			list = 1;
+			s = fmt->name;
 		} else {
 			path__join(group_name, sizeof(group_name), strace_groups_dir, s);
 			if (access(group_name, R_OK) == 0)
 				list = 1;
 		}
-
+do_concat:
 		if (lists[list]) {
 			sprintf(lists[list] + strlen(lists[list]), ",%s", s);
 		} else {
@@ -3249,6 +3328,7 @@ int cmd_trace(int argc, const char **argv)
 		.trace_syscalls = false,
 		.kernel_syscallchains = false,
 		.max_stack = UINT_MAX,
+		.max_events = ULONG_MAX,
 	};
 	const char *output_name = NULL;
 	const struct option trace_options[] = {
@@ -3301,6 +3381,8 @@ int cmd_trace(int argc, const char **argv)
 		     &record_parse_callchain_opt),
 	OPT_BOOLEAN(0, "kernel-syscall-graph", &trace.kernel_syscallchains,
 		    "Show the kernel callchains on the syscall exit path"),
+	OPT_ULONG(0, "max-events", &trace.max_events,
+		"Set the maximum number of events to print, exit after that is reached. "),
 	OPT_UINTEGER(0, "min-stack", &trace.min_stack,
 		     "Set the minimum stack depth when parsing the callchain, "
 		     "anything below the specified depth will be ignored."),
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index c72cc73a6b09..9531f7bd7d9b 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -5,6 +5,7 @@ HEADERS='
 include/uapi/drm/drm.h
 include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
+include/uapi/linux/fs.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
 include/uapi/linux/in.h
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 21bf7f5a3cf5..0ed4a34c74c4 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -81,6 +81,7 @@ struct record_opts {
 	unsigned     initial_delay;
 	bool         use_clockid;
 	clockid_t    clockid;
+	u64          clockid_res_ns;
 	unsigned int proc_map_timeout;
 };
 
diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
deleted file mode 100644
index b494a67a1c67..000000000000
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ /dev/null
@@ -1,339 +0,0 @@
-#!/usr/bin/python2
-# call-graph-from-sql.py: create call-graph from sql database
-# Copyright (c) 2014-2017, Intel Corporation.
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-# more details.
-
-# To use this script you will need to have exported data using either the
-# export-to-sqlite.py or the export-to-postgresql.py script.  Refer to those
-# scripts for details.
-#
-# Following on from the example in the export scripts, a
-# call-graph can be displayed for the pt_example database like this:
-#
-#	python tools/perf/scripts/python/call-graph-from-sql.py pt_example
-#
-# Note that for PostgreSQL, this script supports connecting to remote databases
-# by setting hostname, port, username, password, and dbname e.g.
-#
-#	python tools/perf/scripts/python/call-graph-from-sql.py "hostname=myhost username=myuser password=mypassword dbname=pt_example"
-#
-# The result is a GUI window with a tree representing a context-sensitive
-# call-graph.  Expanding a couple of levels of the tree and adjusting column
-# widths to suit will display something like:
-#
-#                                         Call Graph: pt_example
-# Call Path                          Object      Count   Time(ns)  Time(%)  Branch Count   Branch Count(%)
-# v- ls
-#     v- 2638:2638
-#         v- _start                  ld-2.19.so    1     10074071   100.0         211135            100.0
-#           |- unknown               unknown       1        13198     0.1              1              0.0
-#           >- _dl_start             ld-2.19.so    1      1400980    13.9          19637              9.3
-#           >- _d_linit_internal     ld-2.19.so    1       448152     4.4          11094              5.3
-#           v-__libc_start_main@plt  ls            1      8211741    81.5         180397             85.4
-#              >- _dl_fixup          ld-2.19.so    1         7607     0.1            108              0.1
-#              >- __cxa_atexit       libc-2.19.so  1        11737     0.1             10              0.0
-#              >- __libc_csu_init    ls            1        10354     0.1             10              0.0
-#              |- _setjmp            libc-2.19.so  1            0     0.0              4              0.0
-#              v- main               ls            1      8182043    99.6         180254             99.9
-#
-# Points to note:
-#	The top level is a command name (comm)
-#	The next level is a thread (pid:tid)
-#	Subsequent levels are functions
-#	'Count' is the number of calls
-#	'Time' is the elapsed time until the function returns
-#	Percentages are relative to the level above
-#	'Branch Count' is the total number of branches for that function and all
-#       functions that it calls
-
-import sys
-from PySide.QtCore import *
-from PySide.QtGui import *
-from PySide.QtSql import *
-from decimal import *
-
-class TreeItem():
-
-	def __init__(self, db, row, parent_item):
-		self.db = db
-		self.row = row
-		self.parent_item = parent_item
-		self.query_done = False;
-		self.child_count = 0
-		self.child_items = []
-		self.data = ["", "", "", "", "", "", ""]
-		self.comm_id = 0
-		self.thread_id = 0
-		self.call_path_id = 1
-		self.branch_count = 0
-		self.time = 0
-		if not parent_item:
-			self.setUpRoot()
-
-	def setUpRoot(self):
-		self.query_done = True
-		query = QSqlQuery(self.db)
-		ret = query.exec_('SELECT id, comm FROM comms')
-		if not ret:
-			raise Exception("Query failed: " + query.lastError().text())
-		while query.next():
-			if not query.value(0):
-				continue
-			child_item = TreeItem(self.db, self.child_count, self)
-			self.child_items.append(child_item)
-			self.child_count += 1
-			child_item.setUpLevel1(query.value(0), query.value(1))
-
-	def setUpLevel1(self, comm_id, comm):
-		self.query_done = True;
-		self.comm_id = comm_id
-		self.data[0] = comm
-		self.child_items = []
-		self.child_count = 0
-		query = QSqlQuery(self.db)
-		ret = query.exec_('SELECT thread_id, ( SELECT pid FROM threads WHERE id = thread_id ), ( SELECT tid FROM threads WHERE id = thread_id ) FROM comm_threads WHERE comm_id = ' + str(comm_id))
-		if not ret:
-			raise Exception("Query failed: " + query.lastError().text())
-		while query.next():
-			child_item = TreeItem(self.db, self.child_count, self)
-			self.child_items.append(child_item)
-			self.child_count += 1
-			child_item.setUpLevel2(comm_id, query.value(0), query.value(1), query.value(2))
-
-	def setUpLevel2(self, comm_id, thread_id, pid, tid):
-		self.comm_id = comm_id
-		self.thread_id = thread_id
-		self.data[0] = str(pid) + ":" + str(tid)
-
-	def getChildItem(self, row):
-		return self.child_items[row]
-
-	def getParentItem(self):
-		return self.parent_item
-
-	def getRow(self):
-		return self.row
-
-	def timePercent(self, b):
-		if not self.time:
-			return "0.0"
-		x = (b * Decimal(100)) / self.time
-		return str(x.quantize(Decimal('.1'), rounding=ROUND_HALF_UP))
-
-	def branchPercent(self, b):
-		if not self.branch_count:
-			return "0.0"
-		x = (b * Decimal(100)) / self.branch_count
-		return str(x.quantize(Decimal('.1'), rounding=ROUND_HALF_UP))
-
-	def addChild(self, call_path_id, name, dso, count, time, branch_count):
-		child_item = TreeItem(self.db, self.child_count, self)
-		child_item.comm_id = self.comm_id
-		child_item.thread_id = self.thread_id
-		child_item.call_path_id = call_path_id
-		child_item.branch_count = branch_count
-		child_item.time = time
-		child_item.data[0] = name
-		if dso == "[kernel.kallsyms]":
-			dso = "[kernel]"
-		child_item.data[1] = dso
-		child_item.data[2] = str(count)
-		child_item.data[3] = str(time)
-		child_item.data[4] = self.timePercent(time)
-		child_item.data[5] = str(branch_count)
-		child_item.data[6] = self.branchPercent(branch_count)
-		self.child_items.append(child_item)
-		self.child_count += 1
-
-	def selectCalls(self):
-		self.query_done = True;
-		query = QSqlQuery(self.db)
-		ret = query.exec_('SELECT id, call_path_id, branch_count, call_time, return_time, '
-				  '( SELECT name FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ), '
-				  '( SELECT short_name FROM dsos WHERE id = ( SELECT dso_id FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ) ), '
-				  '( SELECT ip FROM call_paths where id = call_path_id ) '
-				  'FROM calls WHERE parent_call_path_id = ' + str(self.call_path_id) + ' AND comm_id = ' + str(self.comm_id) + ' AND thread_id = ' + str(self.thread_id) +
-				  ' ORDER BY call_path_id')
-		if not ret:
-			raise Exception("Query failed: " + query.lastError().text())
-		last_call_path_id = 0
-		name = ""
-		dso = ""
-		count = 0
-		branch_count = 0
-		total_branch_count = 0
-		time = 0
-		total_time = 0
-		while query.next():
-			if query.value(1) == last_call_path_id:
-				count += 1
-				branch_count += query.value(2)
-				time += query.value(4) - query.value(3)
-			else:
-				if count:
-					self.addChild(last_call_path_id, name, dso, count, time, branch_count)
-				last_call_path_id = query.value(1)
-				name = query.value(5)
-				dso = query.value(6)
-				count = 1
-				total_branch_count += branch_count
-				total_time += time
-				branch_count = query.value(2)
-				time = query.value(4) - query.value(3)
-		if count:
-			self.addChild(last_call_path_id, name, dso, count, time, branch_count)
-		total_branch_count += branch_count
-		total_time += time
-		# Top level does not have time or branch count, so fix that here
-		if total_branch_count > self.branch_count:
-			self.branch_count = total_branch_count
-			if self.branch_count:
-				for child_item in self.child_items:
-					child_item.data[6] = self.branchPercent(child_item.branch_count)
-		if total_time > self.time:
-			self.time = total_time
-			if self.time:
-				for child_item in self.child_items:
-					child_item.data[4] = self.timePercent(child_item.time)
-
-	def childCount(self):
-		if not self.query_done:
-			self.selectCalls()
-		return self.child_count
-
-	def columnCount(self):
-		return 7
-
-	def columnHeader(self, column):
-		headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
-		return headers[column]
-
-	def getData(self, column):
-		return self.data[column]
-
-class TreeModel(QAbstractItemModel):
-
-	def __init__(self, db, parent=None):
-		super(TreeModel, self).__init__(parent)
-		self.db = db
-		self.root = TreeItem(db, 0, None)
-
-	def columnCount(self, parent):
-		return self.root.columnCount()
-
-	def rowCount(self, parent):
-		if parent.isValid():
-			parent_item = parent.internalPointer()
-		else:
-			parent_item = self.root
-		return parent_item.childCount()
-
-	def headerData(self, section, orientation, role):
-		if role == Qt.TextAlignmentRole:
-			if section > 1:
-				return Qt.AlignRight
-		if role != Qt.DisplayRole:
-			return None
-		if orientation != Qt.Horizontal:
-			return None
-		return self.root.columnHeader(section)
-
-	def parent(self, child):
-		child_item = child.internalPointer()
-		if child_item is self.root:
-			return QModelIndex()
-		parent_item = child_item.getParentItem()
-		return self.createIndex(parent_item.getRow(), 0, parent_item)
-
-	def index(self, row, column, parent):
-		if parent.isValid():
-			parent_item = parent.internalPointer()
-		else:
-			parent_item = self.root
-		child_item = parent_item.getChildItem(row)
-		return self.createIndex(row, column, child_item)
-
-	def data(self, index, role):
-		if role == Qt.TextAlignmentRole:
-			if index.column() > 1:
-				return Qt.AlignRight
-		if role != Qt.DisplayRole:
-			return None
-		index_item = index.internalPointer()
-		return index_item.getData(index.column())
-
-class MainWindow(QMainWindow):
-
-	def __init__(self, db, dbname, parent=None):
-		super(MainWindow, self).__init__(parent)
-
-		self.setObjectName("MainWindow")
-		self.setWindowTitle("Call Graph: " + dbname)
-		self.move(100, 100)
-		self.resize(800, 600)
-		style = self.style()
-		icon = style.standardIcon(QStyle.SP_MessageBoxInformation)
-		self.setWindowIcon(icon);
-
-		self.model = TreeModel(db)
-
-		self.view = QTreeView()
-		self.view.setModel(self.model)
-
-		self.setCentralWidget(self.view)
-
-if __name__ == '__main__':
-	if (len(sys.argv) < 2):
-		print >> sys.stderr, "Usage is: call-graph-from-sql.py <database name>"
-		raise Exception("Too few arguments")
-
-	dbname = sys.argv[1]
-
-	is_sqlite3 = False
-	try:
-		f = open(dbname)
-		if f.read(15) == "SQLite format 3":
-			is_sqlite3 = True
-		f.close()
-	except:
-		pass
-
-	if is_sqlite3:
-		db = QSqlDatabase.addDatabase('QSQLITE')
-	else:
-		db = QSqlDatabase.addDatabase('QPSQL')
-		opts = dbname.split()
-		for opt in opts:
-			if '=' in opt:
-				opt = opt.split('=')
-				if opt[0] == 'hostname':
-					db.setHostName(opt[1])
-				elif opt[0] == 'port':
-					db.setPort(int(opt[1]))
-				elif opt[0] == 'username':
-					db.setUserName(opt[1])
-				elif opt[0] == 'password':
-					db.setPassword(opt[1])
-				elif opt[0] == 'dbname':
-					dbname = opt[1]
-			else:
-				dbname = opt
-
-	db.setDatabaseName(dbname)
-	if not db.open():
-		raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text())
-
-	app = QApplication(sys.argv)
-	window = MainWindow(db, dbname)
-	window.show()
-	err = app.exec_()
-	db.close()
-	sys.exit(err)
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index e46f51b17513..0564dd7377f2 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -59,7 +59,7 @@ import datetime
 #	pt_example=# \q
 #
 # An example of using the database is provided by the script
-# call-graph-from-sql.py.  Refer to that script for details.
+# exported-sql-viewer.py.  Refer to that script for details.
 #
 # Tables:
 #
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index e4bb82c8aba9..245caf2643ed 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -40,7 +40,7 @@ import datetime
 #	sqlite> .quit
 #
 # An example of using the database is provided by the script
-# call-graph-from-sql.py.  Refer to that script for details.
+# exported-sql-viewer.py.  Refer to that script for details.
 #
 # The database structure is practically the same as created by the script
 # export-to-postgresql.py. Refer to that script for details.  A notable
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
new file mode 100755
index 000000000000..24cb0bd56afa
--- /dev/null
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -0,0 +1,2128 @@
+#!/usr/bin/python2
+# SPDX-License-Identifier: GPL-2.0
+# exported-sql-viewer.py: view data from sql database
+# Copyright (c) 2014-2018, Intel Corporation.
+
+# To use this script you will need to have exported data using either the
+# export-to-sqlite.py or the export-to-postgresql.py script.  Refer to those
+# scripts for details.
+#
+# Following on from the example in the export scripts, a
+# call-graph can be displayed for the pt_example database like this:
+#
+#	python tools/perf/scripts/python/exported-sql-viewer.py pt_example
+#
+# Note that for PostgreSQL, this script supports connecting to remote databases
+# by setting hostname, port, username, password, and dbname e.g.
+#
+#	python tools/perf/scripts/python/exported-sql-viewer.py "hostname=myhost username=myuser password=mypassword dbname=pt_example"
+#
+# The result is a GUI window with a tree representing a context-sensitive
+# call-graph.  Expanding a couple of levels of the tree and adjusting column
+# widths to suit will display something like:
+#
+#                                         Call Graph: pt_example
+# Call Path                          Object      Count   Time(ns)  Time(%)  Branch Count   Branch Count(%)
+# v- ls
+#     v- 2638:2638
+#         v- _start                  ld-2.19.so    1     10074071   100.0         211135            100.0
+#           |- unknown               unknown       1        13198     0.1              1              0.0
+#           >- _dl_start             ld-2.19.so    1      1400980    13.9          19637              9.3
+#           >- _d_linit_internal     ld-2.19.so    1       448152     4.4          11094              5.3
+#           v-__libc_start_main@plt  ls            1      8211741    81.5         180397             85.4
+#              >- _dl_fixup          ld-2.19.so    1         7607     0.1            108              0.1
+#              >- __cxa_atexit       libc-2.19.so  1        11737     0.1             10              0.0
+#              >- __libc_csu_init    ls            1        10354     0.1             10              0.0
+#              |- _setjmp            libc-2.19.so  1            0     0.0              4              0.0
+#              v- main               ls            1      8182043    99.6         180254             99.9
+#
+# Points to note:
+#	The top level is a command name (comm)
+#	The next level is a thread (pid:tid)
+#	Subsequent levels are functions
+#	'Count' is the number of calls
+#	'Time' is the elapsed time until the function returns
+#	Percentages are relative to the level above
+#	'Branch Count' is the total number of branches for that function and all
+#       functions that it calls
+
+# There is also a "All branches" report, which displays branches and
+# possibly disassembly.  However, presently, the only supported disassembler is
+# Intel XED, and additionally the object code must be present in perf build ID
+# cache. To use Intel XED, libxed.so must be present. To build and install
+# libxed.so:
+#            git clone https://github.com/intelxed/mbuild.git mbuild
+#            git clone https://github.com/intelxed/xed
+#            cd xed
+#            ./mfile.py --share
+#            sudo ./mfile.py --prefix=/usr/local install
+#            sudo ldconfig
+#
+# Example report:
+#
+# Time           CPU  Command  PID    TID    Branch Type            In Tx  Branch
+# 8107675239590  2    ls       22011  22011  return from interrupt  No     ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea260 _start (ld-2.19.so)
+#                                                                              7fab593ea260 48 89 e7                                        mov %rsp, %rdi
+# 8107675239899  2    ls       22011  22011  hardware interrupt     No         7fab593ea260 _start (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel])
+# 8107675241900  2    ls       22011  22011  return from interrupt  No     ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea260 _start (ld-2.19.so)
+#                                                                              7fab593ea260 48 89 e7                                        mov %rsp, %rdi
+#                                                                              7fab593ea263 e8 c8 06 00 00                                  callq  0x7fab593ea930
+# 8107675241900  2    ls       22011  22011  call                   No         7fab593ea263 _start+0x3 (ld-2.19.so) -> 7fab593ea930 _dl_start (ld-2.19.so)
+#                                                                              7fab593ea930 55                                              pushq  %rbp
+#                                                                              7fab593ea931 48 89 e5                                        mov %rsp, %rbp
+#                                                                              7fab593ea934 41 57                                           pushq  %r15
+#                                                                              7fab593ea936 41 56                                           pushq  %r14
+#                                                                              7fab593ea938 41 55                                           pushq  %r13
+#                                                                              7fab593ea93a 41 54                                           pushq  %r12
+#                                                                              7fab593ea93c 53                                              pushq  %rbx
+#                                                                              7fab593ea93d 48 89 fb                                        mov %rdi, %rbx
+#                                                                              7fab593ea940 48 83 ec 68                                     sub $0x68, %rsp
+#                                                                              7fab593ea944 0f 31                                           rdtsc
+#                                                                              7fab593ea946 48 c1 e2 20                                     shl $0x20, %rdx
+#                                                                              7fab593ea94a 89 c0                                           mov %eax, %eax
+#                                                                              7fab593ea94c 48 09 c2                                        or %rax, %rdx
+#                                                                              7fab593ea94f 48 8b 05 1a 15 22 00                            movq  0x22151a(%rip), %rax
+# 8107675242232  2    ls       22011  22011  hardware interrupt     No         7fab593ea94f _dl_start+0x1f (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel])
+# 8107675242900  2    ls       22011  22011  return from interrupt  No     ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea94f _dl_start+0x1f (ld-2.19.so)
+#                                                                              7fab593ea94f 48 8b 05 1a 15 22 00                            movq  0x22151a(%rip), %rax
+#                                                                              7fab593ea956 48 89 15 3b 13 22 00                            movq  %rdx, 0x22133b(%rip)
+# 8107675243232  2    ls       22011  22011  hardware interrupt     No         7fab593ea956 _dl_start+0x26 (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel])
+
+import sys
+import weakref
+import threading
+import string
+import cPickle
+import re
+import os
+from PySide.QtCore import *
+from PySide.QtGui import *
+from PySide.QtSql import *
+from decimal import *
+from ctypes import *
+from multiprocessing import Process, Array, Value, Event
+
+# Data formatting helpers
+
+def tohex(ip):
+	if ip < 0:
+		ip += 1 << 64
+	return "%x" % ip
+
+def offstr(offset):
+	if offset:
+		return "+0x%x" % offset
+	return ""
+
+def dsoname(name):
+	if name == "[kernel.kallsyms]":
+		return "[kernel]"
+	return name
+
+# Percent to one decimal place
+
+def PercentToOneDP(n, d):
+	if not d:
+		return "0.0"
+	x = (n * Decimal(100)) / d
+	return str(x.quantize(Decimal(".1"), rounding=ROUND_HALF_UP))
+
+# Helper for queries that must not fail
+
+def QueryExec(query, stmt):
+	ret = query.exec_(stmt)
+	if not ret:
+		raise Exception("Query failed: " + query.lastError().text())
+
+# Background thread
+
+class Thread(QThread):
+
+	done = Signal(object)
+
+	def __init__(self, task, param=None, parent=None):
+		super(Thread, self).__init__(parent)
+		self.task = task
+		self.param = param
+
+	def run(self):
+		while True:
+			if self.param is None:
+				done, result = self.task()
+			else:
+				done, result = self.task(self.param)
+			self.done.emit(result)
+			if done:
+				break
+
+# Tree data model
+
+class TreeModel(QAbstractItemModel):
+
+	def __init__(self, root, parent=None):
+		super(TreeModel, self).__init__(parent)
+		self.root = root
+		self.last_row_read = 0
+
+	def Item(self, parent):
+		if parent.isValid():
+			return parent.internalPointer()
+		else:
+			return self.root
+
+	def rowCount(self, parent):
+		result = self.Item(parent).childCount()
+		if result < 0:
+			result = 0
+			self.dataChanged.emit(parent, parent)
+		return result
+
+	def hasChildren(self, parent):
+		return self.Item(parent).hasChildren()
+
+	def headerData(self, section, orientation, role):
+		if role == Qt.TextAlignmentRole:
+			return self.columnAlignment(section)
+		if role != Qt.DisplayRole:
+			return None
+		if orientation != Qt.Horizontal:
+			return None
+		return self.columnHeader(section)
+
+	def parent(self, child):
+		child_item = child.internalPointer()
+		if child_item is self.root:
+			return QModelIndex()
+		parent_item = child_item.getParentItem()
+		return self.createIndex(parent_item.getRow(), 0, parent_item)
+
+	def index(self, row, column, parent):
+		child_item = self.Item(parent).getChildItem(row)
+		return self.createIndex(row, column, child_item)
+
+	def DisplayData(self, item, index):
+		return item.getData(index.column())
+
+	def FetchIfNeeded(self, row):
+		if row > self.last_row_read:
+			self.last_row_read = row
+			if row + 10 >= self.root.child_count:
+				self.fetcher.Fetch(glb_chunk_sz)
+
+	def columnAlignment(self, column):
+		return Qt.AlignLeft
+
+	def columnFont(self, column):
+		return None
+
+	def data(self, index, role):
+		if role == Qt.TextAlignmentRole:
+			return self.columnAlignment(index.column())
+		if role == Qt.FontRole:
+			return self.columnFont(index.column())
+		if role != Qt.DisplayRole:
+			return None
+		item = index.internalPointer()
+		return self.DisplayData(item, index)
+
+# Table data model
+
+class TableModel(QAbstractTableModel):
+
+	def __init__(self, parent=None):
+		super(TableModel, self).__init__(parent)
+		self.child_count = 0
+		self.child_items = []
+		self.last_row_read = 0
+
+	def Item(self, parent):
+		if parent.isValid():
+			return parent.internalPointer()
+		else:
+			return self
+
+	def rowCount(self, parent):
+		return self.child_count
+
+	def headerData(self, section, orientation, role):
+		if role == Qt.TextAlignmentRole:
+			return self.columnAlignment(section)
+		if role != Qt.DisplayRole:
+			return None
+		if orientation != Qt.Horizontal:
+			return None
+		return self.columnHeader(section)
+
+	def index(self, row, column, parent):
+		return self.createIndex(row, column, self.child_items[row])
+
+	def DisplayData(self, item, index):
+		return item.getData(index.column())
+
+	def FetchIfNeeded(self, row):
+		if row > self.last_row_read:
+			self.last_row_read = row
+			if row + 10 >= self.child_count:
+				self.fetcher.Fetch(glb_chunk_sz)
+
+	def columnAlignment(self, column):
+		return Qt.AlignLeft
+
+	def columnFont(self, column):
+		return None
+
+	def data(self, index, role):
+		if role == Qt.TextAlignmentRole:
+			return self.columnAlignment(index.column())
+		if role == Qt.FontRole:
+			return self.columnFont(index.column())
+		if role != Qt.DisplayRole:
+			return None
+		item = index.internalPointer()
+		return self.DisplayData(item, index)
+
+# Model cache
+
+model_cache = weakref.WeakValueDictionary()
+model_cache_lock = threading.Lock()
+
+def LookupCreateModel(model_name, create_fn):
+	model_cache_lock.acquire()
+	try:
+		model = model_cache[model_name]
+	except:
+		model = None
+	if model is None:
+		model = create_fn()
+		model_cache[model_name] = model
+	model_cache_lock.release()
+	return model
+
+# Find bar
+
+class FindBar():
+
+	def __init__(self, parent, finder, is_reg_expr=False):
+		self.finder = finder
+		self.context = []
+		self.last_value = None
+		self.last_pattern = None
+
+		label = QLabel("Find:")
+		label.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.textbox = QComboBox()
+		self.textbox.setEditable(True)
+		self.textbox.currentIndexChanged.connect(self.ValueChanged)
+
+		self.progress = QProgressBar()
+		self.progress.setRange(0, 0)
+		self.progress.hide()
+
+		if is_reg_expr:
+			self.pattern = QCheckBox("Regular Expression")
+		else:
+			self.pattern = QCheckBox("Pattern")
+		self.pattern.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.next_button = QToolButton()
+		self.next_button.setIcon(parent.style().standardIcon(QStyle.SP_ArrowDown))
+		self.next_button.released.connect(lambda: self.NextPrev(1))
+
+		self.prev_button = QToolButton()
+		self.prev_button.setIcon(parent.style().standardIcon(QStyle.SP_ArrowUp))
+		self.prev_button.released.connect(lambda: self.NextPrev(-1))
+
+		self.close_button = QToolButton()
+		self.close_button.setIcon(parent.style().standardIcon(QStyle.SP_DockWidgetCloseButton))
+		self.close_button.released.connect(self.Deactivate)
+
+		self.hbox = QHBoxLayout()
+		self.hbox.setContentsMargins(0, 0, 0, 0)
+
+		self.hbox.addWidget(label)
+		self.hbox.addWidget(self.textbox)
+		self.hbox.addWidget(self.progress)
+		self.hbox.addWidget(self.pattern)
+		self.hbox.addWidget(self.next_button)
+		self.hbox.addWidget(self.prev_button)
+		self.hbox.addWidget(self.close_button)
+
+		self.bar = QWidget()
+		self.bar.setLayout(self.hbox);
+		self.bar.hide()
+
+	def Widget(self):
+		return self.bar
+
+	def Activate(self):
+		self.bar.show()
+		self.textbox.setFocus()
+
+	def Deactivate(self):
+		self.bar.hide()
+
+	def Busy(self):
+		self.textbox.setEnabled(False)
+		self.pattern.hide()
+		self.next_button.hide()
+		self.prev_button.hide()
+		self.progress.show()
+
+	def Idle(self):
+		self.textbox.setEnabled(True)
+		self.progress.hide()
+		self.pattern.show()
+		self.next_button.show()
+		self.prev_button.show()
+
+	def Find(self, direction):
+		value = self.textbox.currentText()
+		pattern = self.pattern.isChecked()
+		self.last_value = value
+		self.last_pattern = pattern
+		self.finder.Find(value, direction, pattern, self.context)
+
+	def ValueChanged(self):
+		value = self.textbox.currentText()
+		pattern = self.pattern.isChecked()
+		index = self.textbox.currentIndex()
+		data = self.textbox.itemData(index)
+		# Store the pattern in the combo box to keep it with the text value
+		if data == None:
+			self.textbox.setItemData(index, pattern)
+		else:
+			self.pattern.setChecked(data)
+		self.Find(0)
+
+	def NextPrev(self, direction):
+		value = self.textbox.currentText()
+		pattern = self.pattern.isChecked()
+		if value != self.last_value:
+			index = self.textbox.findText(value)
+			# Allow for a button press before the value has been added to the combo box
+			if index < 0:
+				index = self.textbox.count()
+				self.textbox.addItem(value, pattern)
+				self.textbox.setCurrentIndex(index)
+				return
+			else:
+				self.textbox.setItemData(index, pattern)
+		elif pattern != self.last_pattern:
+			# Keep the pattern recorded in the combo box up to date
+			index = self.textbox.currentIndex()
+			self.textbox.setItemData(index, pattern)
+		self.Find(direction)
+
+	def NotFound(self):
+		QMessageBox.information(self.bar, "Find", "'" + self.textbox.currentText() + "' not found")
+
+# Context-sensitive call graph data model item base
+
+class CallGraphLevelItemBase(object):
+
+	def __init__(self, glb, row, parent_item):
+		self.glb = glb
+		self.row = row
+		self.parent_item = parent_item
+		self.query_done = False;
+		self.child_count = 0
+		self.child_items = []
+
+	def getChildItem(self, row):
+		return self.child_items[row]
+
+	def getParentItem(self):
+		return self.parent_item
+
+	def getRow(self):
+		return self.row
+
+	def childCount(self):
+		if not self.query_done:
+			self.Select()
+			if not self.child_count:
+				return -1
+		return self.child_count
+
+	def hasChildren(self):
+		if not self.query_done:
+			return True
+		return self.child_count > 0
+
+	def getData(self, column):
+		return self.data[column]
+
+# Context-sensitive call graph data model level 2+ item base
+
+class CallGraphLevelTwoPlusItemBase(CallGraphLevelItemBase):
+
+	def __init__(self, glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item):
+		super(CallGraphLevelTwoPlusItemBase, self).__init__(glb, row, parent_item)
+		self.comm_id = comm_id
+		self.thread_id = thread_id
+		self.call_path_id = call_path_id
+		self.branch_count = branch_count
+		self.time = time
+
+	def Select(self):
+		self.query_done = True;
+		query = QSqlQuery(self.glb.db)
+		QueryExec(query, "SELECT call_path_id, name, short_name, COUNT(calls.id), SUM(return_time - call_time), SUM(branch_count)"
+					" FROM calls"
+					" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
+					" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
+					" INNER JOIN dsos ON symbols.dso_id = dsos.id"
+					" WHERE parent_call_path_id = " + str(self.call_path_id) +
+					" AND comm_id = " + str(self.comm_id) +
+					" AND thread_id = " + str(self.thread_id) +
+					" GROUP BY call_path_id, name, short_name"
+					" ORDER BY call_path_id")
+		while query.next():
+			child_item = CallGraphLevelThreeItem(self.glb, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), int(query.value(5)), self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+
+# Context-sensitive call graph data model level three item
+
+class CallGraphLevelThreeItem(CallGraphLevelTwoPlusItemBase):
+
+	def __init__(self, glb, row, comm_id, thread_id, call_path_id, name, dso, count, time, branch_count, parent_item):
+		super(CallGraphLevelThreeItem, self).__init__(glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item)
+		dso = dsoname(dso)
+		self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
+		self.dbid = call_path_id
+
+# Context-sensitive call graph data model level two item
+
+class CallGraphLevelTwoItem(CallGraphLevelTwoPlusItemBase):
+
+	def __init__(self, glb, row, comm_id, thread_id, pid, tid, parent_item):
+		super(CallGraphLevelTwoItem, self).__init__(glb, row, comm_id, thread_id, 1, 0, 0, parent_item)
+		self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
+		self.dbid = thread_id
+
+	def Select(self):
+		super(CallGraphLevelTwoItem, self).Select()
+		for child_item in self.child_items:
+			self.time += child_item.time
+			self.branch_count += child_item.branch_count
+		for child_item in self.child_items:
+			child_item.data[4] = PercentToOneDP(child_item.time, self.time)
+			child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
+
+# Context-sensitive call graph data model level one item
+
+class CallGraphLevelOneItem(CallGraphLevelItemBase):
+
+	def __init__(self, glb, row, comm_id, comm, parent_item):
+		super(CallGraphLevelOneItem, self).__init__(glb, row, parent_item)
+		self.data = [comm, "", "", "", "", "", ""]
+		self.dbid = comm_id
+
+	def Select(self):
+		self.query_done = True;
+		query = QSqlQuery(self.glb.db)
+		QueryExec(query, "SELECT thread_id, pid, tid"
+					" FROM comm_threads"
+					" INNER JOIN threads ON thread_id = threads.id"
+					" WHERE comm_id = " + str(self.dbid))
+		while query.next():
+			child_item = CallGraphLevelTwoItem(self.glb, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+
+# Context-sensitive call graph data model root item
+
+class CallGraphRootItem(CallGraphLevelItemBase):
+
+	def __init__(self, glb):
+		super(CallGraphRootItem, self).__init__(glb, 0, None)
+		self.dbid = 0
+		self.query_done = True;
+		query = QSqlQuery(glb.db)
+		QueryExec(query, "SELECT id, comm FROM comms")
+		while query.next():
+			if not query.value(0):
+				continue
+			child_item = CallGraphLevelOneItem(glb, self.child_count, query.value(0), query.value(1), self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+
+# Context-sensitive call graph data model
+
+class CallGraphModel(TreeModel):
+
+	def __init__(self, glb, parent=None):
+		super(CallGraphModel, self).__init__(CallGraphRootItem(glb), parent)
+		self.glb = glb
+
+	def columnCount(self, parent=None):
+		return 7
+
+	def columnHeader(self, column):
+		headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
+		return headers[column]
+
+	def columnAlignment(self, column):
+		alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
+		return alignment[column]
+
+	def FindSelect(self, value, pattern, query):
+		if pattern:
+			# postgresql and sqlite pattern patching differences:
+			#   postgresql LIKE is case sensitive but sqlite LIKE is not
+			#   postgresql LIKE allows % and _ to be escaped with \ but sqlite LIKE does not
+			#   postgresql supports ILIKE which is case insensitive
+			#   sqlite supports GLOB (text only) which uses * and ? and is case sensitive
+			if not self.glb.dbref.is_sqlite3:
+				# Escape % and _
+				s = value.replace("%", "\%")
+				s = s.replace("_", "\_")
+				# Translate * and ? into SQL LIKE pattern characters % and _
+				trans = string.maketrans("*?", "%_")
+				match = " LIKE '" + str(s).translate(trans) + "'"
+			else:
+				match = " GLOB '" + str(value) + "'"
+		else:
+			match = " = '" + str(value) + "'"
+		QueryExec(query, "SELECT call_path_id, comm_id, thread_id"
+						" FROM calls"
+						" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
+						" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
+						" WHERE symbols.name" + match +
+						" GROUP BY comm_id, thread_id, call_path_id"
+						" ORDER BY comm_id, thread_id, call_path_id")
+
+	def FindPath(self, query):
+		# Turn the query result into a list of ids that the tree view can walk
+		# to open the tree at the right place.
+		ids = []
+		parent_id = query.value(0)
+		while parent_id:
+			ids.insert(0, parent_id)
+			q2 = QSqlQuery(self.glb.db)
+			QueryExec(q2, "SELECT parent_id"
+					" FROM call_paths"
+					" WHERE id = " + str(parent_id))
+			if not q2.next():
+				break
+			parent_id = q2.value(0)
+		# The call path root is not used
+		if ids[0] == 1:
+			del ids[0]
+		ids.insert(0, query.value(2))
+		ids.insert(0, query.value(1))
+		return ids
+
+	def Found(self, query, found):
+		if found:
+			return self.FindPath(query)
+		return []
+
+	def FindValue(self, value, pattern, query, last_value, last_pattern):
+		if last_value == value and pattern == last_pattern:
+			found = query.first()
+		else:
+			self.FindSelect(value, pattern, query)
+			found = query.next()
+		return self.Found(query, found)
+
+	def FindNext(self, query):
+		found = query.next()
+		if not found:
+			found = query.first()
+		return self.Found(query, found)
+
+	def FindPrev(self, query):
+		found = query.previous()
+		if not found:
+			found = query.last()
+		return self.Found(query, found)
+
+	def FindThread(self, c):
+		if c.direction == 0 or c.value != c.last_value or c.pattern != c.last_pattern:
+			ids = self.FindValue(c.value, c.pattern, c.query, c.last_value, c.last_pattern)
+		elif c.direction > 0:
+			ids = self.FindNext(c.query)
+		else:
+			ids = self.FindPrev(c.query)
+		return (True, ids)
+
+	def Find(self, value, direction, pattern, context, callback):
+		class Context():
+			def __init__(self, *x):
+				self.value, self.direction, self.pattern, self.query, self.last_value, self.last_pattern = x
+			def Update(self, *x):
+				self.value, self.direction, self.pattern, self.last_value, self.last_pattern = x + (self.value, self.pattern)
+		if len(context):
+			context[0].Update(value, direction, pattern)
+		else:
+			context.append(Context(value, direction, pattern, QSqlQuery(self.glb.db), None, None))
+		# Use a thread so the UI is not blocked during the SELECT
+		thread = Thread(self.FindThread, context[0])
+		thread.done.connect(lambda ids, t=thread, c=callback: self.FindDone(t, c, ids), Qt.QueuedConnection)
+		thread.start()
+
+	def FindDone(self, thread, callback, ids):
+		callback(ids)
+
+# Vertical widget layout
+
+class VBox():
+
+	def __init__(self, w1, w2, w3=None):
+		self.vbox = QWidget()
+		self.vbox.setLayout(QVBoxLayout());
+
+		self.vbox.layout().setContentsMargins(0, 0, 0, 0)
+
+		self.vbox.layout().addWidget(w1)
+		self.vbox.layout().addWidget(w2)
+		if w3:
+			self.vbox.layout().addWidget(w3)
+
+	def Widget(self):
+		return self.vbox
+
+# Context-sensitive call graph window
+
+class CallGraphWindow(QMdiSubWindow):
+
+	def __init__(self, glb, parent=None):
+		super(CallGraphWindow, self).__init__(parent)
+
+		self.model = LookupCreateModel("Context-Sensitive Call Graph", lambda x=glb: CallGraphModel(x))
+
+		self.view = QTreeView()
+		self.view.setModel(self.model)
+
+		for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
+			self.view.setColumnWidth(c, w)
+
+		self.find_bar = FindBar(self, self)
+
+		self.vbox = VBox(self.view, self.find_bar.Widget())
+
+		self.setWidget(self.vbox.Widget())
+
+		AddSubWindow(glb.mainwindow.mdi_area, self, "Context-Sensitive Call Graph")
+
+	def DisplayFound(self, ids):
+		if not len(ids):
+			return False
+		parent = QModelIndex()
+		for dbid in ids:
+			found = False
+			n = self.model.rowCount(parent)
+			for row in xrange(n):
+				child = self.model.index(row, 0, parent)
+				if child.internalPointer().dbid == dbid:
+					found = True
+					self.view.setCurrentIndex(child)
+					parent = child
+					break
+			if not found:
+				break
+		return found
+
+	def Find(self, value, direction, pattern, context):
+		self.view.setFocus()
+		self.find_bar.Busy()
+		self.model.Find(value, direction, pattern, context, self.FindDone)
+
+	def FindDone(self, ids):
+		found = True
+		if not self.DisplayFound(ids):
+			found = False
+		self.find_bar.Idle()
+		if not found:
+			self.find_bar.NotFound()
+
+# Child data item  finder
+
+class ChildDataItemFinder():
+
+	def __init__(self, root):
+		self.root = root
+		self.value, self.direction, self.pattern, self.last_value, self.last_pattern = (None,) * 5
+		self.rows = []
+		self.pos = 0
+
+	def FindSelect(self):
+		self.rows = []
+		if self.pattern:
+			pattern = re.compile(self.value)
+			for child in self.root.child_items:
+				for column_data in child.data:
+					if re.search(pattern, str(column_data)) is not None:
+						self.rows.append(child.row)
+						break
+		else:
+			for child in self.root.child_items:
+				for column_data in child.data:
+					if self.value in str(column_data):
+						self.rows.append(child.row)
+						break
+
+	def FindValue(self):
+		self.pos = 0
+		if self.last_value != self.value or self.pattern != self.last_pattern:
+			self.FindSelect()
+		if not len(self.rows):
+			return -1
+		return self.rows[self.pos]
+
+	def FindThread(self):
+		if self.direction == 0 or self.value != self.last_value or self.pattern != self.last_pattern:
+			row = self.FindValue()
+		elif len(self.rows):
+			if self.direction > 0:
+				self.pos += 1
+				if self.pos >= len(self.rows):
+					self.pos = 0
+			else:
+				self.pos -= 1
+				if self.pos < 0:
+					self.pos = len(self.rows) - 1
+			row = self.rows[self.pos]
+		else:
+			row = -1
+		return (True, row)
+
+	def Find(self, value, direction, pattern, context, callback):
+		self.value, self.direction, self.pattern, self.last_value, self.last_pattern = (value, direction,pattern, self.value, self.pattern)
+		# Use a thread so the UI is not blocked
+		thread = Thread(self.FindThread)
+		thread.done.connect(lambda row, t=thread, c=callback: self.FindDone(t, c, row), Qt.QueuedConnection)
+		thread.start()
+
+	def FindDone(self, thread, callback, row):
+		callback(row)
+
+# Number of database records to fetch in one go
+
+glb_chunk_sz = 10000
+
+# size of pickled integer big enough for record size
+
+glb_nsz = 8
+
+# Background process for SQL data fetcher
+
+class SQLFetcherProcess():
+
+	def __init__(self, dbref, sql, buffer, head, tail, fetch_count, fetching_done, process_target, wait_event, fetched_event, prep):
+		# Need a unique connection name
+		conn_name = "SQLFetcher" + str(os.getpid())
+		self.db, dbname = dbref.Open(conn_name)
+		self.sql = sql
+		self.buffer = buffer
+		self.head = head
+		self.tail = tail
+		self.fetch_count = fetch_count
+		self.fetching_done = fetching_done
+		self.process_target = process_target
+		self.wait_event = wait_event
+		self.fetched_event = fetched_event
+		self.prep = prep
+		self.query = QSqlQuery(self.db)
+		self.query_limit = 0 if "$$last_id$$" in sql else 2
+		self.last_id = -1
+		self.fetched = 0
+		self.more = True
+		self.local_head = self.head.value
+		self.local_tail = self.tail.value
+
+	def Select(self):
+		if self.query_limit:
+			if self.query_limit == 1:
+				return
+			self.query_limit -= 1
+		stmt = self.sql.replace("$$last_id$$", str(self.last_id))
+		QueryExec(self.query, stmt)
+
+	def Next(self):
+		if not self.query.next():
+			self.Select()
+			if not self.query.next():
+				return None
+		self.last_id = self.query.value(0)
+		return self.prep(self.query)
+
+	def WaitForTarget(self):
+		while True:
+			self.wait_event.clear()
+			target = self.process_target.value
+			if target > self.fetched or target < 0:
+				break
+			self.wait_event.wait()
+		return target
+
+	def HasSpace(self, sz):
+		if self.local_tail <= self.local_head:
+			space = len(self.buffer) - self.local_head
+			if space > sz:
+				return True
+			if space >= glb_nsz:
+				# Use 0 (or space < glb_nsz) to mean there is no more at the top of the buffer
+				nd = cPickle.dumps(0, cPickle.HIGHEST_PROTOCOL)
+				self.buffer[self.local_head : self.local_head + len(nd)] = nd
+			self.local_head = 0
+		if self.local_tail - self.local_head > sz:
+			return True
+		return False
+
+	def WaitForSpace(self, sz):
+		if self.HasSpace(sz):
+			return
+		while True:
+			self.wait_event.clear()
+			self.local_tail = self.tail.value
+			if self.HasSpace(sz):
+				return
+			self.wait_event.wait()
+
+	def AddToBuffer(self, obj):
+		d = cPickle.dumps(obj, cPickle.HIGHEST_PROTOCOL)
+		n = len(d)
+		nd = cPickle.dumps(n, cPickle.HIGHEST_PROTOCOL)
+		sz = n + glb_nsz
+		self.WaitForSpace(sz)
+		pos = self.local_head
+		self.buffer[pos : pos + len(nd)] = nd
+		self.buffer[pos + glb_nsz : pos + sz] = d
+		self.local_head += sz
+
+	def FetchBatch(self, batch_size):
+		fetched = 0
+		while batch_size > fetched:
+			obj = self.Next()
+			if obj is None:
+				self.more = False
+				break
+			self.AddToBuffer(obj)
+			fetched += 1
+		if fetched:
+			self.fetched += fetched
+			with self.fetch_count.get_lock():
+				self.fetch_count.value += fetched
+			self.head.value = self.local_head
+			self.fetched_event.set()
+
+	def Run(self):
+		while self.more:
+			target = self.WaitForTarget()
+			if target < 0:
+				break
+			batch_size = min(glb_chunk_sz, target - self.fetched)
+			self.FetchBatch(batch_size)
+		self.fetching_done.value = True
+		self.fetched_event.set()
+
+def SQLFetcherFn(*x):
+	process = SQLFetcherProcess(*x)
+	process.Run()
+
+# SQL data fetcher
+
+class SQLFetcher(QObject):
+
+	done = Signal(object)
+
+	def __init__(self, glb, sql, prep, process_data, parent=None):
+		super(SQLFetcher, self).__init__(parent)
+		self.process_data = process_data
+		self.more = True
+		self.target = 0
+		self.last_target = 0
+		self.fetched = 0
+		self.buffer_size = 16 * 1024 * 1024
+		self.buffer = Array(c_char, self.buffer_size, lock=False)
+		self.head = Value(c_longlong)
+		self.tail = Value(c_longlong)
+		self.local_tail = 0
+		self.fetch_count = Value(c_longlong)
+		self.fetching_done = Value(c_bool)
+		self.last_count = 0
+		self.process_target = Value(c_longlong)
+		self.wait_event = Event()
+		self.fetched_event = Event()
+		glb.AddInstanceToShutdownOnExit(self)
+		self.process = Process(target=SQLFetcherFn, args=(glb.dbref, sql, self.buffer, self.head, self.tail, self.fetch_count, self.fetching_done, self.process_target, self.wait_event, self.fetched_event, prep))
+		self.process.start()
+		self.thread = Thread(self.Thread)
+		self.thread.done.connect(self.ProcessData, Qt.QueuedConnection)
+		self.thread.start()
+
+	def Shutdown(self):
+		# Tell the thread and process to exit
+		self.process_target.value = -1
+		self.wait_event.set()
+		self.more = False
+		self.fetching_done.value = True
+		self.fetched_event.set()
+
+	def Thread(self):
+		if not self.more:
+			return True, 0
+		while True:
+			self.fetched_event.clear()
+			fetch_count = self.fetch_count.value
+			if fetch_count != self.last_count:
+				break
+			if self.fetching_done.value:
+				self.more = False
+				return True, 0
+			self.fetched_event.wait()
+		count = fetch_count - self.last_count
+		self.last_count = fetch_count
+		self.fetched += count
+		return False, count
+
+	def Fetch(self, nr):
+		if not self.more:
+			# -1 inidcates there are no more
+			return -1
+		result = self.fetched
+		extra = result + nr - self.target
+		if extra > 0:
+			self.target += extra
+			# process_target < 0 indicates shutting down
+			if self.process_target.value >= 0:
+				self.process_target.value = self.target
+			self.wait_event.set()
+		return result
+
+	def RemoveFromBuffer(self):
+		pos = self.local_tail
+		if len(self.buffer) - pos < glb_nsz:
+			pos = 0
+		n = cPickle.loads(self.buffer[pos : pos + glb_nsz])
+		if n == 0:
+			pos = 0
+			n = cPickle.loads(self.buffer[0 : glb_nsz])
+		pos += glb_nsz
+		obj = cPickle.loads(self.buffer[pos : pos + n])
+		self.local_tail = pos + n
+		return obj
+
+	def ProcessData(self, count):
+		for i in xrange(count):
+			obj = self.RemoveFromBuffer()
+			self.process_data(obj)
+		self.tail.value = self.local_tail
+		self.wait_event.set()
+		self.done.emit(count)
+
+# Fetch more records bar
+
+class FetchMoreRecordsBar():
+
+	def __init__(self, model, parent):
+		self.model = model
+
+		self.label = QLabel("Number of records (x " + "{:,}".format(glb_chunk_sz) + ") to fetch:")
+		self.label.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.fetch_count = QSpinBox()
+		self.fetch_count.setRange(1, 1000000)
+		self.fetch_count.setValue(10)
+		self.fetch_count.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.fetch = QPushButton("Go!")
+		self.fetch.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+		self.fetch.released.connect(self.FetchMoreRecords)
+
+		self.progress = QProgressBar()
+		self.progress.setRange(0, 100)
+		self.progress.hide()
+
+		self.done_label = QLabel("All records fetched")
+		self.done_label.hide()
+
+		self.spacer = QLabel("")
+
+		self.close_button = QToolButton()
+		self.close_button.setIcon(parent.style().standardIcon(QStyle.SP_DockWidgetCloseButton))
+		self.close_button.released.connect(self.Deactivate)
+
+		self.hbox = QHBoxLayout()
+		self.hbox.setContentsMargins(0, 0, 0, 0)
+
+		self.hbox.addWidget(self.label)
+		self.hbox.addWidget(self.fetch_count)
+		self.hbox.addWidget(self.fetch)
+		self.hbox.addWidget(self.spacer)
+		self.hbox.addWidget(self.progress)
+		self.hbox.addWidget(self.done_label)
+		self.hbox.addWidget(self.close_button)
+
+		self.bar = QWidget()
+		self.bar.setLayout(self.hbox);
+		self.bar.show()
+
+		self.in_progress = False
+		self.model.progress.connect(self.Progress)
+
+		self.done = False
+
+		if not model.HasMoreRecords():
+			self.Done()
+
+	def Widget(self):
+		return self.bar
+
+	def Activate(self):
+		self.bar.show()
+		self.fetch.setFocus()
+
+	def Deactivate(self):
+		self.bar.hide()
+
+	def Enable(self, enable):
+		self.fetch.setEnabled(enable)
+		self.fetch_count.setEnabled(enable)
+
+	def Busy(self):
+		self.Enable(False)
+		self.fetch.hide()
+		self.spacer.hide()
+		self.progress.show()
+
+	def Idle(self):
+		self.in_progress = False
+		self.Enable(True)
+		self.progress.hide()
+		self.fetch.show()
+		self.spacer.show()
+
+	def Target(self):
+		return self.fetch_count.value() * glb_chunk_sz
+
+	def Done(self):
+		self.done = True
+		self.Idle()
+		self.label.hide()
+		self.fetch_count.hide()
+		self.fetch.hide()
+		self.spacer.hide()
+		self.done_label.show()
+
+	def Progress(self, count):
+		if self.in_progress:
+			if count:
+				percent = ((count - self.start) * 100) / self.Target()
+				if percent >= 100:
+					self.Idle()
+				else:
+					self.progress.setValue(percent)
+		if not count:
+			# Count value of zero means no more records
+			self.Done()
+
+	def FetchMoreRecords(self):
+		if self.done:
+			return
+		self.progress.setValue(0)
+		self.Busy()
+		self.in_progress = True
+		self.start = self.model.FetchMoreRecords(self.Target())
+
+# Brance data model level two item
+
+class BranchLevelTwoItem():
+
+	def __init__(self, row, text, parent_item):
+		self.row = row
+		self.parent_item = parent_item
+		self.data = [""] * 8
+		self.data[7] = text
+		self.level = 2
+
+	def getParentItem(self):
+		return self.parent_item
+
+	def getRow(self):
+		return self.row
+
+	def childCount(self):
+		return 0
+
+	def hasChildren(self):
+		return False
+
+	def getData(self, column):
+		return self.data[column]
+
+# Brance data model level one item
+
+class BranchLevelOneItem():
+
+	def __init__(self, glb, row, data, parent_item):
+		self.glb = glb
+		self.row = row
+		self.parent_item = parent_item
+		self.child_count = 0
+		self.child_items = []
+		self.data = data[1:]
+		self.dbid = data[0]
+		self.level = 1
+		self.query_done = False
+
+	def getChildItem(self, row):
+		return self.child_items[row]
+
+	def getParentItem(self):
+		return self.parent_item
+
+	def getRow(self):
+		return self.row
+
+	def Select(self):
+		self.query_done = True
+
+		if not self.glb.have_disassembler:
+			return
+
+		query = QSqlQuery(self.glb.db)
+
+		QueryExec(query, "SELECT cpu, to_dso_id, to_symbol_id, to_sym_offset, short_name, long_name, build_id, sym_start, to_ip"
+				  " FROM samples"
+				  " INNER JOIN dsos ON samples.to_dso_id = dsos.id"
+				  " INNER JOIN symbols ON samples.to_symbol_id = symbols.id"
+				  " WHERE samples.id = " + str(self.dbid))
+		if not query.next():
+			return
+		cpu = query.value(0)
+		dso = query.value(1)
+		sym = query.value(2)
+		if dso == 0 or sym == 0:
+			return
+		off = query.value(3)
+		short_name = query.value(4)
+		long_name = query.value(5)
+		build_id = query.value(6)
+		sym_start = query.value(7)
+		ip = query.value(8)
+
+		QueryExec(query, "SELECT samples.dso_id, symbol_id, sym_offset, sym_start"
+				  " FROM samples"
+				  " INNER JOIN symbols ON samples.symbol_id = symbols.id"
+				  " WHERE samples.id > " + str(self.dbid) + " AND cpu = " + str(cpu) +
+				  " ORDER BY samples.id"
+				  " LIMIT 1")
+		if not query.next():
+			return
+		if query.value(0) != dso:
+			# Cannot disassemble from one dso to another
+			return
+		bsym = query.value(1)
+		boff = query.value(2)
+		bsym_start = query.value(3)
+		if bsym == 0:
+			return
+		tot = bsym_start + boff + 1 - sym_start - off
+		if tot <= 0 or tot > 16384:
+			return
+
+		inst = self.glb.disassembler.Instruction()
+		f = self.glb.FileFromNamesAndBuildId(short_name, long_name, build_id)
+		if not f:
+			return
+		mode = 0 if Is64Bit(f) else 1
+		self.glb.disassembler.SetMode(inst, mode)
+
+		buf_sz = tot + 16
+		buf = create_string_buffer(tot + 16)
+		f.seek(sym_start + off)
+		buf.value = f.read(buf_sz)
+		buf_ptr = addressof(buf)
+		i = 0
+		while tot > 0:
+			cnt, text = self.glb.disassembler.DisassembleOne(inst, buf_ptr, buf_sz, ip)
+			if cnt:
+				byte_str = tohex(ip).rjust(16)
+				for k in xrange(cnt):
+					byte_str += " %02x" % ord(buf[i])
+					i += 1
+				while k < 15:
+					byte_str += "   "
+					k += 1
+				self.child_items.append(BranchLevelTwoItem(0, byte_str + " " + text, self))
+				self.child_count += 1
+			else:
+				return
+			buf_ptr += cnt
+			tot -= cnt
+			buf_sz -= cnt
+			ip += cnt
+
+	def childCount(self):
+		if not self.query_done:
+			self.Select()
+			if not self.child_count:
+				return -1
+		return self.child_count
+
+	def hasChildren(self):
+		if not self.query_done:
+			return True
+		return self.child_count > 0
+
+	def getData(self, column):
+		return self.data[column]
+
+# Brance data model root item
+
+class BranchRootItem():
+
+	def __init__(self):
+		self.child_count = 0
+		self.child_items = []
+		self.level = 0
+
+	def getChildItem(self, row):
+		return self.child_items[row]
+
+	def getParentItem(self):
+		return None
+
+	def getRow(self):
+		return 0
+
+	def childCount(self):
+		return self.child_count
+
+	def hasChildren(self):
+		return self.child_count > 0
+
+	def getData(self, column):
+		return ""
+
+# Branch data preparation
+
+def BranchDataPrep(query):
+	data = []
+	for i in xrange(0, 8):
+		data.append(query.value(i))
+	data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) +
+			" (" + dsoname(query.value(11)) + ")" + " -> " +
+			tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) +
+			" (" + dsoname(query.value(15)) + ")")
+	return data
+
+# Branch data model
+
+class BranchModel(TreeModel):
+
+	progress = Signal(object)
+
+	def __init__(self, glb, event_id, where_clause, parent=None):
+		super(BranchModel, self).__init__(BranchRootItem(), parent)
+		self.glb = glb
+		self.event_id = event_id
+		self.more = True
+		self.populated = 0
+		sql = ("SELECT samples.id, time, cpu, comm, pid, tid, branch_types.name,"
+			" CASE WHEN in_tx = '0' THEN 'No' ELSE 'Yes' END,"
+			" ip, symbols.name, sym_offset, dsos.short_name,"
+			" to_ip, to_symbols.name, to_sym_offset, to_dsos.short_name"
+			" FROM samples"
+			" INNER JOIN comms ON comm_id = comms.id"
+			" INNER JOIN threads ON thread_id = threads.id"
+			" INNER JOIN branch_types ON branch_type = branch_types.id"
+			" INNER JOIN symbols ON symbol_id = symbols.id"
+			" INNER JOIN symbols to_symbols ON to_symbol_id = to_symbols.id"
+			" INNER JOIN dsos ON samples.dso_id = dsos.id"
+			" INNER JOIN dsos AS to_dsos ON samples.to_dso_id = to_dsos.id"
+			" WHERE samples.id > $$last_id$$" + where_clause +
+			" AND evsel_id = " + str(self.event_id) +
+			" ORDER BY samples.id"
+			" LIMIT " + str(glb_chunk_sz))
+		self.fetcher = SQLFetcher(glb, sql, BranchDataPrep, self.AddSample)
+		self.fetcher.done.connect(self.Update)
+		self.fetcher.Fetch(glb_chunk_sz)
+
+	def columnCount(self, parent=None):
+		return 8
+
+	def columnHeader(self, column):
+		return ("Time", "CPU", "Command", "PID", "TID", "Branch Type", "In Tx", "Branch")[column]
+
+	def columnFont(self, column):
+		if column != 7:
+			return None
+		return QFont("Monospace")
+
+	def DisplayData(self, item, index):
+		if item.level == 1:
+			self.FetchIfNeeded(item.row)
+		return item.getData(index.column())
+
+	def AddSample(self, data):
+		child = BranchLevelOneItem(self.glb, self.populated, data, self.root)
+		self.root.child_items.append(child)
+		self.populated += 1
+
+	def Update(self, fetched):
+		if not fetched:
+			self.more = False
+			self.progress.emit(0)
+		child_count = self.root.child_count
+		count = self.populated - child_count
+		if count > 0:
+			parent = QModelIndex()
+			self.beginInsertRows(parent, child_count, child_count + count - 1)
+			self.insertRows(child_count, count, parent)
+			self.root.child_count += count
+			self.endInsertRows()
+			self.progress.emit(self.root.child_count)
+
+	def FetchMoreRecords(self, count):
+		current = self.root.child_count
+		if self.more:
+			self.fetcher.Fetch(count)
+		else:
+			self.progress.emit(0)
+		return current
+
+	def HasMoreRecords(self):
+		return self.more
+
+# Branch window
+
+class BranchWindow(QMdiSubWindow):
+
+	def __init__(self, glb, event_id, name, where_clause, parent=None):
+		super(BranchWindow, self).__init__(parent)
+
+		model_name = "Branch Events " + str(event_id)
+		if len(where_clause):
+			model_name = where_clause + " " + model_name
+
+		self.model = LookupCreateModel(model_name, lambda: BranchModel(glb, event_id, where_clause))
+
+		self.view = QTreeView()
+		self.view.setUniformRowHeights(True)
+		self.view.setModel(self.model)
+
+		self.ResizeColumnsToContents()
+
+		self.find_bar = FindBar(self, self, True)
+
+		self.finder = ChildDataItemFinder(self.model.root)
+
+		self.fetch_bar = FetchMoreRecordsBar(self.model, self)
+
+		self.vbox = VBox(self.view, self.find_bar.Widget(), self.fetch_bar.Widget())
+
+		self.setWidget(self.vbox.Widget())
+
+		AddSubWindow(glb.mainwindow.mdi_area, self, name + " Branch Events")
+
+	def ResizeColumnToContents(self, column, n):
+		# Using the view's resizeColumnToContents() here is extrememly slow
+		# so implement a crude alternative
+		mm = "MM" if column else "MMMM"
+		font = self.view.font()
+		metrics = QFontMetrics(font)
+		max = 0
+		for row in xrange(n):
+			val = self.model.root.child_items[row].data[column]
+			len = metrics.width(str(val) + mm)
+			max = len if len > max else max
+		val = self.model.columnHeader(column)
+		len = metrics.width(str(val) + mm)
+		max = len if len > max else max
+		self.view.setColumnWidth(column, max)
+
+	def ResizeColumnsToContents(self):
+		n = min(self.model.root.child_count, 100)
+		if n < 1:
+			# No data yet, so connect a signal to notify when there is
+			self.model.rowsInserted.connect(self.UpdateColumnWidths)
+			return
+		columns = self.model.columnCount()
+		for i in xrange(columns):
+			self.ResizeColumnToContents(i, n)
+
+	def UpdateColumnWidths(self, *x):
+		# This only needs to be done once, so disconnect the signal now
+		self.model.rowsInserted.disconnect(self.UpdateColumnWidths)
+		self.ResizeColumnsToContents()
+
+	def Find(self, value, direction, pattern, context):
+		self.view.setFocus()
+		self.find_bar.Busy()
+		self.finder.Find(value, direction, pattern, context, self.FindDone)
+
+	def FindDone(self, row):
+		self.find_bar.Idle()
+		if row >= 0:
+			self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex()))
+		else:
+			self.find_bar.NotFound()
+
+# Event list
+
+def GetEventList(db):
+	events = []
+	query = QSqlQuery(db)
+	QueryExec(query, "SELECT name FROM selected_events WHERE id > 0 ORDER BY id")
+	while query.next():
+		events.append(query.value(0))
+	return events
+
+# SQL data preparation
+
+def SQLTableDataPrep(query, count):
+	data = []
+	for i in xrange(count):
+		data.append(query.value(i))
+	return data
+
+# SQL table data model item
+
+class SQLTableItem():
+
+	def __init__(self, row, data):
+		self.row = row
+		self.data = data
+
+	def getData(self, column):
+		return self.data[column]
+
+# SQL table data model
+
+class SQLTableModel(TableModel):
+
+	progress = Signal(object)
+
+	def __init__(self, glb, sql, column_count, parent=None):
+		super(SQLTableModel, self).__init__(parent)
+		self.glb = glb
+		self.more = True
+		self.populated = 0
+		self.fetcher = SQLFetcher(glb, sql, lambda x, y=column_count: SQLTableDataPrep(x, y), self.AddSample)
+		self.fetcher.done.connect(self.Update)
+		self.fetcher.Fetch(glb_chunk_sz)
+
+	def DisplayData(self, item, index):
+		self.FetchIfNeeded(item.row)
+		return item.getData(index.column())
+
+	def AddSample(self, data):
+		child = SQLTableItem(self.populated, data)
+		self.child_items.append(child)
+		self.populated += 1
+
+	def Update(self, fetched):
+		if not fetched:
+			self.more = False
+			self.progress.emit(0)
+		child_count = self.child_count
+		count = self.populated - child_count
+		if count > 0:
+			parent = QModelIndex()
+			self.beginInsertRows(parent, child_count, child_count + count - 1)
+			self.insertRows(child_count, count, parent)
+			self.child_count += count
+			self.endInsertRows()
+			self.progress.emit(self.child_count)
+
+	def FetchMoreRecords(self, count):
+		current = self.child_count
+		if self.more:
+			self.fetcher.Fetch(count)
+		else:
+			self.progress.emit(0)
+		return current
+
+	def HasMoreRecords(self):
+		return self.more
+
+# SQL automatic table data model
+
+class SQLAutoTableModel(SQLTableModel):
+
+	def __init__(self, glb, table_name, parent=None):
+		sql = "SELECT * FROM " + table_name + " WHERE id > $$last_id$$ ORDER BY id LIMIT " + str(glb_chunk_sz)
+		if table_name == "comm_threads_view":
+			# For now, comm_threads_view has no id column
+			sql = "SELECT * FROM " + table_name + " WHERE comm_id > $$last_id$$ ORDER BY comm_id LIMIT " + str(glb_chunk_sz)
+		self.column_headers = []
+		query = QSqlQuery(glb.db)
+		if glb.dbref.is_sqlite3:
+			QueryExec(query, "PRAGMA table_info(" + table_name + ")")
+			while query.next():
+				self.column_headers.append(query.value(1))
+			if table_name == "sqlite_master":
+				sql = "SELECT * FROM " + table_name
+		else:
+			if table_name[:19] == "information_schema.":
+				sql = "SELECT * FROM " + table_name
+				select_table_name = table_name[19:]
+				schema = "information_schema"
+			else:
+				select_table_name = table_name
+				schema = "public"
+			QueryExec(query, "SELECT column_name FROM information_schema.columns WHERE table_schema = '" + schema + "' and table_name = '" + select_table_name + "'")
+			while query.next():
+				self.column_headers.append(query.value(0))
+		super(SQLAutoTableModel, self).__init__(glb, sql, len(self.column_headers), parent)
+
+	def columnCount(self, parent=None):
+		return len(self.column_headers)
+
+	def columnHeader(self, column):
+		return self.column_headers[column]
+
+# Base class for custom ResizeColumnsToContents
+
+class ResizeColumnsToContentsBase(QObject):
+
+	def __init__(self, parent=None):
+		super(ResizeColumnsToContentsBase, self).__init__(parent)
+
+	def ResizeColumnToContents(self, column, n):
+		# Using the view's resizeColumnToContents() here is extrememly slow
+		# so implement a crude alternative
+		font = self.view.font()
+		metrics = QFontMetrics(font)
+		max = 0
+		for row in xrange(n):
+			val = self.data_model.child_items[row].data[column]
+			len = metrics.width(str(val) + "MM")
+			max = len if len > max else max
+		val = self.data_model.columnHeader(column)
+		len = metrics.width(str(val) + "MM")
+		max = len if len > max else max
+		self.view.setColumnWidth(column, max)
+
+	def ResizeColumnsToContents(self):
+		n = min(self.data_model.child_count, 100)
+		if n < 1:
+			# No data yet, so connect a signal to notify when there is
+			self.data_model.rowsInserted.connect(self.UpdateColumnWidths)
+			return
+		columns = self.data_model.columnCount()
+		for i in xrange(columns):
+			self.ResizeColumnToContents(i, n)
+
+	def UpdateColumnWidths(self, *x):
+		# This only needs to be done once, so disconnect the signal now
+		self.data_model.rowsInserted.disconnect(self.UpdateColumnWidths)
+		self.ResizeColumnsToContents()
+
+# Table window
+
+class TableWindow(QMdiSubWindow, ResizeColumnsToContentsBase):
+
+	def __init__(self, glb, table_name, parent=None):
+		super(TableWindow, self).__init__(parent)
+
+		self.data_model = LookupCreateModel(table_name + " Table", lambda: SQLAutoTableModel(glb, table_name))
+
+		self.model = QSortFilterProxyModel()
+		self.model.setSourceModel(self.data_model)
+
+		self.view = QTableView()
+		self.view.setModel(self.model)
+		self.view.setEditTriggers(QAbstractItemView.NoEditTriggers)
+		self.view.verticalHeader().setVisible(False)
+		self.view.sortByColumn(-1, Qt.AscendingOrder)
+		self.view.setSortingEnabled(True)
+
+		self.ResizeColumnsToContents()
+
+		self.find_bar = FindBar(self, self, True)
+
+		self.finder = ChildDataItemFinder(self.data_model)
+
+		self.fetch_bar = FetchMoreRecordsBar(self.data_model, self)
+
+		self.vbox = VBox(self.view, self.find_bar.Widget(), self.fetch_bar.Widget())
+
+		self.setWidget(self.vbox.Widget())
+
+		AddSubWindow(glb.mainwindow.mdi_area, self, table_name + " Table")
+
+	def Find(self, value, direction, pattern, context):
+		self.view.setFocus()
+		self.find_bar.Busy()
+		self.finder.Find(value, direction, pattern, context, self.FindDone)
+
+	def FindDone(self, row):
+		self.find_bar.Idle()
+		if row >= 0:
+			self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex()))
+		else:
+			self.find_bar.NotFound()
+
+# Table list
+
+def GetTableList(glb):
+	tables = []
+	query = QSqlQuery(glb.db)
+	if glb.dbref.is_sqlite3:
+		QueryExec(query, "SELECT name FROM sqlite_master WHERE type IN ( 'table' , 'view' ) ORDER BY name")
+	else:
+		QueryExec(query, "SELECT table_name FROM information_schema.tables WHERE table_schema = 'public' AND table_type IN ( 'BASE TABLE' , 'VIEW' ) ORDER BY table_name")
+	while query.next():
+		tables.append(query.value(0))
+	if glb.dbref.is_sqlite3:
+		tables.append("sqlite_master")
+	else:
+		tables.append("information_schema.tables")
+		tables.append("information_schema.views")
+		tables.append("information_schema.columns")
+	return tables
+
+# Action Definition
+
+def CreateAction(label, tip, callback, parent=None, shortcut=None):
+	action = QAction(label, parent)
+	if shortcut != None:
+		action.setShortcuts(shortcut)
+	action.setStatusTip(tip)
+	action.triggered.connect(callback)
+	return action
+
+# Typical application actions
+
+def CreateExitAction(app, parent=None):
+	return CreateAction("&Quit", "Exit the application", app.closeAllWindows, parent, QKeySequence.Quit)
+
+# Typical MDI actions
+
+def CreateCloseActiveWindowAction(mdi_area):
+	return CreateAction("Cl&ose", "Close the active window", mdi_area.closeActiveSubWindow, mdi_area)
+
+def CreateCloseAllWindowsAction(mdi_area):
+	return CreateAction("Close &All", "Close all the windows", mdi_area.closeAllSubWindows, mdi_area)
+
+def CreateTileWindowsAction(mdi_area):
+	return CreateAction("&Tile", "Tile the windows", mdi_area.tileSubWindows, mdi_area)
+
+def CreateCascadeWindowsAction(mdi_area):
+	return CreateAction("&Cascade", "Cascade the windows", mdi_area.cascadeSubWindows, mdi_area)
+
+def CreateNextWindowAction(mdi_area):
+	return CreateAction("Ne&xt", "Move the focus to the next window", mdi_area.activateNextSubWindow, mdi_area, QKeySequence.NextChild)
+
+def CreatePreviousWindowAction(mdi_area):
+	return CreateAction("Pre&vious", "Move the focus to the previous window", mdi_area.activatePreviousSubWindow, mdi_area, QKeySequence.PreviousChild)
+
+# Typical MDI window menu
+
+class WindowMenu():
+
+	def __init__(self, mdi_area, menu):
+		self.mdi_area = mdi_area
+		self.window_menu = menu.addMenu("&Windows")
+		self.close_active_window = CreateCloseActiveWindowAction(mdi_area)
+		self.close_all_windows = CreateCloseAllWindowsAction(mdi_area)
+		self.tile_windows = CreateTileWindowsAction(mdi_area)
+		self.cascade_windows = CreateCascadeWindowsAction(mdi_area)
+		self.next_window = CreateNextWindowAction(mdi_area)
+		self.previous_window = CreatePreviousWindowAction(mdi_area)
+		self.window_menu.aboutToShow.connect(self.Update)
+
+	def Update(self):
+		self.window_menu.clear()
+		sub_window_count = len(self.mdi_area.subWindowList())
+		have_sub_windows = sub_window_count != 0
+		self.close_active_window.setEnabled(have_sub_windows)
+		self.close_all_windows.setEnabled(have_sub_windows)
+		self.tile_windows.setEnabled(have_sub_windows)
+		self.cascade_windows.setEnabled(have_sub_windows)
+		self.next_window.setEnabled(have_sub_windows)
+		self.previous_window.setEnabled(have_sub_windows)
+		self.window_menu.addAction(self.close_active_window)
+		self.window_menu.addAction(self.close_all_windows)
+		self.window_menu.addSeparator()
+		self.window_menu.addAction(self.tile_windows)
+		self.window_menu.addAction(self.cascade_windows)
+		self.window_menu.addSeparator()
+		self.window_menu.addAction(self.next_window)
+		self.window_menu.addAction(self.previous_window)
+		if sub_window_count == 0:
+			return
+		self.window_menu.addSeparator()
+		nr = 1
+		for sub_window in self.mdi_area.subWindowList():
+			label = str(nr) + " " + sub_window.name
+			if nr < 10:
+				label = "&" + label
+			action = self.window_menu.addAction(label)
+			action.setCheckable(True)
+			action.setChecked(sub_window == self.mdi_area.activeSubWindow())
+			action.triggered.connect(lambda x=nr: self.setActiveSubWindow(x))
+			self.window_menu.addAction(action)
+			nr += 1
+
+	def setActiveSubWindow(self, nr):
+		self.mdi_area.setActiveSubWindow(self.mdi_area.subWindowList()[nr - 1])
+
+# Font resize
+
+def ResizeFont(widget, diff):
+	font = widget.font()
+	sz = font.pointSize()
+	font.setPointSize(sz + diff)
+	widget.setFont(font)
+
+def ShrinkFont(widget):
+	ResizeFont(widget, -1)
+
+def EnlargeFont(widget):
+	ResizeFont(widget, 1)
+
+# Unique name for sub-windows
+
+def NumberedWindowName(name, nr):
+	if nr > 1:
+		name += " <" + str(nr) + ">"
+	return name
+
+def UniqueSubWindowName(mdi_area, name):
+	nr = 1
+	while True:
+		unique_name = NumberedWindowName(name, nr)
+		ok = True
+		for sub_window in mdi_area.subWindowList():
+			if sub_window.name == unique_name:
+				ok = False
+				break
+		if ok:
+			return unique_name
+		nr += 1
+
+# Add a sub-window
+
+def AddSubWindow(mdi_area, sub_window, name):
+	unique_name = UniqueSubWindowName(mdi_area, name)
+	sub_window.setMinimumSize(200, 100)
+	sub_window.resize(800, 600)
+	sub_window.setWindowTitle(unique_name)
+	sub_window.setAttribute(Qt.WA_DeleteOnClose)
+	sub_window.setWindowIcon(sub_window.style().standardIcon(QStyle.SP_FileIcon))
+	sub_window.name = unique_name
+	mdi_area.addSubWindow(sub_window)
+	sub_window.show()
+
+# Main window
+
+class MainWindow(QMainWindow):
+
+	def __init__(self, glb, parent=None):
+		super(MainWindow, self).__init__(parent)
+
+		self.glb = glb
+
+		self.setWindowTitle("Exported SQL Viewer: " + glb.dbname)
+		self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
+		self.setMinimumSize(200, 100)
+
+		self.mdi_area = QMdiArea()
+		self.mdi_area.setHorizontalScrollBarPolicy(Qt.ScrollBarAsNeeded)
+		self.mdi_area.setVerticalScrollBarPolicy(Qt.ScrollBarAsNeeded)
+
+		self.setCentralWidget(self.mdi_area)
+
+		menu = self.menuBar()
+
+		file_menu = menu.addMenu("&File")
+		file_menu.addAction(CreateExitAction(glb.app, self))
+
+		edit_menu = menu.addMenu("&Edit")
+		edit_menu.addAction(CreateAction("&Find...", "Find items", self.Find, self, QKeySequence.Find))
+		edit_menu.addAction(CreateAction("Fetch &more records...", "Fetch more records", self.FetchMoreRecords, self, [QKeySequence(Qt.Key_F8)]))
+		edit_menu.addAction(CreateAction("&Shrink Font", "Make text smaller", self.ShrinkFont, self, [QKeySequence("Ctrl+-")]))
+		edit_menu.addAction(CreateAction("&Enlarge Font", "Make text bigger", self.EnlargeFont, self, [QKeySequence("Ctrl++")]))
+
+		reports_menu = menu.addMenu("&Reports")
+		reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
+
+		self.EventMenu(GetEventList(glb.db), reports_menu)
+
+		self.TableMenu(GetTableList(glb), menu)
+
+		self.window_menu = WindowMenu(self.mdi_area, menu)
+
+	def Find(self):
+		win = self.mdi_area.activeSubWindow()
+		if win:
+			try:
+				win.find_bar.Activate()
+			except:
+				pass
+
+	def FetchMoreRecords(self):
+		win = self.mdi_area.activeSubWindow()
+		if win:
+			try:
+				win.fetch_bar.Activate()
+			except:
+				pass
+
+	def ShrinkFont(self):
+		win = self.mdi_area.activeSubWindow()
+		ShrinkFont(win.view)
+
+	def EnlargeFont(self):
+		win = self.mdi_area.activeSubWindow()
+		EnlargeFont(win.view)
+
+	def EventMenu(self, events, reports_menu):
+		branches_events = 0
+		for event in events:
+			event = event.split(":")[0]
+			if event == "branches":
+				branches_events += 1
+		dbid = 0
+		for event in events:
+			dbid += 1
+			event = event.split(":")[0]
+			if event == "branches":
+				label = "All branches" if branches_events == 1 else "All branches " + "(id=" + dbid + ")"
+				reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewBranchView(x), self))
+
+	def TableMenu(self, tables, menu):
+		table_menu = menu.addMenu("&Tables")
+		for table in tables:
+			table_menu.addAction(CreateAction(table, "Create a new window containing a table view", lambda t=table: self.NewTableView(t), self))
+
+	def NewCallGraph(self):
+		CallGraphWindow(self.glb, self)
+
+	def NewBranchView(self, event_id):
+		BranchWindow(self.glb, event_id, "", "", self)
+
+	def NewTableView(self, table_name):
+		TableWindow(self.glb, table_name, self)
+
+# XED Disassembler
+
+class xed_state_t(Structure):
+
+	_fields_ = [
+		("mode", c_int),
+		("width", c_int)
+	]
+
+class XEDInstruction():
+
+	def __init__(self, libxed):
+		# Current xed_decoded_inst_t structure is 192 bytes. Use 512 to allow for future expansion
+		xedd_t = c_byte * 512
+		self.xedd = xedd_t()
+		self.xedp = addressof(self.xedd)
+		libxed.xed_decoded_inst_zero(self.xedp)
+		self.state = xed_state_t()
+		self.statep = addressof(self.state)
+		# Buffer for disassembled instruction text
+		self.buffer = create_string_buffer(256)
+		self.bufferp = addressof(self.buffer)
+
+class LibXED():
+
+	def __init__(self):
+		self.libxed = CDLL("libxed.so")
+
+		self.xed_tables_init = self.libxed.xed_tables_init
+		self.xed_tables_init.restype = None
+		self.xed_tables_init.argtypes = []
+
+		self.xed_decoded_inst_zero = self.libxed.xed_decoded_inst_zero
+		self.xed_decoded_inst_zero.restype = None
+		self.xed_decoded_inst_zero.argtypes = [ c_void_p ]
+
+		self.xed_operand_values_set_mode = self.libxed.xed_operand_values_set_mode
+		self.xed_operand_values_set_mode.restype = None
+		self.xed_operand_values_set_mode.argtypes = [ c_void_p, c_void_p ]
+
+		self.xed_decoded_inst_zero_keep_mode = self.libxed.xed_decoded_inst_zero_keep_mode
+		self.xed_decoded_inst_zero_keep_mode.restype = None
+		self.xed_decoded_inst_zero_keep_mode.argtypes = [ c_void_p ]
+
+		self.xed_decode = self.libxed.xed_decode
+		self.xed_decode.restype = c_int
+		self.xed_decode.argtypes = [ c_void_p, c_void_p, c_uint ]
+
+		self.xed_format_context = self.libxed.xed_format_context
+		self.xed_format_context.restype = c_uint
+		self.xed_format_context.argtypes = [ c_int, c_void_p, c_void_p, c_int, c_ulonglong, c_void_p, c_void_p ]
+
+		self.xed_tables_init()
+
+	def Instruction(self):
+		return XEDInstruction(self)
+
+	def SetMode(self, inst, mode):
+		if mode:
+			inst.state.mode = 4 # 32-bit
+			inst.state.width = 4 # 4 bytes
+		else:
+			inst.state.mode = 1 # 64-bit
+			inst.state.width = 8 # 8 bytes
+		self.xed_operand_values_set_mode(inst.xedp, inst.statep)
+
+	def DisassembleOne(self, inst, bytes_ptr, bytes_cnt, ip):
+		self.xed_decoded_inst_zero_keep_mode(inst.xedp)
+		err = self.xed_decode(inst.xedp, bytes_ptr, bytes_cnt)
+		if err:
+			return 0, ""
+		# Use AT&T mode (2), alternative is Intel (3)
+		ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0)
+		if not ok:
+			return 0, ""
+		# Return instruction length and the disassembled instruction text
+		# For now, assume the length is in byte 166
+		return inst.xedd[166], inst.buffer.value
+
+def TryOpen(file_name):
+	try:
+		return open(file_name, "rb")
+	except:
+		return None
+
+def Is64Bit(f):
+	result = sizeof(c_void_p)
+	# ELF support only
+	pos = f.tell()
+	f.seek(0)
+	header = f.read(7)
+	f.seek(pos)
+	magic = header[0:4]
+	eclass = ord(header[4])
+	encoding = ord(header[5])
+	version = ord(header[6])
+	if magic == chr(127) + "ELF" and eclass > 0 and eclass < 3 and encoding > 0 and encoding < 3 and version == 1:
+		result = True if eclass == 2 else False
+	return result
+
+# Global data
+
+class Glb():
+
+	def __init__(self, dbref, db, dbname):
+		self.dbref = dbref
+		self.db = db
+		self.dbname = dbname
+		self.home_dir = os.path.expanduser("~")
+		self.buildid_dir = os.getenv("PERF_BUILDID_DIR")
+		if self.buildid_dir:
+			self.buildid_dir += "/.build-id/"
+		else:
+			self.buildid_dir = self.home_dir + "/.debug/.build-id/"
+		self.app = None
+		self.mainwindow = None
+		self.instances_to_shutdown_on_exit = weakref.WeakSet()
+		try:
+			self.disassembler = LibXED()
+			self.have_disassembler = True
+		except:
+			self.have_disassembler = False
+
+	def FileFromBuildId(self, build_id):
+		file_name = self.buildid_dir + build_id[0:2] + "/" + build_id[2:] + "/elf"
+		return TryOpen(file_name)
+
+	def FileFromNamesAndBuildId(self, short_name, long_name, build_id):
+		# Assume current machine i.e. no support for virtualization
+		if short_name[0:7] == "[kernel" and os.path.basename(long_name) == "kcore":
+			file_name = os.getenv("PERF_KCORE")
+			f = TryOpen(file_name) if file_name else None
+			if f:
+				return f
+			# For now, no special handling if long_name is /proc/kcore
+			f = TryOpen(long_name)
+			if f:
+				return f
+		f = self.FileFromBuildId(build_id)
+		if f:
+			return f
+		return None
+
+	def AddInstanceToShutdownOnExit(self, instance):
+		self.instances_to_shutdown_on_exit.add(instance)
+
+	# Shutdown any background processes or threads
+	def ShutdownInstances(self):
+		for x in self.instances_to_shutdown_on_exit:
+			try:
+				x.Shutdown()
+			except:
+				pass
+
+# Database reference
+
+class DBRef():
+
+	def __init__(self, is_sqlite3, dbname):
+		self.is_sqlite3 = is_sqlite3
+		self.dbname = dbname
+
+	def Open(self, connection_name):
+		dbname = self.dbname
+		if self.is_sqlite3:
+			db = QSqlDatabase.addDatabase("QSQLITE", connection_name)
+		else:
+			db = QSqlDatabase.addDatabase("QPSQL", connection_name)
+			opts = dbname.split()
+			for opt in opts:
+				if "=" in opt:
+					opt = opt.split("=")
+					if opt[0] == "hostname":
+						db.setHostName(opt[1])
+					elif opt[0] == "port":
+						db.setPort(int(opt[1]))
+					elif opt[0] == "username":
+						db.setUserName(opt[1])
+					elif opt[0] == "password":
+						db.setPassword(opt[1])
+					elif opt[0] == "dbname":
+						dbname = opt[1]
+				else:
+					dbname = opt
+
+		db.setDatabaseName(dbname)
+		if not db.open():
+			raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text())
+		return db, dbname
+
+# Main
+
+def Main():
+	if (len(sys.argv) < 2):
+		print >> sys.stderr, "Usage is: exported-sql-viewer.py <database name>"
+		raise Exception("Too few arguments")
+
+	dbname = sys.argv[1]
+
+	is_sqlite3 = False
+	try:
+		f = open(dbname)
+		if f.read(15) == "SQLite format 3":
+			is_sqlite3 = True
+		f.close()
+	except:
+		pass
+
+	dbref = DBRef(is_sqlite3, dbname)
+	db, dbname = dbref.Open("main")
+	glb = Glb(dbref, db, dbname)
+	app = QApplication(sys.argv)
+	glb.app = app
+	mainwindow = MainWindow(glb)
+	glb.mainwindow = mainwindow
+	mainwindow.show()
+	err = app.exec_()
+	glb.ShutdownInstances()
+	db.close()
+	sys.exit(err)
+
+if __name__ == "__main__":
+	Main()
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index c3b0afd67760..304313073242 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -5,6 +5,7 @@ ifeq ($(SRCARCH),$(filter $(SRCARCH),x86))
 libperf-y += ioctl.o
 endif
 libperf-y += kcmp.o
+libperf-y += mount_flags.o
 libperf-y += pkey_alloc.o
 libperf-y += prctl.o
 libperf-y += sockaddr.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 2570152d3909..039c29039b2c 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -24,6 +24,7 @@ struct strarray {
 }
 
 size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const char *intfmt, int val);
+size_t strarray__scnprintf_flags(struct strarray *sa, char *bf, size_t size, unsigned long flags);
 
 struct trace;
 struct thread;
@@ -122,6 +123,12 @@ size_t syscall_arg__scnprintf_kcmp_type(char *bf, size_t size, struct syscall_ar
 size_t syscall_arg__scnprintf_kcmp_idx(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_KCMP_IDX syscall_arg__scnprintf_kcmp_idx
 
+unsigned long syscall_arg__mask_val_mount_flags(struct syscall_arg *arg, unsigned long flags);
+#define SCAMV_MOUNT_FLAGS syscall_arg__mask_val_mount_flags
+
+size_t syscall_arg__scnprintf_mount_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_MOUNT_FLAGS syscall_arg__scnprintf_mount_flags
+
 size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PKEY_ALLOC_ACCESS_RIGHTS syscall_arg__scnprintf_pkey_alloc_access_rights
 
diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c
index d64d049ab991..010406500c30 100644
--- a/tools/perf/trace/beauty/clone.c
+++ b/tools/perf/trace/beauty/clone.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/cone.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh
index 9d3816815e60..9aa94fd523a9 100755
--- a/tools/perf/trace/beauty/drm_ioctl.sh
+++ b/tools/perf/trace/beauty/drm_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/
 
diff --git a/tools/perf/trace/beauty/eventfd.c b/tools/perf/trace/beauty/eventfd.c
index 5d6a477a6400..db5b9b492113 100644
--- a/tools/perf/trace/beauty/eventfd.c
+++ b/tools/perf/trace/beauty/eventfd.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #ifndef EFD_SEMAPHORE
 #define EFD_SEMAPHORE		1
 #endif
diff --git a/tools/perf/trace/beauty/fcntl.c b/tools/perf/trace/beauty/fcntl.c
index 9e8900c13cb1..e6de31674e24 100644
--- a/tools/perf/trace/beauty/fcntl.c
+++ b/tools/perf/trace/beauty/fcntl.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/fcntl.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/flock.c b/tools/perf/trace/beauty/flock.c
index c4ff6ad30b06..cf02ae5f0ba6 100644
--- a/tools/perf/trace/beauty/flock.c
+++ b/tools/perf/trace/beauty/flock.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 
 #include "trace/beauty/beauty.h"
 #include <linux/kernel.h>
diff --git a/tools/perf/trace/beauty/futex_op.c b/tools/perf/trace/beauty/futex_op.c
index 61850fbc85ff..1136bde56406 100644
--- a/tools/perf/trace/beauty/futex_op.c
+++ b/tools/perf/trace/beauty/futex_op.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <linux/futex.h>
 
 #ifndef FUTEX_WAIT_BITSET
diff --git a/tools/perf/trace/beauty/futex_val3.c b/tools/perf/trace/beauty/futex_val3.c
index 26f6b3253511..138b7d588a70 100644
--- a/tools/perf/trace/beauty/futex_val3.c
+++ b/tools/perf/trace/beauty/futex_val3.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <linux/futex.h>
 
 #ifndef FUTEX_BITSET_MATCH_ANY
diff --git a/tools/perf/trace/beauty/ioctl.c b/tools/perf/trace/beauty/ioctl.c
index 1be3b4cf0827..5d2a7fd8d407 100644
--- a/tools/perf/trace/beauty/ioctl.c
+++ b/tools/perf/trace/beauty/ioctl.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/ioctl.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/kcmp.c b/tools/perf/trace/beauty/kcmp.c
index f62040eb9d5c..b276a274f203 100644
--- a/tools/perf/trace/beauty/kcmp.c
+++ b/tools/perf/trace/beauty/kcmp.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/kcmp.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh
index a3c304caa336..df8b17486d57 100755
--- a/tools/perf/trace/beauty/kcmp_type.sh
+++ b/tools/perf/trace/beauty/kcmp_type.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh
index c4699fd46bb6..4ce54f5bf756 100755
--- a/tools/perf/trace/beauty/kvm_ioctl.sh
+++ b/tools/perf/trace/beauty/kvm_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh
index 431639eb4d29..4527d290cdfc 100755
--- a/tools/perf/trace/beauty/madvise_behavior.sh
+++ b/tools/perf/trace/beauty/madvise_behavior.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 9f68077b241b..c534bd96ef5c 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -1,5 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <uapi/linux/mman.h>
+#include <linux/log2.h>
 
 static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 					       struct syscall_arg *arg)
@@ -30,50 +31,23 @@ static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 
 #define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot
 
+static size_t mmap__scnprintf_flags(unsigned long flags, char *bf, size_t size)
+{
+#include "trace/beauty/generated/mmap_flags_array.c"
+       static DEFINE_STRARRAY(mmap_flags);
+
+       return strarray__scnprintf_flags(&strarray__mmap_flags, bf, size, flags);
+}
+
 static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 						struct syscall_arg *arg)
 {
-	int printed = 0, flags = arg->val;
+	unsigned long flags = arg->val;
 
 	if (flags & MAP_ANONYMOUS)
 		arg->mask |= (1 << 4) | (1 << 5); /* Mask 4th ('fd') and 5th ('offset') args, ignored */
 
-#define	P_MMAP_FLAG(n) \
-	if (flags & MAP_##n) { \
-		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
-		flags &= ~MAP_##n; \
-	}
-
-	P_MMAP_FLAG(SHARED);
-	P_MMAP_FLAG(PRIVATE);
-#ifdef MAP_32BIT
-	P_MMAP_FLAG(32BIT);
-#endif
-	P_MMAP_FLAG(ANONYMOUS);
-	P_MMAP_FLAG(DENYWRITE);
-	P_MMAP_FLAG(EXECUTABLE);
-	P_MMAP_FLAG(FILE);
-	P_MMAP_FLAG(FIXED);
-#ifdef MAP_FIXED_NOREPLACE
-	P_MMAP_FLAG(FIXED_NOREPLACE);
-#endif
-	P_MMAP_FLAG(GROWSDOWN);
-	P_MMAP_FLAG(HUGETLB);
-	P_MMAP_FLAG(LOCKED);
-	P_MMAP_FLAG(NONBLOCK);
-	P_MMAP_FLAG(NORESERVE);
-	P_MMAP_FLAG(POPULATE);
-	P_MMAP_FLAG(STACK);
-	P_MMAP_FLAG(UNINITIALIZED);
-#ifdef MAP_SYNC
-	P_MMAP_FLAG(SYNC);
-#endif
-#undef P_MMAP_FLAG
-
-	if (flags)
-		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
-	return printed;
+	return mmap__scnprintf_flags(flags, bf, size);
 }
 
 #define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh
new file mode 100755
index 000000000000..22c3fdca8975
--- /dev/null
+++ b/tools/perf/trace/beauty/mmap_flags.sh
@@ -0,0 +1,32 @@
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+if [ $# -ne 2 ] ; then
+	[ $# -eq 1 ] && hostarch=$1 || hostarch=`uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/`
+	header_dir=tools/include/uapi/asm-generic
+	arch_header_dir=tools/arch/${hostarch}/include/uapi/asm
+else
+	header_dir=$1
+	arch_header_dir=$2
+fi
+
+arch_mman=${arch_header_dir}/mman.h
+
+# those in egrep -vw are flags, we want just the bits
+
+printf "static const char *mmap_flags[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MAP_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
+egrep -q $regex ${arch_mman} && \
+(egrep $regex ${arch_mman} | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman} &&
+(egrep $regex ${header_dir}/mman-common.h | \
+	egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.h>.*' ${arch_mman} &&
+(egrep $regex ${header_dir}/mman.h | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+printf "};\n"
diff --git a/tools/perf/trace/beauty/mode_t.c b/tools/perf/trace/beauty/mode_t.c
index d929ad7dd97b..6879d36d3004 100644
--- a/tools/perf/trace/beauty/mode_t.c
+++ b/tools/perf/trace/beauty/mode_t.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
diff --git a/tools/perf/trace/beauty/mount_flags.c b/tools/perf/trace/beauty/mount_flags.c
new file mode 100644
index 000000000000..712935c6620a
--- /dev/null
+++ b/tools/perf/trace/beauty/mount_flags.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * trace/beauty/mount_flags.c
+ *
+ *  Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/log2.h>
+#include <sys/mount.h>
+
+static size_t mount__scnprintf_flags(unsigned long flags, char *bf, size_t size)
+{
+#include "trace/beauty/generated/mount_flags_array.c"
+	static DEFINE_STRARRAY(mount_flags);
+
+	return strarray__scnprintf_flags(&strarray__mount_flags, bf, size, flags);
+}
+
+unsigned long syscall_arg__mask_val_mount_flags(struct syscall_arg *arg __maybe_unused, unsigned long flags)
+{
+	// do_mount in fs/namespace.c:
+	/*
+	 * Pre-0.97 versions of mount() didn't have a flags word.  When the
+	 * flags word was introduced its top half was required to have the
+	 * magic value 0xC0ED, and this remained so until 2.4.0-test9.
+	 * Therefore, if this magic number is present, it carries no
+	 * information and must be discarded.
+	 */
+	if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
+		flags &= ~MS_MGC_MSK;
+
+	return flags;
+}
+
+size_t syscall_arg__scnprintf_mount_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+	unsigned long flags = arg->val;
+
+	return mount__scnprintf_flags(flags, bf, size);
+}
diff --git a/tools/perf/trace/beauty/mount_flags.sh b/tools/perf/trace/beauty/mount_flags.sh
new file mode 100755
index 000000000000..45547573a1db
--- /dev/null
+++ b/tools/perf/trace/beauty/mount_flags.sh
@@ -0,0 +1,15 @@
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+
+printf "static const char *mount_flags[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
+egrep $regex ${header_dir}/fs.h | egrep -v '(MSK|VERBOSE|MGC_VAL)\>' | \
+	sed -r "s/$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 ${header_dir}/fs.h | \
+	sed -r "s/$regex/\2 \1/g" | \
+	xargs printf "\t[%s + 1] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c
index c064d6aae659..1b9d6306d274 100644
--- a/tools/perf/trace/beauty/msg_flags.c
+++ b/tools/perf/trace/beauty/msg_flags.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/socket.h>
 
diff --git a/tools/perf/trace/beauty/open_flags.c b/tools/perf/trace/beauty/open_flags.c
index 6aec6178a99d..cc673fec9184 100644
--- a/tools/perf/trace/beauty/open_flags.c
+++ b/tools/perf/trace/beauty/open_flags.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
diff --git a/tools/perf/trace/beauty/perf_event_open.c b/tools/perf/trace/beauty/perf_event_open.c
index 2bafd7c995ff..981185c1974b 100644
--- a/tools/perf/trace/beauty/perf_event_open.c
+++ b/tools/perf/trace/beauty/perf_event_open.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #ifndef PERF_FLAG_FD_NO_GROUP
 # define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
 #endif
diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh
index 6492c74df928..9aabd9743ef6 100755
--- a/tools/perf/trace/beauty/perf_ioctl.sh
+++ b/tools/perf/trace/beauty/perf_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/pid.c b/tools/perf/trace/beauty/pid.c
index 0313df342830..1a6acc46807b 100644
--- a/tools/perf/trace/beauty/pid.c
+++ b/tools/perf/trace/beauty/pid.c
@@ -1,4 +1,5 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
+
 size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg)
 {
 	int pid = arg->val;
diff --git a/tools/perf/trace/beauty/pkey_alloc.c b/tools/perf/trace/beauty/pkey_alloc.c
index 2ba784a3734a..1b8ed4cac815 100644
--- a/tools/perf/trace/beauty/pkey_alloc.c
+++ b/tools/perf/trace/beauty/pkey_alloc.c
@@ -1,40 +1,36 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/pkey_alloc.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
 #include <linux/kernel.h>
 #include <linux/log2.h>
 
-static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, size_t size)
+size_t strarray__scnprintf_flags(struct strarray *sa, char *bf, size_t size, unsigned long flags)
 {
 	int i, printed = 0;
 
-#include "trace/beauty/generated/pkey_alloc_access_rights_array.c"
-	static DEFINE_STRARRAY(pkey_alloc_access_rights);
-
-	if (access_rights == 0) {
-		const char *s = strarray__pkey_alloc_access_rights.entries[0];
+	if (flags == 0) {
+		const char *s = sa->entries[0];
 		if (s)
 			return scnprintf(bf, size, "%s", s);
 		return scnprintf(bf, size, "%d", 0);
 	}
 
-	for (i = 1; i < strarray__pkey_alloc_access_rights.nr_entries; ++i) {
-		int bit = 1 << (i - 1);
+	for (i = 1; i < sa->nr_entries; ++i) {
+		unsigned long bit = 1UL << (i - 1);
 
-		if (!(access_rights & bit))
+		if (!(flags & bit))
 			continue;
 
 		if (printed != 0)
 			printed += scnprintf(bf + printed, size - printed, "|");
 
-		if (strarray__pkey_alloc_access_rights.entries[i] != NULL)
-			printed += scnprintf(bf + printed, size - printed, "%s", strarray__pkey_alloc_access_rights.entries[i]);
+		if (sa->entries[i] != NULL)
+			printed += scnprintf(bf + printed, size - printed, "%s", sa->entries[i]);
 		else
 			printed += scnprintf(bf + printed, size - printed, "0x%#", bit);
 	}
@@ -42,6 +38,14 @@ static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, s
 	return printed;
 }
 
+static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, size_t size)
+{
+#include "trace/beauty/generated/pkey_alloc_access_rights_array.c"
+	static DEFINE_STRARRAY(pkey_alloc_access_rights);
+
+	return strarray__scnprintf_flags(&strarray__pkey_alloc_access_rights, bf, size, access_rights);
+}
+
 size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg)
 {
 	unsigned long cmd = arg->val;
diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
index e0a51aeb20b2..f8f1b560cf8a 100755
--- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
+++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
diff --git a/tools/perf/trace/beauty/prctl.c b/tools/perf/trace/beauty/prctl.c
index 246130dad6c4..be7a5d395975 100644
--- a/tools/perf/trace/beauty/prctl.c
+++ b/tools/perf/trace/beauty/prctl.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/prctl.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
index f24722146ebe..d32f8f1124af 100755
--- a/tools/perf/trace/beauty/prctl_option.sh
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/sched_policy.c b/tools/perf/trace/beauty/sched_policy.c
index ba5096ae76b6..48f2b5c9aa3e 100644
--- a/tools/perf/trace/beauty/sched_policy.c
+++ b/tools/perf/trace/beauty/sched_policy.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sched.h>
 
 /*
diff --git a/tools/perf/trace/beauty/seccomp.c b/tools/perf/trace/beauty/seccomp.c
index b7097fd5fed9..e36156b19c70 100644
--- a/tools/perf/trace/beauty/seccomp.c
+++ b/tools/perf/trace/beauty/seccomp.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #ifndef SECCOMP_SET_MODE_STRICT
 #define SECCOMP_SET_MODE_STRICT 0
 #endif
diff --git a/tools/perf/trace/beauty/signum.c b/tools/perf/trace/beauty/signum.c
index bde18a53f090..587fec545b8a 100644
--- a/tools/perf/trace/beauty/signum.c
+++ b/tools/perf/trace/beauty/signum.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <signal.h>
 
 static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg)
diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
index eb511bb5fbd3..e0803b957593 100755
--- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
index 6818392968b2..7a464a7bf913 100755
--- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c
index 71a79f72d9d9..9410ad230f10 100644
--- a/tools/perf/trace/beauty/sockaddr.c
+++ b/tools/perf/trace/beauty/sockaddr.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 // Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c
index 65227269384b..d971a2596417 100644
--- a/tools/perf/trace/beauty/socket.c
+++ b/tools/perf/trace/beauty/socket.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/socket.c
  *
diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh
index a3cc24633bec..de0f2f29017f 100755
--- a/tools/perf/trace/beauty/socket_ipproto.sh
+++ b/tools/perf/trace/beauty/socket_ipproto.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/socket_type.c b/tools/perf/trace/beauty/socket_type.c
index bca26aef4a77..a63a9a332aa0 100644
--- a/tools/perf/trace/beauty/socket_type.c
+++ b/tools/perf/trace/beauty/socket_type.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/socket.h>
 
diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c
index 5643b692af4c..630f2760dd66 100644
--- a/tools/perf/trace/beauty/statx.c
+++ b/tools/perf/trace/beauty/statx.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/statx.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
index 0f6a5197d0be..439773daaf77 100755
--- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
+++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/waitid_options.c b/tools/perf/trace/beauty/waitid_options.c
index 8465281a093d..42ff58ad613b 100644
--- a/tools/perf/trace/beauty/waitid_options.c
+++ b/tools/perf/trace/beauty/waitid_options.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/wait.h>
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 28cd6a17491b..6936daf89ddd 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -139,6 +139,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i
 #include "arch/x86/annotate/instructions.c"
 #include "arch/powerpc/annotate/instructions.c"
 #include "arch/s390/annotate/instructions.c"
+#include "arch/sparc/annotate/instructions.c"
 
 static struct arch architectures[] = {
 	{
@@ -170,6 +171,13 @@ static struct arch architectures[] = {
 			.comment_char = '#',
 		},
 	},
+	{
+		.name = "sparc",
+		.init = sparc__annotate_init,
+		.objdump = {
+			.comment_char = '#',
+		},
+	},
 };
 
 static void ins__delete(struct ins_operands *ops)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c4617bcfd521..72d5ba2479bf 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -962,16 +962,23 @@ s64 perf_event__process_auxtrace(struct perf_session *session,
 #define PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ	64
 #define PERF_ITRACE_MAX_LAST_BRANCH_SZ		1024
 
-void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
+				    bool no_sample)
 {
-	synth_opts->instructions = true;
 	synth_opts->branches = true;
 	synth_opts->transactions = true;
 	synth_opts->ptwrites = true;
 	synth_opts->pwr_events = true;
 	synth_opts->errors = true;
-	synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
-	synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	if (no_sample) {
+		synth_opts->period_type = PERF_ITRACE_PERIOD_INSTRUCTIONS;
+		synth_opts->period = 1;
+		synth_opts->calls = true;
+	} else {
+		synth_opts->instructions = true;
+		synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+		synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	}
 	synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
 	synth_opts->last_branch_sz = PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
 	synth_opts->initial_skip = 0;
@@ -999,7 +1006,7 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 	}
 
 	if (!str) {
-		itrace_synth_opts__set_default(synth_opts);
+		itrace_synth_opts__set_default(synth_opts, false);
 		return 0;
 	}
 
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index d88f6e9eb461..8e50f96d4b23 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -58,6 +58,7 @@ enum itrace_period_type {
 /**
  * struct itrace_synth_opts - AUX area tracing synthesis options.
  * @set: indicates whether or not options have been set
+ * @default_no_sample: Default to no sampling.
  * @inject: indicates the event (not just the sample) must be fully synthesized
  *          because 'perf inject' will write it out
  * @instructions: whether to synthesize 'instructions' events
@@ -82,6 +83,7 @@ enum itrace_period_type {
  */
 struct itrace_synth_opts {
 	bool			set;
+	bool			default_no_sample;
 	bool			inject;
 	bool			instructions;
 	bool			branches;
@@ -528,7 +530,8 @@ int perf_event__process_auxtrace_error(struct perf_session *session,
 				       union perf_event *event);
 int itrace_parse_synth_opts(const struct option *opt, const char *str,
 			    int unset);
-void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
+				    bool no_sample);
 
 size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp);
 void perf_session__auxtrace_error_inc(struct perf_session *session,
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 2ae640257fdb..73430b73570d 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -244,6 +244,27 @@ static void cs_etm__free(struct perf_session *session)
 	zfree(&aux);
 }
 
+static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address)
+{
+	struct machine *machine;
+
+	machine = etmq->etm->machine;
+
+	if (address >= etmq->etm->kernel_start) {
+		if (machine__is_host(machine))
+			return PERF_RECORD_MISC_KERNEL;
+		else
+			return PERF_RECORD_MISC_GUEST_KERNEL;
+	} else {
+		if (machine__is_host(machine))
+			return PERF_RECORD_MISC_USER;
+		else if (perf_guest)
+			return PERF_RECORD_MISC_GUEST_USER;
+		else
+			return PERF_RECORD_MISC_HYPERVISOR;
+	}
+}
+
 static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 			      size_t size, u8 *buffer)
 {
@@ -258,10 +279,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 		return -1;
 
 	machine = etmq->etm->machine;
-	if (address >= etmq->etm->kernel_start)
-		cpumode = PERF_RECORD_MISC_KERNEL;
-	else
-		cpumode = PERF_RECORD_MISC_USER;
+	cpumode = cs_etm__cpu_mode(etmq, address);
 
 	thread = etmq->thread;
 	if (!thread) {
@@ -653,7 +671,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	struct perf_sample sample = {.ip = 0,};
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
-	event->sample.header.misc = PERF_RECORD_MISC_USER;
+	event->sample.header.misc = cs_etm__cpu_mode(etmq, addr);
 	event->sample.header.size = sizeof(struct perf_event_header);
 
 	sample.ip = addr;
@@ -665,7 +683,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	sample.cpu = etmq->packet->cpu;
 	sample.flags = 0;
 	sample.insn_len = 1;
-	sample.cpumode = event->header.misc;
+	sample.cpumode = event->sample.header.misc;
 
 	if (etm->synth_opts.last_branch) {
 		cs_etm__copy_last_branch_rb(etmq);
@@ -706,12 +724,15 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 		u64			nr;
 		struct branch_entry	entries;
 	} dummy_bs;
+	u64 ip;
+
+	ip = cs_etm__last_executed_instr(etmq->prev_packet);
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
-	event->sample.header.misc = PERF_RECORD_MISC_USER;
+	event->sample.header.misc = cs_etm__cpu_mode(etmq, ip);
 	event->sample.header.size = sizeof(struct perf_event_header);
 
-	sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
+	sample.ip = ip;
 	sample.pid = etmq->pid;
 	sample.tid = etmq->tid;
 	sample.addr = cs_etm__first_executed_instr(etmq->packet);
@@ -720,7 +741,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 	sample.period = 1;
 	sample.cpu = etmq->packet->cpu;
 	sample.flags = 0;
-	sample.cpumode = PERF_RECORD_MISC_USER;
+	sample.cpumode = event->sample.header.misc;
 
 	/*
 	 * perf report cannot handle events without a branch stack
@@ -1432,7 +1453,8 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
 		etm->synth_opts = *session->itrace_synth_opts;
 	} else {
-		itrace_synth_opts__set_default(&etm->synth_opts);
+		itrace_synth_opts__set_default(&etm->synth_opts,
+				session->itrace_synth_opts->default_no_sample);
 		etm->synth_opts.callchain = false;
 	}
 
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 1f3ccc368530..d01b8355f4ca 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -63,6 +63,7 @@ struct perf_env {
 	struct numa_node	*numa_nodes;
 	struct memory_node	*memory_nodes;
 	unsigned long long	 memory_bsize;
+	u64                     clockid_res_ns;
 };
 
 extern struct perf_env perf_env;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index bc646185f8d9..e9c108a6b1c3 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -308,6 +308,7 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
 	event->fork.pid  = tgid;
 	event->fork.tid  = pid;
 	event->fork.header.type = PERF_RECORD_FORK;
+	event->fork.header.misc = PERF_RECORD_MISC_FORK_EXEC;
 
 	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index be440df29615..e88e6f9b1463 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -358,7 +358,7 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 	struct perf_evsel *pos;
 
 	evlist__for_each_entry(evlist, pos) {
-		if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+		if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->fd)
 			continue;
 		perf_evsel__disable(pos);
 	}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 29d7b97f66fb..6d187059a373 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -232,6 +232,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->leader	   = evsel;
 	evsel->unit	   = "";
 	evsel->scale	   = 1.0;
+	evsel->max_events  = ULONG_MAX;
 	evsel->evlist	   = NULL;
 	evsel->bpf_fd	   = -1;
 	INIT_LIST_HEAD(&evsel->node);
@@ -793,6 +794,9 @@ static void apply_config_terms(struct perf_evsel *evsel,
 		case PERF_EVSEL__CONFIG_TERM_MAX_STACK:
 			max_stack = term->val.max_stack;
 			break;
+		case PERF_EVSEL__CONFIG_TERM_MAX_EVENTS:
+			evsel->max_events = term->val.max_events;
+			break;
 		case PERF_EVSEL__CONFIG_TERM_INHERIT:
 			/*
 			 * attr->inherit should has already been set by
@@ -1203,16 +1207,27 @@ int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter)
 
 int perf_evsel__enable(struct perf_evsel *evsel)
 {
-	return perf_evsel__run_ioctl(evsel,
-				     PERF_EVENT_IOC_ENABLE,
-				     0);
+	int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0);
+
+	if (!err)
+		evsel->disabled = false;
+
+	return err;
 }
 
 int perf_evsel__disable(struct perf_evsel *evsel)
 {
-	return perf_evsel__run_ioctl(evsel,
-				     PERF_EVENT_IOC_DISABLE,
-				     0);
+	int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0);
+	/*
+	 * We mark it disabled here so that tools that disable a event can
+	 * ignore events after they disable it. I.e. the ring buffer may have
+	 * already a few more events queued up before the kernel got the stop
+	 * request.
+	 */
+	if (!err)
+		evsel->disabled = true;
+
+	return err;
 }
 
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4107c39f4a54..3147ca76c6fc 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -46,6 +46,7 @@ enum term_type {
 	PERF_EVSEL__CONFIG_TERM_STACK_USER,
 	PERF_EVSEL__CONFIG_TERM_INHERIT,
 	PERF_EVSEL__CONFIG_TERM_MAX_STACK,
+	PERF_EVSEL__CONFIG_TERM_MAX_EVENTS,
 	PERF_EVSEL__CONFIG_TERM_OVERWRITE,
 	PERF_EVSEL__CONFIG_TERM_DRV_CFG,
 	PERF_EVSEL__CONFIG_TERM_BRANCH,
@@ -65,6 +66,7 @@ struct perf_evsel_config_term {
 		bool	inherit;
 		bool	overwrite;
 		char	*branch;
+		unsigned long max_events;
 	} val;
 	bool weak;
 };
@@ -99,6 +101,8 @@ struct perf_evsel {
 	struct perf_counts	*prev_raw_counts;
 	int			idx;
 	u32			ids;
+	unsigned long		max_events;
+	unsigned long		nr_events_printed;
 	char			*name;
 	double			scale;
 	const char		*unit;
@@ -119,6 +123,7 @@ struct perf_evsel {
 	bool			snapshot;
 	bool 			supported;
 	bool 			needs_swap;
+	bool 			disabled;
 	bool			no_aux_samples;
 	bool			immediate;
 	bool			system_wide;
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index de322d51c7fe..b72440bf9a79 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -29,6 +29,12 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
 #elif defined(__powerpc__)
 #define GEN_ELF_ARCH	EM_PPC
 #define GEN_ELF_CLASS	ELFCLASS32
+#elif defined(__sparc__) && defined(__arch64__)
+#define GEN_ELF_ARCH	EM_SPARCV9
+#define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__sparc__)
+#define GEN_ELF_ARCH	EM_SPARC
+#define GEN_ELF_CLASS	ELFCLASS32
 #else
 #error "unsupported architecture"
 #endif
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 1ec1d9bc2d63..4fd45be95a43 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1034,6 +1034,13 @@ static int write_auxtrace(struct feat_fd *ff,
 	return err;
 }
 
+static int write_clockid(struct feat_fd *ff,
+			 struct perf_evlist *evlist __maybe_unused)
+{
+	return do_write(ff, &ff->ph->env.clockid_res_ns,
+			sizeof(ff->ph->env.clockid_res_ns));
+}
+
 static int cpu_cache_level__sort(const void *a, const void *b)
 {
 	struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a;
@@ -1508,6 +1515,12 @@ static void print_cpu_topology(struct feat_fd *ff, FILE *fp)
 		fprintf(fp, "# Core ID and Socket ID information is not available\n");
 }
 
+static void print_clockid(struct feat_fd *ff, FILE *fp)
+{
+	fprintf(fp, "# clockid frequency: %"PRIu64" MHz\n",
+		ff->ph->env.clockid_res_ns * 1000);
+}
+
 static void free_event_desc(struct perf_evsel *events)
 {
 	struct perf_evsel *evsel;
@@ -2531,6 +2544,15 @@ out:
 	return ret;
 }
 
+static int process_clockid(struct feat_fd *ff,
+			   void *data __maybe_unused)
+{
+	if (do_read_u64(ff, &ff->ph->env.clockid_res_ns))
+		return -1;
+
+	return 0;
+}
+
 struct feature_ops {
 	int (*write)(struct feat_fd *ff, struct perf_evlist *evlist);
 	void (*print)(struct feat_fd *ff, FILE *fp);
@@ -2590,6 +2612,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPN(CACHE,		cache,		true),
 	FEAT_OPR(SAMPLE_TIME,	sample_time,	false),
 	FEAT_OPR(MEM_TOPOLOGY,	mem_topology,	true),
+	FEAT_OPR(CLOCKID,       clockid,        false)
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index e17903caa71d..0d553ddca0a3 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -38,6 +38,7 @@ enum {
 	HEADER_CACHE,
 	HEADER_SAMPLE_TIME,
 	HEADER_MEM_TOPOLOGY,
+	HEADER_CLOCKID,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 7f0c83b6332b..7b27d77306c2 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -269,6 +269,13 @@ static int intel_bts_do_fix_overlap(struct auxtrace_queue *queue,
 	return 0;
 }
 
+static inline u8 intel_bts_cpumode(struct intel_bts *bts, uint64_t ip)
+{
+	return machine__kernel_ip(bts->machine, ip) ?
+	       PERF_RECORD_MISC_KERNEL :
+	       PERF_RECORD_MISC_USER;
+}
+
 static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 					 struct branch *branch)
 {
@@ -281,12 +288,8 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	    bts->num_events++ <= bts->synth_opts.initial_skip)
 		return 0;
 
-	event.sample.header.type = PERF_RECORD_SAMPLE;
-	event.sample.header.misc = PERF_RECORD_MISC_USER;
-	event.sample.header.size = sizeof(struct perf_event_header);
-
-	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = le64_to_cpu(branch->from);
+	sample.cpumode = intel_bts_cpumode(bts, sample.ip);
 	sample.pid = btsq->pid;
 	sample.tid = btsq->tid;
 	sample.addr = le64_to_cpu(branch->to);
@@ -298,6 +301,10 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	sample.insn_len = btsq->intel_pt_insn.length;
 	memcpy(sample.insn, btsq->intel_pt_insn.buf, INTEL_PT_INSN_BUF_SZ);
 
+	event.sample.header.type = PERF_RECORD_SAMPLE;
+	event.sample.header.misc = sample.cpumode;
+	event.sample.header.size = sizeof(struct perf_event_header);
+
 	if (bts->synth_opts.inject) {
 		event.sample.header.size = bts->branches_event_size;
 		ret = perf_event__synthesize_sample(&event,
@@ -910,7 +917,8 @@ int intel_bts_process_auxtrace_info(union perf_event *event,
 	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
 		bts->synth_opts = *session->itrace_synth_opts;
 	} else {
-		itrace_synth_opts__set_default(&bts->synth_opts);
+		itrace_synth_opts__set_default(&bts->synth_opts,
+				session->itrace_synth_opts->default_no_sample);
 		if (session->itrace_synth_opts)
 			bts->synth_opts.thread_stack =
 				session->itrace_synth_opts->thread_stack;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 48c1d415c6b0..86cc9a64e982 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -407,6 +407,13 @@ intel_pt_cache_lookup(struct dso *dso, struct machine *machine, u64 offset)
 	return auxtrace_cache__lookup(dso->auxtrace_cache, offset);
 }
 
+static inline u8 intel_pt_cpumode(struct intel_pt *pt, uint64_t ip)
+{
+	return ip >= pt->kernel_start ?
+	       PERF_RECORD_MISC_KERNEL :
+	       PERF_RECORD_MISC_USER;
+}
+
 static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 				   uint64_t *insn_cnt_ptr, uint64_t *ip,
 				   uint64_t to_ip, uint64_t max_insn_cnt,
@@ -429,10 +436,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 	if (to_ip && *ip == to_ip)
 		goto out_no_cache;
 
-	if (*ip >= ptq->pt->kernel_start)
-		cpumode = PERF_RECORD_MISC_KERNEL;
-	else
-		cpumode = PERF_RECORD_MISC_USER;
+	cpumode = intel_pt_cpumode(ptq->pt, *ip);
 
 	thread = ptq->thread;
 	if (!thread) {
@@ -759,7 +763,8 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 	if (pt->synth_opts.callchain) {
 		size_t sz = sizeof(struct ip_callchain);
 
-		sz += pt->synth_opts.callchain_sz * sizeof(u64);
+		/* Add 1 to callchain_sz for callchain context */
+		sz += (pt->synth_opts.callchain_sz + 1) * sizeof(u64);
 		ptq->chain = zalloc(sz);
 		if (!ptq->chain)
 			goto out_free;
@@ -1058,15 +1063,11 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
 				   union perf_event *event,
 				   struct perf_sample *sample)
 {
-	event->sample.header.type = PERF_RECORD_SAMPLE;
-	event->sample.header.misc = PERF_RECORD_MISC_USER;
-	event->sample.header.size = sizeof(struct perf_event_header);
-
 	if (!pt->timeless_decoding)
 		sample->time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
-	sample->cpumode = PERF_RECORD_MISC_USER;
 	sample->ip = ptq->state->from_ip;
+	sample->cpumode = intel_pt_cpumode(pt, sample->ip);
 	sample->pid = ptq->pid;
 	sample->tid = ptq->tid;
 	sample->addr = ptq->state->to_ip;
@@ -1075,6 +1076,10 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
 	sample->flags = ptq->flags;
 	sample->insn_len = ptq->insn_len;
 	memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
+
+	event->sample.header.type = PERF_RECORD_SAMPLE;
+	event->sample.header.misc = sample->cpumode;
+	event->sample.header.size = sizeof(struct perf_event_header);
 }
 
 static int intel_pt_inject_event(union perf_event *event,
@@ -1160,7 +1165,8 @@ static void intel_pt_prep_sample(struct intel_pt *pt,
 
 	if (pt->synth_opts.callchain) {
 		thread_stack__sample(ptq->thread, ptq->chain,
-				     pt->synth_opts.callchain_sz, sample->ip);
+				     pt->synth_opts.callchain_sz + 1,
+				     sample->ip, pt->kernel_start);
 		sample->callchain = ptq->chain;
 	}
 
@@ -2559,7 +2565,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
 		pt->synth_opts = *session->itrace_synth_opts;
 	} else {
-		itrace_synth_opts__set_default(&pt->synth_opts);
+		itrace_synth_opts__set_default(&pt->synth_opts,
+				session->itrace_synth_opts->default_no_sample);
 		if (use_browser != -1) {
 			pt->synth_opts.branches = false;
 			pt->synth_opts.callchain = true;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 111ae858cbcb..8f36ce813bc5 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1708,6 +1708,7 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 	struct thread *parent = machine__findnew_thread(machine,
 							event->fork.ppid,
 							event->fork.ptid);
+	bool do_maps_clone = true;
 	int err = 0;
 
 	if (dump_trace)
@@ -1736,9 +1737,25 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 
 	thread = machine__findnew_thread(machine, event->fork.pid,
 					 event->fork.tid);
+	/*
+	 * When synthesizing FORK events, we are trying to create thread
+	 * objects for the already running tasks on the machine.
+	 *
+	 * Normally, for a kernel FORK event, we want to clone the parent's
+	 * maps because that is what the kernel just did.
+	 *
+	 * But when synthesizing, this should not be done.  If we do, we end up
+	 * with overlapping maps as we process the sythesized MMAP2 events that
+	 * get delivered shortly thereafter.
+	 *
+	 * Use the FORK event misc flags in an internal way to signal this
+	 * situation, so we can elide the map clone when appropriate.
+	 */
+	if (event->fork.header.misc & PERF_RECORD_MISC_FORK_EXEC)
+		do_maps_clone = false;
 
 	if (thread == NULL || parent == NULL ||
-	    thread__fork(thread, parent, sample->time) < 0) {
+	    thread__fork(thread, parent, sample->time, do_maps_clone) < 0) {
 		dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
 		err = -1;
 	}
@@ -2140,6 +2157,27 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 	return 0;
 }
 
+static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
+			     struct callchain_cursor *cursor,
+			     struct symbol **parent,
+			     struct addr_location *root_al,
+			     u8 *cpumode, int ent)
+{
+	int err = 0;
+
+	while (--ent >= 0) {
+		u64 ip = chain->ips[ent];
+
+		if (ip >= PERF_CONTEXT_MAX) {
+			err = add_callchain_ip(thread, cursor, parent,
+					       root_al, cpumode, ip,
+					       false, NULL, NULL, 0);
+			break;
+		}
+	}
+	return err;
+}
+
 static int thread__resolve_callchain_sample(struct thread *thread,
 					    struct callchain_cursor *cursor,
 					    struct perf_evsel *evsel,
@@ -2246,6 +2284,12 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	}
 
 check_calls:
+	if (callchain_param.order != ORDER_CALLEE) {
+		err = find_prev_cpumode(chain, thread, cursor, parent, root_al,
+					&cpumode, chain->nr - first_call);
+		if (err)
+			return (err < 0) ? err : 0;
+	}
 	for (i = first_call, nr_entries = 0;
 	     i < chain_nr && nr_entries < max_stack; i++) {
 		u64 ip;
@@ -2260,9 +2304,15 @@ check_calls:
 			continue;
 #endif
 		ip = chain->ips[j];
-
 		if (ip < PERF_CONTEXT_MAX)
                        ++nr_entries;
+		else if (callchain_param.order != ORDER_CALLEE) {
+			err = find_prev_cpumode(chain, thread, cursor, parent,
+						root_al, &cpumode, j);
+			if (err)
+				return (err < 0) ? err : 0;
+			continue;
+		}
 
 		err = add_callchain_ip(thread, cursor, parent,
 				       root_al, &cpumode, ip,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f8cd3e7c9186..59be3466d64d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -926,6 +926,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
 	[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
 	[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
 	[PARSE_EVENTS__TERM_TYPE_MAX_STACK]		= "max-stack",
+	[PARSE_EVENTS__TERM_TYPE_MAX_EVENTS]		= "nr",
 	[PARSE_EVENTS__TERM_TYPE_OVERWRITE]		= "overwrite",
 	[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]		= "no-overwrite",
 	[PARSE_EVENTS__TERM_TYPE_DRV_CFG]		= "driver-config",
@@ -1037,6 +1038,9 @@ do {									   \
 	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
 		CHECK_TYPE_VAL(NUM);
 		break;
+	case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+		CHECK_TYPE_VAL(NUM);
+		break;
 	default:
 		err->str = strdup("unknown term");
 		err->idx = term->err_term;
@@ -1084,6 +1088,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	case PARSE_EVENTS__TERM_TYPE_INHERIT:
 	case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
 	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+	case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
 	case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
 	case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
 		return config_term_common(attr, term, err);
@@ -1162,6 +1167,9 @@ do {								\
 		case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
 			ADD_CONFIG_TERM(MAX_STACK, max_stack, term->val.num);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+			ADD_CONFIG_TERM(MAX_EVENTS, max_events, term->val.num);
+			break;
 		case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
 			ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 1 : 0);
 			break;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 4473dac27aee..5ed035cbcbb7 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -71,6 +71,7 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_NOINHERIT,
 	PARSE_EVENTS__TERM_TYPE_INHERIT,
 	PARSE_EVENTS__TERM_TYPE_MAX_STACK,
+	PARSE_EVENTS__TERM_TYPE_MAX_EVENTS,
 	PARSE_EVENTS__TERM_TYPE_NOOVERWRITE,
 	PARSE_EVENTS__TERM_TYPE_OVERWRITE,
 	PARSE_EVENTS__TERM_TYPE_DRV_CFG,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 5f761f3ed0f3..7805c71aaae2 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -269,6 +269,7 @@ time			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_TIME); }
 call-graph		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CALLGRAPH); }
 stack-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_STACKSIZE); }
 max-stack		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_STACK); }
+nr			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_EVENTS); }
 inherit			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_INHERIT); }
 no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); }
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 0281d5e2cd67..66a84d5846c8 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -324,7 +324,17 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss)
 			plt_entry_size = 16;
 			break;
 
-		default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/sparc/xtensa need to be checked */
+		case EM_SPARC:
+			plt_header_size = 48;
+			plt_entry_size = 12;
+			break;
+
+		case EM_SPARCV9:
+			plt_header_size = 128;
+			plt_entry_size = 32;
+			break;
+
+		default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/xtensa need to be checked */
 			plt_header_size = shdr_plt.sh_entsize;
 			plt_entry_size = shdr_plt.sh_entsize;
 			break;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 20f49779116b..d026d215bdc6 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -123,7 +123,8 @@ struct symbol_conf {
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
-			*field_sep;
+			*field_sep,
+			*graph_function;
 	const char	*default_guest_vmlinux_name,
 			*default_guest_kallsyms,
 			*default_guest_modules;
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index c091635bf7dc..61a4286a74dc 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -310,20 +310,46 @@ void thread_stack__free(struct thread *thread)
 	}
 }
 
-void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
-			  size_t sz, u64 ip)
+static inline u64 callchain_context(u64 ip, u64 kernel_start)
 {
-	size_t i;
+	return ip < kernel_start ? PERF_CONTEXT_USER : PERF_CONTEXT_KERNEL;
+}
 
-	if (!thread || !thread->ts)
-		chain->nr = 1;
-	else
-		chain->nr = min(sz, thread->ts->cnt + 1);
+void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+			  size_t sz, u64 ip, u64 kernel_start)
+{
+	u64 context = callchain_context(ip, kernel_start);
+	u64 last_context;
+	size_t i, j;
 
-	chain->ips[0] = ip;
+	if (sz < 2) {
+		chain->nr = 0;
+		return;
+	}
 
-	for (i = 1; i < chain->nr; i++)
-		chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
+	chain->ips[0] = context;
+	chain->ips[1] = ip;
+
+	if (!thread || !thread->ts) {
+		chain->nr = 2;
+		return;
+	}
+
+	last_context = context;
+
+	for (i = 2, j = 1; i < sz && j <= thread->ts->cnt; i++, j++) {
+		ip = thread->ts->stack[thread->ts->cnt - j].ret_addr;
+		context = callchain_context(ip, kernel_start);
+		if (context != last_context) {
+			if (i >= sz - 1)
+				break;
+			chain->ips[i++] = context;
+			last_context = context;
+		}
+		chain->ips[i] = ip;
+	}
+
+	chain->nr = i;
 }
 
 struct call_return_processor *
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index b7e41c4ebfdd..f97c00a8c251 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -84,7 +84,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 			u64 to_ip, u16 insn_len, u64 trace_nr);
 void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
 void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
-			  size_t sz, u64 ip);
+			  size_t sz, u64 ip, u64 kernel_start);
 int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
 size_t thread_stack__depth(struct thread *thread);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 2048d393ece6..3d9ed7d0e281 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -330,7 +330,8 @@ static int thread__prepare_access(struct thread *thread)
 }
 
 static int thread__clone_map_groups(struct thread *thread,
-				    struct thread *parent)
+				    struct thread *parent,
+				    bool do_maps_clone)
 {
 	/* This is new thread, we share map groups for process. */
 	if (thread->pid_ == parent->pid_)
@@ -341,15 +342,11 @@ static int thread__clone_map_groups(struct thread *thread,
 			 thread->pid_, thread->tid, parent->pid_, parent->tid);
 		return 0;
 	}
-
 	/* But this one is new process, copy maps. */
-	if (map_groups__clone(thread, parent->mg) < 0)
-		return -ENOMEM;
-
-	return 0;
+	return do_maps_clone ? map_groups__clone(thread, parent->mg) : 0;
 }
 
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone)
 {
 	if (parent->comm_set) {
 		const char *comm = thread__comm_str(parent);
@@ -362,7 +359,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 	}
 
 	thread->ppid = parent->tid;
-	return thread__clone_map_groups(thread, parent);
+	return thread__clone_map_groups(thread, parent, do_maps_clone);
 }
 
 void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 07606aa6998d..30e2b4c165fe 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -42,6 +42,8 @@ struct thread {
 	void				*addr_space;
 	struct unwind_libunwind_ops	*unwind_libunwind_ops;
 #endif
+	bool			filter;
+	int			filter_entry_depth;
 };
 
 struct machine;
@@ -87,7 +89,7 @@ struct comm *thread__comm(const struct thread *thread);
 struct comm *thread__exec_comm(const struct thread *thread);
 const char *thread__comm_str(const struct thread *thread);
 int thread__insert_map(struct thread *thread, struct map *map);
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
 struct thread *thread__main_thread(struct machine *machine, struct thread *thread);
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 6f318b15950e..5eff9bfc5758 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -45,13 +45,13 @@ static int __report_module(struct addr_location *al, u64 ip,
 		Dwarf_Addr s;
 
 		dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
-		if (s != al->map->start)
+		if (s != al->map->start - al->map->pgoff)
 			mod = 0;
 	}
 
 	if (!mod)
 		mod = dwfl_report_elf(ui->dwfl, dso->short_name,
-				      (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start,
+				      (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start - al->map->pgoff,
 				      false);
 
 	return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1;