Merge tag 'perf-core-for-mingo-4.13-20170718' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

- Initial support for namespaces, using setns to access files in
  namespaces, grabbing their build-ids, etc. We still need to work
  more to deal with namespaces that vanish before we can get the
  needed data to do analysis, but this should be as good as what is
  in bcc now (Krister Johansen)

- Add header record types to pipe-mode, now this command:

  $ perf record -o - -e cycles sleep 1 | perf report --stdio --header

  Will show the same as in non-pipe mode, i.e. involving a perf.data
  file (David Carrillo-Cisneros)

- Implement a visual marker for fused x86 instructions in the annotate
  TUI browser, available now in 'perf report', more work needed to have
  it available as well in 'perf top' (Jin Yao)

  Further explanation from one of Jin's patches:

       │   ┌──cmpl   $0x0,argp_program_version_hook
 81.93 │   ├──je     20
       │   │  lock   cmpxchg %esi,0x38a9a4(%rip)
       │   │↓ jne    29
       │   │↓ jmp    43
 11.47 │20:└─→cmpxch %esi,0x38a999(%rip)

  That means the cmpl+je is a fused instruction pair and they should be
  considered together.

- Record the branch type and then show statistics and info about
  in callchain entries (Jin Yao)

  Example from one of Jin's patches:

  # perf record -g -j any,save_type
  # perf report --branch-history --stdio --no-children

  38.50%  div.c:45                [.] main                    div
          |
          ---main div.c:42 (RET CROSS_2M cycles:2)
             compute_flag div.c:28 (cycles:2)
             compute_flag div.c:27 (RET CROSS_2M cycles:1)
             rand rand.c:28 (cycles:1)
             rand rand.c:28 (RET CROSS_2M cycles:1)
             __random random.c:298 (cycles:1)
             __random random.c:297 (COND_BWD CROSS_2M cycles:1)
             __random random.c:295 (cycles:1)
             __random random.c:295 (COND_BWD CROSS_2M cycles:1)
             __random random.c:295 (cycles:1)
             __random random.c:295 (RET CROSS_2M cycles:9)

- Beautify the fcntl syscall, which is an interesting one in the sense
  that infrastructure had to be put in place to change the formatters of
  some arguments according to the value in a previous one, i.e. cmd
  dictates how arg and the syscall return will be formatted.
  (Arnaldo Carvalho de Melo

Infrastructure changes:

- 'perf test attr' fixes (Jiri Olsa)

Vendor events changes:

- Add POWER9 PMU events Sukadev (Bhattiprolu)

- Support additional POWER8+ PVR in PMU mapfile (Shriya)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 267 insertions, 1 deletions

diff --git a/tools/include/uapi/asm-generic/fcntl.h b/tools/include/uapi/asm-generic/fcntl.h
new file mode 100644
index 000000000000..ac190958c981
--- /dev/null
+++ b/tools/include/uapi/asm-generic/fcntl.h
@@ -0,0 +1,220 @@
+#ifndef _ASM_GENERIC_FCNTL_H
+#define _ASM_GENERIC_FCNTL_H
+
+#include <linux/types.h>
+
+/*
+ * FMODE_EXEC is 0x20
+ * FMODE_NONOTIFY is 0x4000000
+ * These cannot be used by userspace O_* until internal and external open
+ * flags are split.
+ * -Eric Paris
+ */
+
+/*
+ * When introducing new O_* bits, please check its uniqueness in fcntl_init().
+ */
+
+#define O_ACCMODE	00000003
+#define O_RDONLY	00000000
+#define O_WRONLY	00000001
+#define O_RDWR		00000002
+#ifndef O_CREAT
+#define O_CREAT		00000100	/* not fcntl */
+#endif
+#ifndef O_EXCL
+#define O_EXCL		00000200	/* not fcntl */
+#endif
+#ifndef O_NOCTTY
+#define O_NOCTTY	00000400	/* not fcntl */
+#endif
+#ifndef O_TRUNC
+#define O_TRUNC		00001000	/* not fcntl */
+#endif
+#ifndef O_APPEND
+#define O_APPEND	00002000
+#endif
+#ifndef O_NONBLOCK
+#define O_NONBLOCK	00004000
+#endif
+#ifndef O_DSYNC
+#define O_DSYNC		00010000	/* used to be O_SYNC, see below */
+#endif
+#ifndef FASYNC
+#define FASYNC		00020000	/* fcntl, for BSD compatibility */
+#endif
+#ifndef O_DIRECT
+#define O_DIRECT	00040000	/* direct disk access hint */
+#endif
+#ifndef O_LARGEFILE
+#define O_LARGEFILE	00100000
+#endif
+#ifndef O_DIRECTORY
+#define O_DIRECTORY	00200000	/* must be a directory */
+#endif
+#ifndef O_NOFOLLOW
+#define O_NOFOLLOW	00400000	/* don't follow links */
+#endif
+#ifndef O_NOATIME
+#define O_NOATIME	01000000
+#endif
+#ifndef O_CLOEXEC
+#define O_CLOEXEC	02000000	/* set close_on_exec */
+#endif
+
+/*
+ * Before Linux 2.6.33 only O_DSYNC semantics were implemented, but using
+ * the O_SYNC flag.  We continue to use the existing numerical value
+ * for O_DSYNC semantics now, but using the correct symbolic name for it.
+ * This new value is used to request true Posix O_SYNC semantics.  It is
+ * defined in this strange way to make sure applications compiled against
+ * new headers get at least O_DSYNC semantics on older kernels.
+ *
+ * This has the nice side-effect that we can simply test for O_DSYNC
+ * wherever we do not care if O_DSYNC or O_SYNC is used.
+ *
+ * Note: __O_SYNC must never be used directly.
+ */
+#ifndef O_SYNC
+#define __O_SYNC	04000000
+#define O_SYNC		(__O_SYNC|O_DSYNC)
+#endif
+
+#ifndef O_PATH
+#define O_PATH		010000000
+#endif
+
+#ifndef __O_TMPFILE
+#define __O_TMPFILE	020000000
+#endif
+
+/* a horrid kludge trying to make sure that this will fail on old kernels */
+#define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
+#define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT)
+
+#ifndef O_NDELAY
+#define O_NDELAY	O_NONBLOCK
+#endif
+
+#define F_DUPFD		0	/* dup */
+#define F_GETFD		1	/* get close_on_exec */
+#define F_SETFD		2	/* set/clear close_on_exec */
+#define F_GETFL		3	/* get file->f_flags */
+#define F_SETFL		4	/* set file->f_flags */
+#ifndef F_GETLK
+#define F_GETLK		5
+#define F_SETLK		6
+#define F_SETLKW	7
+#endif
+#ifndef F_SETOWN
+#define F_SETOWN	8	/* for sockets. */
+#define F_GETOWN	9	/* for sockets. */
+#endif
+#ifndef F_SETSIG
+#define F_SETSIG	10	/* for sockets. */
+#define F_GETSIG	11	/* for sockets. */
+#endif
+
+#ifndef CONFIG_64BIT
+#ifndef F_GETLK64
+#define F_GETLK64	12	/*  using 'struct flock64' */
+#define F_SETLK64	13
+#define F_SETLKW64	14
+#endif
+#endif
+
+#ifndef F_SETOWN_EX
+#define F_SETOWN_EX	15
+#define F_GETOWN_EX	16
+#endif
+
+#ifndef F_GETOWNER_UIDS
+#define F_GETOWNER_UIDS	17
+#endif
+
+/*
+ * Open File Description Locks
+ *
+ * Usually record locks held by a process are released on *any* close and are
+ * not inherited across a fork().
+ *
+ * These cmd values will set locks that conflict with process-associated
+ * record  locks, but are "owned" by the open file description, not the
+ * process. This means that they are inherited across fork() like BSD (flock)
+ * locks, and they are only released automatically when the last reference to
+ * the the open file against which they were acquired is put.
+ */
+#define F_OFD_GETLK	36
+#define F_OFD_SETLK	37
+#define F_OFD_SETLKW	38
+
+#define F_OWNER_TID	0
+#define F_OWNER_PID	1
+#define F_OWNER_PGRP	2
+
+struct f_owner_ex {
+	int	type;
+	__kernel_pid_t	pid;
+};
+
+/* for F_[GET|SET]FL */
+#define FD_CLOEXEC	1	/* actually anything with low bit set goes */
+
+/* for posix fcntl() and lockf() */
+#ifndef F_RDLCK
+#define F_RDLCK		0
+#define F_WRLCK		1
+#define F_UNLCK		2
+#endif
+
+/* for old implementation of bsd flock () */
+#ifndef F_EXLCK
+#define F_EXLCK		4	/* or 3 */
+#define F_SHLCK		8	/* or 4 */
+#endif
+
+/* operations for bsd flock(), also used by the kernel implementation */
+#define LOCK_SH		1	/* shared lock */
+#define LOCK_EX		2	/* exclusive lock */
+#define LOCK_NB		4	/* or'd with one of the above to prevent
+				   blocking */
+#define LOCK_UN		8	/* remove lock */
+
+#define LOCK_MAND	32	/* This is a mandatory flock ... */
+#define LOCK_READ	64	/* which allows concurrent read operations */
+#define LOCK_WRITE	128	/* which allows concurrent write operations */
+#define LOCK_RW		192	/* which allows concurrent read & write ops */
+
+#define F_LINUX_SPECIFIC_BASE	1024
+
+#ifndef HAVE_ARCH_STRUCT_FLOCK
+#ifndef __ARCH_FLOCK_PAD
+#define __ARCH_FLOCK_PAD
+#endif
+
+struct flock {
+	short	l_type;
+	short	l_whence;
+	__kernel_off_t	l_start;
+	__kernel_off_t	l_len;
+	__kernel_pid_t	l_pid;
+	__ARCH_FLOCK_PAD
+};
+#endif
+
+#ifndef HAVE_ARCH_STRUCT_FLOCK64
+#ifndef __ARCH_FLOCK64_PAD
+#define __ARCH_FLOCK64_PAD
+#endif
+
+struct flock64 {
+	short  l_type;
+	short  l_whence;
+	__kernel_loff_t l_start;
+	__kernel_loff_t l_len;
+	__kernel_pid_t  l_pid;
+	__ARCH_FLOCK64_PAD
+};
+#endif
+
+#endif /* _ASM_GENERIC_FCNTL_H */
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 813afd6eee71..ec69d55bcec7 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -43,6 +43,27 @@
 /* (1U << 31) is reserved for signed error codes */
 
 /*
+ * Set/Get write life time hints. {GET,SET}_RW_HINT operate on the
+ * underlying inode, while {GET,SET}_FILE_RW_HINT operate only on
+ * the specific file.
+ */
+#define F_GET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 11)
+#define F_SET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 12)
+#define F_GET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 13)
+#define F_SET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 14)
+
+/*
+ * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
+ * used to clear any hints previously set.
+ */
+#define RWF_WRITE_LIFE_NOT_SET	0
+#define RWH_WRITE_LIFE_NONE	1
+#define RWH_WRITE_LIFE_SHORT	2
+#define RWH_WRITE_LIFE_MEDIUM	3
+#define RWH_WRITE_LIFE_LONG	4
+#define RWH_WRITE_LIFE_EXTREME	5
+
+/*
  * Types of directory notifications that may be requested.
  */
 #define DN_ACCESS	0x00000001	/* File accessed */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index b1c0b187acfe..642db5fa3286 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -174,6 +174,8 @@ enum perf_branch_sample_type_shift {
 	PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT	= 14, /* no flags */
 	PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT	= 15, /* no cycles */
 
+	PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT	= 16, /* save branch type */
+
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
 
@@ -198,9 +200,30 @@ enum perf_branch_sample_type {
 	PERF_SAMPLE_BRANCH_NO_FLAGS	= 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT,
 	PERF_SAMPLE_BRANCH_NO_CYCLES	= 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT,
 
+	PERF_SAMPLE_BRANCH_TYPE_SAVE	=
+		1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT,
+
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
+/*
+ * Common flow change classification
+ */
+enum {
+	PERF_BR_UNKNOWN		= 0,	/* unknown */
+	PERF_BR_COND		= 1,	/* conditional */
+	PERF_BR_UNCOND		= 2,	/* unconditional  */
+	PERF_BR_IND		= 3,	/* indirect */
+	PERF_BR_CALL		= 4,	/* function call */
+	PERF_BR_IND_CALL	= 5,	/* indirect function call */
+	PERF_BR_RET		= 6,	/* function return */
+	PERF_BR_SYSCALL		= 7,	/* syscall */
+	PERF_BR_SYSRET		= 8,	/* syscall return */
+	PERF_BR_COND_CALL	= 9,	/* conditional function call */
+	PERF_BR_COND_RET	= 10,	/* conditional function return */
+	PERF_BR_MAX,
+};
+
 #define PERF_SAMPLE_BRANCH_PLM_ALL \
 	(PERF_SAMPLE_BRANCH_USER|\
 	 PERF_SAMPLE_BRANCH_KERNEL|\
@@ -1015,6 +1038,7 @@ union perf_mem_data_src {
  *     in_tx: running in a hardware transaction
  *     abort: aborting a hardware transaction
  *    cycles: cycles from last branch (or 0 if not supported)
+ *      type: branch type
  */
 struct perf_branch_entry {
 	__u64	from;
@@ -1024,7 +1048,8 @@ struct perf_branch_entry {
 		in_tx:1,    /* in transaction */
 		abort:1,    /* transaction abort */
 		cycles:16,  /* cycle count to last branch */
-		reserved:44;
+		type:4,     /* branch type */
+		reserved:40;
 };
 
 #endif /* _UAPI_LINUX_PERF_EVENT_H */