Merge Linus' tree to be be to apply submitted patches to newer code than

current trivial.git base

270 files changed, 14089 insertions, 2277 deletions

diff --git a/tools/include/tools/endian.h b/tools/include/tools/endian.h
new file mode 100644
index 000000000000..8001194008da
--- /dev/null
+++ b/tools/include/tools/endian.h
@@ -0,0 +1,56 @@
+#ifndef _TOOLS_ENDIAN_H
+#define _TOOLS_ENDIAN_H
+
+#include <byteswap.h>
+
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+
+#ifndef htole16
+#define htole16(x) (x)
+#endif
+#ifndef htole32
+#define htole32(x) (x)
+#endif
+#ifndef htole64
+#define htole64(x) (x)
+#endif
+
+#ifndef le16toh
+#define le16toh(x) (x)
+#endif
+
+#ifndef le32toh
+#define le32toh(x) (x)
+#endif
+
+#ifndef le64toh
+#define le64toh(x) (x)
+#endif
+
+#else /* __BYTE_ORDER */
+
+#ifndef htole16
+#define htole16(x) __bswap_16(x)
+#endif
+#ifndef htole32
+#define htole32(x) __bswap_32(x)
+#endif
+#ifndef htole64
+#define htole64(x) __bswap_64(x)
+#endif
+
+#ifndef le16toh
+#define le16toh(x) __bswap_16(x)
+#endif
+
+#ifndef le32toh
+#define le32toh(x) __bswap_32(x)
+#endif
+
+#ifndef le64toh
+#define le64toh(x) __bswap_64(x)
+#endif
+
+#endif
+
+#endif /* _TOOLS_ENDIAN_H */
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index ce00f7ee6455..36c08b1f4afb 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -10,9 +10,14 @@ LIB_OBJS=
 
 LIB_H += fs/debugfs.h
 LIB_H += fs/fs.h
+# See comment below about piggybacking...
+LIB_H += fd/array.h
 
 LIB_OBJS += $(OUTPUT)fs/debugfs.o
 LIB_OBJS += $(OUTPUT)fs/fs.o
+# XXX piggybacking here, need to introduce libapikfd, or rename this
+# to plain libapik.a and make it have it all api goodies
+LIB_OBJS += $(OUTPUT)fd/array.o
 
 LIBFILE = libapikfs.a
 
@@ -29,7 +34,7 @@ $(LIBFILE): $(LIB_OBJS)
 $(LIB_OBJS): $(LIB_H)
 
 libapi_dirs:
-        $(QUIET_MKDIR)mkdir -p $(OUTPUT)fs/
+        $(QUIET_MKDIR)mkdir -p $(OUTPUT)fd $(OUTPUT)fs
 
 $(OUTPUT)%.o: %.c libapi_dirs
         $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
diff --git a/tools/lib/api/fd/array.c b/tools/lib/api/fd/array.c
new file mode 100644
index 000000000000..0e636c4339b8
--- /dev/null
+++ b/tools/lib/api/fd/array.c
@@ -0,0 +1,127 @@
+/*
+ * Copyright (C) 2014, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include "array.h"
+#include <errno.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+void fdarray__init(struct fdarray *fda, int nr_autogrow)
+{
+        fda->entries     = NULL;
+        fda->priv        = NULL;
+        fda->nr          = fda->nr_alloc = 0;
+        fda->nr_autogrow = nr_autogrow;
+}
+
+int fdarray__grow(struct fdarray *fda, int nr)
+{
+        void *priv;
+        int nr_alloc = fda->nr_alloc + nr;
+        size_t psize = sizeof(fda->priv[0]) * nr_alloc;
+        size_t size  = sizeof(struct pollfd) * nr_alloc;
+        struct pollfd *entries = realloc(fda->entries, size);
+
+        if (entries == NULL)
+                return -ENOMEM;
+
+        priv = realloc(fda->priv, psize);
+        if (priv == NULL) {
+                free(entries);
+                return -ENOMEM;
+        }
+
+        fda->nr_alloc = nr_alloc;
+        fda->entries  = entries;
+        fda->priv     = priv;
+        return 0;
+}
+
+struct fdarray *fdarray__new(int nr_alloc, int nr_autogrow)
+{
+        struct fdarray *fda = calloc(1, sizeof(*fda));
+
+        if (fda != NULL) {
+                if (fdarray__grow(fda, nr_alloc)) {
+                        free(fda);
+                        fda = NULL;
+                } else {
+                        fda->nr_autogrow = nr_autogrow;
+                }
+        }
+
+        return fda;
+}
+
+void fdarray__exit(struct fdarray *fda)
+{
+        free(fda->entries);
+        free(fda->priv);
+        fdarray__init(fda, 0);
+}
+
+void fdarray__delete(struct fdarray *fda)
+{
+        fdarray__exit(fda);
+        free(fda);
+}
+
+int fdarray__add(struct fdarray *fda, int fd, short revents)
+{
+        int pos = fda->nr;
+
+        if (fda->nr == fda->nr_alloc &&
+            fdarray__grow(fda, fda->nr_autogrow) < 0)
+                return -ENOMEM;
+
+        fda->entries[fda->nr].fd     = fd;
+        fda->entries[fda->nr].events = revents;
+        fda->nr++;
+        return pos;
+}
+
+int fdarray__filter(struct fdarray *fda, short revents,
+                    void (*entry_destructor)(struct fdarray *fda, int fd))
+{
+        int fd, nr = 0;
+
+        if (fda->nr == 0)
+                return 0;
+
+        for (fd = 0; fd < fda->nr; ++fd) {
+                if (fda->entries[fd].revents & revents) {
+                        if (entry_destructor)
+                                entry_destructor(fda, fd);
+
+                        continue;
+                }
+
+                if (fd != nr) {
+                        fda->entries[nr] = fda->entries[fd];
+                        fda->priv[nr]    = fda->priv[fd];
+                }
+
+                ++nr;
+        }
+
+        return fda->nr = nr;
+}
+
+int fdarray__poll(struct fdarray *fda, int timeout)
+{
+        return poll(fda->entries, fda->nr, timeout);
+}
+
+int fdarray__fprintf(struct fdarray *fda, FILE *fp)
+{
+        int fd, printed = fprintf(fp, "%d [ ", fda->nr);
+
+        for (fd = 0; fd < fda->nr; ++fd)
+                printed += fprintf(fp, "%s%d", fd ? ", " : "", fda->entries[fd].fd);
+
+        return printed + fprintf(fp, " ]");
+}
diff --git a/tools/lib/api/fd/array.h b/tools/lib/api/fd/array.h
new file mode 100644
index 000000000000..45db01818f45
--- /dev/null
+++ b/tools/lib/api/fd/array.h
@@ -0,0 +1,46 @@
+#ifndef __API_FD_ARRAY__
+#define __API_FD_ARRAY__
+
+#include <stdio.h>
+
+struct pollfd;
+
+/**
+ * struct fdarray: Array of file descriptors
+ *
+ * @priv: Per array entry priv area, users should access just its contents,
+ *        not set it to anything, as it is kept in synch with @entries, being
+ *        realloc'ed, * for instance, in fdarray__{grow,filter}.
+ *
+ *        I.e. using 'fda->priv[N].idx = * value' where N < fda->nr is ok,
+ *        but doing 'fda->priv = malloc(M)' is not allowed.
+ */
+struct fdarray {
+        int            nr;
+        int            nr_alloc;
+        int            nr_autogrow;
+        struct pollfd *entries;
+        union {
+                int    idx;
+        } *priv;
+};
+
+void fdarray__init(struct fdarray *fda, int nr_autogrow);
+void fdarray__exit(struct fdarray *fda);
+
+struct fdarray *fdarray__new(int nr_alloc, int nr_autogrow);
+void fdarray__delete(struct fdarray *fda);
+
+int fdarray__add(struct fdarray *fda, int fd, short revents);
+int fdarray__poll(struct fdarray *fda, int timeout);
+int fdarray__filter(struct fdarray *fda, short revents,
+                    void (*entry_destructor)(struct fdarray *fda, int fd));
+int fdarray__grow(struct fdarray *fda, int extra);
+int fdarray__fprintf(struct fdarray *fda, FILE *fp);
+
+static inline int fdarray__available_entries(struct fdarray *fda)
+{
+        return fda->nr_alloc - fda->nr;
+}
+
+#endif /* __API_FD_ARRAY__ */
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 782d86e961b9..717221e98450 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -15,6 +15,7 @@ perf.data
 perf.data.old
 output.svg
 perf-archive
+perf-with-kcore
 tags
 TAGS
 cscope*
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index b3b8abae62b8..e463caa3eb49 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -196,10 +196,10 @@ If specified the 'Weighted diff' column is displayed with value 'd' computed as:
 
   - period being the hist entry period value
 
-  - WEIGHT-A/WEIGHT-B being user suplied weights in the the '-c' option
+  - WEIGHT-A/WEIGHT-B being user supplied weights in the the '-c' option
     behind ':' separator like '-c wdiff:1,2'.
-    - WIEGHT-A being the weight of the data file
-    - WIEGHT-B being the weight of the baseline data file
+    - WEIGHT-A being the weight of the data file
+    - WEIGHT-B being the weight of the baseline data file
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index 6e689dc89a2f..6252e776009c 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -100,7 +100,7 @@ OPTIONS
 STAT REPORT OPTIONS
 -------------------
 --vcpu=<value>::
-       analyze events which occures on this vcpu. (default: all vcpus)
+       analyze events which occur on this vcpu. (default: all vcpus)
 
 --event=<value>::
        event to be analyzed. Possible values: vmexit, mmio (x86 only),
@@ -134,7 +134,7 @@ STAT LIVE OPTIONS
     Analyze events only for given process ID(s) (comma separated list).
 
 --vcpu=<value>::
-       analyze events which occures on this vcpu. (default: all vcpus)
+       analyze events which occur on this vcpu. (default: all vcpus)
 
 
 --event=<value>::
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 6fce6a622206..cbb4f743d921 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -19,7 +19,7 @@ various perf commands with the -e option.
 EVENT MODIFIERS
 ---------------
 
-Events can optionally have a modifer by appending a colon and one or
+Events can optionally have a modifier by appending a colon and one or
 more modifiers. Modifiers allow the user to restrict the events to be
 counted. The following modifiers exist:
 
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 1513935c399b..aaa869be3dc1 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -104,6 +104,9 @@ OPTIONS
         Specify path to the executable or shared library file for user
         space tracing. Can also be used with --funcs option.
 
+--demangle-kernel::
+        Demangle kernel symbols.
+
 In absence of -m/-x options, perf probe checks if the first argument after
 the options is an absolute path name. If its an absolute path, perf probe
 uses it as a target module/target user space binary to probe.
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index d460049cae8e..398f8d53bd6d 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -146,7 +146,7 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 
 -N::
 --no-buildid-cache::
-Do not update the builid cache. This saves some overhead in situations
+Do not update the buildid cache. This saves some overhead in situations
 where the information in the perf.data file (which includes buildids)
 is sufficient.
 
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index d2b59af62bc0..0927bf4e6c2a 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -147,7 +147,7 @@ OPTIONS
 -w::
 --column-widths=<width[,width...]>::
         Force each column width to the provided list, for large terminal
-        readability.
+        readability.  0 means no limit (default behavior).
 
 -t::
 --field-separator=::
@@ -276,6 +276,9 @@ OPTIONS
         Demangle symbol names to human readable form. It's enabled by default,
         disable with --no-demangle.
 
+--demangle-kernel::
+        Demangle kernel symbol names to human readable form (for C++ kernels).
+
 --mem-mode::
         Use the data addresses of samples in addition to instruction addresses
         to build the histograms.  To generate meaningful output, the perf.data
diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index d00bef231340..dfbb506d2c34 100644
--- a/tools/perf/Documentation/perf-script-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -181,8 +181,8 @@ strings for flag and symbolic fields.  These correspond to the strings
 and values parsed from the 'print fmt' fields of the event format
 files:
 
-  flag_str($event_name, $field_name, $field_value) - returns the string represention corresponding to $field_value for the flag field $field_name of event $event_name
-  symbol_str($event_name, $field_name, $field_value) - returns the string represention corresponding to $field_value for the symbolic field $field_name of event $event_name
+  flag_str($event_name, $field_name, $field_value) - returns the string representation corresponding to $field_value for the flag field $field_name of event $event_name
+  symbol_str($event_name, $field_name, $field_value) - returns the string representation corresponding to $field_value for the symbolic field $field_name of event $event_name
 
 Perf::Trace::Context Module
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt
index 9f1f054b8432..54acba221558 100644
--- a/tools/perf/Documentation/perf-script-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -263,7 +263,7 @@ and having the counts we've tallied as values.
 
 The print_syscall_totals() function iterates over the entries in the
 dictionary and displays a line for each entry containing the syscall
-name (the dictonary keys contain the syscall ids, which are passed to
+name (the dictionary keys contain the syscall ids, which are passed to
 the Util function syscall_name(), which translates the raw syscall
 numbers to the corresponding syscall name strings).  The output is
 displayed after all the events in the trace have been processed, by
@@ -576,8 +576,8 @@ strings for flag and symbolic fields.  These correspond to the strings
 and values parsed from the 'print fmt' fields of the event format
 files:
 
-  flag_str(event_name, field_name, field_value) - returns the string represention corresponding to field_value for the flag field field_name of event event_name
-  symbol_str(event_name, field_name, field_value) - returns the string represention corresponding to field_value for the symbolic field field_name of event event_name
+  flag_str(event_name, field_name, field_value) - returns the string representation corresponding to field_value for the flag field field_name of event event_name
+  symbol_str(event_name, field_name, field_value) - returns the string representation corresponding to field_value for the symbolic field field_name of event event_name
 
 The *autodict* function returns a special kind of Python
 dictionary that implements Perl's 'autovivifying' hashes in Python
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 05f9a0a6784c..21494806c0ab 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -115,7 +115,7 @@ OPTIONS
 -f::
 --fields::
         Comma separated list of fields to print. Options are:
-        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline.
+        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline, period.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -f sw:comm,tid,time,ip,sym  and -f trace:time,cpu,trace
@@ -140,7 +140,7 @@ OPTIONS
     
                 "Overriding previous field request for all events."
     
-        Alternativey, consider the order:
+        Alternatively, consider the order:
     
                 -f comm,tid,time,ip,sym -f trace:
     
diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt
index d1d3e5121f89..31a5c3ea7f74 100644
--- a/tools/perf/Documentation/perf-test.txt
+++ b/tools/perf/Documentation/perf-test.txt
@@ -25,7 +25,7 @@ OPTIONS
 -------
 -s::
 --skip::
-        Tests to skip (comma separater numeric list).
+        Tests to skip (comma separated numeric list).
 
 -v::
 --verbose::
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 180ae02137a5..3265b1070518 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -98,6 +98,9 @@ Default is to monitor all CPUS.
 --hide_user_symbols::
         Hide user symbols.
 
+--demangle-kernel::
+        Demangle kernel symbols.
+
 -D::
 --dump-symtab::
         Dump the symbol table used for profiling.
@@ -193,6 +196,12 @@ Default is to monitor all CPUS.
         sum of shown entries will be always 100%. "absolute" means it retains
         the original value before and after the filter is applied.
 
+-w::
+--column-widths=<width[,width...]>::
+        Force each column width to the provided list, for large terminal
+        readability.  0 means no limit (default behavior).
+
+
 INTERACTIVE PROMPTING KEYS
 --------------------------
 
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 02aac831bdd9..7e1b1f2bb83c 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -20,7 +20,7 @@ scheduling events, etc.
 This is a live mode tool in addition to working with perf.data files like
 the other perf tools. Files can be generated using the 'perf record' command
 but the session needs to include the raw_syscalls events (-e 'raw_syscalls:*').
-Alernatively, the 'perf trace record' can be used as a shortcut to
+Alternatively, 'perf trace record' can be used as a shortcut to
 automatically include the raw_syscalls events when writing events to a file.
 
 The following options apply to perf trace; options to perf trace record are
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 2240974b7745..262916f4a377 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -126,6 +126,7 @@ PYRF_OBJS =
 SCRIPT_SH =
 
 SCRIPT_SH += perf-archive.sh
+SCRIPT_SH += perf-with-kcore.sh
 
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
@@ -263,6 +264,7 @@ LIB_H += util/xyarray.h
 LIB_H += util/header.h
 LIB_H += util/help.h
 LIB_H += util/session.h
+LIB_H += util/ordered-events.h
 LIB_H += util/strbuf.h
 LIB_H += util/strlist.h
 LIB_H += util/strfilter.h
@@ -347,6 +349,7 @@ LIB_OBJS += $(OUTPUT)util/machine.o
 LIB_OBJS += $(OUTPUT)util/map.o
 LIB_OBJS += $(OUTPUT)util/pstack.o
 LIB_OBJS += $(OUTPUT)util/session.o
+LIB_OBJS += $(OUTPUT)util/ordered-events.o
 LIB_OBJS += $(OUTPUT)util/comm.o
 LIB_OBJS += $(OUTPUT)util/thread.o
 LIB_OBJS += $(OUTPUT)util/thread_map.o
@@ -399,6 +402,7 @@ LIB_OBJS += $(OUTPUT)tests/perf-record.o
 LIB_OBJS += $(OUTPUT)tests/rdpmc.o
 LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o
 LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o
+LIB_OBJS += $(OUTPUT)tests/fdarray.o
 LIB_OBJS += $(OUTPUT)tests/pmu.o
 LIB_OBJS += $(OUTPUT)tests/hists_common.o
 LIB_OBJS += $(OUTPUT)tests/hists_link.o
@@ -423,6 +427,7 @@ endif
 endif
 LIB_OBJS += $(OUTPUT)tests/mmap-thread-lookup.o
 LIB_OBJS += $(OUTPUT)tests/thread-mg-share.o
+LIB_OBJS += $(OUTPUT)tests/switch-tracking.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
@@ -765,7 +770,7 @@ $(LIBTRACEEVENT)-clean:
 install-traceevent-plugins: $(LIBTRACEEVENT)
         $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) install_plugins
 
-LIBAPIKFS_SOURCES = $(wildcard $(LIB_PATH)fs/*.[ch])
+LIBAPIKFS_SOURCES = $(wildcard $(LIB_PATH)fs/*.[ch] $(LIB_PATH)fd/*.[ch])
 
 # if subdir is set, we've been called from above so target has been built
 # already
@@ -875,6 +880,8 @@ install-bin: all install-gtk
                 $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
         $(call QUIET_INSTALL, perf-archive) \
                 $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+        $(call QUIET_INSTALL, perf-with-kcore) \
+                $(INSTALL) $(OUTPUT)perf-with-kcore -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 ifndef NO_LIBPERL
         $(call QUIET_INSTALL, perl-scripts) \
                 $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
@@ -920,7 +927,7 @@ config-clean:
         @$(MAKE) -C config/feature-checks clean >/dev/null
 
 clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean
-        $(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
+        $(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
         $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
         $(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
         $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c
index 9f870d27cb39..62eff847f91c 100644
--- a/tools/perf/arch/arm/tests/dwarf-unwind.c
+++ b/tools/perf/arch/arm/tests/dwarf-unwind.c
@@ -3,6 +3,7 @@
 #include "thread.h"
 #include "map.h"
 #include "event.h"
+#include "debug.h"
 #include "tests/tests.h"
 
 #define STACK_SIZE 8192
diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c
index 729ed69a6664..62c397ed3d97 100644
--- a/tools/perf/arch/arm/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm/util/unwind-libunwind.c
@@ -3,6 +3,7 @@
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
+#include "../../util/debug.h"
 
 int libunwind__arch_reg_id(int regnum)
 {
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index e9441b9e2a30..1d3f39c3aa56 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -6,6 +6,8 @@
 #include <asm/perf_regs.h>
 
 #define PERF_REGS_MASK  ((1ULL << PERF_REG_ARM64_MAX) - 1)
+#define PERF_REGS_MAX   PERF_REG_ARM64_MAX
+
 #define PERF_REG_IP     PERF_REG_ARM64_PC
 #define PERF_REG_SP     PERF_REG_ARM64_SP
 
diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c
index 436ee43859dc..a87afa91a99e 100644
--- a/tools/perf/arch/arm64/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm64/util/unwind-libunwind.c
@@ -3,6 +3,7 @@
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
+#include "../../util/debug.h"
 
 int libunwind__arch_reg_id(int regnum)
 {
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 42faf369211c..49776f190abf 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -12,6 +12,11 @@ const char *const arm_triplets[] = {
         NULL
 };
 
+const char *const arm64_triplets[] = {
+        "aarch64-linux-android-",
+        NULL
+};
+
 const char *const powerpc_triplets[] = {
         "powerpc-unknown-linux-gnu-",
         "powerpc64-unknown-linux-gnu-",
@@ -105,6 +110,8 @@ static const char *normalize_arch(char *arch)
                 return "x86";
         if (!strcmp(arch, "sun4u") || !strncmp(arch, "sparc", 5))
                 return "sparc";
+        if (!strcmp(arch, "aarch64") || !strcmp(arch, "arm64"))
+                return "arm64";
         if (!strncmp(arch, "arm", 3) || !strcmp(arch, "sa110"))
                 return "arm";
         if (!strncmp(arch, "s390", 4))
@@ -159,6 +166,8 @@ static int perf_session_env__lookup_binutils_path(struct perf_session_env *env,
 
         if (!strcmp(arch, "arm"))
                 path_list = arm_triplets;
+        else if (!strcmp(arch, "arm64"))
+                path_list = arm64_triplets;
         else if (!strcmp(arch, "powerpc"))
                 path_list = powerpc_triplets;
         else if (!strcmp(arch, "sh"))
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index b92219b1900d..6f7782bea5dd 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -1,6 +1,6 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/skip-callchain-idx.o
 endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
-LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index a7c23a4b3778..d73ef8bb08c7 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -15,6 +15,7 @@
 
 #include "util/thread.h"
 #include "util/callchain.h"
+#include "util/debug.h"
 
 /*
  * When saving the callchain on Power, the kernel conservatively saves
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index a84206e9c4aa..fc9bebd2cca0 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -26,6 +26,7 @@ static unsigned int nsecs    = 10;
 /* amount of futexes per thread */
 static unsigned int nfutexes = 1024;
 static bool fshared = false, done = false, silent = false;
+static int futex_flag = 0;
 
 struct timeval start, end, runtime;
 static pthread_mutex_t thread_lock;
@@ -75,8 +76,7 @@ static void *workerfn(void *arg)
                          * such as internal waitqueue handling, thus enlarging
                          * the critical region protected by hb->lock.
                          */
-                        ret = futex_wait(&w->futex[i], 1234, NULL,
-                                         fshared ? 0 : FUTEX_PRIVATE_FLAG);
+                        ret = futex_wait(&w->futex[i], 1234, NULL, futex_flag);
                         if (!silent &&
                             (!ret || errno != EAGAIN || errno != EWOULDBLOCK))
                                 warn("Non-expected futex return call");
@@ -135,6 +135,9 @@ int bench_futex_hash(int argc, const char **argv,
         if (!worker)
                 goto errmem;
 
+        if (!fshared)
+                futex_flag = FUTEX_PRIVATE_FLAG;
+
         printf("Run summary [PID %d]: %d threads, each operating on %d [%s] futexes for %d secs.\n\n",
                getpid(), nthreads, nfutexes, fshared ? "shared":"private", nsecs);
 
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 732403bfd31a..bedff6b5b3cf 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -30,16 +30,18 @@ static u_int32_t futex1 = 0, futex2 = 0;
 static unsigned int nrequeue = 1;
 
 static pthread_t *worker;
-static bool done = 0, silent = 0;
+static bool done = false, silent = false, fshared = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static struct stats requeuetime_stats, requeued_stats;
 static unsigned int ncpus, threads_starting, nthreads = 0;
+static int futex_flag = 0;
 
 static const struct option options[] = {
         OPT_UINTEGER('t', "threads",  &nthreads, "Specify amount of threads"),
         OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"),
         OPT_BOOLEAN( 's', "silent",   &silent,   "Silent mode: do not display data/details"),
+        OPT_BOOLEAN( 'S', "shared",   &fshared,  "Use shared futexes instead of private ones"),
         OPT_END()
 };
 
@@ -70,7 +72,7 @@ static void *workerfn(void *arg __maybe_unused)
         pthread_cond_wait(&thread_worker, &thread_lock);
         pthread_mutex_unlock(&thread_lock);
 
-        futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+        futex_wait(&futex1, 0, NULL, futex_flag);
         return NULL;
 }
 
@@ -127,9 +129,12 @@ int bench_futex_requeue(int argc, const char **argv,
         if (!worker)
                 err(EXIT_FAILURE, "calloc");
 
-        printf("Run summary [PID %d]: Requeuing %d threads (from %p to %p), "
-               "%d at a time.\n\n",
-               getpid(), nthreads, &futex1, &futex2, nrequeue);
+        if (!fshared)
+                futex_flag = FUTEX_PRIVATE_FLAG;
+
+        printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %p), "
+               "%d at a time.\n\n",  getpid(), nthreads,
+               fshared ? "shared":"private", &futex1, &futex2, nrequeue);
 
         init_stats(&requeued_stats);
         init_stats(&requeuetime_stats);
@@ -156,16 +161,20 @@ int bench_futex_requeue(int argc, const char **argv,
 
                 /* Ok, all threads are patiently blocked, start requeueing */
                 gettimeofday(&start, NULL);
-                for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue)
+                for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue) {
                         /*
                          * Do not wakeup any tasks blocked on futex1, allowing
                          * us to really measure futex_wait functionality.
                          */
-                        futex_cmp_requeue(&futex1, 0, &futex2, 0, nrequeue,
-                                          FUTEX_PRIVATE_FLAG);
+                        futex_cmp_requeue(&futex1, 0, &futex2, 0,
+                                          nrequeue, futex_flag);
+                }
                 gettimeofday(&end, NULL);
                 timersub(&end, &start, &runtime);
 
+                if (nrequeued > nthreads)
+                        nrequeued = nthreads;
+
                 update_stats(&requeued_stats, nrequeued);
                 update_stats(&requeuetime_stats, runtime.tv_usec);
 
@@ -175,7 +184,7 @@ int bench_futex_requeue(int argc, const char **argv,
                 }
 
                 /* everybody should be blocked on futex2, wake'em up */
-                nrequeued = futex_wake(&futex2, nthreads, FUTEX_PRIVATE_FLAG);
+                nrequeued = futex_wake(&futex2, nthreads, futex_flag);
                 if (nthreads != nrequeued)
                         warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
 
@@ -184,7 +193,6 @@ int bench_futex_requeue(int argc, const char **argv,
                         if (ret)
                                 err(EXIT_FAILURE, "pthread_join");
                 }
-
         }
 
         /* cleanup & report results */
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 50022cbce87e..929f762be47e 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -31,16 +31,18 @@ static u_int32_t futex1 = 0;
 static unsigned int nwakes = 1;
 
 pthread_t *worker;
-static bool done = false, silent = false;
+static bool done = false, silent = false, fshared = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static struct stats waketime_stats, wakeup_stats;
 static unsigned int ncpus, threads_starting, nthreads = 0;
+static int futex_flag = 0;
 
 static const struct option options[] = {
         OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
         OPT_UINTEGER('w', "nwakes",  &nwakes,   "Specify amount of threads to wake at once"),
         OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
+        OPT_BOOLEAN( 'S', "shared",  &fshared,  "Use shared futexes instead of private ones"),
         OPT_END()
 };
 
@@ -58,7 +60,7 @@ static void *workerfn(void *arg __maybe_unused)
         pthread_cond_wait(&thread_worker, &thread_lock);
         pthread_mutex_unlock(&thread_lock);
 
-        futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+        futex_wait(&futex1, 0, NULL, futex_flag);
         return NULL;
 }
 
@@ -130,9 +132,12 @@ int bench_futex_wake(int argc, const char **argv,
         if (!worker)
                 err(EXIT_FAILURE, "calloc");
 
-        printf("Run summary [PID %d]: blocking on %d threads (at futex %p), "
+        if (!fshared)
+                futex_flag = FUTEX_PRIVATE_FLAG;
+
+        printf("Run summary [PID %d]: blocking on %d threads (at [%s] futex %p), "
                "waking up %d at a time.\n\n",
-               getpid(), nthreads, &futex1, nwakes);
+               getpid(), nthreads, fshared ? "shared":"private",  &futex1, nwakes);
 
         init_stats(&wakeup_stats);
         init_stats(&waketime_stats);
@@ -160,7 +165,7 @@ int bench_futex_wake(int argc, const char **argv,
                 /* Ok, all threads are patiently blocked, start waking folks up */
                 gettimeofday(&start, NULL);
                 while (nwoken != nthreads)
-                        nwoken += futex_wake(&futex1, nwakes, FUTEX_PRIVATE_FLAG);
+                        nwoken += futex_wake(&futex1, nwakes, futex_flag);
                 gettimeofday(&end, NULL);
                 timersub(&end, &start, &runtime);
 
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index 52a56599a543..d7f281c2828d 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -26,7 +26,7 @@
 #include <sys/socket.h>
 #include <sys/wait.h>
 #include <sys/time.h>
-#include <sys/poll.h>
+#include <poll.h>
 #include <limits.h>
 #include <err.h>
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 1ec429fef2be..e7417fe97a97 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -36,7 +36,8 @@
 
 struct perf_annotate {
         struct perf_tool tool;
-        bool       force, use_tui, use_stdio, use_gtk;
+        struct perf_session *session;
+        bool       use_tui, use_stdio, use_gtk;
         bool       full_paths;
         bool       print_line;
         bool       skip_missing;
@@ -50,6 +51,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
                                   struct addr_location *al,
                                   struct perf_annotate *ann)
 {
+        struct hists *hists = evsel__hists(evsel);
         struct hist_entry *he;
         int ret;
 
@@ -65,13 +67,12 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
                 return 0;
         }
 
-        he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, 1, 1, 0,
-                                true);
+        he = __hists__add_entry(hists, al, NULL, NULL, NULL, 1, 1, 0, true);
         if (he == NULL)
                 return -ENOMEM;
 
         ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-        hists__inc_nr_samples(&evsel->hists, true);
+        hists__inc_nr_samples(hists, true);
         return ret;
 }
 
@@ -188,18 +189,9 @@ find_next:
 static int __cmd_annotate(struct perf_annotate *ann)
 {
         int ret;
-        struct perf_session *session;
+        struct perf_session *session = ann->session;
         struct perf_evsel *pos;
         u64 total_nr_samples;
-        struct perf_data_file file = {
-                .path  = input_name,
-                .mode  = PERF_DATA_MODE_READ,
-                .force = ann->force,
-        };
-
-        session = perf_session__new(&file, false, &ann->tool);
-        if (session == NULL)
-                return -ENOMEM;
 
         machines__set_symbol_filter(&session->machines, symbol__annotate_init);
 
@@ -207,22 +199,23 @@ static int __cmd_annotate(struct perf_annotate *ann)
                 ret = perf_session__cpu_bitmap(session, ann->cpu_list,
                                                ann->cpu_bitmap);
                 if (ret)
-                        goto out_delete;
+                        goto out;
         }
 
         if (!objdump_path) {
                 ret = perf_session_env__lookup_objdump(&session->header.env);
                 if (ret)
-                        goto out_delete;
+                        goto out;
         }
 
         ret = perf_session__process_events(session, &ann->tool);
         if (ret)
-                goto out_delete;
+                goto out;
 
         if (dump_trace) {
                 perf_session__fprintf_nr_events(session, stdout);
-                goto out_delete;
+                perf_evlist__fprintf_nr_events(session->evlist, stdout);
+                goto out;
         }
 
         if (verbose > 3)
@@ -233,7 +226,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
 
         total_nr_samples = 0;
         evlist__for_each(session->evlist, pos) {
-                struct hists *hists = &pos->hists;
+                struct hists *hists = evsel__hists(pos);
                 u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 
                 if (nr_samples > 0) {
@@ -250,8 +243,8 @@ static int __cmd_annotate(struct perf_annotate *ann)
         }
 
         if (total_nr_samples == 0) {
-                ui__error("The %s file has no samples!\n", file.path);
-                goto out_delete;
+                ui__error("The %s file has no samples!\n", session->file->path);
+                goto out;
         }
 
         if (use_browser == 2) {
@@ -261,24 +254,12 @@ static int __cmd_annotate(struct perf_annotate *ann)
                                          "perf_gtk__show_annotations");
                 if (show_annotations == NULL) {
                         ui__error("GTK browser not found!\n");
-                        goto out_delete;
+                        goto out;
                 }
                 show_annotations();
         }
 
-out_delete:
-        /*
-         * Speed up the exit process, for large files this can
-         * take quite a while.
-         *
-         * XXX Enable this when using valgrind or if we ever
-         * librarize this command.
-         *
-         * Also experiment with obstacks to see how much speed
-         * up we'll get here.
-         *
-         * perf_session__delete(session);
-         */
+out:
         return ret;
 }
 
@@ -297,10 +278,14 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
                         .comm   = perf_event__process_comm,
                         .exit   = perf_event__process_exit,
                         .fork   = perf_event__process_fork,
-                        .ordered_samples = true,
+                        .ordered_events = true,
                         .ordering_requires_timestamps = true,
                 },
         };
+        struct perf_data_file file = {
+                .path  = input_name,
+                .mode  = PERF_DATA_MODE_READ,
+        };
         const struct option options[] = {
         OPT_STRING('i', "input", &input_name, "file",
                     "input file name"),
@@ -308,7 +293,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
                    "only consider symbols in these dsos"),
         OPT_STRING('s', "symbol", &annotate.sym_hist_filter, "symbol",
                     "symbol to annotate"),
-        OPT_BOOLEAN('f', "force", &annotate.force, "don't complain, do it"),
+        OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
         OPT_INCR('v', "verbose", &verbose,
                     "be more verbose (show symbol address, etc)"),
         OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
@@ -341,6 +326,10 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
                     "Show event group information together"),
         OPT_END()
         };
+        int ret = hists__init();
+
+        if (ret < 0)
+                return ret;
 
         argc = parse_options(argc, argv, options, annotate_usage, 0);
 
@@ -353,11 +342,16 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 
         setup_browser(true);
 
+        annotate.session = perf_session__new(&file, false, &annotate.tool);
+        if (annotate.session == NULL)
+                return -1;
+
         symbol_conf.priv_size = sizeof(struct annotation);
         symbol_conf.try_vmlinux_path = true;
 
-        if (symbol__init() < 0)
-                return -1;
+        ret = symbol__init(&annotate.session->header.env);
+        if (ret < 0)
+                goto out_delete;
 
         if (setup_sorting() < 0)
                 usage_with_options(annotate_usage, options);
@@ -373,5 +367,20 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
                 annotate.sym_hist_filter = argv[0];
         }
 
-        return __cmd_annotate(&annotate);
+        ret = __cmd_annotate(&annotate);
+
+out_delete:
+        /*
+         * Speed up the exit process, for large files this can
+         * take quite a while.
+         *
+         * XXX Enable this when using valgrind or if we ever
+         * librarize this command.
+         *
+         * Also experiment with obstacks to see how much speed
+         * up we'll get here.
+         *
+         * perf_session__delete(session);
+         */
+        return ret;
 }
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 2a2c78f80876..70385756da63 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -246,20 +246,9 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
         return true;
 }
 
-static int build_id_cache__fprintf_missing(const char *filename, bool force, FILE *fp)
+static int build_id_cache__fprintf_missing(struct perf_session *session, FILE *fp)
 {
-        struct perf_data_file file = {
-                .path  = filename,
-                .mode  = PERF_DATA_MODE_READ,
-                .force = force,
-        };
-        struct perf_session *session = perf_session__new(&file, false, NULL);
-        if (session == NULL)
-                return -1;
-
         perf_session__fprintf_dsos_buildid(session, fp, dso__missing_buildid_cache, 0);
-        perf_session__delete(session);
-
         return 0;
 }
 
@@ -302,6 +291,12 @@ int cmd_buildid_cache(int argc, const char **argv,
                    *missing_filename = NULL,
                    *update_name_list_str = NULL,
                    *kcore_filename;
+        char sbuf[STRERR_BUFSIZE];
+
+        struct perf_data_file file = {
+                .mode  = PERF_DATA_MODE_READ,
+        };
+        struct perf_session *session = NULL;
 
         const struct option buildid_cache_options[] = {
         OPT_STRING('a', "add", &add_name_list_str,
@@ -326,8 +321,17 @@ int cmd_buildid_cache(int argc, const char **argv,
         argc = parse_options(argc, argv, buildid_cache_options,
                              buildid_cache_usage, 0);
 
-        if (symbol__init() < 0)
-                return -1;
+        if (missing_filename) {
+                file.path = missing_filename;
+                file.force = force;
+
+                session = perf_session__new(&file, false, NULL);
+                if (session == NULL)
+                        return -1;
+        }
+
+        if (symbol__init(session ? &session->header.env : NULL) < 0)
+                goto out;
 
         setup_pager();
 
@@ -344,7 +348,7 @@ int cmd_buildid_cache(int argc, const char **argv,
                                                 continue;
                                         }
                                         pr_warning("Couldn't add %s: %s\n",
-                                                   pos->s, strerror(errno));
+                                                   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
                                 }
 
                         strlist__delete(list);
@@ -362,7 +366,7 @@ int cmd_buildid_cache(int argc, const char **argv,
                                                 continue;
                                         }
                                         pr_warning("Couldn't remove %s: %s\n",
-                                                   pos->s, strerror(errno));
+                                                   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
                                 }
 
                         strlist__delete(list);
@@ -370,7 +374,7 @@ int cmd_buildid_cache(int argc, const char **argv,
         }
 
         if (missing_filename)
-                ret = build_id_cache__fprintf_missing(missing_filename, force, stdout);
+                ret = build_id_cache__fprintf_missing(session, stdout);
 
         if (update_name_list_str) {
                 list = strlist__new(true, update_name_list_str);
@@ -383,7 +387,7 @@ int cmd_buildid_cache(int argc, const char **argv,
                                                 continue;
                                         }
                                         pr_warning("Couldn't update %s: %s\n",
-                                                   pos->s, strerror(errno));
+                                                   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
                                 }
 
                         strlist__delete(list);
@@ -394,5 +398,9 @@ int cmd_buildid_cache(int argc, const char **argv,
             build_id_cache__add_kcore(kcore_filename, debugdir, force))
                 pr_warning("Couldn't add %s\n", kcore_filename);
 
+out:
+        if (session)
+                perf_session__delete(session);
+
         return ret;
 }
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 9a5a035cb426..25114c9a6801 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -327,6 +327,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
                                       struct machine *machine)
 {
         struct addr_location al;
+        struct hists *hists = evsel__hists(evsel);
 
         if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
                 pr_warning("problem processing %d event, skipping it.\n",
@@ -334,7 +335,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
                 return -1;
         }
 
-        if (hists__add_entry(&evsel->hists, &al, sample->period,
+        if (hists__add_entry(hists, &al, sample->period,
                              sample->weight, sample->transaction)) {
                 pr_warning("problem incrementing symbol period, skipping event\n");
                 return -1;
@@ -346,9 +347,9 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
          * hists__output_resort() and precompute needs the total
          * period in order to sort entries by percentage delta.
          */
-        evsel->hists.stats.total_period += sample->period;
+        hists->stats.total_period += sample->period;
         if (!al.filtered)
-                evsel->hists.stats.total_non_filtered_period += sample->period;
+                hists->stats.total_non_filtered_period += sample->period;
 
         return 0;
 }
@@ -360,7 +361,7 @@ static struct perf_tool tool = {
         .exit   = perf_event__process_exit,
         .fork   = perf_event__process_fork,
         .lost   = perf_event__process_lost,
-        .ordered_samples = true,
+        .ordered_events = true,
         .ordering_requires_timestamps = true,
 };
 
@@ -382,7 +383,7 @@ static void perf_evlist__collapse_resort(struct perf_evlist *evlist)
         struct perf_evsel *evsel;
 
         evlist__for_each(evlist, evsel) {
-                struct hists *hists = &evsel->hists;
+                struct hists *hists = evsel__hists(evsel);
 
                 hists__collapse_resort(hists, NULL);
         }
@@ -631,24 +632,26 @@ static void data_process(void)
         bool first = true;
 
         evlist__for_each(evlist_base, evsel_base) {
+                struct hists *hists_base = evsel__hists(evsel_base);
                 struct data__file *d;
                 int i;
 
                 data__for_each_file_new(i, d) {
                         struct perf_evlist *evlist = d->session->evlist;
                         struct perf_evsel *evsel;
+                        struct hists *hists;
 
                         evsel = evsel_match(evsel_base, evlist);
                         if (!evsel)
                                 continue;
 
-                        d->hists = &evsel->hists;
+                        hists = evsel__hists(evsel);
+                        d->hists = hists;
 
-                        hists__match(&evsel_base->hists, &evsel->hists);
+                        hists__match(hists_base, hists);
 
                         if (!show_baseline_only)
-                                hists__link(&evsel_base->hists,
-                                            &evsel->hists);
+                                hists__link(hists_base, hists);
                 }
 
                 fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n",
@@ -659,7 +662,7 @@ static void data_process(void)
                 if (verbose || data__files_cnt > 2)
                         data__fprintf();
 
-                hists__process(&evsel_base->hists);
+                hists__process(hists_base);
         }
 }
 
@@ -683,7 +686,7 @@ static int __cmd_diff(void)
                 d->session = perf_session__new(&d->file, false, &tool);
                 if (!d->session) {
                         pr_err("Failed to open %s\n", d->file.path);
-                        ret = -ENOMEM;
+                        ret = -1;
                         goto out_delete;
                 }
 
@@ -1139,11 +1142,16 @@ static int data_init(int argc, const char **argv)
 
 int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 {
+        int ret = hists__init();
+
+        if (ret < 0)
+                return ret;
+
         perf_config(perf_default_config, NULL);
 
         argc = parse_options(argc, argv, options, diff_usage, 0);
 
-        if (symbol__init() < 0)
+        if (symbol__init(NULL) < 0)
                 return -1;
 
         if (data_init(argc, argv) < 0)
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index 66e12f55c052..0f93f859b782 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -28,7 +28,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
 
         session = perf_session__new(&file, 0, NULL);
         if (session == NULL)
-                return -ENOMEM;
+                return -1;
 
         evlist__for_each(session->evlist, pos)
                 perf_evsel__fprintf(pos, details, stdout);
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 0384d930480b..25d20628212e 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -103,6 +103,8 @@ static int check_emacsclient_version(void)
 
 static void exec_woman_emacs(const char *path, const char *page)
 {
+        char sbuf[STRERR_BUFSIZE];
+
         if (!check_emacsclient_version()) {
                 /* This works only with emacsclient version >= 22. */
                 struct strbuf man_page = STRBUF_INIT;
@@ -111,16 +113,19 @@ static void exec_woman_emacs(const char *path, const char *page)
                         path = "emacsclient";
                 strbuf_addf(&man_page, "(woman \"%s\")", page);
                 execlp(path, "emacsclient", "-e", man_page.buf, NULL);
-                warning("failed to exec '%s': %s", path, strerror(errno));
+                warning("failed to exec '%s': %s", path,
+                        strerror_r(errno, sbuf, sizeof(sbuf)));
         }
 }
 
 static void exec_man_konqueror(const char *path, const char *page)
 {
         const char *display = getenv("DISPLAY");
+
         if (display && *display) {
                 struct strbuf man_page = STRBUF_INIT;
                 const char *filename = "kfmclient";
+                char sbuf[STRERR_BUFSIZE];
 
                 /* It's simpler to launch konqueror using kfmclient. */
                 if (path) {
@@ -139,24 +144,31 @@ static void exec_man_konqueror(const char *path, const char *page)
                         path = "kfmclient";
                 strbuf_addf(&man_page, "man:%s(1)", page);
                 execlp(path, filename, "newTab", man_page.buf, NULL);
-                warning("failed to exec '%s': %s", path, strerror(errno));
+                warning("failed to exec '%s': %s", path,
+                        strerror_r(errno, sbuf, sizeof(sbuf)));
         }
 }
 
 static void exec_man_man(const char *path, const char *page)
 {
+        char sbuf[STRERR_BUFSIZE];
+
         if (!path)
                 path = "man";
         execlp(path, "man", page, NULL);
-        warning("failed to exec '%s': %s", path, strerror(errno));
+        warning("failed to exec '%s': %s", path,
+                strerror_r(errno, sbuf, sizeof(sbuf)));
 }
 
 static void exec_man_cmd(const char *cmd, const char *page)
 {
         struct strbuf shell_cmd = STRBUF_INIT;
+        char sbuf[STRERR_BUFSIZE];
+
         strbuf_addf(&shell_cmd, "%s %s", cmd, page);
         execl("/bin/sh", "sh", "-c", shell_cmd.buf, NULL);
-        warning("failed to exec '%s': %s", cmd, strerror(errno));
+        warning("failed to exec '%s': %s", cmd,
+                strerror_r(errno, sbuf, sizeof(sbuf)));
 }
 
 static void add_man_viewer(const char *name)
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 9a02807387d6..de99ca1bb942 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -23,6 +23,7 @@
 
 struct perf_inject {
         struct perf_tool        tool;
+        struct perf_session     *session;
         bool                    build_ids;
         bool                    sched_stat;
         const char              *input_name;
@@ -340,12 +341,8 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel,
 
 static int __cmd_inject(struct perf_inject *inject)
 {
-        struct perf_session *session;
         int ret = -EINVAL;
-        struct perf_data_file file = {
-                .path = inject->input_name,
-                .mode = PERF_DATA_MODE_READ,
-        };
+        struct perf_session *session = inject->session;
         struct perf_data_file *file_out = &inject->output;
 
         signal(SIGINT, sig_handler);
@@ -357,16 +354,12 @@ static int __cmd_inject(struct perf_inject *inject)
                 inject->tool.tracing_data = perf_event__repipe_tracing_data;
         }
 
-        session = perf_session__new(&file, true, &inject->tool);
-        if (session == NULL)
-                return -ENOMEM;
-
         if (inject->build_ids) {
                 inject->tool.sample = perf_event__inject_buildid;
         } else if (inject->sched_stat) {
                 struct perf_evsel *evsel;
 
-                inject->tool.ordered_samples = true;
+                inject->tool.ordered_events = true;
 
                 evlist__for_each(session->evlist, evsel) {
                         const char *name = perf_evsel__name(evsel);
@@ -396,8 +389,6 @@ static int __cmd_inject(struct perf_inject *inject)
                 perf_session__write_header(session, session->evlist, file_out->fd, true);
         }
 
-        perf_session__delete(session);
-
         return ret;
 }
 
@@ -427,6 +418,11 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
                         .mode = PERF_DATA_MODE_WRITE,
                 },
         };
+        struct perf_data_file file = {
+                .mode = PERF_DATA_MODE_READ,
+        };
+        int ret;
+
         const struct option options[] = {
                 OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
                             "Inject build-ids into the output stream"),
@@ -461,8 +457,17 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
                 return -1;
         }
 
-        if (symbol__init() < 0)
+        file.path = inject.input_name;
+        inject.session = perf_session__new(&file, true, &inject.tool);
+        if (inject.session == NULL)
+                return -1;
+
+        if (symbol__init(&inject.session->header.env) < 0)
                 return -1;
 
-        return __cmd_inject(&inject);
+        ret = __cmd_inject(&inject);
+
+        perf_session__delete(inject.session);
+
+        return ret;
 }
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index bef3376bfaf3..f295141025bc 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -256,7 +256,9 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 static struct perf_tool perf_kmem = {
         .sample          = process_sample_event,
         .comm            = perf_event__process_comm,
-        .ordered_samples = true,
+        .mmap            = perf_event__process_mmap,
+        .mmap2           = perf_event__process_mmap2,
+        .ordered_events  = true,
 };
 
 static double fragmentation(unsigned long n_req, unsigned long n_alloc)
@@ -403,10 +405,9 @@ static void sort_result(void)
         __sort_result(&root_caller_stat, &root_caller_sorted, &caller_sort);
 }
 
-static int __cmd_kmem(void)
+static int __cmd_kmem(struct perf_session *session)
 {
         int err = -EINVAL;
-        struct perf_session *session;
         const struct perf_evsel_str_handler kmem_tracepoints[] = {
                 { "kmem:kmalloc",               perf_evsel__process_alloc_event, },
                 { "kmem:kmem_cache_alloc",      perf_evsel__process_alloc_event, },
@@ -415,34 +416,22 @@ static int __cmd_kmem(void)
                 { "kmem:kfree",                 perf_evsel__process_free_event, },
                 { "kmem:kmem_cache_free",       perf_evsel__process_free_event, },
         };
-        struct perf_data_file file = {
-                .path = input_name,
-                .mode = PERF_DATA_MODE_READ,
-        };
-
-        session = perf_session__new(&file, false, &perf_kmem);
-        if (session == NULL)
-                return -ENOMEM;
-
-        if (perf_session__create_kernel_maps(session) < 0)
-                goto out_delete;
 
         if (!perf_session__has_traces(session, "kmem record"))
-                goto out_delete;
+                goto out;
 
         if (perf_session__set_tracepoints_handlers(session, kmem_tracepoints)) {
                 pr_err("Initializing perf session tracepoint handlers failed\n");
-                return -1;
+                goto out;
         }
 
         setup_pager();
         err = perf_session__process_events(session, &perf_kmem);
         if (err != 0)
-                goto out_delete;
+                goto out;
         sort_result();
         print_result(session);
-out_delete:
-        perf_session__delete(session);
+out:
         return err;
 }
 
@@ -689,29 +678,46 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
                 NULL,
                 NULL
         };
+        struct perf_session *session;
+        struct perf_data_file file = {
+                .path = input_name,
+                .mode = PERF_DATA_MODE_READ,
+        };
+        int ret = -1;
+
         argc = parse_options_subcommand(argc, argv, kmem_options,
                                         kmem_subcommands, kmem_usage, 0);
 
         if (!argc)
                 usage_with_options(kmem_usage, kmem_options);
 
-        symbol__init();
-
         if (!strncmp(argv[0], "rec", 3)) {
+                symbol__init(NULL);
                 return __cmd_record(argc, argv);
-        } else if (!strcmp(argv[0], "stat")) {
+        }
+
+        session = perf_session__new(&file, false, &perf_kmem);
+        if (session == NULL)
+                return -1;
+
+        symbol__init(&session->header.env);
+
+        if (!strcmp(argv[0], "stat")) {
                 if (cpu__setup_cpunode_map())
-                        return -1;
+                        goto out_delete;
 
                 if (list_empty(&caller_sort))
                         setup_sorting(&caller_sort, default_sort_order);
                 if (list_empty(&alloc_sort))
                         setup_sorting(&alloc_sort, default_sort_order);
 
-                return __cmd_kmem();
+                ret = __cmd_kmem(session);
         } else
                 usage_with_options(kmem_usage, kmem_options);
 
-        return 0;
+out_delete:
+        perf_session__delete(session);
+
+        return ret;
 }
 
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 43367eb00510..b65eb0507b38 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -376,7 +376,7 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
                                           struct perf_sample *sample)
 {
         /* Only kvm_entry records vcpu id. */
-        if (!thread->priv && kvm_entry_event(evsel)) {
+        if (!thread__priv(thread) && kvm_entry_event(evsel)) {
                 struct vcpu_event_record *vcpu_record;
 
                 vcpu_record = zalloc(sizeof(*vcpu_record));
@@ -386,10 +386,10 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
                 }
 
                 vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, VCPU_ID);
-                thread->priv = vcpu_record;
+                thread__set_priv(thread, vcpu_record);
         }
 
-        return thread->priv;
+        return thread__priv(thread);
 }
 
 static bool handle_kvm_event(struct perf_kvm_stat *kvm,
@@ -543,14 +543,12 @@ static void print_vcpu_info(struct perf_kvm_stat *kvm)
 
         pr_info("Analyze events for ");
 
-        if (kvm->live) {
-                if (kvm->opts.target.system_wide)
-                        pr_info("all VMs, ");
-                else if (kvm->opts.target.pid)
-                        pr_info("pid(s) %s, ", kvm->opts.target.pid);
-                else
-                        pr_info("dazed and confused on what is monitored, ");
-        }
+        if (kvm->opts.target.system_wide)
+                pr_info("all VMs, ");
+        else if (kvm->opts.target.pid)
+                pr_info("pid(s) %s, ", kvm->opts.target.pid);
+        else
+                pr_info("dazed and confused on what is monitored, ");
 
         if (vcpu == -1)
                 pr_info("all VCPUs:\n\n");
@@ -592,8 +590,8 @@ static void print_result(struct perf_kvm_stat *kvm)
         pr_info("%9s ", "Samples%");
 
         pr_info("%9s ", "Time%");
-        pr_info("%10s ", "Min Time");
-        pr_info("%10s ", "Max Time");
+        pr_info("%11s ", "Min Time");
+        pr_info("%11s ", "Max Time");
         pr_info("%16s ", "Avg time");
         pr_info("\n\n");
 
@@ -610,8 +608,8 @@ static void print_result(struct perf_kvm_stat *kvm)
                 pr_info("%10llu ", (unsigned long long)ecount);
                 pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
                 pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
-                pr_info("%8" PRIu64 "us ", min / 1000);
-                pr_info("%8" PRIu64 "us ", max / 1000);
+                pr_info("%9.2fus ", (double)min / 1e3);
+                pr_info("%9.2fus ", (double)max / 1e3);
                 pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3,
                         kvm_event_rel_stddev(vcpu, event));
                 pr_info("\n");
@@ -732,7 +730,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
                         return -1;
                 }
 
-                err = perf_session_queue_event(kvm->session, event, &sample, 0);
+                err = perf_session_queue_event(kvm->session, event, &kvm->tool, &sample, 0);
                 /*
                  * FIXME: Here we can't consume the event, as perf_session_queue_event will
                  *        point to it, and it'll get possibly overwritten by the kernel.
@@ -785,7 +783,7 @@ static int perf_kvm__mmap_read(struct perf_kvm_stat *kvm)
 
         /* flush queue after each round in which we processed events */
         if (ntotal) {
-                kvm->session->ordered_samples.next_flush = flush_time;
+                kvm->session->ordered_events.next_flush = flush_time;
                 err = kvm->tool.finished_round(&kvm->tool, NULL, kvm->session);
                 if (err) {
                         if (kvm->lost_events)
@@ -885,15 +883,11 @@ static int fd_set_nonblock(int fd)
         return 0;
 }
 
-static
-int perf_kvm__handle_stdin(struct termios *tc_now, struct termios *tc_save)
+static int perf_kvm__handle_stdin(void)
 {
         int c;
 
-        tcsetattr(0, TCSANOW, tc_now);
         c = getc(stdin);
-        tcsetattr(0, TCSAFLUSH, tc_save);
-
         if (c == 'q')
                 return 1;
 
@@ -902,9 +896,8 @@ int perf_kvm__handle_stdin(struct termios *tc_now, struct termios *tc_save)
 
 static int kvm_events_live_report(struct perf_kvm_stat *kvm)
 {
-        struct pollfd *pollfds = NULL;
-        int nr_fds, nr_stdin, ret, err = -EINVAL;
-        struct termios tc, save;
+        int nr_stdin, ret, err = -EINVAL;
+        struct termios save;
 
         /* live flag must be set first */
         kvm->live = true;
@@ -919,41 +912,25 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
                 goto out;
         }
 
+        set_term_quiet_input(&save);
         init_kvm_event_record(kvm);
 
-        tcgetattr(0, &save);
-        tc = save;
-        tc.c_lflag &= ~(ICANON | ECHO);
-        tc.c_cc[VMIN] = 0;
-        tc.c_cc[VTIME] = 0;
-
         signal(SIGINT, sig_handler);
         signal(SIGTERM, sig_handler);
 
-        /* copy pollfds -- need to add timerfd and stdin */
-        nr_fds = kvm->evlist->nr_fds;
-        pollfds = zalloc(sizeof(struct pollfd) * (nr_fds + 2));
-        if (!pollfds) {
-                err = -ENOMEM;
-                goto out;
-        }
-        memcpy(pollfds, kvm->evlist->pollfd,
-                sizeof(struct pollfd) * kvm->evlist->nr_fds);
-
         /* add timer fd */
         if (perf_kvm__timerfd_create(kvm) < 0) {
                 err = -1;
                 goto out;
         }
 
-        pollfds[nr_fds].fd = kvm->timerfd;
-        pollfds[nr_fds].events = POLLIN;
-        nr_fds++;
+        if (perf_evlist__add_pollfd(kvm->evlist, kvm->timerfd) < 0)
+                goto out;
+
+        nr_stdin = perf_evlist__add_pollfd(kvm->evlist, fileno(stdin));
+        if (nr_stdin < 0)
+                goto out;
 
-        pollfds[nr_fds].fd = fileno(stdin);
-        pollfds[nr_fds].events = POLLIN;
-        nr_stdin = nr_fds;
-        nr_fds++;
         if (fd_set_nonblock(fileno(stdin)) != 0)
                 goto out;
 
@@ -961,6 +938,7 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
         perf_evlist__enable(kvm->evlist);
 
         while (!done) {
+                struct fdarray *fda = &kvm->evlist->pollfd;
                 int rc;
 
                 rc = perf_kvm__mmap_read(kvm);
@@ -971,11 +949,11 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
                 if (err)
                         goto out;
 
-                if (pollfds[nr_stdin].revents & POLLIN)
-                        done = perf_kvm__handle_stdin(&tc, &save);
+                if (fda->entries[nr_stdin].revents & POLLIN)
+                        done = perf_kvm__handle_stdin();
 
                 if (!rc && !done)
-                        err = poll(pollfds, nr_fds, 100);
+                        err = fdarray__poll(fda, 100);
         }
 
         perf_evlist__disable(kvm->evlist);
@@ -989,7 +967,7 @@ out:
         if (kvm->timerfd >= 0)
                 close(kvm->timerfd);
 
-        free(pollfds);
+        tcsetattr(0, TCSAFLUSH, &save);
         return err;
 }
 
@@ -998,6 +976,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
         int err, rc = -1;
         struct perf_evsel *pos;
         struct perf_evlist *evlist = kvm->evlist;
+        char sbuf[STRERR_BUFSIZE];
 
         perf_evlist__config(evlist, &kvm->opts);
 
@@ -1034,12 +1013,14 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 
         err = perf_evlist__open(evlist);
         if (err < 0) {
-                printf("Couldn't create the events: %s\n", strerror(errno));
+                printf("Couldn't create the events: %s\n",
+                       strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out;
         }
 
         if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
-                ui__error("Failed to mmap the events: %s\n", strerror(errno));
+                ui__error("Failed to mmap the events: %s\n",
+                          strerror_r(errno, sbuf, sizeof(sbuf)));
                 perf_evlist__close(evlist);
                 goto out;
         }
@@ -1058,7 +1039,7 @@ static int read_events(struct perf_kvm_stat *kvm)
         struct perf_tool eops = {
                 .sample                 = process_sample_event,
                 .comm                   = perf_event__process_comm,
-                .ordered_samples        = true,
+                .ordered_events         = true,
         };
         struct perf_data_file file = {
                 .path = kvm->file_name,
@@ -1069,9 +1050,11 @@ static int read_events(struct perf_kvm_stat *kvm)
         kvm->session = perf_session__new(&file, false, &kvm->tool);
         if (!kvm->session) {
                 pr_err("Initializing perf session failed\n");
-                return -EINVAL;
+                return -1;
         }
 
+        symbol__init(&kvm->session->header.env);
+
         if (!perf_session__has_traces(kvm->session, "kvm record"))
                 return -EINVAL;
 
@@ -1088,8 +1071,8 @@ static int read_events(struct perf_kvm_stat *kvm)
 
 static int parse_target_str(struct perf_kvm_stat *kvm)
 {
-        if (kvm->pid_str) {
-                kvm->pid_list = intlist__new(kvm->pid_str);
+        if (kvm->opts.target.pid) {
+                kvm->pid_list = intlist__new(kvm->opts.target.pid);
                 if (kvm->pid_list == NULL) {
                         pr_err("Error parsing process id string\n");
                         return -EINVAL;
@@ -1191,7 +1174,7 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
                 OPT_STRING('k', "key", &kvm->sort_key, "sort-key",
                             "key for sorting: sample(sort by samples number)"
                             " time (sort by avg time)"),
-                OPT_STRING('p', "pid", &kvm->pid_str, "pid",
+                OPT_STRING('p', "pid", &kvm->opts.target.pid, "pid",
                            "analyze events only for given process id(s)"),
                 OPT_END()
         };
@@ -1201,8 +1184,6 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
                 NULL
         };
 
-        symbol__init();
-
         if (argc) {
                 argc = parse_options(argc, argv,
                                      kvm_events_report_options,
@@ -1212,6 +1193,9 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
                                            kvm_events_report_options);
         }
 
+        if (!kvm->opts.target.pid)
+                kvm->opts.target.system_wide = true;
+
         return kvm_events_report_vcpu(kvm);
 }
 
@@ -1311,7 +1295,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
         kvm->tool.exit   = perf_event__process_exit;
         kvm->tool.fork   = perf_event__process_fork;
         kvm->tool.lost   = process_lost_event;
-        kvm->tool.ordered_samples = true;
+        kvm->tool.ordered_events = true;
         perf_tool__fill_defaults(&kvm->tool);
 
         /* set defaults */
@@ -1322,7 +1306,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
         kvm->opts.target.uid_str = NULL;
         kvm->opts.target.uid = UINT_MAX;
 
-        symbol__init();
+        symbol__init(NULL);
         disable_buildid_cache();
 
         use_browser = 0;
@@ -1369,11 +1353,12 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
          */
         kvm->session = perf_session__new(&file, false, &kvm->tool);
         if (kvm->session == NULL) {
-                err = -ENOMEM;
+                err = -1;
                 goto out;
         }
         kvm->session->evlist = kvm->evlist;
         perf_session__set_id_hdr_size(kvm->session);
+        ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true);
         machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target,
                                     kvm->evlist->threads, false);
         err = kvm_live_open_events(kvm);
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 6148afc995c6..e7ec71589da6 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -852,7 +852,7 @@ static int __cmd_report(bool display_info)
         struct perf_tool eops = {
                 .sample          = process_sample_event,
                 .comm            = perf_event__process_comm,
-                .ordered_samples = true,
+                .ordered_events  = true,
         };
         struct perf_data_file file = {
                 .path = input_name,
@@ -862,9 +862,11 @@ static int __cmd_report(bool display_info)
         session = perf_session__new(&file, false, &eops);
         if (!session) {
                 pr_err("Initializing perf session failed\n");
-                return -ENOMEM;
+                return -1;
         }
 
+        symbol__init(&session->header.env);
+
         if (!perf_session__has_traces(session, "lock record"))
                 goto out_delete;
 
@@ -974,7 +976,6 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
         unsigned int i;
         int rc = 0;
 
-        symbol__init();
         for (i = 0; i < LOCKHASH_SIZE; i++)
                 INIT_LIST_HEAD(lockhash_table + i);
 
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 4a1a6c94a5eb..24db6ffe2957 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -124,7 +124,7 @@ static int report_raw_events(struct perf_mem *mem)
                                                          &mem->tool);
 
         if (session == NULL)
-                return -ENOMEM;
+                return -1;
 
         if (mem->cpu_list) {
                 ret = perf_session__cpu_bitmap(session, mem->cpu_list,
@@ -133,7 +133,7 @@ static int report_raw_events(struct perf_mem *mem)
                         goto out_delete;
         }
 
-        if (symbol__init() < 0)
+        if (symbol__init(&session->header.env) < 0)
                 return -1;
 
         printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
@@ -194,7 +194,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
                         .lost           = perf_event__process_lost,
                         .fork           = perf_event__process_fork,
                         .build_id       = perf_event__process_build_id,
-                        .ordered_samples = true,
+                        .ordered_events = true,
                 },
                 .input_name              = "perf.data",
         };
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index c63fa2925075..7af26acf06d9 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -290,8 +290,11 @@ static void cleanup_params(void)
 
 static void pr_err_with_code(const char *msg, int err)
 {
+        char sbuf[STRERR_BUFSIZE];
+
         pr_err("%s", msg);
-        pr_debug(" Reason: %s (Code: %d)", strerror(-err), err);
+        pr_debug(" Reason: %s (Code: %d)",
+                 strerror_r(-err, sbuf, sizeof(sbuf)), err);
         pr_err("\n");
 }
 
@@ -372,7 +375,9 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
         OPT_CALLBACK('x', "exec", NULL, "executable|path",
                         "target executable name or path", opt_set_target),
         OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
-                    "Disable symbol demangling"),
+                    "Enable symbol demangling"),
+        OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
+                    "Enable kernel symbol demangling"),
         OPT_END()
         };
         int ret;
@@ -467,7 +472,8 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
                         usage_with_options(probe_usage, options);
                 }
 
-                ret = show_line_range(&params.line_range, params.target);
+                ret = show_line_range(&params.line_range, params.target,
+                                      params.uprobes);
                 if (ret < 0)
                         pr_err_with_code("  Error: Failed to show lines.", ret);
                 return ret;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4869050e7194..2583a9b04317 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -14,6 +14,8 @@
 #include "util/parse-options.h"
 #include "util/parse-events.h"
 
+#include "util/callchain.h"
+#include "util/cgroup.h"
 #include "util/header.h"
 #include "util/event.h"
 #include "util/evlist.h"
@@ -65,8 +67,9 @@ static int process_synthesized_event(struct perf_tool *tool,
         return record__write(rec, event, event->header.size);
 }
 
-static int record__mmap_read(struct record *rec, struct perf_mmap *md)
+static int record__mmap_read(struct record *rec, int idx)
 {
+        struct perf_mmap *md = &rec->evlist->mmap[idx];
         unsigned int head = perf_mmap__read_head(md);
         unsigned int old = md->prev;
         unsigned char *data = md->base + page_size;
@@ -102,8 +105,7 @@ static int record__mmap_read(struct record *rec, struct perf_mmap *md)
         }
 
         md->prev = old;
-        perf_mmap__write_tail(md, old);
-
+        perf_evlist__mmap_consume(rec->evlist, idx);
 out:
         return rc;
 }
@@ -161,7 +163,7 @@ try_again:
 
         if (perf_evlist__apply_filters(evlist)) {
                 error("failed to set filter with %d (%s)\n", errno,
-                        strerror(errno));
+                        strerror_r(errno, msg, sizeof(msg)));
                 rc = -1;
                 goto out;
         }
@@ -175,7 +177,8 @@ try_again:
                                "(current value: %u)\n", opts->mmap_pages);
                         rc = -errno;
                 } else {
-                        pr_err("failed to mmap with %d (%s)\n", errno, strerror(errno));
+                        pr_err("failed to mmap with %d (%s)\n", errno,
+                                strerror_r(errno, msg, sizeof(msg)));
                         rc = -errno;
                 }
                 goto out;
@@ -244,7 +247,7 @@ static int record__mmap_read_all(struct record *rec)
 
         for (i = 0; i < rec->evlist->nr_mmaps; i++) {
                 if (rec->evlist->mmap[i].base) {
-                        if (record__mmap_read(rec, &rec->evlist->mmap[i]) != 0) {
+                        if (record__mmap_read(rec, i) != 0) {
                                 rc = -1;
                                 goto out;
                         }
@@ -307,7 +310,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
         struct record_opts *opts = &rec->opts;
         struct perf_data_file *file = &rec->file;
         struct perf_session *session;
-        bool disabled = false;
+        bool disabled = false, draining = false;
 
         rec->progname = argv[0];
 
@@ -456,9 +459,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                 }
 
                 if (hits == rec->samples) {
-                        if (done)
+                        if (done || draining)
                                 break;
-                        err = poll(rec->evlist->pollfd, rec->evlist->nr_fds, -1);
+                        err = perf_evlist__poll(rec->evlist, -1);
                         /*
                          * Propagate error, only if there's any. Ignore positive
                          * number of returned events and interrupt error.
@@ -466,6 +469,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                         if (err > 0 || (err < 0 && errno == EINTR))
                                 err = 0;
                         waking++;
+
+                        if (perf_evlist__filter_pollfd(rec->evlist, POLLERR | POLLHUP) == 0)
+                                draining = true;
                 }
 
                 /*
@@ -480,7 +486,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
         }
 
         if (forks && workload_exec_errno) {
-                char msg[512];
+                char msg[STRERR_BUFSIZE];
                 const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
                 pr_err("Workload failed: %s\n", emsg);
                 err = -1;
@@ -620,145 +626,56 @@ error:
         return ret;
 }
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-static int get_stack_size(char *str, unsigned long *_size)
-{
-        char *endptr;
-        unsigned long size;
-        unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
-
-        size = strtoul(str, &endptr, 0);
-
-        do {
-                if (*endptr)
-                        break;
-
-                size = round_up(size, sizeof(u64));
-                if (!size || size > max_size)
-                        break;
-
-                *_size = size;
-                return 0;
-
-        } while (0);
-
-        pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
-               max_size, str);
-        return -1;
-}
-#endif /* HAVE_DWARF_UNWIND_SUPPORT */
-
-int record_parse_callchain(const char *arg, struct record_opts *opts)
-{
-        char *tok, *name, *saveptr = NULL;
-        char *buf;
-        int ret = -1;
-
-        /* We need buffer that we know we can write to. */
-        buf = malloc(strlen(arg) + 1);
-        if (!buf)
-                return -ENOMEM;
-
-        strcpy(buf, arg);
-
-        tok = strtok_r((char *)buf, ",", &saveptr);
-        name = tok ? : (char *)buf;
-
-        do {
-                /* Framepointer style */
-                if (!strncmp(name, "fp", sizeof("fp"))) {
-                        if (!strtok_r(NULL, ",", &saveptr)) {
-                                opts->call_graph = CALLCHAIN_FP;
-                                ret = 0;
-                        } else
-                                pr_err("callchain: No more arguments "
-                                       "needed for -g fp\n");
-                        break;
-
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-                /* Dwarf style */
-                } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
-                        const unsigned long default_stack_dump_size = 8192;
-
-                        ret = 0;
-                        opts->call_graph = CALLCHAIN_DWARF;
-                        opts->stack_dump_size = default_stack_dump_size;
-
-                        tok = strtok_r(NULL, ",", &saveptr);
-                        if (tok) {
-                                unsigned long size = 0;
-
-                                ret = get_stack_size(tok, &size);
-                                opts->stack_dump_size = size;
-                        }
-#endif /* HAVE_DWARF_UNWIND_SUPPORT */
-                } else {
-                        pr_err("callchain: Unknown --call-graph option "
-                               "value: %s\n", arg);
-                        break;
-                }
-
-        } while (0);
-
-        free(buf);
-        return ret;
-}
-
-static void callchain_debug(struct record_opts *opts)
+static void callchain_debug(void)
 {
         static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF" };
 
-        pr_debug("callchain: type %s\n", str[opts->call_graph]);
+        pr_debug("callchain: type %s\n", str[callchain_param.record_mode]);
 
-        if (opts->call_graph == CALLCHAIN_DWARF)
+        if (callchain_param.record_mode == CALLCHAIN_DWARF)
                 pr_debug("callchain: stack dump size %d\n",
-                         opts->stack_dump_size);
+                         callchain_param.dump_size);
 }
 
-int record_parse_callchain_opt(const struct option *opt,
+int record_parse_callchain_opt(const struct option *opt __maybe_unused,
                                const char *arg,
                                int unset)
 {
-        struct record_opts *opts = opt->value;
         int ret;
 
-        opts->call_graph_enabled = !unset;
+        callchain_param.enabled = !unset;
 
         /* --no-call-graph */
         if (unset) {
-                opts->call_graph = CALLCHAIN_NONE;
+                callchain_param.record_mode = CALLCHAIN_NONE;
                 pr_debug("callchain: disabled\n");
                 return 0;
         }
 
-        ret = record_parse_callchain(arg, opts);
+        ret = parse_callchain_record_opt(arg);
         if (!ret)
-                callchain_debug(opts);
+                callchain_debug();
 
         return ret;
 }
 
-int record_callchain_opt(const struct option *opt,
+int record_callchain_opt(const struct option *opt __maybe_unused,
                          const char *arg __maybe_unused,
                          int unset __maybe_unused)
 {
-        struct record_opts *opts = opt->value;
+        callchain_param.enabled = true;
 
-        opts->call_graph_enabled = !unset;
+        if (callchain_param.record_mode == CALLCHAIN_NONE)
+                callchain_param.record_mode = CALLCHAIN_FP;
 
-        if (opts->call_graph == CALLCHAIN_NONE)
-                opts->call_graph = CALLCHAIN_FP;
-
-        callchain_debug(opts);
+        callchain_debug();
         return 0;
 }
 
 static int perf_record_config(const char *var, const char *value, void *cb)
 {
-        struct record *rec = cb;
-
         if (!strcmp(var, "record.call-graph"))
-                return record_parse_callchain(value, &rec->opts);
+                var = "call-graph.record-mode"; /* fall-through */
 
         return perf_default_config(var, value, cb);
 }
@@ -781,6 +698,7 @@ static const char * const record_usage[] = {
  */
 static struct record record = {
         .opts = {
+                .sample_time         = true,
                 .mmap_pages          = UINT_MAX,
                 .user_freq           = UINT_MAX,
                 .user_interval       = ULLONG_MAX,
@@ -907,7 +825,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
                 usage_with_options(record_usage, record_options);
         }
 
-        symbol__init();
+        symbol__init(NULL);
 
         if (symbol_conf.kptr_restrict)
                 pr_warning(
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 21d830bafff3..140a6cd88351 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -58,17 +58,19 @@ struct report {
         const char              *symbol_filter_str;
         float                   min_percent;
         u64                     nr_entries;
+        u64                     queue_size;
         DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
 static int report__config(const char *var, const char *value, void *cb)
 {
+        struct report *rep = cb;
+
         if (!strcmp(var, "report.group")) {
                 symbol_conf.event_group = perf_config_bool(var, value);
                 return 0;
         }
         if (!strcmp(var, "report.percent-limit")) {
-                struct report *rep = cb;
                 rep->min_percent = strtof(value, NULL);
                 return 0;
         }
@@ -76,6 +78,10 @@ static int report__config(const char *var, const char *value, void *cb)
                 symbol_conf.cumulate_callchain = perf_config_bool(var, value);
                 return 0;
         }
+        if (!strcmp(var, "report.queue-size")) {
+                rep->queue_size = perf_config_u64(var, value);
+                return 0;
+        }
 
         return perf_default_config(var, value, cb);
 }
@@ -251,6 +257,13 @@ static int report__setup_sample_type(struct report *rep)
                 }
         }
 
+        if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
+                if ((sample_type & PERF_SAMPLE_REGS_USER) &&
+                    (sample_type & PERF_SAMPLE_STACK_USER))
+                        callchain_param.record_mode = CALLCHAIN_DWARF;
+                else
+                        callchain_param.record_mode = CALLCHAIN_FP;
+        }
         return 0;
 }
 
@@ -282,12 +295,14 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
                 evname = buf;
 
                 for_each_group_member(pos, evsel) {
+                        const struct hists *pos_hists = evsel__hists(pos);
+
                         if (symbol_conf.filter_relative) {
-                                nr_samples += pos->hists.stats.nr_non_filtered_samples;
-                                nr_events += pos->hists.stats.total_non_filtered_period;
+                                nr_samples += pos_hists->stats.nr_non_filtered_samples;
+                                nr_events += pos_hists->stats.total_non_filtered_period;
                         } else {
-                                nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
-                                nr_events += pos->hists.stats.total_period;
+                                nr_samples += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE];
+                                nr_events += pos_hists->stats.total_period;
                         }
                 }
         }
@@ -312,7 +327,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
         struct perf_evsel *pos;
 
         evlist__for_each(evlist, pos) {
-                struct hists *hists = &pos->hists;
+                struct hists *hists = evsel__hists(pos);
                 const char *evname = perf_evsel__name(pos);
 
                 if (symbol_conf.event_group &&
@@ -421,7 +436,7 @@ static void report__collapse_hists(struct report *rep)
         ui_progress__init(&prog, rep->nr_entries, "Merging related events...");
 
         evlist__for_each(rep->session->evlist, pos) {
-                struct hists *hists = &pos->hists;
+                struct hists *hists = evsel__hists(pos);
 
                 if (pos->idx == 0)
                         hists->symbol_filter_str = rep->symbol_filter_str;
@@ -431,7 +446,7 @@ static void report__collapse_hists(struct report *rep)
                 /* Non-group events are considered as leader */
                 if (symbol_conf.event_group &&
                     !perf_evsel__is_group_leader(pos)) {
-                        struct hists *leader_hists = &pos->leader->hists;
+                        struct hists *leader_hists = evsel__hists(pos->leader);
 
                         hists__match(leader_hists, hists);
                         hists__link(leader_hists, hists);
@@ -479,6 +494,7 @@ static int __cmd_report(struct report *rep)
 
                 if (dump_trace) {
                         perf_session__fprintf_nr_events(session, stdout);
+                        perf_evlist__fprintf_nr_events(session->evlist, stdout);
                         return 0;
                 }
         }
@@ -494,7 +510,7 @@ static int __cmd_report(struct report *rep)
         }
 
         evlist__for_each(session->evlist, pos)
-                hists__output_resort(&pos->hists);
+                hists__output_resort(evsel__hists(pos));
 
         return report__browse_hists(rep);
 }
@@ -559,7 +575,6 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
         struct stat st;
         bool has_br_stack = false;
         int branch_mode = -1;
-        int ret = -1;
         char callchain_default_opt[] = "fractal,0.5,callee";
         const char * const report_usage[] = {
                 "perf report [<options>]",
@@ -578,7 +593,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                         .attr            = perf_event__process_attr,
                         .tracing_data    = perf_event__process_tracing_data,
                         .build_id        = perf_event__process_build_id,
-                        .ordered_samples = true,
+                        .ordered_events  = true,
                         .ordering_requires_timestamps = true,
                 },
                 .max_stack               = PERF_MAX_STACK_DEPTH,
@@ -674,6 +689,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                    "objdump binary to use for disassembly and annotations"),
         OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
                     "Disable symbol demangling"),
+        OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
+                    "Enable kernel symbol demangling"),
         OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
         OPT_CALLBACK(0, "percent-limit", &report, "percent",
                      "Don't show entries under that percent", parse_percent_limit),
@@ -684,6 +701,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
         struct perf_data_file file = {
                 .mode  = PERF_DATA_MODE_READ,
         };
+        int ret = hists__init();
+
+        if (ret < 0)
+                return ret;
 
         perf_config(report__config, &report);
 
@@ -712,14 +733,19 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 repeat:
         session = perf_session__new(&file, false, &report.tool);
         if (session == NULL)
-                return -ENOMEM;
+                return -1;
+
+        if (report.queue_size) {
+                ordered_events__set_alloc_size(&session->ordered_events,
+                                               report.queue_size);
+        }
 
         report.session = session;
 
         has_br_stack = perf_header__has_feat(&session->header,
                                              HEADER_BRANCH_STACK);
 
-        if (branch_mode == -1 && has_br_stack) {
+        if ((branch_mode == -1 && has_br_stack) || branch_mode == 1) {
                 sort__mode = SORT_MODE__BRANCH;
                 symbol_conf.cumulate_callchain = false;
         }
@@ -787,7 +813,7 @@ repeat:
                 }
         }
 
-        if (symbol__init() < 0)
+        if (symbol__init(&session->header.env) < 0)
                 goto error;
 
         if (argc) {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index f83c08c0dd87..891c3930080e 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -428,6 +428,7 @@ static u64 get_cpu_usage_nsec_parent(void)
 static int self_open_counters(void)
 {
         struct perf_event_attr attr;
+        char sbuf[STRERR_BUFSIZE];
         int fd;
 
         memset(&attr, 0, sizeof(attr));
@@ -440,7 +441,8 @@ static int self_open_counters(void)
 
         if (fd < 0)
                 pr_err("Error: sys_perf_event_open() syscall returned "
-                       "with %d (%s)\n", fd, strerror(errno));
+                       "with %d (%s)\n", fd,
+                       strerror_r(errno, sbuf, sizeof(sbuf)));
         return fd;
 }
 
@@ -1429,9 +1431,6 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
 {
         int err = 0;
 
-        evsel->hists.stats.total_period += sample->period;
-        hists__inc_nr_samples(&evsel->hists, true);
-
         if (evsel->handler != NULL) {
                 tracepoint_handler f = evsel->handler;
                 err = f(tool, evsel, sample, machine);
@@ -1462,6 +1461,8 @@ static int perf_sched__read_events(struct perf_sched *sched,
                 return -1;
         }
 
+        symbol__init(&session->header.env);
+
         if (perf_session__set_tracepoints_handlers(session, handlers))
                 goto out_delete;
 
@@ -1662,7 +1663,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
                         .comm            = perf_event__process_comm,
                         .lost            = perf_event__process_lost,
                         .fork            = perf_sched__process_fork_event,
-                        .ordered_samples = true,
+                        .ordered_events = true,
                 },
                 .cmp_pid              = LIST_HEAD_INIT(sched.cmp_pid),
                 .sort_list            = LIST_HEAD_INIT(sched.sort_list),
@@ -1747,7 +1748,6 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
         if (!strcmp(argv[0], "script"))
                 return cmd_script(argc, argv, prefix);
 
-        symbol__init();
         if (!strncmp(argv[0], "rec", 3)) {
                 return __cmd_record(argc, argv);
         } else if (!strncmp(argv[0], "lat", 3)) {
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index f57035b89c15..9708a1290571 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -44,6 +44,7 @@ enum perf_output_field {
         PERF_OUTPUT_ADDR            = 1U << 10,
         PERF_OUTPUT_SYMOFFSET       = 1U << 11,
         PERF_OUTPUT_SRCLINE         = 1U << 12,
+        PERF_OUTPUT_PERIOD          = 1U << 13,
 };
 
 struct output_option {
@@ -63,6 +64,7 @@ struct output_option {
         {.str = "addr",  .field = PERF_OUTPUT_ADDR},
         {.str = "symoff", .field = PERF_OUTPUT_SYMOFFSET},
         {.str = "srcline", .field = PERF_OUTPUT_SRCLINE},
+        {.str = "period", .field = PERF_OUTPUT_PERIOD},
 };
 
 /* default set to maintain compatibility with current format */
@@ -80,7 +82,8 @@ static struct {
                 .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
                               PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
                               PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-                                  PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
+                              PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
+                              PERF_OUTPUT_PERIOD,
 
                 .invalid_fields = PERF_OUTPUT_TRACE,
         },
@@ -91,7 +94,8 @@ static struct {
                 .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
                               PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
                               PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-                                  PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
+                              PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
+                              PERF_OUTPUT_PERIOD,
 
                 .invalid_fields = PERF_OUTPUT_TRACE,
         },
@@ -110,7 +114,8 @@ static struct {
                 .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
                               PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
                               PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-                                  PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
+                              PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
+                              PERF_OUTPUT_PERIOD,
 
                 .invalid_fields = PERF_OUTPUT_TRACE,
         },
@@ -184,10 +189,6 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
                 if (perf_evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP",
                                             PERF_OUTPUT_IP))
                         return -EINVAL;
-
-                if (!no_callchain &&
-                    !(attr->sample_type & PERF_SAMPLE_CALLCHAIN))
-                        symbol_conf.use_callchain = false;
         }
 
         if (PRINT_FIELD(ADDR) &&
@@ -233,6 +234,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
                                         PERF_OUTPUT_CPU))
                 return -EINVAL;
 
+        if (PRINT_FIELD(PERIOD) &&
+                perf_evsel__check_stype(evsel, PERF_SAMPLE_PERIOD, "PERIOD",
+                                        PERF_OUTPUT_PERIOD))
+                return -EINVAL;
+
         return 0;
 }
 
@@ -290,6 +296,19 @@ static int perf_session__check_output_opt(struct perf_session *session)
                 set_print_ip_opts(&evsel->attr);
         }
 
+        if (!no_callchain) {
+                bool use_callchain = false;
+
+                evlist__for_each(session->evlist, evsel) {
+                        if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
+                                use_callchain = true;
+                                break;
+                        }
+                }
+                if (!use_callchain)
+                        symbol_conf.use_callchain = false;
+        }
+
         /*
          * set default for tracepoints to print symbols only
          * if callchains are present
@@ -439,6 +458,9 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 
         print_sample_start(sample, thread, evsel);
 
+        if (PRINT_FIELD(PERIOD))
+                printf("%10" PRIu64 " ", sample->period);
+
         if (PRINT_FIELD(EVNAME)) {
                 const char *evname = perf_evsel__name(evsel);
                 printf("%s: ", evname ? evname : "[unknown]");
@@ -476,6 +498,11 @@ static int default_start_script(const char *script __maybe_unused,
         return 0;
 }
 
+static int default_flush_script(void)
+{
+        return 0;
+}
+
 static int default_stop_script(void)
 {
         return 0;
@@ -489,6 +516,7 @@ static int default_generate_script(struct pevent *pevent __maybe_unused,
 
 static struct scripting_ops default_scripting_ops = {
         .start_script           = default_start_script,
+        .flush_script           = default_flush_script,
         .stop_script            = default_stop_script,
         .process_event          = process_event,
         .generate_script        = default_generate_script,
@@ -504,6 +532,11 @@ static void setup_scripting(void)
         scripting_ops = &default_scripting_ops;
 }
 
+static int flush_scripting(void)
+{
+        return scripting_ops->flush_script();
+}
+
 static int cleanup_scripting(void)
 {
         pr_debug("\nperf script stopped\n");
@@ -552,7 +585,6 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 
         scripting_ops->process_event(event, sample, evsel, thread, &al);
 
-        evsel->hists.stats.total_period += sample->period;
         return 0;
 }
 
@@ -1471,12 +1503,13 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
         bool show_full_info = false;
         bool header = false;
         bool header_only = false;
+        bool script_started = false;
         char *rec_script_path = NULL;
         char *rep_script_path = NULL;
         struct perf_session *session;
         char *script_path = NULL;
         const char **__argv;
-        int i, j, err;
+        int i, j, err = 0;
         struct perf_script script = {
                 .tool = {
                         .sample          = process_sample_event,
@@ -1488,7 +1521,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
                         .attr            = process_attr,
                         .tracing_data    = perf_event__process_tracing_data,
                         .build_id        = perf_event__process_build_id,
-                        .ordered_samples = true,
+                        .ordered_events  = true,
                         .ordering_requires_timestamps = true,
                 },
         };
@@ -1523,7 +1556,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
                      "comma separated output fields prepend with 'type:'. "
                      "Valid types: hw,sw,trace,raw. "
                      "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-                     "addr,symoff", parse_output_fields),
+                     "addr,symoff,period", parse_output_fields),
         OPT_BOOLEAN('a', "all-cpus", &system_wide,
                     "system-wide collection from all CPUs"),
         OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
@@ -1718,26 +1751,28 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
                 exit(-1);
         }
 
-        if (symbol__init() < 0)
-                return -1;
         if (!script_name)
                 setup_pager();
 
         session = perf_session__new(&file, false, &script.tool);
         if (session == NULL)
-                return -ENOMEM;
+                return -1;
 
         if (header || header_only) {
                 perf_session__fprintf_info(session, stdout, show_full_info);
                 if (header_only)
-                        return 0;
+                        goto out_delete;
         }
 
+        if (symbol__init(&session->header.env) < 0)
+                goto out_delete;
+
         script.session = session;
 
         if (cpu_list) {
-                if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap))
-                        return -1;
+                err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
+                if (err < 0)
+                        goto out_delete;
         }
 
         if (!no_callchain)
@@ -1752,53 +1787,62 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
                 if (output_set_by_user()) {
                         fprintf(stderr,
                                 "custom fields not supported for generated scripts");
-                        return -1;
+                        err = -EINVAL;
+                        goto out_delete;
                 }
 
                 input = open(file.path, O_RDONLY);      /* input_name */
                 if (input < 0) {
+                        err = -errno;
                         perror("failed to open file");
-                        return -1;
+                        goto out_delete;
                 }
 
                 err = fstat(input, &perf_stat);
                 if (err < 0) {
                         perror("failed to stat file");
-                        return -1;
+                        goto out_delete;
                 }
 
                 if (!perf_stat.st_size) {
                         fprintf(stderr, "zero-sized file, nothing to do!\n");
-                        return 0;
+                        goto out_delete;
                 }
 
                 scripting_ops = script_spec__lookup(generate_script_lang);
                 if (!scripting_ops) {
                         fprintf(stderr, "invalid language specifier");
-                        return -1;
+                        err = -ENOENT;
+                        goto out_delete;
                 }
 
                 err = scripting_ops->generate_script(session->tevent.pevent,
                                                      "perf-script");
-                goto out;
+                goto out_delete;
         }
 
         if (script_name) {
                 err = scripting_ops->start_script(script_name, argc, argv);
                 if (err)
-                        goto out;
+                        goto out_delete;
                 pr_debug("perf script started with script %s\n\n", script_name);
+                script_started = true;
         }
 
 
         err = perf_session__check_output_opt(session);
         if (err < 0)
-                goto out;
+                goto out_delete;
 
         err = __cmd_script(&script);
 
+        flush_scripting();
+
+out_delete:
         perf_session__delete(session);
-        cleanup_scripting();
+
+        if (script_started)
+                cleanup_scripting();
 out:
         return err;
 }
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 3e80aa10cfd8..055ce9232c9e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -43,6 +43,7 @@
 
 #include "perf.h"
 #include "builtin.h"
+#include "util/cgroup.h"
 #include "util/util.h"
 #include "util/parse-options.h"
 #include "util/parse-events.h"
@@ -593,7 +594,7 @@ static int __run_perf_stat(int argc, const char **argv)
 
         if (perf_evlist__apply_filters(evsel_list)) {
                 error("failed to set filter with %d (%s)\n", errno,
-                        strerror(errno));
+                        strerror_r(errno, msg, sizeof(msg)));
                 return -1;
         }
 
@@ -732,7 +733,7 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
         }
 }
 
-static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
+static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
         double msecs = avg / 1e6;
         const char *fmt_v, *fmt_n;
@@ -741,7 +742,7 @@ static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
         fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
         fmt_n = csv_output ? "%s" : "%-25s";
 
-        aggr_printout(evsel, cpu, nr);
+        aggr_printout(evsel, id, nr);
 
         scnprintf(name, sizeof(name), "%s%s",
                   perf_evsel__name(evsel), csv_output ? "" : " (msec)");
@@ -947,11 +948,12 @@ static void print_ll_cache_misses(int cpu,
         fprintf(output, " of all LL-cache hits   ");
 }
 
-static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
+static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
         double total, ratio = 0.0, total2;
         double sc =  evsel->scale;
         const char *fmt;
+        int cpu = cpu_map__id_to_cpu(id);
 
         if (csv_output) {
                 fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
@@ -962,7 +964,7 @@ static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
                         fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
         }
 
-        aggr_printout(evsel, cpu, nr);
+        aggr_printout(evsel, id, nr);
 
         if (aggr_mode == AGGR_GLOBAL)
                 cpu = 0;
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 2f1a5220c090..35b425b6293f 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1605,7 +1605,9 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
         int ret = -EINVAL;
 
         if (session == NULL)
-                return -ENOMEM;
+                return -1;
+
+        symbol__init(&session->header.env);
 
         (void)perf_header__process_sections(&session->header,
                                             perf_data_file__fd(session->file),
@@ -1920,7 +1922,7 @@ int cmd_timechart(int argc, const char **argv,
                         .fork            = process_fork_event,
                         .exit            = process_exit_event,
                         .sample          = process_sample_event,
-                        .ordered_samples = true,
+                        .ordered_events  = true,
                 },
                 .proc_num = 15,
                 .min_time = 1000000,
@@ -1982,8 +1984,6 @@ int cmd_timechart(int argc, const char **argv,
                 return -1;
         }
 
-        symbol__init();
-
         if (argc && !strncmp(argv[0], "rec", 3)) {
                 argc = parse_options(argc, argv, record_options, record_usage,
                                      PARSE_OPT_STOP_AT_NON_OPTION);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 377971dc89a3..0aa7747ff139 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -59,7 +59,7 @@
 
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
-#include <sys/poll.h>
+#include <poll.h>
 #include <sys/prctl.h>
 #include <sys/wait.h>
 #include <sys/uio.h>
@@ -251,6 +251,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
         char bf[160];
         int printed = 0;
         const int win_width = top->winsize.ws_col - 1;
+        struct hists *hists = evsel__hists(top->sym_evsel);
 
         puts(CONSOLE_CLEAR);
 
@@ -261,13 +262,13 @@ static void perf_top__print_sym_table(struct perf_top *top)
 
         printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
 
-        if (top->sym_evsel->hists.stats.nr_lost_warned !=
-            top->sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST]) {
-                top->sym_evsel->hists.stats.nr_lost_warned =
-                        top->sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST];
+        if (hists->stats.nr_lost_warned !=
+            hists->stats.nr_events[PERF_RECORD_LOST]) {
+                hists->stats.nr_lost_warned =
+                              hists->stats.nr_events[PERF_RECORD_LOST];
                 color_fprintf(stdout, PERF_COLOR_RED,
                               "WARNING: LOST %d chunks, Check IO/CPU overload",
-                              top->sym_evsel->hists.stats.nr_lost_warned);
+                              hists->stats.nr_lost_warned);
                 ++printed;
         }
 
@@ -276,16 +277,19 @@ static void perf_top__print_sym_table(struct perf_top *top)
                 return;
         }
 
-        hists__collapse_resort(&top->sym_evsel->hists, NULL);
-        hists__output_resort(&top->sym_evsel->hists);
-        hists__decay_entries(&top->sym_evsel->hists,
-                             top->hide_user_symbols,
-                             top->hide_kernel_symbols);
-        hists__output_recalc_col_len(&top->sym_evsel->hists,
-                                     top->print_entries - printed);
+        if (top->zero) {
+                hists__delete_entries(hists);
+        } else {
+                hists__decay_entries(hists, top->hide_user_symbols,
+                                     top->hide_kernel_symbols);
+        }
+
+        hists__collapse_resort(hists, NULL);
+        hists__output_resort(hists);
+
+        hists__output_recalc_col_len(hists, top->print_entries - printed);
         putchar('\n');
-        hists__fprintf(&top->sym_evsel->hists, false,
-                       top->print_entries - printed, win_width,
+        hists__fprintf(hists, false, top->print_entries - printed, win_width,
                        top->min_percent, stdout);
 }
 
@@ -328,6 +332,7 @@ static void perf_top__prompt_symbol(struct perf_top *top, const char *msg)
 {
         char *buf = malloc(0), *p;
         struct hist_entry *syme = top->sym_filter_entry, *n, *found = NULL;
+        struct hists *hists = evsel__hists(top->sym_evsel);
         struct rb_node *next;
         size_t dummy = 0;
 
@@ -345,7 +350,7 @@ static void perf_top__prompt_symbol(struct perf_top *top, const char *msg)
         if (p)
                 *p = 0;
 
-        next = rb_first(&top->sym_evsel->hists.entries);
+        next = rb_first(&hists->entries);
         while (next) {
                 n = rb_entry(next, struct hist_entry, rb_node);
                 if (n->ms.sym && !strcmp(buf, n->ms.sym->name)) {
@@ -427,18 +432,13 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 
         if (!perf_top__key_mapped(top, c)) {
                 struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
-                struct termios tc, save;
+                struct termios save;
 
                 perf_top__print_mapped_keys(top);
                 fprintf(stdout, "\nEnter selection, or unmapped key to continue: ");
                 fflush(stdout);
 
-                tcgetattr(0, &save);
-                tc = save;
-                tc.c_lflag &= ~(ICANON | ECHO);
-                tc.c_cc[VMIN] = 0;
-                tc.c_cc[VTIME] = 0;
-                tcsetattr(0, TCSANOW, &tc);
+                set_term_quiet_input(&save);
 
                 poll(&stdin_poll, 1, -1);
                 c = getc(stdin);
@@ -537,16 +537,24 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 static void perf_top__sort_new_samples(void *arg)
 {
         struct perf_top *t = arg;
+        struct hists *hists;
+
         perf_top__reset_sample_counters(t);
 
         if (t->evlist->selected != NULL)
                 t->sym_evsel = t->evlist->selected;
 
-        hists__collapse_resort(&t->sym_evsel->hists, NULL);
-        hists__output_resort(&t->sym_evsel->hists);
-        hists__decay_entries(&t->sym_evsel->hists,
-                             t->hide_user_symbols,
-                             t->hide_kernel_symbols);
+        hists = evsel__hists(t->sym_evsel);
+
+        if (t->zero) {
+                hists__delete_entries(hists);
+        } else {
+                hists__decay_entries(hists, t->hide_user_symbols,
+                                     t->hide_kernel_symbols);
+        }
+
+        hists__collapse_resort(hists, NULL);
+        hists__output_resort(hists);
 }
 
 static void *display_thread_tui(void *arg)
@@ -567,8 +575,10 @@ static void *display_thread_tui(void *arg)
          * Zooming in/out UIDs. For now juse use whatever the user passed
          * via --uid.
          */
-        evlist__for_each(top->evlist, pos)
-                pos->hists.uid_filter_str = top->record_opts.target.uid_str;
+        evlist__for_each(top->evlist, pos) {
+                struct hists *hists = evsel__hists(pos);
+                hists->uid_filter_str = top->record_opts.target.uid_str;
+        }
 
         perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent,
                                       &top->session->header.env);
@@ -577,23 +587,32 @@ static void *display_thread_tui(void *arg)
         return NULL;
 }
 
+static void display_sig(int sig __maybe_unused)
+{
+        done = 1;
+}
+
+static void display_setup_sig(void)
+{
+        signal(SIGSEGV, display_sig);
+        signal(SIGFPE,  display_sig);
+        signal(SIGINT,  display_sig);
+        signal(SIGQUIT, display_sig);
+        signal(SIGTERM, display_sig);
+}
+
 static void *display_thread(void *arg)
 {
         struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
-        struct termios tc, save;
+        struct termios save;
         struct perf_top *top = arg;
         int delay_msecs, c;
 
-        tcgetattr(0, &save);
-        tc = save;
-        tc.c_lflag &= ~(ICANON | ECHO);
-        tc.c_cc[VMIN] = 0;
-        tc.c_cc[VTIME] = 0;
-
+        display_setup_sig();
         pthread__unblock_sigwinch();
 repeat:
         delay_msecs = top->delay_secs * 1000;
-        tcsetattr(0, TCSANOW, &tc);
+        set_term_quiet_input(&save);
         /* trash return*/
         getc(stdin);
 
@@ -620,13 +639,16 @@ repeat:
                 }
         }
 
+        tcsetattr(0, TCSAFLUSH, &save);
         return NULL;
 }
 
-static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
+static int symbol_filter(struct map *map, struct symbol *sym)
 {
         const char *name = sym->name;
 
+        if (!map->dso->kernel)
+                return 0;
         /*
          * ppc64 uses function descriptors and appends a '.' to the
          * start of every instruction address. Remove it.
@@ -750,6 +772,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
         }
 
         if (al.sym == NULL || !al.sym->ignore) {
+                struct hists *hists = evsel__hists(evsel);
                 struct hist_entry_iter iter = {
                         .add_entry_cb = hist_iter__top_callback,
                 };
@@ -759,14 +782,14 @@ static void perf_event__process_sample(struct perf_tool *tool,
                 else
                         iter.ops = &hist_iter_normal;
 
-                pthread_mutex_lock(&evsel->hists.lock);
+                pthread_mutex_lock(&hists->lock);
 
                 err = hist_entry_iter__add(&iter, &al, evsel, sample,
                                            top->max_stack, top);
                 if (err < 0)
                         pr_err("Problem incrementing symbol period, skipping event\n");
 
-                pthread_mutex_unlock(&evsel->hists.lock);
+                pthread_mutex_unlock(&hists->lock);
         }
 
         return;
@@ -831,7 +854,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
                         perf_event__process_sample(&top->tool, event, evsel,
                                                    &sample, machine);
                 } else if (event->header.type < PERF_RECORD_MAX) {
-                        hists__inc_nr_events(&evsel->hists, event->header.type);
+                        hists__inc_nr_events(evsel__hists(evsel), event->header.type);
                         machine__process_event(machine, event, &sample);
                 } else
                         ++session->stats.nr_unknown_events;
@@ -876,7 +899,7 @@ try_again:
 
         if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
                 ui__error("Failed to mmap with %d (%s)\n",
-                            errno, strerror(errno));
+                            errno, strerror_r(errno, msg, sizeof(msg)));
                 goto out_err;
         }
 
@@ -911,7 +934,7 @@ static int __cmd_top(struct perf_top *top)
 
         top->session = perf_session__new(NULL, false, NULL);
         if (top->session == NULL)
-                return -ENOMEM;
+                return -1;
 
         machines__set_symbol_filter(&top->session->machines, symbol_filter);
 
@@ -946,7 +969,7 @@ static int __cmd_top(struct perf_top *top)
                 perf_evlist__enable(top->evlist);
 
         /* Wait for a minimal set of events before starting the snapshot */
-        poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
+        perf_evlist__poll(top->evlist, 100);
 
         perf_top__mmap_read(top);
 
@@ -963,7 +986,7 @@ static int __cmd_top(struct perf_top *top)
                 param.sched_priority = top->realtime_prio;
                 if (sched_setscheduler(0, SCHED_FIFO, &param)) {
                         ui__error("Could not set realtime priority.\n");
-                        goto out_delete;
+                        goto out_join;
                 }
         }
 
@@ -973,10 +996,12 @@ static int __cmd_top(struct perf_top *top)
                 perf_top__mmap_read(top);
 
                 if (hits == top->samples)
-                        ret = poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
+                        ret = perf_evlist__poll(top->evlist, 100);
         }
 
         ret = 0;
+out_join:
+        pthread_join(thread, NULL);
 out_delete:
         perf_session__delete(top->session);
         top->session = NULL;
@@ -1000,10 +1025,8 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 
 static int perf_top_config(const char *var, const char *value, void *cb)
 {
-        struct perf_top *top = cb;
-
         if (!strcmp(var, "top.call-graph"))
-                return record_parse_callchain(value, &top->record_opts);
+                var = "call-graph.record-mode"; /* fall-through */
         if (!strcmp(var, "top.children")) {
                 symbol_conf.cumulate_callchain = perf_config_bool(var, value);
                 return 0;
@@ -1024,7 +1047,6 @@ parse_percent_limit(const struct option *opt, const char *arg,
 
 int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-        int status = -1;
         char errbuf[BUFSIZ];
         struct perf_top top = {
                 .count_filter        = 5,
@@ -1122,6 +1144,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
                     "Interleave source code with assembly code (default)"),
         OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
                     "Display raw encoding of assembly instructions (default)"),
+        OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
+                    "Enable kernel symbol demangling"),
         OPT_STRING(0, "objdump", &objdump_path, "path",
                     "objdump binary to use for disassembly and annotations"),
         OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
@@ -1131,12 +1155,19 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
                      "Don't show entries under that percent", parse_percent_limit),
         OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
                      "How to display percentage of filtered entries", parse_filter_percentage),
+        OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
+                   "width[,width...]",
+                   "don't try to adjust column width, use these fixed values"),
         OPT_END()
         };
         const char * const top_usage[] = {
                 "perf top [<options>]",
                 NULL
         };
+        int status = hists__init();
+
+        if (status < 0)
+                return status;
 
         top.evlist = perf_evlist__new();
         if (top.evlist == NULL)
@@ -1217,7 +1248,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
         symbol_conf.priv_size = sizeof(struct annotation);
 
         symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
-        if (symbol__init() < 0)
+        if (symbol__init(NULL) < 0)
                 return -1;
 
         sort__setup_elide(stdout);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index a6c375224f46..fb126459b134 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -402,6 +402,31 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 
 #define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
 
+static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
+                                                  struct syscall_arg *arg)
+{
+        int printed = 0, flags = arg->val;
+
+#define P_MREMAP_FLAG(n) \
+        if (flags & MREMAP_##n) { \
+                printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+                flags &= ~MREMAP_##n; \
+        }
+
+        P_MREMAP_FLAG(MAYMOVE);
+#ifdef MREMAP_FIXED
+        P_MREMAP_FLAG(FIXED);
+#endif
+#undef P_MREMAP_FLAG
+
+        if (flags)
+                printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+        return printed;
+}
+
+#define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags
+
 static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
                                                       struct syscall_arg *arg)
 {
@@ -1004,6 +1029,7 @@ static struct syscall_fmt {
                              [2] = SCA_MMAP_PROT, /* prot */ }, },
         { .name     = "mremap",     .hexret = true,
           .arg_scnprintf = { [0] = SCA_HEX, /* addr */
+                             [3] = SCA_MREMAP_FLAGS, /* flags */
                              [4] = SCA_HEX, /* new_addr */ }, },
         { .name     = "munlock",    .errmsg = true,
           .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
@@ -1163,13 +1189,13 @@ static struct thread_trace *thread__trace(struct thread *thread, FILE *fp)
         if (thread == NULL)
                 goto fail;
 
-        if (thread->priv == NULL)
-                thread->priv = thread_trace__new();
+        if (thread__priv(thread) == NULL)
+                thread__set_priv(thread, thread_trace__new());
                 
-        if (thread->priv == NULL)
+        if (thread__priv(thread) == NULL)
                 goto fail;
 
-        ttrace = thread->priv;
+        ttrace = thread__priv(thread);
         ++ttrace->nr_events;
 
         return ttrace;
@@ -1222,7 +1248,7 @@ struct trace {
 
 static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
 {
-        struct thread_trace *ttrace = thread->priv;
+        struct thread_trace *ttrace = thread__priv(thread);
 
         if (fd > ttrace->paths.max) {
                 char **npath = realloc(ttrace->paths.table, (fd + 1) * sizeof(char *));
@@ -1275,7 +1301,7 @@ static int thread__read_fd_path(struct thread *thread, int fd)
 static const char *thread__fd_path(struct thread *thread, int fd,
                                    struct trace *trace)
 {
-        struct thread_trace *ttrace = thread->priv;
+        struct thread_trace *ttrace = thread__priv(thread);
 
         if (ttrace == NULL)
                 return NULL;
@@ -1312,7 +1338,7 @@ static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
 {
         int fd = arg->val;
         size_t printed = syscall_arg__scnprintf_fd(bf, size, arg);
-        struct thread_trace *ttrace = arg->thread->priv;
+        struct thread_trace *ttrace = thread__priv(arg->thread);
 
         if (ttrace && fd >= 0 && fd <= ttrace->paths.max)
                 zfree(&ttrace->paths.table[fd]);
@@ -1385,7 +1411,7 @@ static int trace__tool_process(struct perf_tool *tool,
 
 static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 {
-        int err = symbol__init();
+        int err = symbol__init(NULL);
 
         if (err)
                 return err;
@@ -1669,7 +1695,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
                            union perf_event *event __maybe_unused,
                            struct perf_sample *sample)
 {
-        int ret;
+        long ret;
         u64 duration = 0;
         struct thread *thread;
         int id = perf_evsel__sc_tp_uint(evsel, id, sample);
@@ -1722,9 +1748,9 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 
         if (sc->fmt == NULL) {
 signed_print:
-                fprintf(trace->output, ") = %d", ret);
+                fprintf(trace->output, ") = %ld", ret);
         } else if (ret < 0 && sc->fmt->errmsg) {
-                char bf[256];
+                char bf[STRERR_BUFSIZE];
                 const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
                            *e = audit_errno_to_name(-ret);
 
@@ -1732,7 +1758,7 @@ signed_print:
         } else if (ret == 0 && sc->fmt->timeout)
                 fprintf(trace->output, ") = 0 Timeout");
         else if (sc->fmt->hexret)
-                fprintf(trace->output, ") = %#x", ret);
+                fprintf(trace->output, ") = %#lx", ret);
         else
                 goto signed_print;
 
@@ -2018,6 +2044,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
         int err = -1, i;
         unsigned long before;
         const bool forks = argc > 0;
+        bool draining = false;
+        char sbuf[STRERR_BUFSIZE];
 
         trace->live = true;
 
@@ -2079,7 +2107,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
         err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
         if (err < 0) {
-                fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno));
+                fprintf(trace->output, "Couldn't mmap the events: %s\n",
+                        strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
@@ -2143,8 +2172,12 @@ next_event:
         if (trace->nr_events == before) {
                 int timeout = done ? 100 : -1;
 
-                if (poll(evlist->pollfd, evlist->nr_fds, timeout) > 0)
+                if (!draining && perf_evlist__poll(evlist, timeout) > 0) {
+                        if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP) == 0)
+                                draining = true;
+
                         goto again;
+                }
         } else {
                 goto again;
         }
@@ -2209,18 +2242,18 @@ static int trace__replay(struct trace *trace)
         trace->tool.tracing_data = perf_event__process_tracing_data;
         trace->tool.build_id      = perf_event__process_build_id;
 
-        trace->tool.ordered_samples = true;
+        trace->tool.ordered_events = true;
         trace->tool.ordering_requires_timestamps = true;
 
         /* add tid to output */
         trace->multiple_threads = true;
 
-        if (symbol__init() < 0)
-                return -1;
-
         session = perf_session__new(&file, false, &trace->tool);
         if (session == NULL)
-                return -ENOMEM;
+                return -1;
+
+        if (symbol__init(&session->header.env) < 0)
+                goto out;
 
         trace->host = &session->machines.host;
 
@@ -2348,7 +2381,7 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
         FILE *fp = data->fp;
         size_t printed = data->printed;
         struct trace *trace = data->trace;
-        struct thread_trace *ttrace = thread->priv;
+        struct thread_trace *ttrace = thread__priv(thread);
         double ratio;
 
         if (ttrace == NULL)
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 1f67aa02d240..58f609198c6d 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -48,10 +48,6 @@ ifneq ($(ARCH),$(filter $(ARCH),x86 arm))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
-ifeq ($(ARCH),powerpc)
-  CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
-endif
-
 ifeq ($(LIBUNWIND_LIBS),)
   NO_LIBUNWIND := 1
 else
@@ -120,6 +116,29 @@ ifdef PARSER_DEBUG
   CFLAGS             += -DPARSER_DEBUG
 endif
 
+ifndef NO_LIBPYTHON
+  # Try different combinations to accommodate systems that only have
+  # python[2][-config] in weird combinations but always preferring
+  # python2 and python2-config as per pep-0394. If we catch a
+  # python[-config] in version 3, the version check will kill it.
+  PYTHON2 := $(if $(call get-executable,python2),python2,python)
+  override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2))
+  PYTHON2_CONFIG := \
+    $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config)
+  override PYTHON_CONFIG := \
+    $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG))
+
+  PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+
+  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+
+  FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
+  FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
+  FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
+  FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
+endif
+
 CFLAGS += -fno-omit-frame-pointer
 CFLAGS += -ggdb3
 CFLAGS += -funwind-tables
@@ -355,6 +374,12 @@ ifndef NO_LIBELF
   endif # NO_DWARF
 endif # NO_LIBELF
 
+ifeq ($(ARCH),powerpc)
+  ifndef NO_DWARF
+    CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
+  endif
+endif
+
 ifndef NO_LIBUNWIND
   ifneq ($(feature-libunwind), 1)
     msg := $(warning No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR);
@@ -482,21 +507,14 @@ define disable-python_code
   NO_LIBPYTHON := 1
 endef
 
-override PYTHON := \
-  $(call get-executable-or-default,PYTHON,python)
-
-ifndef PYTHON
-  $(call disable-python,python interpreter)
+ifdef NO_LIBPYTHON
+  $(call disable-python)
 else
 
-  PYTHON_WORD := $(call shell-wordify,$(PYTHON))
-
-  ifdef NO_LIBPYTHON
-    $(call disable-python)
+  ifndef PYTHON
+    $(call disable-python,python interpreter)
   else
-
-    override PYTHON_CONFIG := \
-      $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON)-config)
+    PYTHON_WORD := $(call shell-wordify,$(PYTHON))
 
     ifndef PYTHON_CONFIG
       $(call disable-python,python-config tool)
@@ -635,11 +653,13 @@ else
 sysconfdir = $(prefix)/etc
 ETC_PERFCONFIG = etc/perfconfig
 endif
+ifndef lib
 ifeq ($(IS_X86_64),1)
 lib = lib64
 else
 lib = lib
 endif
+endif # lib
 libdir = $(prefix)/$(lib)
 
 # Shell quote (do not use $(call) to accommodate ancient setups);
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 6088f8d8a434..72ab2984718e 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -101,25 +101,11 @@ FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 test-libperl.bin:
         $(BUILD) $(FLAGS_PERL_EMBED)
 
-override PYTHON := python
-override PYTHON_CONFIG := python-config
-
-escape-for-shell-sq =  $(subst ','\'',$(1))
-shell-sq = '$(escape-for-shell-sq)'
-
-PYTHON_CONFIG_SQ = $(call shell-sq,$(PYTHON_CONFIG))
-
-PYTHON_EMBED_LDOPTS = $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
-PYTHON_EMBED_LDFLAGS = $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
-PYTHON_EMBED_LIBADD = $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
-PYTHON_EMBED_CCOPTS = $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-FLAGS_PYTHON_EMBED = $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
-
 test-libpython.bin:
-        $(BUILD) $(FLAGS_PYTHON_EMBED)
+        $(BUILD)
 
 test-libpython-version.bin:
-        $(BUILD) $(FLAGS_PYTHON_EMBED)
+        $(BUILD)
 
 test-libbfd.bin:
         $(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
index 4d985e0f03f5..7076a62d0ff7 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/perf/config/utilities.mak
@@ -132,7 +132,7 @@ endef
 #
 # Usage: bool-value = $(call is-absolute,path)
 #
-is-absolute = $(shell echo $(shell-sq) | grep ^/ -q && echo y)
+is-absolute = $(shell echo $(shell-sq) | grep -q ^/ && echo y)
 
 # lookup
 #
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 937e4324ad94..a3b13d7dc1d4 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -13,7 +13,7 @@
 #define wmb()           asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #define rmb()           asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #define cpu_relax()     asm volatile("rep; nop" ::: "memory");
-#define CPUINFO_PROC    "model name"
+#define CPUINFO_PROC    {"model name"}
 #ifndef __NR_perf_event_open
 # define __NR_perf_event_open 336
 #endif
@@ -30,7 +30,7 @@
 #define wmb()           asm volatile("sfence" ::: "memory")
 #define rmb()           asm volatile("lfence" ::: "memory")
 #define cpu_relax()     asm volatile("rep; nop" ::: "memory");
-#define CPUINFO_PROC    "model name"
+#define CPUINFO_PROC    {"model name"}
 #ifndef __NR_perf_event_open
 # define __NR_perf_event_open 298
 #endif
@@ -47,14 +47,14 @@
 #define mb()            asm volatile ("sync" ::: "memory")
 #define wmb()           asm volatile ("sync" ::: "memory")
 #define rmb()           asm volatile ("sync" ::: "memory")
-#define CPUINFO_PROC    "cpu"
+#define CPUINFO_PROC    {"cpu"}
 #endif
 
 #ifdef __s390__
 #define mb()            asm volatile("bcr 15,0" ::: "memory")
 #define wmb()           asm volatile("bcr 15,0" ::: "memory")
 #define rmb()           asm volatile("bcr 15,0" ::: "memory")
-#define CPUINFO_PROC    "vendor_id"
+#define CPUINFO_PROC    {"vendor_id"}
 #endif
 
 #ifdef __sh__
@@ -67,14 +67,14 @@
 # define wmb()          asm volatile("" ::: "memory")
 # define rmb()          asm volatile("" ::: "memory")
 #endif
-#define CPUINFO_PROC    "cpu type"
+#define CPUINFO_PROC    {"cpu type"}
 #endif
 
 #ifdef __hppa__
 #define mb()            asm volatile("" ::: "memory")
 #define wmb()           asm volatile("" ::: "memory")
 #define rmb()           asm volatile("" ::: "memory")
-#define CPUINFO_PROC    "cpu"
+#define CPUINFO_PROC    {"cpu"}
 #endif
 
 #ifdef __sparc__
@@ -87,14 +87,14 @@
 #endif
 #define wmb()           asm volatile("":::"memory")
 #define rmb()           asm volatile("":::"memory")
-#define CPUINFO_PROC    "cpu"
+#define CPUINFO_PROC    {"cpu"}
 #endif
 
 #ifdef __alpha__
 #define mb()            asm volatile("mb" ::: "memory")
 #define wmb()           asm volatile("wmb" ::: "memory")
 #define rmb()           asm volatile("mb" ::: "memory")
-#define CPUINFO_PROC    "cpu model"
+#define CPUINFO_PROC    {"cpu model"}
 #endif
 
 #ifdef __ia64__
@@ -102,7 +102,7 @@
 #define wmb()           asm volatile ("mf" ::: "memory")
 #define rmb()           asm volatile ("mf" ::: "memory")
 #define cpu_relax()     asm volatile ("hint @pause" ::: "memory")
-#define CPUINFO_PROC    "model name"
+#define CPUINFO_PROC    {"model name"}
 #endif
 
 #ifdef __arm__
@@ -113,7 +113,7 @@
 #define mb()            ((void(*)(void))0xffff0fa0)()
 #define wmb()           ((void(*)(void))0xffff0fa0)()
 #define rmb()           ((void(*)(void))0xffff0fa0)()
-#define CPUINFO_PROC    "Processor"
+#define CPUINFO_PROC    {"model name", "Processor"}
 #endif
 
 #ifdef __aarch64__
@@ -133,28 +133,28 @@
                                 : "memory")
 #define wmb()   mb()
 #define rmb()   mb()
-#define CPUINFO_PROC    "cpu model"
+#define CPUINFO_PROC    {"cpu model"}
 #endif
 
 #ifdef __arc__
 #define mb()            asm volatile("" ::: "memory")
 #define wmb()           asm volatile("" ::: "memory")
 #define rmb()           asm volatile("" ::: "memory")
-#define CPUINFO_PROC    "Processor"
+#define CPUINFO_PROC    {"Processor"}
 #endif
 
 #ifdef __metag__
 #define mb()            asm volatile("" ::: "memory")
 #define wmb()           asm volatile("" ::: "memory")
 #define rmb()           asm volatile("" ::: "memory")
-#define CPUINFO_PROC    "CPU"
+#define CPUINFO_PROC    {"CPU"}
 #endif
 
 #ifdef __xtensa__
 #define mb()            asm volatile("memw" ::: "memory")
 #define wmb()           asm volatile("memw" ::: "memory")
 #define rmb()           asm volatile("" ::: "memory")
-#define CPUINFO_PROC    "core ID"
+#define CPUINFO_PROC    {"core ID"}
 #endif
 
 #ifdef __tile__
@@ -162,7 +162,7 @@
 #define wmb()           asm volatile ("mf" ::: "memory")
 #define rmb()           asm volatile ("mf" ::: "memory")
 #define cpu_relax()     asm volatile ("mfspr zero, PASS" ::: "memory")
-#define CPUINFO_PROC    "model name"
+#define CPUINFO_PROC    {"model name"}
 #endif
 
 #define barrier() asm volatile ("" ::: "memory")
diff --git a/tools/perf/perf-with-kcore.sh b/tools/perf/perf-with-kcore.sh
new file mode 100644
index 000000000000..c7ff90a90e4e
--- /dev/null
+++ b/tools/perf/perf-with-kcore.sh
@@ -0,0 +1,259 @@
+#!/bin/bash
+# perf-with-kcore: use perf with a copy of kcore
+# Copyright (c) 2014, 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.
+
+set -e
+
+usage()
+{
+        echo "Usage: perf-with-kcore <perf sub-command> <perf.data directory> [<sub-command options> [ -- <workload>]]" >&2
+        echo "       <perf sub-command> can be record, script, report or inject" >&2
+        echo "   or: perf-with-kcore fix_buildid_cache_permissions" >&2
+        exit 1
+}
+
+find_perf()
+{
+        if [ -n "$PERF" ] ; then
+                return
+        fi
+        PERF=`which perf || true`
+        if [ -z "$PERF" ] ; then
+                echo "Failed to find perf" >&2
+                exit 1
+        fi
+        if [ ! -x "$PERF" ] ; then
+                echo "Failed to find perf" >&2
+                exit 1
+        fi
+        echo "Using $PERF"
+        "$PERF" version
+}
+
+copy_kcore()
+{
+        echo "Copying kcore"
+
+        if [ $EUID -eq 0 ] ; then
+                SUDO=""
+        else
+                SUDO="sudo"
+        fi
+
+        rm -f perf.data.junk
+        ("$PERF" record -o perf.data.junk $PERF_OPTIONS -- sleep 60) >/dev/null 2>/dev/null &
+        PERF_PID=$!
+
+        # Need to make sure that perf has started
+        sleep 1
+
+        KCORE=$(($SUDO "$PERF" buildid-cache -v -f -k /proc/kcore >/dev/null) 2>&1)
+        case "$KCORE" in
+        "kcore added to build-id cache directory "*)
+                KCORE_DIR=${KCORE#"kcore added to build-id cache directory "}
+        ;;
+        *)
+                kill $PERF_PID
+                wait >/dev/null 2>/dev/null || true
+                rm perf.data.junk
+                echo "$KCORE"
+                echo "Failed to find kcore" >&2
+                exit 1
+        ;;
+        esac
+
+        kill $PERF_PID
+        wait >/dev/null 2>/dev/null || true
+        rm perf.data.junk
+
+        $SUDO cp -a "$KCORE_DIR" "$(pwd)/$PERF_DATA_DIR"
+        $SUDO rm -f "$KCORE_DIR/kcore"
+        $SUDO rm -f "$KCORE_DIR/kallsyms"
+        $SUDO rm -f "$KCORE_DIR/modules"
+        $SUDO rmdir "$KCORE_DIR"
+
+        KCORE_DIR_BASENAME=$(basename "$KCORE_DIR")
+        KCORE_DIR="$(pwd)/$PERF_DATA_DIR/$KCORE_DIR_BASENAME"
+
+        $SUDO chown $UID "$KCORE_DIR"
+        $SUDO chown $UID "$KCORE_DIR/kcore"
+        $SUDO chown $UID "$KCORE_DIR/kallsyms"
+        $SUDO chown $UID "$KCORE_DIR/modules"
+
+        $SUDO chgrp $GROUPS "$KCORE_DIR"
+        $SUDO chgrp $GROUPS "$KCORE_DIR/kcore"
+        $SUDO chgrp $GROUPS "$KCORE_DIR/kallsyms"
+        $SUDO chgrp $GROUPS "$KCORE_DIR/modules"
+
+        ln -s "$KCORE_DIR_BASENAME" "$PERF_DATA_DIR/kcore_dir"
+}
+
+fix_buildid_cache_permissions()
+{
+        if [ $EUID -ne 0 ] ; then
+                echo "This script must be run as root via sudo " >&2
+                exit 1
+        fi
+
+        if [ -z "$SUDO_USER" ] ; then
+                echo "This script must be run via sudo" >&2
+                exit 1
+        fi
+
+        USER_HOME=$(bash <<< "echo ~$SUDO_USER")
+
+        if [ "$HOME" != "$USER_HOME" ] ; then
+                echo "Fix unnecessary because root has a home: $HOME" >&2
+                exit 1
+        fi
+
+        echo "Fixing buildid cache permissions"
+
+        find "$USER_HOME/.debug" -xdev -type d          ! -user "$SUDO_USER" -ls -exec chown    "$SUDO_USER" \{\} \;
+        find "$USER_HOME/.debug" -xdev -type f -links 1 ! -user "$SUDO_USER" -ls -exec chown    "$SUDO_USER" \{\} \;
+        find "$USER_HOME/.debug" -xdev -type l          ! -user "$SUDO_USER" -ls -exec chown -h "$SUDO_USER" \{\} \;
+
+        if [ -n "$SUDO_GID" ] ; then
+                find "$USER_HOME/.debug" -xdev -type d          ! -group "$SUDO_GID" -ls -exec chgrp    "$SUDO_GID" \{\} \;
+                find "$USER_HOME/.debug" -xdev -type f -links 1 ! -group "$SUDO_GID" -ls -exec chgrp    "$SUDO_GID" \{\} \;
+                find "$USER_HOME/.debug" -xdev -type l          ! -group "$SUDO_GID" -ls -exec chgrp -h "$SUDO_GID" \{\} \;
+        fi
+
+        echo "Done"
+}
+
+check_buildid_cache_permissions()
+{
+        if [ $EUID -eq 0 ] ; then
+                return
+        fi
+
+        PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type d          ! -user "$USER" -print -quit)
+        PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type f -links 1 ! -user "$USER" -print -quit)
+        PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type l          ! -user "$USER" -print -quit)
+
+        PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type d          ! -group "$GROUPS" -print -quit)
+        PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type f -links 1 ! -group "$GROUPS" -print -quit)
+        PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type l          ! -group "$GROUPS" -print -quit)
+
+        if [ -n "$PERMISSIONS_OK" ] ; then
+                echo "*** WARNING *** buildid cache permissions may need fixing" >&2
+        fi
+}
+
+record()
+{
+        echo "Recording"
+
+        if [ $EUID -ne 0 ] ; then
+
+                if [ "$(cat /proc/sys/kernel/kptr_restrict)" -ne 0 ] ; then
+                        echo "*** WARNING *** /proc/sys/kernel/kptr_restrict prevents access to kernel addresses" >&2
+                fi
+
+                if echo "$PERF_OPTIONS" | grep -q ' -a \|^-a \| -a$\|^-a$\| --all-cpus \|^--all-cpus \| --all-cpus$\|^--all-cpus$' ; then
+                        echo "*** WARNING *** system-wide tracing without root access will not be able to read all necessary information from /proc" >&2
+                fi
+
+                if echo "$PERF_OPTIONS" | grep -q 'intel_pt\|intel_bts\| -I\|^-I' ; then
+                        if [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt -1 ] ; then
+                                echo "*** WARNING *** /proc/sys/kernel/perf_event_paranoid restricts buffer size and tracepoint (sched_switch) use" >&2
+                        fi
+
+                        if echo "$PERF_OPTIONS" | grep -q ' --per-thread \|^--per-thread \| --per-thread$\|^--per-thread$' ; then
+                                true
+                        elif echo "$PERF_OPTIONS" | grep -q ' -t \|^-t \| -t$\|^-t$' ; then
+                                true
+                        elif [ ! -r /sys/kernel/debug -o ! -x /sys/kernel/debug ] ; then
+                                echo "*** WARNING *** /sys/kernel/debug permissions prevent tracepoint (sched_switch) use" >&2
+                        fi
+                fi
+        fi
+
+        if [ -z "$1" ] ; then
+                echo "Workload is required for recording" >&2
+                usage
+        fi
+
+        if [ -e "$PERF_DATA_DIR" ] ; then
+                echo "'$PERF_DATA_DIR' exists" >&2
+                exit 1
+        fi
+
+        find_perf
+
+        mkdir "$PERF_DATA_DIR"
+
+        echo "$PERF record -o $PERF_DATA_DIR/perf.data $PERF_OPTIONS -- $*"
+        "$PERF" record -o "$PERF_DATA_DIR/perf.data" $PERF_OPTIONS -- $* || true
+
+        if rmdir "$PERF_DATA_DIR" > /dev/null 2>/dev/null ; then
+                exit 1
+        fi
+
+        copy_kcore
+
+        echo "Done"
+}
+
+subcommand()
+{
+        find_perf
+        check_buildid_cache_permissions
+        echo "$PERF $PERF_SUB_COMMAND -i $PERF_DATA_DIR/perf.data --kallsyms=$PERF_DATA_DIR/kcore_dir/kallsyms $*"
+        "$PERF" $PERF_SUB_COMMAND -i "$PERF_DATA_DIR/perf.data" "--kallsyms=$PERF_DATA_DIR/kcore_dir/kallsyms" $*
+}
+
+if [ "$1" = "fix_buildid_cache_permissions" ] ; then
+        fix_buildid_cache_permissions
+        exit 0
+fi
+
+PERF_SUB_COMMAND=$1
+PERF_DATA_DIR=$2
+shift || true
+shift || true
+
+if [ -z "$PERF_SUB_COMMAND" ] ; then
+        usage
+fi
+
+if [ -z "$PERF_DATA_DIR" ] ; then
+        usage
+fi
+
+case "$PERF_SUB_COMMAND" in
+"record")
+        while [ "$1" != "--" ] ; do
+                PERF_OPTIONS+="$1 "
+                shift || break
+        done
+        if [ "$1" != "--" ] ; then
+                echo "Options and workload are required for recording" >&2
+                usage
+        fi
+        shift
+        record $*
+;;
+"script")
+        subcommand $*
+;;
+"report")
+        subcommand $*
+;;
+"inject")
+        subcommand $*
+;;
+*)
+        usage
+;;
+esac
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 2282d41879a2..452a8474d29d 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -313,6 +313,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
         int status;
         struct stat st;
         const char *prefix;
+        char sbuf[STRERR_BUFSIZE];
 
         prefix = NULL;
         if (p->option & RUN_SETUP)
@@ -343,7 +344,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
         status = 1;
         /* Check for ENOSPC and EIO errors.. */
         if (fflush(stdout)) {
-                fprintf(stderr, "write failure on standard output: %s", strerror(errno));
+                fprintf(stderr, "write failure on standard output: %s",
+                        strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out;
         }
         if (ferror(stdout)) {
@@ -351,7 +353,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
                 goto out;
         }
         if (fclose(stdout)) {
-                fprintf(stderr, "close failed on standard output: %s", strerror(errno));
+                fprintf(stderr, "close failed on standard output: %s",
+                        strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out;
         }
         status = 0;
@@ -466,6 +469,7 @@ void pthread__unblock_sigwinch(void)
 int main(int argc, const char **argv)
 {
         const char *cmd;
+        char sbuf[STRERR_BUFSIZE];
 
         /* The page_size is placed in util object. */
         page_size = sysconf(_SC_PAGE_SIZE);
@@ -561,7 +565,7 @@ int main(int argc, const char **argv)
         }
 
         fprintf(stderr, "Failed to run command '%s': %s\n",
-                cmd, strerror(errno));
+                cmd, strerror_r(errno, sbuf, sizeof(sbuf)));
 out:
         return 1;
 }
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 510c65f72858..220d44e44c1b 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -41,8 +41,6 @@ void pthread__unblock_sigwinch(void);
 
 struct record_opts {
         struct target target;
-        int          call_graph;
-        bool         call_graph_enabled;
         bool         group;
         bool         inherit_stat;
         bool         no_buffering;
@@ -60,7 +58,6 @@ struct record_opts {
         u64          branch_stack;
         u64          default_interval;
         u64          user_interval;
-        u16          stack_dump_size;
         bool         sample_transaction;
         unsigned     initial_delay;
 };
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 6f8b01bc6033..162c978f1491 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -6,6 +6,7 @@
 #include <unistd.h>
 #include <string.h>
 #include "builtin.h"
+#include "hist.h"
 #include "intlist.h"
 #include "tests.h"
 #include "debug.h"
@@ -154,6 +155,18 @@ static struct test {
                 .func = test__hists_cumulate,
         },
         {
+                .desc = "Test tracking with sched_switch",
+                .func = test__switch_tracking,
+        },
+        {
+                .desc = "Filter fds with revents mask in a fdarray",
+                .func = test__fdarray__filter,
+        },
+        {
+                .desc = "Add fd to a fdarray, making it autogrow",
+                .func = test__fdarray__add,
+        },
+        {
                 .func = NULL,
         },
 };
@@ -185,9 +198,11 @@ static bool perf_test__matches(int curr, int argc, const char *argv[])
 static int run_test(struct test *test)
 {
         int status, err = -1, child = fork();
+        char sbuf[STRERR_BUFSIZE];
 
         if (child < 0) {
-                pr_err("failed to fork test: %s\n", strerror(errno));
+                pr_err("failed to fork test: %s\n",
+                        strerror_r(errno, sbuf, sizeof(sbuf)));
                 return -1;
         }
 
@@ -288,6 +303,10 @@ int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused)
         OPT_END()
         };
         struct intlist *skiplist = NULL;
+        int ret = hists__init();
+
+        if (ret < 0)
+                return ret;
 
         argc = parse_options(argc, argv, test_options, test_usage, 0);
         if (argc >= 1 && !strcmp(argv[0], "list"))
@@ -297,7 +316,7 @@ int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused)
         symbol_conf.sort_by_name = true;
         symbol_conf.try_vmlinux_path = true;
 
-        if (symbol__init() < 0)
+        if (symbol__init(NULL) < 0)
                 return -1;
 
         if (skip != NULL)
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 96adb730b744..fc25e57f4a5d 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -9,6 +9,7 @@
 #include "perf_regs.h"
 #include "map.h"
 #include "thread.h"
+#include "callchain.h"
 
 static int mmap_handler(struct perf_tool *tool __maybe_unused,
                         union perf_event *event,
@@ -120,6 +121,8 @@ int test__dwarf_unwind(void)
                 return -1;
         }
 
+        callchain_param.record_mode = CALLCHAIN_DWARF;
+
         if (init_live_machine(machine)) {
                 pr_err("Could not init machine\n");
                 goto out;
diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
new file mode 100644
index 000000000000..d24b837951d4
--- /dev/null
+++ b/tools/perf/tests/fdarray.c
@@ -0,0 +1,174 @@
+#include <api/fd/array.h>
+#include "util/debug.h"
+#include "tests/tests.h"
+
+static void fdarray__init_revents(struct fdarray *fda, short revents)
+{
+        int fd;
+
+        fda->nr = fda->nr_alloc;
+
+        for (fd = 0; fd < fda->nr; ++fd) {
+                fda->entries[fd].fd      = fda->nr - fd;
+                fda->entries[fd].revents = revents;
+        }
+}
+
+static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE *fp)
+{
+        int printed = 0;
+
+        if (!verbose)
+                return 0;
+
+        printed += fprintf(fp, "\n%s: ", prefix);
+        return printed + fdarray__fprintf(fda, fp);
+}
+
+int test__fdarray__filter(void)
+{
+        int nr_fds, expected_fd[2], fd, err = TEST_FAIL;
+        struct fdarray *fda = fdarray__new(5, 5);
+
+        if (fda == NULL) {
+                pr_debug("\nfdarray__new() failed!");
+                goto out;
+        }
+
+        fdarray__init_revents(fda, POLLIN);
+        nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+        if (nr_fds != fda->nr_alloc) {
+                pr_debug("\nfdarray__filter()=%d != %d shouldn't have filtered anything",
+                         nr_fds, fda->nr_alloc);
+                goto out_delete;
+        }
+
+        fdarray__init_revents(fda, POLLHUP);
+        nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+        if (nr_fds != 0) {
+                pr_debug("\nfdarray__filter()=%d != %d, should have filtered all fds",
+                         nr_fds, fda->nr_alloc);
+                goto out_delete;
+        }
+
+        fdarray__init_revents(fda, POLLHUP);
+        fda->entries[2].revents = POLLIN;
+        expected_fd[0] = fda->entries[2].fd;
+
+        pr_debug("\nfiltering all but fda->entries[2]:");
+        fdarray__fprintf_prefix(fda, "before", stderr);
+        nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+        fdarray__fprintf_prefix(fda, " after", stderr);
+        if (nr_fds != 1) {
+                pr_debug("\nfdarray__filter()=%d != 1, should have left just one event", nr_fds);
+                goto out_delete;
+        }
+
+        if (fda->entries[0].fd != expected_fd[0]) {
+                pr_debug("\nfda->entries[0].fd=%d != %d\n",
+                         fda->entries[0].fd, expected_fd[0]);
+                goto out_delete;
+        }
+
+        fdarray__init_revents(fda, POLLHUP);
+        fda->entries[0].revents = POLLIN;
+        expected_fd[0] = fda->entries[0].fd;
+        fda->entries[3].revents = POLLIN;
+        expected_fd[1] = fda->entries[3].fd;
+
+        pr_debug("\nfiltering all but (fda->entries[0], fda->entries[3]):");
+        fdarray__fprintf_prefix(fda, "before", stderr);
+        nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+        fdarray__fprintf_prefix(fda, " after", stderr);
+        if (nr_fds != 2) {
+                pr_debug("\nfdarray__filter()=%d != 2, should have left just two events",
+                         nr_fds);
+                goto out_delete;
+        }
+
+        for (fd = 0; fd < 2; ++fd) {
+                if (fda->entries[fd].fd != expected_fd[fd]) {
+                        pr_debug("\nfda->entries[%d].fd=%d != %d\n", fd,
+                                 fda->entries[fd].fd, expected_fd[fd]);
+                        goto out_delete;
+                }
+        }
+
+        pr_debug("\n");
+
+        err = 0;
+out_delete:
+        fdarray__delete(fda);
+out:
+        return err;
+}
+
+int test__fdarray__add(void)
+{
+        int err = TEST_FAIL;
+        struct fdarray *fda = fdarray__new(2, 2);
+
+        if (fda == NULL) {
+                pr_debug("\nfdarray__new() failed!");
+                goto out;
+        }
+
+#define FDA_CHECK(_idx, _fd, _revents)                                     \
+        if (fda->entries[_idx].fd != _fd) {                                \
+                pr_debug("\n%d: fda->entries[%d](%d) != %d!",              \
+                         __LINE__, _idx, fda->entries[1].fd, _fd);         \
+                goto out_delete;                                           \
+        }                                                                  \
+        if (fda->entries[_idx].events != (_revents)) {                     \
+                pr_debug("\n%d: fda->entries[%d].revents(%d) != %d!",      \
+                         __LINE__, _idx, fda->entries[_idx].fd, _revents); \
+                goto out_delete;                                           \
+        }
+
+#define FDA_ADD(_idx, _fd, _revents, _nr)                                  \
+        if (fdarray__add(fda, _fd, _revents) < 0) {                        \
+                pr_debug("\n%d: fdarray__add(fda, %d, %d) failed!",        \
+                         __LINE__,_fd, _revents);                          \
+                goto out_delete;                                           \
+        }                                                                  \
+        if (fda->nr != _nr) {                                              \
+                pr_debug("\n%d: fdarray__add(fda, %d, %d)=%d != %d",       \
+                         __LINE__,_fd, _revents, fda->nr, _nr);            \
+                goto out_delete;                                           \
+        }                                                                  \
+        FDA_CHECK(_idx, _fd, _revents)
+
+        FDA_ADD(0, 1, POLLIN, 1);
+        FDA_ADD(1, 2, POLLERR, 2);
+
+        fdarray__fprintf_prefix(fda, "before growing array", stderr);
+
+        FDA_ADD(2, 35, POLLHUP, 3);
+
+        if (fda->entries == NULL) {
+                pr_debug("\nfdarray__add(fda, 35, POLLHUP) should have allocated fda->pollfd!");
+                goto out_delete;
+        }
+
+        fdarray__fprintf_prefix(fda, "after 3rd add", stderr);
+
+        FDA_ADD(3, 88, POLLIN | POLLOUT, 4);
+
+        fdarray__fprintf_prefix(fda, "after 4th add", stderr);
+
+        FDA_CHECK(0, 1, POLLIN);
+        FDA_CHECK(1, 2, POLLERR);
+        FDA_CHECK(2, 35, POLLHUP);
+        FDA_CHECK(3, 88, POLLIN | POLLOUT);
+
+#undef FDA_ADD
+#undef FDA_CHECK
+
+        pr_debug("\n");
+
+        err = 0;
+out_delete:
+        fdarray__delete(fda);
+out:
+        return err;
+}
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 0ac240db2e24..614d5c4978ab 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -245,7 +245,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec
 static int test1(struct perf_evsel *evsel, struct machine *machine)
 {
         int err;
-        struct hists *hists = &evsel->hists;
+        struct hists *hists = evsel__hists(evsel);
         /*
          * expected output:
          *
@@ -295,7 +295,7 @@ out:
 static int test2(struct perf_evsel *evsel, struct machine *machine)
 {
         int err;
-        struct hists *hists = &evsel->hists;
+        struct hists *hists = evsel__hists(evsel);
         /*
          * expected output:
          *
@@ -442,7 +442,7 @@ out:
 static int test3(struct perf_evsel *evsel, struct machine *machine)
 {
         int err;
-        struct hists *hists = &evsel->hists;
+        struct hists *hists = evsel__hists(evsel);
         /*
          * expected output:
          *
@@ -498,7 +498,7 @@ out:
 static int test4(struct perf_evsel *evsel, struct machine *machine)
 {
         int err;
-        struct hists *hists = &evsel->hists;
+        struct hists *hists = evsel__hists(evsel);
         /*
          * expected output:
          *
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 821f581fd930..5a31787cc6b9 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -66,11 +66,12 @@ static int add_hist_entries(struct perf_evlist *evlist,
                                 .ops = &hist_iter_normal,
                                 .hide_unresolved = false,
                         };
+                        struct hists *hists = evsel__hists(evsel);
 
                         /* make sure it has no filter at first */
-                        evsel->hists.thread_filter = NULL;
-                        evsel->hists.dso_filter = NULL;
-                        evsel->hists.symbol_filter_str = NULL;
+                        hists->thread_filter = NULL;
+                        hists->dso_filter = NULL;
+                        hists->symbol_filter_str = NULL;
 
                         sample.pid = fake_samples[i].pid;
                         sample.tid = fake_samples[i].pid;
@@ -134,7 +135,7 @@ int test__hists_filter(void)
                 goto out;
 
         evlist__for_each(evlist, evsel) {
-                struct hists *hists = &evsel->hists;
+                struct hists *hists = evsel__hists(evsel);
 
                 hists__collapse_resort(hists, NULL);
                 hists__output_resort(hists);
@@ -160,7 +161,7 @@ int test__hists_filter(void)
                                 hists->stats.total_non_filtered_period);
 
                 /* now applying thread filter for 'bash' */
-                evsel->hists.thread_filter = fake_samples[9].thread;
+                hists->thread_filter = fake_samples[9].thread;
                 hists__filter_by_thread(hists);
 
                 if (verbose > 2) {
@@ -185,11 +186,11 @@ int test__hists_filter(void)
                                 hists->stats.total_non_filtered_period == 400);
 
                 /* remove thread filter first */
-                evsel->hists.thread_filter = NULL;
+                hists->thread_filter = NULL;
                 hists__filter_by_thread(hists);
 
                 /* now applying dso filter for 'kernel' */
-                evsel->hists.dso_filter = fake_samples[0].map->dso;
+                hists->dso_filter = fake_samples[0].map->dso;
                 hists__filter_by_dso(hists);
 
                 if (verbose > 2) {
@@ -214,7 +215,7 @@ int test__hists_filter(void)
                                 hists->stats.total_non_filtered_period == 300);
 
                 /* remove dso filter first */
-                evsel->hists.dso_filter = NULL;
+                hists->dso_filter = NULL;
                 hists__filter_by_dso(hists);
 
                 /*
@@ -224,7 +225,7 @@ int test__hists_filter(void)
                  * be counted as a separate entry but the sample count and
                  * total period will be remained.
                  */
-                evsel->hists.symbol_filter_str = "main";
+                hists->symbol_filter_str = "main";
                 hists__filter_by_symbol(hists);
 
                 if (verbose > 2) {
@@ -249,8 +250,8 @@ int test__hists_filter(void)
                                 hists->stats.total_non_filtered_period == 300);
 
                 /* now applying all filters at once. */
-                evsel->hists.thread_filter = fake_samples[1].thread;
-                evsel->hists.dso_filter = fake_samples[1].map->dso;
+                hists->thread_filter = fake_samples[1].thread;
+                hists->dso_filter = fake_samples[1].map->dso;
                 hists__filter_by_thread(hists);
                 hists__filter_by_dso(hists);
 
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index d4b34b0f50a2..278ba8344c23 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -73,6 +73,8 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
          * "bash [libc] malloc" so total 9 entries will be in the tree.
          */
         evlist__for_each(evlist, evsel) {
+                struct hists *hists = evsel__hists(evsel);
+
                 for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) {
                         const union perf_event event = {
                                 .header = {
@@ -87,7 +89,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
                                                           &sample) < 0)
                                 goto out;
 
-                        he = __hists__add_entry(&evsel->hists, &al, NULL,
+                        he = __hists__add_entry(hists, &al, NULL,
                                                 NULL, NULL, 1, 1, 0, true);
                         if (he == NULL)
                                 goto out;
@@ -111,7 +113,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
                                                           &sample) < 0)
                                 goto out;
 
-                        he = __hists__add_entry(&evsel->hists, &al, NULL,
+                        he = __hists__add_entry(hists, &al, NULL,
                                                 NULL, NULL, 1, 1, 0, true);
                         if (he == NULL)
                                 goto out;
@@ -271,6 +273,7 @@ static int validate_link(struct hists *leader, struct hists *other)
 int test__hists_link(void)
 {
         int err = -1;
+        struct hists *hists, *first_hists;
         struct machines machines;
         struct machine *machine = NULL;
         struct perf_evsel *evsel, *first;
@@ -306,24 +309,28 @@ int test__hists_link(void)
                 goto out;
 
         evlist__for_each(evlist, evsel) {
-                hists__collapse_resort(&evsel->hists, NULL);
+                hists = evsel__hists(evsel);
+                hists__collapse_resort(hists, NULL);
 
                 if (verbose > 2)
-                        print_hists_in(&evsel->hists);
+                        print_hists_in(hists);
         }
 
         first = perf_evlist__first(evlist);
         evsel = perf_evlist__last(evlist);
 
+        first_hists = evsel__hists(first);
+        hists = evsel__hists(evsel);
+
         /* match common entries */
-        hists__match(&first->hists, &evsel->hists);
-        err = validate_match(&first->hists, &evsel->hists);
+        hists__match(first_hists, hists);
+        err = validate_match(first_hists, hists);
         if (err)
                 goto out;
 
         /* link common and/or dummy entries */
-        hists__link(&first->hists, &evsel->hists);
-        err = validate_link(&first->hists, &evsel->hists);
+        hists__link(first_hists, hists);
+        err = validate_link(first_hists, hists);
         if (err)
                 goto out;
 
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index e3bbd6c54c1b..a748f2be1222 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -122,7 +122,7 @@ typedef int (*test_fn_t)(struct perf_evsel *, struct machine *);
 static int test1(struct perf_evsel *evsel, struct machine *machine)
 {
         int err;
-        struct hists *hists = &evsel->hists;
+        struct hists *hists = evsel__hists(evsel);
         struct hist_entry *he;
         struct rb_root *root;
         struct rb_node *node;
@@ -159,7 +159,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine)
                 print_hists_out(hists);
         }
 
-        root = &evsel->hists.entries;
+        root = &hists->entries;
         node = rb_first(root);
         he = rb_entry(node, struct hist_entry, rb_node);
         TEST_ASSERT_VAL("Invalid hist entry",
@@ -224,7 +224,7 @@ out:
 static int test2(struct perf_evsel *evsel, struct machine *machine)
 {
         int err;
-        struct hists *hists = &evsel->hists;
+        struct hists *hists = evsel__hists(evsel);
         struct hist_entry *he;
         struct rb_root *root;
         struct rb_node *node;
@@ -259,7 +259,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine)
                 print_hists_out(hists);
         }
 
-        root = &evsel->hists.entries;
+        root = &hists->entries;
         node = rb_first(root);
         he = rb_entry(node, struct hist_entry, rb_node);
         TEST_ASSERT_VAL("Invalid hist entry",
@@ -280,7 +280,7 @@ out:
 static int test3(struct perf_evsel *evsel, struct machine *machine)
 {
         int err;
-        struct hists *hists = &evsel->hists;
+        struct hists *hists = evsel__hists(evsel);
         struct hist_entry *he;
         struct rb_root *root;
         struct rb_node *node;
@@ -313,7 +313,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
                 print_hists_out(hists);
         }
 
-        root = &evsel->hists.entries;
+        root = &hists->entries;
         node = rb_first(root);
         he = rb_entry(node, struct hist_entry, rb_node);
         TEST_ASSERT_VAL("Invalid hist entry",
@@ -354,7 +354,7 @@ out:
 static int test4(struct perf_evsel *evsel, struct machine *machine)
 {
         int err;
-        struct hists *hists = &evsel->hists;
+        struct hists *hists = evsel__hists(evsel);
         struct hist_entry *he;
         struct rb_root *root;
         struct rb_node *node;
@@ -391,7 +391,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                 print_hists_out(hists);
         }
 
-        root = &evsel->hists.entries;
+        root = &hists->entries;
         node = rb_first(root);
         he = rb_entry(node, struct hist_entry, rb_node);
         TEST_ASSERT_VAL("Invalid hist entry",
@@ -456,7 +456,7 @@ out:
 static int test5(struct perf_evsel *evsel, struct machine *machine)
 {
         int err;
-        struct hists *hists = &evsel->hists;
+        struct hists *hists = evsel__hists(evsel);
         struct hist_entry *he;
         struct rb_root *root;
         struct rb_node *node;
@@ -494,7 +494,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine)
                 print_hists_out(hists);
         }
 
-        root = &evsel->hists.entries;
+        root = &hists->entries;
         node = rb_first(root);
         he = rb_entry(node, struct hist_entry, rb_node);
 
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 142263492f6f..9b9622a33932 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -31,6 +31,7 @@ int test__basic_mmap(void)
         unsigned int nr_events[nsyscalls],
                      expected_nr_events[nsyscalls], i, j;
         struct perf_evsel *evsels[nsyscalls], *evsel;
+        char sbuf[STRERR_BUFSIZE];
 
         threads = thread_map__new(-1, getpid(), UINT_MAX);
         if (threads == NULL) {
@@ -49,7 +50,7 @@ int test__basic_mmap(void)
         sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
         if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
                 pr_debug("sched_setaffinity() failed on CPU %d: %s ",
-                         cpus->map[0], strerror(errno));
+                         cpus->map[0], strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out_free_cpus;
         }
 
@@ -79,7 +80,7 @@ int test__basic_mmap(void)
                 if (perf_evsel__open(evsels[i], cpus, threads) < 0) {
                         pr_debug("failed to open counter: %s, "
                                  "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-                                 strerror(errno));
+                                 strerror_r(errno, sbuf, sizeof(sbuf)));
                         goto out_delete_evlist;
                 }
 
@@ -89,7 +90,7 @@ int test__basic_mmap(void)
 
         if (perf_evlist__mmap(evlist, 128, true) < 0) {
                 pr_debug("failed to mmap events: %d (%s)\n", errno,
-                         strerror(errno));
+                         strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
diff --git a/tools/perf/tests/open-syscall-all-cpus.c b/tools/perf/tests/open-syscall-all-cpus.c
index 5fecdbd2f5f7..8fa82d1700c7 100644
--- a/tools/perf/tests/open-syscall-all-cpus.c
+++ b/tools/perf/tests/open-syscall-all-cpus.c
@@ -12,6 +12,7 @@ int test__open_syscall_event_on_all_cpus(void)
         unsigned int nr_open_calls = 111, i;
         cpu_set_t cpu_set;
         struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
+        char sbuf[STRERR_BUFSIZE];
 
         if (threads == NULL) {
                 pr_debug("thread_map__new\n");
@@ -35,7 +36,7 @@ int test__open_syscall_event_on_all_cpus(void)
         if (perf_evsel__open(evsel, cpus, threads) < 0) {
                 pr_debug("failed to open counter: %s, "
                          "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-                         strerror(errno));
+                         strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out_evsel_delete;
         }
 
@@ -56,7 +57,7 @@ int test__open_syscall_event_on_all_cpus(void)
                 if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
                         pr_debug("sched_setaffinity() failed on CPU %d: %s ",
                                  cpus->map[cpu],
-                                 strerror(errno));
+                                 strerror_r(errno, sbuf, sizeof(sbuf)));
                         goto out_close_fd;
                 }
                 for (i = 0; i < ncalls; ++i) {
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index 0785b64ffd6c..127dcae0b760 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -22,6 +22,7 @@ int test__syscall_open_tp_fields(void)
         struct perf_evlist *evlist = perf_evlist__new();
         struct perf_evsel *evsel;
         int err = -1, i, nr_events = 0, nr_polls = 0;
+        char sbuf[STRERR_BUFSIZE];
 
         if (evlist == NULL) {
                 pr_debug("%s: perf_evlist__new\n", __func__);
@@ -48,13 +49,15 @@ int test__syscall_open_tp_fields(void)
 
         err = perf_evlist__open(evlist);
         if (err < 0) {
-                pr_debug("perf_evlist__open: %s\n", strerror(errno));
+                pr_debug("perf_evlist__open: %s\n",
+                         strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
         err = perf_evlist__mmap(evlist, UINT_MAX, false);
         if (err < 0) {
-                pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
+                pr_debug("perf_evlist__mmap: %s\n",
+                         strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
@@ -102,7 +105,7 @@ int test__syscall_open_tp_fields(void)
                 }
 
                 if (nr_events == before)
-                        poll(evlist->pollfd, evlist->nr_fds, 10);
+                        perf_evlist__poll(evlist, 10);
 
                 if (++nr_polls > 5) {
                         pr_debug("%s: no events!\n", __func__);
diff --git a/tools/perf/tests/open-syscall.c b/tools/perf/tests/open-syscall.c
index c1dc7d25f38c..a33b2daae40f 100644
--- a/tools/perf/tests/open-syscall.c
+++ b/tools/perf/tests/open-syscall.c
@@ -9,6 +9,7 @@ int test__open_syscall_event(void)
         struct perf_evsel *evsel;
         unsigned int nr_open_calls = 111, i;
         struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
+        char sbuf[STRERR_BUFSIZE];
 
         if (threads == NULL) {
                 pr_debug("thread_map__new\n");
@@ -24,7 +25,7 @@ int test__open_syscall_event(void)
         if (perf_evsel__open_per_thread(evsel, threads) < 0) {
                 pr_debug("failed to open counter: %s, "
                          "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-                         strerror(errno));
+                         strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out_evsel_delete;
         }
 
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 5941927a4b7f..7f2f51f93619 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -457,6 +457,36 @@ static int test__checkevent_pmu_events(struct perf_evlist *evlist)
         return 0;
 }
 
+
+static int test__checkevent_pmu_events_mix(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+        /* pmu-event:u */
+        TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+        TEST_ASSERT_VAL("wrong exclude_user",
+                        !evsel->attr.exclude_user);
+        TEST_ASSERT_VAL("wrong exclude_kernel",
+                        evsel->attr.exclude_kernel);
+        TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+        TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+        TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+        /* cpu/pmu-event/u*/
+        evsel = perf_evsel__next(evsel);
+        TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+        TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+        TEST_ASSERT_VAL("wrong exclude_user",
+                        !evsel->attr.exclude_user);
+        TEST_ASSERT_VAL("wrong exclude_kernel",
+                        evsel->attr.exclude_kernel);
+        TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+        TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+        TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+        return 0;
+}
+
 static int test__checkterms_simple(struct list_head *terms)
 {
         struct parse_events_term *term;
@@ -1554,6 +1584,12 @@ static int test_pmu_events(void)
                 e.check = test__checkevent_pmu_events;
 
                 ret = test_event(&e);
+                if (ret)
+                        break;
+                snprintf(name, MAX_NAME, "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name);
+                e.name  = name;
+                e.check = test__checkevent_pmu_events_mix;
+                ret = test_event(&e);
 #undef MAX_NAME
         }
 
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index aca1a83dd13a..7a228a2a070b 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -59,6 +59,7 @@ int test__PERF_RECORD(void)
         int err = -1, errs = 0, i, wakeups = 0;
         u32 cpu;
         int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
+        char sbuf[STRERR_BUFSIZE];
 
         if (evlist == NULL || argv == NULL) {
                 pr_debug("Not enough memory to create evlist\n");
@@ -100,7 +101,8 @@ int test__PERF_RECORD(void)
 
         err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
         if (err < 0) {
-                pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno));
+                pr_debug("sched__get_first_possible_cpu: %s\n",
+                         strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
@@ -110,7 +112,8 @@ int test__PERF_RECORD(void)
          * So that we can check perf_sample.cpu on all the samples.
          */
         if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
-                pr_debug("sched_setaffinity: %s\n", strerror(errno));
+                pr_debug("sched_setaffinity: %s\n",
+                         strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
@@ -120,7 +123,8 @@ int test__PERF_RECORD(void)
          */
         err = perf_evlist__open(evlist);
         if (err < 0) {
-                pr_debug("perf_evlist__open: %s\n", strerror(errno));
+                pr_debug("perf_evlist__open: %s\n",
+                         strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
@@ -131,7 +135,8 @@ int test__PERF_RECORD(void)
          */
         err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
         if (err < 0) {
-                pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
+                pr_debug("perf_evlist__mmap: %s\n",
+                         strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
@@ -263,7 +268,7 @@ int test__PERF_RECORD(void)
                  * perf_event_attr.wakeup_events, just PERF_EVENT_SAMPLE does.
                  */
                 if (total_events == before && false)
-                        poll(evlist->pollfd, evlist->nr_fds, -1);
+                        perf_evlist__poll(evlist, -1);
 
                 sleep(1);
                 if (++wakeups > 5) {
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 12b322fa3475..eeb68bb1972d 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -152,7 +152,7 @@ int test__pmu(void)
                 if (ret)
                         break;
 
-                ret = perf_pmu__config_terms(&formats, &attr, terms);
+                ret = perf_pmu__config_terms(&formats, &attr, terms, false);
                 if (ret)
                         break;
 
diff --git a/tools/perf/tests/rdpmc.c b/tools/perf/tests/rdpmc.c
index c04d1f268576..d31f2c4d9f64 100644
--- a/tools/perf/tests/rdpmc.c
+++ b/tools/perf/tests/rdpmc.c
@@ -100,6 +100,7 @@ static int __test__rdpmc(void)
         };
         u64 delta_sum = 0;
         struct sigaction sa;
+        char sbuf[STRERR_BUFSIZE];
 
         sigfillset(&sa.sa_mask);
         sa.sa_sigaction = segfault_handler;
@@ -109,14 +110,15 @@ static int __test__rdpmc(void)
                                  perf_event_open_cloexec_flag());
         if (fd < 0) {
                 pr_err("Error: sys_perf_event_open() syscall returned "
-                       "with %d (%s)\n", fd, strerror(errno));
+                       "with %d (%s)\n", fd,
+                       strerror_r(errno, sbuf, sizeof(sbuf)));
                 return -1;
         }
 
         addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0);
         if (addr == (void *)(-1)) {
                 pr_err("Error: mmap() syscall returned with (%s)\n",
-                       strerror(errno));
+                       strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out_close;
         }
 
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 983d6b8562a8..1aa21c90731b 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -22,6 +22,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
         volatile int tmp = 0;
         u64 total_periods = 0;
         int nr_samples = 0;
+        char sbuf[STRERR_BUFSIZE];
         union perf_event *event;
         struct perf_evsel *evsel;
         struct perf_evlist *evlist;
@@ -62,14 +63,15 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 
                 err = -errno;
                 pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
-                         strerror(errno), knob, (u64)attr.sample_freq);
+                         strerror_r(errno, sbuf, sizeof(sbuf)),
+                         knob, (u64)attr.sample_freq);
                 goto out_delete_evlist;
         }
 
         err = perf_evlist__mmap(evlist, 128, true);
         if (err < 0) {
                 pr_debug("failed to mmap event: %d (%s)\n", errno,
-                         strerror(errno));
+                         strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
new file mode 100644
index 000000000000..cc68648c7c55
--- /dev/null
+++ b/tools/perf/tests/switch-tracking.c
@@ -0,0 +1,572 @@
+#include <sys/time.h>
+#include <sys/prctl.h>
+#include <time.h>
+#include <stdlib.h>
+
+#include "parse-events.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tests.h"
+
+static int spin_sleep(void)
+{
+        struct timeval start, now, diff, maxtime;
+        struct timespec ts;
+        int err, i;
+
+        maxtime.tv_sec = 0;
+        maxtime.tv_usec = 50000;
+
+        err = gettimeofday(&start, NULL);
+        if (err)
+                return err;
+
+        /* Spin for 50ms */
+        while (1) {
+                for (i = 0; i < 1000; i++)
+                        barrier();
+
+                err = gettimeofday(&now, NULL);
+                if (err)
+                        return err;
+
+                timersub(&now, &start, &diff);
+                if (timercmp(&diff, &maxtime, > /* For checkpatch */))
+                        break;
+        }
+
+        ts.tv_nsec = 50 * 1000 * 1000;
+        ts.tv_sec = 0;
+
+        /* Sleep for 50ms */
+        err = nanosleep(&ts, NULL);
+        if (err == EINTR)
+                err = 0;
+
+        return err;
+}
+
+struct switch_tracking {
+        struct perf_evsel *switch_evsel;
+        struct perf_evsel *cycles_evsel;
+        pid_t *tids;
+        int nr_tids;
+        int comm_seen[4];
+        int cycles_before_comm_1;
+        int cycles_between_comm_2_and_comm_3;
+        int cycles_after_comm_4;
+};
+
+static int check_comm(struct switch_tracking *switch_tracking,
+                      union perf_event *event, const char *comm, int nr)
+{
+        if (event->header.type == PERF_RECORD_COMM &&
+            (pid_t)event->comm.pid == getpid() &&
+            (pid_t)event->comm.tid == getpid() &&
+            strcmp(event->comm.comm, comm) == 0) {
+                if (switch_tracking->comm_seen[nr]) {
+                        pr_debug("Duplicate comm event\n");
+                        return -1;
+                }
+                switch_tracking->comm_seen[nr] = 1;
+                pr_debug3("comm event: %s nr: %d\n", event->comm.comm, nr);
+                return 1;
+        }
+        return 0;
+}
+
+static int check_cpu(struct switch_tracking *switch_tracking, int cpu)
+{
+        int i, nr = cpu + 1;
+
+        if (cpu < 0)
+                return -1;
+
+        if (!switch_tracking->tids) {
+                switch_tracking->tids = calloc(nr, sizeof(pid_t));
+                if (!switch_tracking->tids)
+                        return -1;
+                for (i = 0; i < nr; i++)
+                        switch_tracking->tids[i] = -1;
+                switch_tracking->nr_tids = nr;
+                return 0;
+        }
+
+        if (cpu >= switch_tracking->nr_tids) {
+                void *addr;
+
+                addr = realloc(switch_tracking->tids, nr * sizeof(pid_t));
+                if (!addr)
+                        return -1;
+                switch_tracking->tids = addr;
+                for (i = switch_tracking->nr_tids; i < nr; i++)
+                        switch_tracking->tids[i] = -1;
+                switch_tracking->nr_tids = nr;
+                return 0;
+        }
+
+        return 0;
+}
+
+static int process_sample_event(struct perf_evlist *evlist,
+                                union perf_event *event,
+                                struct switch_tracking *switch_tracking)
+{
+        struct perf_sample sample;
+        struct perf_evsel *evsel;
+        pid_t next_tid, prev_tid;
+        int cpu, err;
+
+        if (perf_evlist__parse_sample(evlist, event, &sample)) {
+                pr_debug("perf_evlist__parse_sample failed\n");
+                return -1;
+        }
+
+        evsel = perf_evlist__id2evsel(evlist, sample.id);
+        if (evsel == switch_tracking->switch_evsel) {
+                next_tid = perf_evsel__intval(evsel, &sample, "next_pid");
+                prev_tid = perf_evsel__intval(evsel, &sample, "prev_pid");
+                cpu = sample.cpu;
+                pr_debug3("sched_switch: cpu: %d prev_tid %d next_tid %d\n",
+                          cpu, prev_tid, next_tid);
+                err = check_cpu(switch_tracking, cpu);
+                if (err)
+                        return err;
+                /*
+                 * Check for no missing sched_switch events i.e. that the
+                 * evsel->system_wide flag has worked.
+                 */
+                if (switch_tracking->tids[cpu] != -1 &&
+                    switch_tracking->tids[cpu] != prev_tid) {
+                        pr_debug("Missing sched_switch events\n");
+                        return -1;
+                }
+                switch_tracking->tids[cpu] = next_tid;
+        }
+
+        if (evsel == switch_tracking->cycles_evsel) {
+                pr_debug3("cycles event\n");
+                if (!switch_tracking->comm_seen[0])
+                        switch_tracking->cycles_before_comm_1 = 1;
+                if (switch_tracking->comm_seen[1] &&
+                    !switch_tracking->comm_seen[2])
+                        switch_tracking->cycles_between_comm_2_and_comm_3 = 1;
+                if (switch_tracking->comm_seen[3])
+                        switch_tracking->cycles_after_comm_4 = 1;
+        }
+
+        return 0;
+}
+
+static int process_event(struct perf_evlist *evlist, union perf_event *event,
+                         struct switch_tracking *switch_tracking)
+{
+        if (event->header.type == PERF_RECORD_SAMPLE)
+                return process_sample_event(evlist, event, switch_tracking);
+
+        if (event->header.type == PERF_RECORD_COMM) {
+                int err, done = 0;
+
+                err = check_comm(switch_tracking, event, "Test COMM 1", 0);
+                if (err < 0)
+                        return -1;
+                done += err;
+                err = check_comm(switch_tracking, event, "Test COMM 2", 1);
+                if (err < 0)
+                        return -1;
+                done += err;
+                err = check_comm(switch_tracking, event, "Test COMM 3", 2);
+                if (err < 0)
+                        return -1;
+                done += err;
+                err = check_comm(switch_tracking, event, "Test COMM 4", 3);
+                if (err < 0)
+                        return -1;
+                done += err;
+                if (done != 1) {
+                        pr_debug("Unexpected comm event\n");
+                        return -1;
+                }
+        }
+
+        return 0;
+}
+
+struct event_node {
+        struct list_head list;
+        union perf_event *event;
+        u64 event_time;
+};
+
+static int add_event(struct perf_evlist *evlist, struct list_head *events,
+                     union perf_event *event)
+{
+        struct perf_sample sample;
+        struct event_node *node;
+
+        node = malloc(sizeof(struct event_node));
+        if (!node) {
+                pr_debug("malloc failed\n");
+                return -1;
+        }
+        node->event = event;
+        list_add(&node->list, events);
+
+        if (perf_evlist__parse_sample(evlist, event, &sample)) {
+                pr_debug("perf_evlist__parse_sample failed\n");
+                return -1;
+        }
+
+        if (!sample.time) {
+                pr_debug("event with no time\n");
+                return -1;
+        }
+
+        node->event_time = sample.time;
+
+        return 0;
+}
+
+static void free_event_nodes(struct list_head *events)
+{
+        struct event_node *node;
+
+        while (!list_empty(events)) {
+                node = list_entry(events->next, struct event_node, list);
+                list_del(&node->list);
+                free(node);
+        }
+}
+
+static int compar(const void *a, const void *b)
+{
+        const struct event_node *nodea = a;
+        const struct event_node *nodeb = b;
+        s64 cmp = nodea->event_time - nodeb->event_time;
+
+        return cmp;
+}
+
+static int process_events(struct perf_evlist *evlist,
+                          struct switch_tracking *switch_tracking)
+{
+        union perf_event *event;
+        unsigned pos, cnt = 0;
+        LIST_HEAD(events);
+        struct event_node *events_array, *node;
+        int i, ret;
+
+        for (i = 0; i < evlist->nr_mmaps; i++) {
+                while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+                        cnt += 1;
+                        ret = add_event(evlist, &events, event);
+                        perf_evlist__mmap_consume(evlist, i);
+                        if (ret < 0)
+                                goto out_free_nodes;
+                }
+        }
+
+        events_array = calloc(cnt, sizeof(struct event_node));
+        if (!events_array) {
+                pr_debug("calloc failed\n");
+                ret = -1;
+                goto out_free_nodes;
+        }
+
+        pos = 0;
+        list_for_each_entry(node, &events, list)
+                events_array[pos++] = *node;
+
+        qsort(events_array, cnt, sizeof(struct event_node), compar);
+
+        for (pos = 0; pos < cnt; pos++) {
+                ret = process_event(evlist, events_array[pos].event,
+                                    switch_tracking);
+                if (ret < 0)
+                        goto out_free;
+        }
+
+        ret = 0;
+out_free:
+        pr_debug("%u events recorded\n", cnt);
+        free(events_array);
+out_free_nodes:
+        free_event_nodes(&events);
+        return ret;
+}
+
+/**
+ * test__switch_tracking - test using sched_switch and tracking events.
+ *
+ * This function implements a test that checks that sched_switch events and
+ * tracking events can be recorded for a workload (current process) using the
+ * evsel->system_wide and evsel->tracking flags (respectively) with other events
+ * sometimes enabled or disabled.
+ */
+int test__switch_tracking(void)
+{
+        const char *sched_switch = "sched:sched_switch";
+        struct switch_tracking switch_tracking = { .tids = NULL, };
+        struct record_opts opts = {
+                .mmap_pages          = UINT_MAX,
+                .user_freq           = UINT_MAX,
+                .user_interval       = ULLONG_MAX,
+                .freq                = 4000,
+                .target              = {
+                        .uses_mmap   = true,
+                },
+        };
+        struct thread_map *threads = NULL;
+        struct cpu_map *cpus = NULL;
+        struct perf_evlist *evlist = NULL;
+        struct perf_evsel *evsel, *cpu_clocks_evsel, *cycles_evsel;
+        struct perf_evsel *switch_evsel, *tracking_evsel;
+        const char *comm;
+        int err = -1;
+
+        threads = thread_map__new(-1, getpid(), UINT_MAX);
+        if (!threads) {
+                pr_debug("thread_map__new failed!\n");
+                goto out_err;
+        }
+
+        cpus = cpu_map__new(NULL);
+        if (!cpus) {
+                pr_debug("cpu_map__new failed!\n");
+                goto out_err;
+        }
+
+        evlist = perf_evlist__new();
+        if (!evlist) {
+                pr_debug("perf_evlist__new failed!\n");
+                goto out_err;
+        }
+
+        perf_evlist__set_maps(evlist, cpus, threads);
+
+        /* First event */
+        err = parse_events(evlist, "cpu-clock:u");
+        if (err) {
+                pr_debug("Failed to parse event dummy:u\n");
+                goto out_err;
+        }
+
+        cpu_clocks_evsel = perf_evlist__last(evlist);
+
+        /* Second event */
+        err = parse_events(evlist, "cycles:u");
+        if (err) {
+                pr_debug("Failed to parse event cycles:u\n");
+                goto out_err;
+        }
+
+        cycles_evsel = perf_evlist__last(evlist);
+
+        /* Third event */
+        if (!perf_evlist__can_select_event(evlist, sched_switch)) {
+                fprintf(stderr, " (no sched_switch)");
+                err = 0;
+                goto out;
+        }
+
+        err = parse_events(evlist, sched_switch);
+        if (err) {
+                pr_debug("Failed to parse event %s\n", sched_switch);
+                goto out_err;
+        }
+
+        switch_evsel = perf_evlist__last(evlist);
+
+        perf_evsel__set_sample_bit(switch_evsel, CPU);
+        perf_evsel__set_sample_bit(switch_evsel, TIME);
+
+        switch_evsel->system_wide = true;
+        switch_evsel->no_aux_samples = true;
+        switch_evsel->immediate = true;
+
+        /* Test moving an event to the front */
+        if (cycles_evsel == perf_evlist__first(evlist)) {
+                pr_debug("cycles event already at front");
+                goto out_err;
+        }
+        perf_evlist__to_front(evlist, cycles_evsel);
+        if (cycles_evsel != perf_evlist__first(evlist)) {
+                pr_debug("Failed to move cycles event to front");
+                goto out_err;
+        }
+
+        perf_evsel__set_sample_bit(cycles_evsel, CPU);
+        perf_evsel__set_sample_bit(cycles_evsel, TIME);
+
+        /* Fourth event */
+        err = parse_events(evlist, "dummy:u");
+        if (err) {
+                pr_debug("Failed to parse event dummy:u\n");
+                goto out_err;
+        }
+
+        tracking_evsel = perf_evlist__last(evlist);
+
+        perf_evlist__set_tracking_event(evlist, tracking_evsel);
+
+        tracking_evsel->attr.freq = 0;
+        tracking_evsel->attr.sample_period = 1;
+
+        perf_evsel__set_sample_bit(tracking_evsel, TIME);
+
+        /* Config events */
+        perf_evlist__config(evlist, &opts);
+
+        /* Check moved event is still at the front */
+        if (cycles_evsel != perf_evlist__first(evlist)) {
+                pr_debug("Front event no longer at front");
+                goto out_err;
+        }
+
+        /* Check tracking event is tracking */
+        if (!tracking_evsel->attr.mmap || !tracking_evsel->attr.comm) {
+                pr_debug("Tracking event not tracking\n");
+                goto out_err;
+        }
+
+        /* Check non-tracking events are not tracking */
+        evlist__for_each(evlist, evsel) {
+                if (evsel != tracking_evsel) {
+                        if (evsel->attr.mmap || evsel->attr.comm) {
+                                pr_debug("Non-tracking event is tracking\n");
+                                goto out_err;
+                        }
+                }
+        }
+
+        if (perf_evlist__open(evlist) < 0) {
+                fprintf(stderr, " (not supported)");
+                err = 0;
+                goto out;
+        }
+
+        err = perf_evlist__mmap(evlist, UINT_MAX, false);
+        if (err) {
+                pr_debug("perf_evlist__mmap failed!\n");
+                goto out_err;
+        }
+
+        perf_evlist__enable(evlist);
+
+        err = perf_evlist__disable_event(evlist, cpu_clocks_evsel);
+        if (err) {
+                pr_debug("perf_evlist__disable_event failed!\n");
+                goto out_err;
+        }
+
+        err = spin_sleep();
+        if (err) {
+                pr_debug("spin_sleep failed!\n");
+                goto out_err;
+        }
+
+        comm = "Test COMM 1";
+        err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+        if (err) {
+                pr_debug("PR_SET_NAME failed!\n");
+                goto out_err;
+        }
+
+        err = perf_evlist__disable_event(evlist, cycles_evsel);
+        if (err) {
+                pr_debug("perf_evlist__disable_event failed!\n");
+                goto out_err;
+        }
+
+        comm = "Test COMM 2";
+        err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+        if (err) {
+                pr_debug("PR_SET_NAME failed!\n");
+                goto out_err;
+        }
+
+        err = spin_sleep();
+        if (err) {
+                pr_debug("spin_sleep failed!\n");
+                goto out_err;
+        }
+
+        comm = "Test COMM 3";
+        err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+        if (err) {
+                pr_debug("PR_SET_NAME failed!\n");
+                goto out_err;
+        }
+
+        err = perf_evlist__enable_event(evlist, cycles_evsel);
+        if (err) {
+                pr_debug("perf_evlist__disable_event failed!\n");
+                goto out_err;
+        }
+
+        comm = "Test COMM 4";
+        err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+        if (err) {
+                pr_debug("PR_SET_NAME failed!\n");
+                goto out_err;
+        }
+
+        err = spin_sleep();
+        if (err) {
+                pr_debug("spin_sleep failed!\n");
+                goto out_err;
+        }
+
+        perf_evlist__disable(evlist);
+
+        switch_tracking.switch_evsel = switch_evsel;
+        switch_tracking.cycles_evsel = cycles_evsel;
+
+        err = process_events(evlist, &switch_tracking);
+
+        zfree(&switch_tracking.tids);
+
+        if (err)
+                goto out_err;
+
+        /* Check all 4 comm events were seen i.e. that evsel->tracking works */
+        if (!switch_tracking.comm_seen[0] || !switch_tracking.comm_seen[1] ||
+            !switch_tracking.comm_seen[2] || !switch_tracking.comm_seen[3]) {
+                pr_debug("Missing comm events\n");
+                goto out_err;
+        }
+
+        /* Check cycles event got enabled */
+        if (!switch_tracking.cycles_before_comm_1) {
+                pr_debug("Missing cycles events\n");
+                goto out_err;
+        }
+
+        /* Check cycles event got disabled */
+        if (switch_tracking.cycles_between_comm_2_and_comm_3) {
+                pr_debug("cycles events even though event was disabled\n");
+                goto out_err;
+        }
+
+        /* Check cycles event got enabled again */
+        if (!switch_tracking.cycles_after_comm_4) {
+                pr_debug("Missing cycles events\n");
+                goto out_err;
+        }
+out:
+        if (evlist) {
+                perf_evlist__disable(evlist);
+                perf_evlist__delete(evlist);
+        } else {
+                cpu_map__delete(cpus);
+                thread_map__delete(threads);
+        }
+
+        return err;
+
+out_err:
+        err = -1;
+        goto out;
+}
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 5ff3db318f12..3a8fedef83bc 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -42,6 +42,7 @@ int test__task_exit(void)
                 .uses_mmap      = true,
         };
         const char *argv[] = { "true", NULL };
+        char sbuf[STRERR_BUFSIZE];
 
         signal(SIGCHLD, sig_handler);
 
@@ -82,13 +83,14 @@ int test__task_exit(void)
 
         err = perf_evlist__open(evlist);
         if (err < 0) {
-                pr_debug("Couldn't open the evlist: %s\n", strerror(-err));
+                pr_debug("Couldn't open the evlist: %s\n",
+                         strerror_r(-err, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
         if (perf_evlist__mmap(evlist, 128, true) < 0) {
                 pr_debug("failed to mmap events: %d (%s)\n", errno,
-                         strerror(errno));
+                         strerror_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
@@ -103,7 +105,7 @@ retry:
         }
 
         if (!exited || !nr_exit) {
-                poll(evlist->pollfd, evlist->nr_fds, -1);
+                perf_evlist__poll(evlist, -1);
                 goto retry;
         }
 
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index ed64790a395f..00e776a87a9c 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -48,6 +48,9 @@ int test__mmap_thread_lookup(void);
 int test__thread_mg_share(void);
 int test__hists_output(void);
 int test__hists_cumulate(void);
+int test__switch_tracking(void);
+int test__fdarray__filter(void);
+int test__fdarray__add(void);
 
 #if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/ui/browsers/header.c b/tools/perf/ui/browsers/header.c
index 89c16b988618..e8278c558d4a 100644
--- a/tools/perf/ui/browsers/header.c
+++ b/tools/perf/ui/browsers/header.c
@@ -1,6 +1,7 @@
 #include "util/cache.h"
 #include "util/debug.h"
 #include "ui/browser.h"
+#include "ui/keysyms.h"
 #include "ui/ui.h"
 #include "ui/util.h"
 #include "ui/libslang.h"
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index a94b11fc5e00..cfb976b3de3a 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -10,6 +10,7 @@
 #include "../../util/pstack.h"
 #include "../../util/sort.h"
 #include "../../util/util.h"
+#include "../../util/top.h"
 #include "../../arch/common.h"
 
 #include "../browser.h"
@@ -34,7 +35,9 @@ struct hist_browser {
 
 extern void hist_browser__init_hpp(void);
 
-static int hists__browser_title(struct hists *hists, char *bf, size_t size);
+static int hists__browser_title(struct hists *hists,
+                                struct hist_browser_timer *hbt,
+                                char *bf, size_t size);
 static void hist_browser__update_nr_entries(struct hist_browser *hb);
 
 static struct rb_node *hists__filter_entries(struct rb_node *nd,
@@ -228,8 +231,10 @@ static void callchain_node__init_have_children(struct callchain_node *node)
 {
         struct callchain_list *chain;
 
-        list_for_each_entry(chain, &node->val, list)
+        if (!list_empty(&node->val)) {
+                chain = list_entry(node->val.prev, struct callchain_list, list);
                 chain->ms.has_children = !RB_EMPTY_ROOT(&node->rb_root);
+        }
 
         callchain_node__init_have_children_rb_tree(node);
 }
@@ -387,7 +392,7 @@ static int hist_browser__run(struct hist_browser *browser,
         browser->b.entries = &browser->hists->entries;
         browser->b.nr_entries = hist_browser__nr_entries(browser);
 
-        hists__browser_title(browser->hists, title, sizeof(title));
+        hists__browser_title(browser->hists, hbt, title, sizeof(title));
 
         if (ui_browser__show(&browser->b, title,
                              "Press '?' for help on key bindings") < 0)
@@ -414,7 +419,8 @@ static int hist_browser__run(struct hist_browser *browser,
                                 ui_browser__warn_lost_events(&browser->b);
                         }
 
-                        hists__browser_title(browser->hists, title, sizeof(title));
+                        hists__browser_title(browser->hists,
+                                             hbt, title, sizeof(title));
                         ui_browser__show_title(&browser->b, title);
                         continue;
                 }
@@ -474,26 +480,87 @@ static char *callchain_list__sym_name(struct callchain_list *cl,
         return bf;
 }
 
+struct callchain_print_arg {
+        /* for hists browser */
+        off_t   row_offset;
+        bool    is_current_entry;
+
+        /* for file dump */
+        FILE    *fp;
+        int     printed;
+};
+
+typedef void (*print_callchain_entry_fn)(struct hist_browser *browser,
+                                         struct callchain_list *chain,
+                                         const char *str, int offset,
+                                         unsigned short row,
+                                         struct callchain_print_arg *arg);
+
+static void hist_browser__show_callchain_entry(struct hist_browser *browser,
+                                               struct callchain_list *chain,
+                                               const char *str, int offset,
+                                               unsigned short row,
+                                               struct callchain_print_arg *arg)
+{
+        int color, width;
+        char folded_sign = callchain_list__folded(chain);
+
+        color = HE_COLORSET_NORMAL;
+        width = browser->b.width - (offset + 2);
+        if (ui_browser__is_current_entry(&browser->b, row)) {
+                browser->selection = &chain->ms;
+                color = HE_COLORSET_SELECTED;
+                arg->is_current_entry = true;
+        }
+
+        ui_browser__set_color(&browser->b, color);
+        hist_browser__gotorc(browser, row, 0);
+        slsmg_write_nstring(" ", offset);
+        slsmg_printf("%c ", folded_sign);
+        slsmg_write_nstring(str, width);
+}
+
+static void hist_browser__fprintf_callchain_entry(struct hist_browser *b __maybe_unused,
+                                                  struct callchain_list *chain,
+                                                  const char *str, int offset,
+                                                  unsigned short row __maybe_unused,
+                                                  struct callchain_print_arg *arg)
+{
+        char folded_sign = callchain_list__folded(chain);
+
+        arg->printed += fprintf(arg->fp, "%*s%c %s\n", offset, " ",
+                                folded_sign, str);
+}
+
+typedef bool (*check_output_full_fn)(struct hist_browser *browser,
+                                     unsigned short row);
+
+static bool hist_browser__check_output_full(struct hist_browser *browser,
+                                            unsigned short row)
+{
+        return browser->b.rows == row;
+}
+
+static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_unused,
+                                          unsigned short row __maybe_unused)
+{
+        return false;
+}
+
 #define LEVEL_OFFSET_STEP 3
 
-static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browser,
-                                                     struct callchain_node *chain_node,
-                                                     u64 total, int level,
-                                                     unsigned short row,
-                                                     off_t *row_offset,
-                                                     bool *is_current_entry)
+static int hist_browser__show_callchain(struct hist_browser *browser,
+                                        struct rb_root *root, int level,
+                                        unsigned short row, u64 total,
+                                        print_callchain_entry_fn print,
+                                        struct callchain_print_arg *arg,
+                                        check_output_full_fn is_output_full)
 {
         struct rb_node *node;
-        int first_row = row, width, offset = level * LEVEL_OFFSET_STEP;
-        u64 new_total, remaining;
+        int first_row = row, offset = level * LEVEL_OFFSET_STEP;
+        u64 new_total;
 
-        if (callchain_param.mode == CHAIN_GRAPH_REL)
-                new_total = chain_node->children_hit;
-        else
-                new_total = total;
-
-        remaining = new_total;
-        node = rb_first(&chain_node->rb_root);
+        node = rb_first(root);
         while (node) {
                 struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
                 struct rb_node *next = rb_next(node);
@@ -503,30 +570,28 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browse
                 int first = true;
                 int extra_offset = 0;
 
-                remaining -= cumul;
-
                 list_for_each_entry(chain, &child->val, list) {
                         char bf[1024], *alloc_str;
                         const char *str;
-                        int color;
                         bool was_first = first;
 
                         if (first)
                                 first = false;
-                        else
+                        else if (level > 1)
                                 extra_offset = LEVEL_OFFSET_STEP;
 
                         folded_sign = callchain_list__folded(chain);
-                        if (*row_offset != 0) {
-                                --*row_offset;
+                        if (arg->row_offset != 0) {
+                                arg->row_offset--;
                                 goto do_next;
                         }
 
                         alloc_str = NULL;
                         str = callchain_list__sym_name(chain, bf, sizeof(bf),
                                                        browser->show_dso);
-                        if (was_first) {
-                                double percent = cumul * 100.0 / new_total;
+
+                        if (was_first && level > 1) {
+                                double percent = cumul * 100.0 / total;
 
                                 if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
                                         str = "Not enough memory!";
@@ -534,22 +599,11 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browse
                                         str = alloc_str;
                         }
 
-                        color = HE_COLORSET_NORMAL;
-                        width = browser->b.width - (offset + extra_offset + 2);
-                        if (ui_browser__is_current_entry(&browser->b, row)) {
-                                browser->selection = &chain->ms;
-                                color = HE_COLORSET_SELECTED;
-                                *is_current_entry = true;
-                        }
+                        print(browser, chain, str, offset + extra_offset, row, arg);
 
-                        ui_browser__set_color(&browser->b, color);
-                        hist_browser__gotorc(browser, row, 0);
-                        slsmg_write_nstring(" ", offset + extra_offset);
-                        slsmg_printf("%c ", folded_sign);
-                        slsmg_write_nstring(str, width);
                         free(alloc_str);
 
-                        if (++row == browser->b.rows)
+                        if (is_output_full(browser, ++row))
                                 goto out;
 do_next:
                         if (folded_sign == '+')
@@ -558,89 +612,21 @@ do_next:
 
                 if (folded_sign == '-') {
                         const int new_level = level + (extra_offset ? 2 : 1);
-                        row += hist_browser__show_callchain_node_rb_tree(browser, child, new_total,
-                                                                         new_level, row, row_offset,
-                                                                         is_current_entry);
-                }
-                if (row == browser->b.rows)
-                        goto out;
-                node = next;
-        }
-out:
-        return row - first_row;
-}
-
-static int hist_browser__show_callchain_node(struct hist_browser *browser,
-                                             struct callchain_node *node,
-                                             int level, unsigned short row,
-                                             off_t *row_offset,
-                                             bool *is_current_entry)
-{
-        struct callchain_list *chain;
-        int first_row = row,
-             offset = level * LEVEL_OFFSET_STEP,
-             width = browser->b.width - offset;
-        char folded_sign = ' ';
-
-        list_for_each_entry(chain, &node->val, list) {
-                char bf[1024], *s;
-                int color;
 
-                folded_sign = callchain_list__folded(chain);
-
-                if (*row_offset != 0) {
-                        --*row_offset;
-                        continue;
-                }
+                        if (callchain_param.mode == CHAIN_GRAPH_REL)
+                                new_total = child->children_hit;
+                        else
+                                new_total = total;
 
-                color = HE_COLORSET_NORMAL;
-                if (ui_browser__is_current_entry(&browser->b, row)) {
-                        browser->selection = &chain->ms;
-                        color = HE_COLORSET_SELECTED;
-                        *is_current_entry = true;
+                        row += hist_browser__show_callchain(browser, &child->rb_root,
+                                                            new_level, row, new_total,
+                                                            print, arg, is_output_full);
                 }
-
-                s = callchain_list__sym_name(chain, bf, sizeof(bf),
-                                             browser->show_dso);
-                hist_browser__gotorc(browser, row, 0);
-                ui_browser__set_color(&browser->b, color);
-                slsmg_write_nstring(" ", offset);
-                slsmg_printf("%c ", folded_sign);
-                slsmg_write_nstring(s, width - 2);
-
-                if (++row == browser->b.rows)
-                        goto out;
-        }
-
-        if (folded_sign == '-')
-                row += hist_browser__show_callchain_node_rb_tree(browser, node,
-                                                                 browser->hists->stats.total_period,
-                                                                 level + 1, row,
-                                                                 row_offset,
-                                                                 is_current_entry);
-out:
-        return row - first_row;
-}
-
-static int hist_browser__show_callchain(struct hist_browser *browser,
-                                        struct rb_root *chain,
-                                        int level, unsigned short row,
-                                        off_t *row_offset,
-                                        bool *is_current_entry)
-{
-        struct rb_node *nd;
-        int first_row = row;
-
-        for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
-                struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
-
-                row += hist_browser__show_callchain_node(browser, node, level,
-                                                         row, row_offset,
-                                                         is_current_entry);
-                if (row == browser->b.rows)
+                if (is_output_full(browser, row))
                         break;
+                node = next;
         }
-
+out:
         return row - first_row;
 }
 
@@ -653,17 +639,18 @@ struct hpp_arg {
 static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
 {
         struct hpp_arg *arg = hpp->ptr;
-        int ret;
+        int ret, len;
         va_list args;
         double percent;
 
         va_start(args, fmt);
+        len = va_arg(args, int);
         percent = va_arg(args, double);
         va_end(args);
 
         ui_browser__set_percent_color(arg->b, percent, arg->current_entry);
 
-        ret = scnprintf(hpp->buf, hpp->size, fmt, percent);
+        ret = scnprintf(hpp->buf, hpp->size, fmt, len, percent);
         slsmg_printf("%s", hpp->buf);
 
         advance_hpp(hpp, ret);
@@ -677,12 +664,12 @@ static u64 __hpp_get_##_field(struct hist_entry *he)			\
 }                                                                       \
                                                                         \
 static int                                                              \
-hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt,               \
                                 struct perf_hpp *hpp,                   \
                                 struct hist_entry *he)                  \
 {                                                                       \
-        return __hpp__fmt(hpp, he, __hpp_get_##_field, " %6.2f%%",      \
-                          __hpp__slsmg_color_printf, true);             \
+        return hpp__fmt(fmt, hpp, he, __hpp_get_##_field, " %*.2f%%",   \
+                        __hpp__slsmg_color_printf, true);               \
 }
 
 #define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)                       \
@@ -692,18 +679,20 @@ static u64 __hpp_get_acc_##_field(struct hist_entry *he)		\
 }                                                                       \
                                                                         \
 static int                                                              \
-hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt,               \
                                 struct perf_hpp *hpp,                   \
                                 struct hist_entry *he)                  \
 {                                                                       \
         if (!symbol_conf.cumulate_callchain) {                          \
-                int ret = scnprintf(hpp->buf, hpp->size, "%8s", "N/A"); \
+                int len = fmt->user_len ?: fmt->len;                    \
+                int ret = scnprintf(hpp->buf, hpp->size,                \
+                                    "%*s", len, "N/A");                 \
                 slsmg_printf("%s", hpp->buf);                           \
                                                                         \
                 return ret;                                             \
         }                                                               \
-        return __hpp__fmt(hpp, he, __hpp_get_acc_##_field, " %6.2f%%",  \
-                          __hpp__slsmg_color_printf, true);             \
+        return hpp__fmt(fmt, hpp, he, __hpp_get_acc_##_field,           \
+                        " %*.2f%%", __hpp__slsmg_color_printf, true);   \
 }
 
 __HPP_COLOR_PERCENT_FN(overhead, period)
@@ -812,10 +801,18 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                 --row_offset;
 
         if (folded_sign == '-' && row != browser->b.rows) {
-                printed += hist_browser__show_callchain(browser, &entry->sorted_chain,
-                                                        1, row, &row_offset,
-                                                        &current_entry);
-                if (current_entry)
+                u64 total = hists__total_period(entry->hists);
+                struct callchain_print_arg arg = {
+                        .row_offset = row_offset,
+                        .is_current_entry = current_entry,
+                };
+
+                printed += hist_browser__show_callchain(browser,
+                                        &entry->sorted_chain, 1, row, total,
+                                        hist_browser__show_callchain_entry, &arg,
+                                        hist_browser__check_output_full);
+
+                if (arg.is_current_entry)
                         browser->he_selection = entry;
         }
 
@@ -847,9 +844,6 @@ static int hists__scnprintf_headers(char *buf, size_t size, struct hists *hists)
                 if (perf_hpp__should_skip(fmt))
                         continue;
 
-                /* We need to add the length of the columns header. */
-                perf_hpp__reset_width(fmt, hists);
-
                 ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
                 if (advance_hpp_check(&dummy_hpp, ret))
                         break;
@@ -1074,113 +1068,21 @@ do_offset:
         }
 }
 
-static int hist_browser__fprintf_callchain_node_rb_tree(struct hist_browser *browser,
-                                                        struct callchain_node *chain_node,
-                                                        u64 total, int level,
-                                                        FILE *fp)
-{
-        struct rb_node *node;
-        int offset = level * LEVEL_OFFSET_STEP;
-        u64 new_total, remaining;
-        int printed = 0;
-
-        if (callchain_param.mode == CHAIN_GRAPH_REL)
-                new_total = chain_node->children_hit;
-        else
-                new_total = total;
-
-        remaining = new_total;
-        node = rb_first(&chain_node->rb_root);
-        while (node) {
-                struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
-                struct rb_node *next = rb_next(node);
-                u64 cumul = callchain_cumul_hits(child);
-                struct callchain_list *chain;
-                char folded_sign = ' ';
-                int first = true;
-                int extra_offset = 0;
-
-                remaining -= cumul;
-
-                list_for_each_entry(chain, &child->val, list) {
-                        char bf[1024], *alloc_str;
-                        const char *str;
-                        bool was_first = first;
-
-                        if (first)
-                                first = false;
-                        else
-                                extra_offset = LEVEL_OFFSET_STEP;
-
-                        folded_sign = callchain_list__folded(chain);
-
-                        alloc_str = NULL;
-                        str = callchain_list__sym_name(chain, bf, sizeof(bf),
-                                                       browser->show_dso);
-                        if (was_first) {
-                                double percent = cumul * 100.0 / new_total;
-
-                                if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
-                                        str = "Not enough memory!";
-                                else
-                                        str = alloc_str;
-                        }
-
-                        printed += fprintf(fp, "%*s%c %s\n", offset + extra_offset, " ", folded_sign, str);
-                        free(alloc_str);
-                        if (folded_sign == '+')
-                                break;
-                }
-
-                if (folded_sign == '-') {
-                        const int new_level = level + (extra_offset ? 2 : 1);
-                        printed += hist_browser__fprintf_callchain_node_rb_tree(browser, child, new_total,
-                                                                                new_level, fp);
-                }
-
-                node = next;
-        }
-
-        return printed;
-}
-
-static int hist_browser__fprintf_callchain_node(struct hist_browser *browser,
-                                                struct callchain_node *node,
-                                                int level, FILE *fp)
-{
-        struct callchain_list *chain;
-        int offset = level * LEVEL_OFFSET_STEP;
-        char folded_sign = ' ';
-        int printed = 0;
-
-        list_for_each_entry(chain, &node->val, list) {
-                char bf[1024], *s;
-
-                folded_sign = callchain_list__folded(chain);
-                s = callchain_list__sym_name(chain, bf, sizeof(bf), browser->show_dso);
-                printed += fprintf(fp, "%*s%c %s\n", offset, " ", folded_sign, s);
-        }
-
-        if (folded_sign == '-')
-                printed += hist_browser__fprintf_callchain_node_rb_tree(browser, node,
-                                                                        browser->hists->stats.total_period,
-                                                                        level + 1,  fp);
-        return printed;
-}
-
 static int hist_browser__fprintf_callchain(struct hist_browser *browser,
-                                           struct rb_root *chain, int level, FILE *fp)
+                                           struct hist_entry *he, FILE *fp)
 {
-        struct rb_node *nd;
-        int printed = 0;
-
-        for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
-                struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
+        u64 total = hists__total_period(he->hists);
+        struct callchain_print_arg arg  = {
+                .fp = fp,
+        };
 
-                printed += hist_browser__fprintf_callchain_node(browser, node, level, fp);
-        }
+        if (symbol_conf.cumulate_callchain)
+                total = he->stat_acc->period;
 
-        return printed;
+        hist_browser__show_callchain(browser, &he->sorted_chain, 1, 0, total,
+                                     hist_browser__fprintf_callchain_entry, &arg,
+                                     hist_browser__check_dump_full);
+        return arg.printed;
 }
 
 static int hist_browser__fprintf_entry(struct hist_browser *browser,
@@ -1219,7 +1121,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
         printed += fprintf(fp, "%s\n", rtrim(s));
 
         if (folded_sign == '-')
-                printed += hist_browser__fprintf_callchain(browser, &he->sorted_chain, 1, fp);
+                printed += hist_browser__fprintf_callchain(browser, he, fp);
 
         return printed;
 }
@@ -1305,7 +1207,15 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser
         return browser->he_selection->thread;
 }
 
-static int hists__browser_title(struct hists *hists, char *bf, size_t size)
+/* Check whether the browser is for 'top' or 'report' */
+static inline bool is_report_browser(void *timer)
+{
+        return timer == NULL;
+}
+
+static int hists__browser_title(struct hists *hists,
+                                struct hist_browser_timer *hbt,
+                                char *bf, size_t size)
 {
         char unit;
         int printed;
@@ -1330,12 +1240,14 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size)
                 ev_name = buf;
 
                 for_each_group_member(pos, evsel) {
+                        struct hists *pos_hists = evsel__hists(pos);
+
                         if (symbol_conf.filter_relative) {
-                                nr_samples += pos->hists.stats.nr_non_filtered_samples;
-                                nr_events += pos->hists.stats.total_non_filtered_period;
+                                nr_samples += pos_hists->stats.nr_non_filtered_samples;
+                                nr_events += pos_hists->stats.total_non_filtered_period;
                         } else {
-                                nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
-                                nr_events += pos->hists.stats.total_period;
+                                nr_samples += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE];
+                                nr_events += pos_hists->stats.total_period;
                         }
                 }
         }
@@ -1357,6 +1269,13 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size)
         if (dso)
                 printed += scnprintf(bf + printed, size - printed,
                                     ", DSO: %s", dso->short_name);
+        if (!is_report_browser(hbt)) {
+                struct perf_top *top = hbt->arg;
+
+                if (top->zero)
+                        printed += scnprintf(bf + printed, size - printed, " [z]");
+        }
+
         return printed;
 }
 
@@ -1368,12 +1287,6 @@ static inline void free_popup_options(char **options, int n)
                 zfree(&options[i]);
 }
 
-/* Check whether the browser is for 'top' or 'report' */
-static inline bool is_report_browser(void *timer)
-{
-        return timer == NULL;
-}
-
 /*
  * Only runtime switching of perf data file will make "input_name" point
  * to a malloced buffer. So add "is_input_name_malloced" flag to decide
@@ -1488,7 +1401,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                                     float min_pcnt,
                                     struct perf_session_env *env)
 {
-        struct hists *hists = &evsel->hists;
+        struct hists *hists = evsel__hists(evsel);
         struct hist_browser *browser = hist_browser__new(hists);
         struct branch_info *bi;
         struct pstack *fstack;
@@ -1498,6 +1411,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
         char buf[64];
         char script_opt[64];
         int delay_secs = hbt ? hbt->refresh : 0;
+        struct perf_hpp_fmt *fmt;
 
 #define HIST_BROWSER_HELP_COMMON                                        \
         "h/?/F1        Show this window\n"                              \
@@ -1529,6 +1443,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
         "P             Print histograms to perf.hist.N\n"
         "t             Zoom into current Thread\n"
         "V             Verbose (DSO names in callchains, etc)\n"
+        "z             Toggle zeroing of samples\n"
         "/             Filter symbol by name";
 
         if (browser == NULL)
@@ -1547,6 +1462,12 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
         memset(options, 0, sizeof(options));
 
+        perf_hpp__for_each_format(fmt)
+                perf_hpp__reset_width(fmt, hists);
+
+        if (symbol_conf.col_width_list_str)
+                perf_hpp__set_user_width(symbol_conf.col_width_list_str);
+
         while (1) {
                 const struct thread *thread = NULL;
                 const struct dso *dso = NULL;
@@ -1623,6 +1544,13 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                 case 'F':
                         symbol_conf.filter_relative ^= 1;
                         continue;
+                case 'z':
+                        if (!is_report_browser(hbt)) {
+                                struct perf_top *top = hbt->arg;
+
+                                top->zero = !top->zero;
+                        }
+                        continue;
                 case K_F1:
                 case 'h':
                 case '?':
@@ -1888,8 +1816,9 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
         struct perf_evsel_menu *menu = container_of(browser,
                                                     struct perf_evsel_menu, b);
         struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node);
+        struct hists *hists = evsel__hists(evsel);
         bool current_entry = ui_browser__is_current_entry(browser, row);
-        unsigned long nr_events = evsel->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+        unsigned long nr_events = hists->stats.nr_events[PERF_RECORD_SAMPLE];
         const char *ev_name = perf_evsel__name(evsel);
         char bf[256], unit;
         const char *warn = " ";
@@ -1904,7 +1833,8 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
                 ev_name = perf_evsel__group_name(evsel);
 
                 for_each_group_member(pos, evsel) {
-                        nr_events += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+                        struct hists *pos_hists = evsel__hists(pos);
+                        nr_events += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE];
                 }
         }
 
@@ -1913,7 +1843,7 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
                            unit, unit == ' ' ? "" : " ", ev_name);
         slsmg_printf("%s", bf);
 
-        nr_events = evsel->hists.stats.nr_events[PERF_RECORD_LOST];
+        nr_events = hists->stats.nr_events[PERF_RECORD_LOST];
         if (nr_events != 0) {
                 menu->lost_events = true;
                 if (!current_entry)
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 6ca60e482cdc..fc654fb77ace 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -11,6 +11,7 @@
 static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
 {
         int ret = 0;
+        int len;
         va_list args;
         double percent;
         const char *markup;
@@ -18,6 +19,7 @@ static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
         size_t size = hpp->size;
 
         va_start(args, fmt);
+        len = va_arg(args, int);
         percent = va_arg(args, double);
         va_end(args);
 
@@ -25,7 +27,7 @@ static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
         if (markup)
                 ret += scnprintf(buf, size, markup);
 
-        ret += scnprintf(buf + ret, size - ret, fmt, percent);
+        ret += scnprintf(buf + ret, size - ret, fmt, len, percent);
 
         if (markup)
                 ret += scnprintf(buf + ret, size - ret, "</span>");
@@ -39,12 +41,12 @@ static u64 he_get_##_field(struct hist_entry *he)				\
         return he->stat._field;                                                 \
 }                                                                               \
                                                                                 \
-static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \
+static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt,                \
                                        struct perf_hpp *hpp,                    \
                                        struct hist_entry *he)                   \
 {                                                                               \
-        return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%",                 \
-                          __percent_color_snprintf, true);                      \
+        return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",              \
+                        __percent_color_snprintf, true);                        \
 }
 
 #define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)                               \
@@ -57,8 +59,8 @@ static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,
                                        struct perf_hpp *hpp,                    \
                                        struct hist_entry *he)                   \
 {                                                                               \
-        return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%",         \
-                              __percent_color_snprintf, true);                  \
+        return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%",      \
+                            __percent_color_snprintf, true);                    \
 }
 
 __HPP_COLOR_PERCENT_FN(overhead, period)
@@ -205,10 +207,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
                 if (perf_hpp__is_sort_entry(fmt))
                         sym_col = col_idx;
 
-                fmt->header(fmt, &hpp, hists_to_evsel(hists));
-
                 gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
-                                                            -1, ltrim(s),
+                                                            -1, fmt->name,
                                                             renderer, "markup",
                                                             col_idx++, NULL);
         }
@@ -319,7 +319,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
         gtk_container_add(GTK_CONTAINER(window), vbox);
 
         evlist__for_each(evlist, pos) {
-                struct hists *hists = &pos->hists;
+                struct hists *hists = evsel__hists(pos);
                 const char *evname = perf_evsel__name(pos);
                 GtkWidget *scrolled_window;
                 GtkWidget *tab_label;
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 498adb23c02e..2af18376b077 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -15,9 +15,9 @@
         __ret;                                                  \
 })
 
-int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
-               hpp_field_fn get_field, const char *fmt,
-               hpp_snprint_fn print_fn, bool fmt_percent)
+static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
+                      hpp_field_fn get_field, const char *fmt, int len,
+                      hpp_snprint_fn print_fn, bool fmt_percent)
 {
         int ret;
         struct hists *hists = he->hists;
@@ -32,9 +32,9 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
                 if (total)
                         percent = 100.0 * get_field(he) / total;
 
-                ret = hpp__call_print_fn(hpp, print_fn, fmt, percent);
+                ret = hpp__call_print_fn(hpp, print_fn, fmt, len, percent);
         } else
-                ret = hpp__call_print_fn(hpp, print_fn, fmt, get_field(he));
+                ret = hpp__call_print_fn(hpp, print_fn, fmt, len, get_field(he));
 
         if (perf_evsel__is_group_event(evsel)) {
                 int prev_idx, idx_delta;
@@ -60,19 +60,19 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
                                  */
                                 if (fmt_percent) {
                                         ret += hpp__call_print_fn(hpp, print_fn,
-                                                                  fmt, 0.0);
+                                                                  fmt, len, 0.0);
                                 } else {
                                         ret += hpp__call_print_fn(hpp, print_fn,
-                                                                  fmt, 0ULL);
+                                                                  fmt, len, 0ULL);
                                 }
                         }
 
                         if (fmt_percent) {
-                                ret += hpp__call_print_fn(hpp, print_fn, fmt,
+                                ret += hpp__call_print_fn(hpp, print_fn, fmt, len,
                                                           100.0 * period / total);
                         } else {
                                 ret += hpp__call_print_fn(hpp, print_fn, fmt,
-                                                          period);
+                                                          len, period);
                         }
 
                         prev_idx = perf_evsel__group_idx(evsel);
@@ -86,10 +86,10 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
                          */
                         if (fmt_percent) {
                                 ret += hpp__call_print_fn(hpp, print_fn,
-                                                          fmt, 0.0);
+                                                          fmt, len, 0.0);
                         } else {
                                 ret += hpp__call_print_fn(hpp, print_fn,
-                                                          fmt, 0ULL);
+                                                          fmt, len, 0ULL);
                         }
                 }
         }
@@ -104,16 +104,35 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
         return ret;
 }
 
-int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
-                   hpp_field_fn get_field, const char *fmt,
-                   hpp_snprint_fn print_fn, bool fmt_percent)
+int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+             struct hist_entry *he, hpp_field_fn get_field,
+             const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent)
+{
+        int len = fmt->user_len ?: fmt->len;
+
+        if (symbol_conf.field_sep) {
+                return __hpp__fmt(hpp, he, get_field, fmtstr, 1,
+                                  print_fn, fmt_percent);
+        }
+
+        if (fmt_percent)
+                len -= 2; /* 2 for a space and a % sign */
+        else
+                len -= 1;
+
+        return  __hpp__fmt(hpp, he, get_field, fmtstr, len, print_fn, fmt_percent);
+}
+
+int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+                 struct hist_entry *he, hpp_field_fn get_field,
+                 const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent)
 {
         if (!symbol_conf.cumulate_callchain) {
-                return snprintf(hpp->buf, hpp->size, "%*s",
-                                fmt_percent ? 8 : 12, "N/A");
+                int len = fmt->user_len ?: fmt->len;
+                return snprintf(hpp->buf, hpp->size, " %*s", len - 1, "N/A");
         }
 
-        return __hpp__fmt(hpp, he, get_field, fmt, print_fn, fmt_percent);
+        return hpp__fmt(fmt, hpp, he, get_field, fmtstr, print_fn, fmt_percent);
 }
 
 static int field_cmp(u64 field_a, u64 field_b)
@@ -190,30 +209,26 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
         return ret;
 }
 
-#define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width)           \
-static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \
-                               struct perf_hpp *hpp,                    \
-                               struct perf_evsel *evsel)                \
-{                                                                       \
-        int len = _min_width;                                           \
-                                                                        \
-        if (symbol_conf.event_group)                                    \
-                len = max(len, evsel->nr_members * _unit_width);        \
-                                                                        \
-        return scnprintf(hpp->buf, hpp->size, "%*s", len, _str);        \
-}
-
-#define __HPP_WIDTH_FN(_type, _min_width, _unit_width)                  \
-static int hpp__width_##_type(struct perf_hpp_fmt *fmt __maybe_unused,  \
-                              struct perf_hpp *hpp __maybe_unused,      \
-                              struct perf_evsel *evsel)                 \
-{                                                                       \
-        int len = _min_width;                                           \
-                                                                        \
-        if (symbol_conf.event_group)                                    \
-                len = max(len, evsel->nr_members * _unit_width);        \
-                                                                        \
-        return len;                                                     \
+static int hpp__width_fn(struct perf_hpp_fmt *fmt,
+                         struct perf_hpp *hpp __maybe_unused,
+                         struct perf_evsel *evsel)
+{
+        int len = fmt->user_len ?: fmt->len;
+
+        if (symbol_conf.event_group)
+                len = max(len, evsel->nr_members * fmt->len);
+
+        if (len < (int)strlen(fmt->name))
+                len = strlen(fmt->name);
+
+        return len;
+}
+
+static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+                          struct perf_evsel *evsel)
+{
+        int len = hpp__width_fn(fmt, hpp, evsel);
+        return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
 }
 
 static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
@@ -221,11 +236,12 @@ static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
         va_list args;
         ssize_t ssize = hpp->size;
         double percent;
-        int ret;
+        int ret, len;
 
         va_start(args, fmt);
+        len = va_arg(args, int);
         percent = va_arg(args, double);
-        ret = value_color_snprintf(hpp->buf, hpp->size, fmt, percent);
+        ret = percent_color_len_snprintf(hpp->buf, hpp->size, fmt, len, percent);
         va_end(args);
 
         return (ret >= ssize) ? (ssize - 1) : ret;
@@ -250,20 +266,19 @@ static u64 he_get_##_field(struct hist_entry *he)				\
         return he->stat._field;                                                 \
 }                                                                               \
                                                                                 \
-static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,          \
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt,                         \
                               struct perf_hpp *hpp, struct hist_entry *he)      \
 {                                                                               \
-        return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%",                 \
-                          hpp_color_scnprintf, true);                           \
+        return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",              \
+                        hpp_color_scnprintf, true);                             \
 }
 
 #define __HPP_ENTRY_PERCENT_FN(_type, _field)                                   \
-static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,         \
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,                         \
                               struct perf_hpp *hpp, struct hist_entry *he)      \
 {                                                                               \
-        const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";         \
-        return __hpp__fmt(hpp, he, he_get_##_field, fmt,                        \
-                          hpp_entry_scnprintf, true);                           \
+        return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",              \
+                        hpp_entry_scnprintf, true);                             \
 }
 
 #define __HPP_SORT_FN(_type, _field)                                            \
@@ -278,20 +293,19 @@ static u64 he_get_acc_##_field(struct hist_entry *he)				\
         return he->stat_acc->_field;                                            \
 }                                                                               \
                                                                                 \
-static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,          \
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt,                         \
                               struct perf_hpp *hpp, struct hist_entry *he)      \
 {                                                                               \
-        return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%",         \
-                              hpp_color_scnprintf, true);                       \
+        return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%",      \
+                            hpp_color_scnprintf, true);                         \
 }
 
 #define __HPP_ENTRY_ACC_PERCENT_FN(_type, _field)                               \
-static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,         \
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,                         \
                               struct perf_hpp *hpp, struct hist_entry *he)      \
 {                                                                               \
-        const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";         \
-        return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, fmt,                \
-                              hpp_entry_scnprintf, true);                       \
+        return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%",      \
+                            hpp_entry_scnprintf, true);                         \
 }
 
 #define __HPP_SORT_ACC_FN(_type, _field)                                        \
@@ -306,12 +320,11 @@ static u64 he_get_raw_##_field(struct hist_entry *he)				\
         return he->stat._field;                                                 \
 }                                                                               \
                                                                                 \
-static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,         \
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,                         \
                               struct perf_hpp *hpp, struct hist_entry *he)      \
 {                                                                               \
-        const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64;    \
-        return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt,                    \
-                          hpp_entry_scnprintf, false);                          \
+        return hpp__fmt(fmt, hpp, he, he_get_raw_##_field, " %*"PRIu64,         \
+                        hpp_entry_scnprintf, false);                            \
 }
 
 #define __HPP_SORT_RAW_FN(_type, _field)                                        \
@@ -321,37 +334,29 @@ static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b)	\
 }
 
 
-#define HPP_PERCENT_FNS(_type, _str, _field, _min_width, _unit_width)   \
-__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)                   \
-__HPP_WIDTH_FN(_type, _min_width, _unit_width)                          \
+#define HPP_PERCENT_FNS(_type, _field)                                  \
 __HPP_COLOR_PERCENT_FN(_type, _field)                                   \
 __HPP_ENTRY_PERCENT_FN(_type, _field)                                   \
 __HPP_SORT_FN(_type, _field)
 
-#define HPP_PERCENT_ACC_FNS(_type, _str, _field, _min_width, _unit_width)\
-__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)                   \
-__HPP_WIDTH_FN(_type, _min_width, _unit_width)                          \
+#define HPP_PERCENT_ACC_FNS(_type, _field)                              \
 __HPP_COLOR_ACC_PERCENT_FN(_type, _field)                               \
 __HPP_ENTRY_ACC_PERCENT_FN(_type, _field)                               \
 __HPP_SORT_ACC_FN(_type, _field)
 
-#define HPP_RAW_FNS(_type, _str, _field, _min_width, _unit_width)       \
-__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)                   \
-__HPP_WIDTH_FN(_type, _min_width, _unit_width)                          \
+#define HPP_RAW_FNS(_type, _field)                                      \
 __HPP_ENTRY_RAW_FN(_type, _field)                                       \
 __HPP_SORT_RAW_FN(_type, _field)
 
-__HPP_HEADER_FN(overhead_self, "Self", 8, 8)
-
-HPP_PERCENT_FNS(overhead, "Overhead", period, 8, 8)
-HPP_PERCENT_FNS(overhead_sys, "sys", period_sys, 8, 8)
-HPP_PERCENT_FNS(overhead_us, "usr", period_us, 8, 8)
-HPP_PERCENT_FNS(overhead_guest_sys, "guest sys", period_guest_sys, 9, 8)
-HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8)
-HPP_PERCENT_ACC_FNS(overhead_acc, "Children", period, 8, 8)
+HPP_PERCENT_FNS(overhead, period)
+HPP_PERCENT_FNS(overhead_sys, period_sys)
+HPP_PERCENT_FNS(overhead_us, period_us)
+HPP_PERCENT_FNS(overhead_guest_sys, period_guest_sys)
+HPP_PERCENT_FNS(overhead_guest_us, period_guest_us)
+HPP_PERCENT_ACC_FNS(overhead_acc, period)
 
-HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12)
-HPP_RAW_FNS(period, "Period", period, 12, 12)
+HPP_RAW_FNS(samples, nr_events)
+HPP_RAW_FNS(period, period)
 
 static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused,
                             struct hist_entry *b __maybe_unused)
@@ -359,47 +364,50 @@ static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused,
         return 0;
 }
 
-#define HPP__COLOR_PRINT_FNS(_name)                     \
+#define HPP__COLOR_PRINT_FNS(_name, _fn)                \
         {                                               \
-                .header = hpp__header_ ## _name,        \
-                .width  = hpp__width_ ## _name,         \
-                .color  = hpp__color_ ## _name,         \
-                .entry  = hpp__entry_ ## _name,         \
+                .name   = _name,                        \
+                .header = hpp__header_fn,               \
+                .width  = hpp__width_fn,                \
+                .color  = hpp__color_ ## _fn,           \
+                .entry  = hpp__entry_ ## _fn,           \
                 .cmp    = hpp__nop_cmp,                 \
                 .collapse = hpp__nop_cmp,               \
-                .sort   = hpp__sort_ ## _name,          \
+                .sort   = hpp__sort_ ## _fn,            \
         }
 
-#define HPP__COLOR_ACC_PRINT_FNS(_name)                 \
+#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn)            \
         {                                               \
-                .header = hpp__header_ ## _name,        \
-                .width  = hpp__width_ ## _name,         \
-                .color  = hpp__color_ ## _name,         \
-                .entry  = hpp__entry_ ## _name,         \
+                .name   = _name,                        \
+                .header = hpp__header_fn,               \
+                .width  = hpp__width_fn,                \
+                .color  = hpp__color_ ## _fn,           \
+                .entry  = hpp__entry_ ## _fn,           \
                 .cmp    = hpp__nop_cmp,                 \
                 .collapse = hpp__nop_cmp,               \
-                .sort   = hpp__sort_ ## _name,          \
+                .sort   = hpp__sort_ ## _fn,            \
         }
 
-#define HPP__PRINT_FNS(_name)                           \
+#define HPP__PRINT_FNS(_name, _fn)                      \
         {                                               \
-                .header = hpp__header_ ## _name,        \
-                .width  = hpp__width_ ## _name,         \
-                .entry  = hpp__entry_ ## _name,         \
+                .name   = _name,                        \
+                .header = hpp__header_fn,               \
+                .width  = hpp__width_fn,                \
+                .entry  = hpp__entry_ ## _fn,           \
                 .cmp    = hpp__nop_cmp,                 \
                 .collapse = hpp__nop_cmp,               \
-                .sort   = hpp__sort_ ## _name,          \
+                .sort   = hpp__sort_ ## _fn,            \
         }
 
 struct perf_hpp_fmt perf_hpp__format[] = {
-        HPP__COLOR_PRINT_FNS(overhead),
-        HPP__COLOR_PRINT_FNS(overhead_sys),
-        HPP__COLOR_PRINT_FNS(overhead_us),
-        HPP__COLOR_PRINT_FNS(overhead_guest_sys),
-        HPP__COLOR_PRINT_FNS(overhead_guest_us),
-        HPP__COLOR_ACC_PRINT_FNS(overhead_acc),
-        HPP__PRINT_FNS(samples),
-        HPP__PRINT_FNS(period)
+        HPP__COLOR_PRINT_FNS("Overhead", overhead),
+        HPP__COLOR_PRINT_FNS("sys", overhead_sys),
+        HPP__COLOR_PRINT_FNS("usr", overhead_us),
+        HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys),
+        HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us),
+        HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc),
+        HPP__PRINT_FNS("Samples", samples),
+        HPP__PRINT_FNS("Period", period)
 };
 
 LIST_HEAD(perf_hpp__list);
@@ -444,14 +452,12 @@ void perf_hpp__init(void)
         /*
          * If user specified field order, no need to setup default fields.
          */
-        if (field_order)
+        if (is_strict_order(field_order))
                 return;
 
         if (symbol_conf.cumulate_callchain) {
                 perf_hpp__column_enable(PERF_HPP__OVERHEAD_ACC);
-
-                perf_hpp__format[PERF_HPP__OVERHEAD].header =
-                                                hpp__header_overhead_self;
+                perf_hpp__format[PERF_HPP__OVERHEAD].name = "Self";
         }
 
         perf_hpp__column_enable(PERF_HPP__OVERHEAD);
@@ -513,11 +519,11 @@ void perf_hpp__column_disable(unsigned col)
 
 void perf_hpp__cancel_cumulate(void)
 {
-        if (field_order)
+        if (is_strict_order(field_order))
                 return;
 
         perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC);
-        perf_hpp__format[PERF_HPP__OVERHEAD].header = hpp__header_overhead;
+        perf_hpp__format[PERF_HPP__OVERHEAD].name = "Overhead";
 }
 
 void perf_hpp__setup_output_field(void)
@@ -622,3 +628,59 @@ unsigned int hists__sort_list_width(struct hists *hists)
 
         return ret;
 }
+
+void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+{
+        int idx;
+
+        if (perf_hpp__is_sort_entry(fmt))
+                return perf_hpp__reset_sort_width(fmt, hists);
+
+        for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) {
+                if (fmt == &perf_hpp__format[idx])
+                        break;
+        }
+
+        if (idx == PERF_HPP__MAX_INDEX)
+                return;
+
+        switch (idx) {
+        case PERF_HPP__OVERHEAD:
+        case PERF_HPP__OVERHEAD_SYS:
+        case PERF_HPP__OVERHEAD_US:
+        case PERF_HPP__OVERHEAD_ACC:
+                fmt->len = 8;
+                break;
+
+        case PERF_HPP__OVERHEAD_GUEST_SYS:
+        case PERF_HPP__OVERHEAD_GUEST_US:
+                fmt->len = 9;
+                break;
+
+        case PERF_HPP__SAMPLES:
+        case PERF_HPP__PERIOD:
+                fmt->len = 12;
+                break;
+
+        default:
+                break;
+        }
+}
+
+void perf_hpp__set_user_width(const char *width_list_str)
+{
+        struct perf_hpp_fmt *fmt;
+        const char *ptr = width_list_str;
+
+        perf_hpp__for_each_format(fmt) {
+                char *p;
+
+                int len = strtol(ptr, &p, 10);
+                fmt->user_len = len;
+
+                if (*p == ',')
+                        ptr = p + 1;
+                else
+                        break;
+        }
+}
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 40af0acb4fe9..15b451acbde6 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -395,10 +395,12 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
         init_rem_hits();
 
-
         perf_hpp__for_each_format(fmt)
                 perf_hpp__reset_width(fmt, hists);
 
+        if (symbol_conf.col_width_list_str)
+                perf_hpp__set_user_width(symbol_conf.col_width_list_str);
+
         if (!show_header)
                 goto print_entries;
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 809b4c50beae..7dabde14ea54 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -232,9 +232,16 @@ static int mov__parse(struct ins_operands *ops)
                 return -1;
 
         target = ++s;
+        comment = strchr(s, '#');
 
-        while (s[0] != '\0' && !isspace(s[0]))
-                ++s;
+        if (comment != NULL)
+                s = comment - 1;
+        else
+                s = strchr(s, '\0') - 1;
+
+        while (s > target && isspace(s[0]))
+                --s;
+        s++;
         prev = *s;
         *s = '\0';
 
@@ -244,7 +251,6 @@ static int mov__parse(struct ins_operands *ops)
         if (ops->target.raw == NULL)
                 goto out_free_source;
 
-        comment = strchr(s, '#');
         if (comment == NULL)
                 return 0;
 
@@ -472,7 +478,7 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 
         pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr));
 
-        if (addr < sym->start || addr > sym->end)
+        if (addr < sym->start || addr >= sym->end)
                 return -ERANGE;
 
         offset = addr - sym->start;
@@ -830,7 +836,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
                     end = map__rip_2objdump(map, sym->end);
 
                 offset = line_ip - start;
-                if ((u64)line_ip < start || (u64)line_ip > end)
+                if ((u64)line_ip < start || (u64)line_ip >= end)
                         offset = -1;
                 else
                         parsed_line = tmp2 + 1;
@@ -899,10 +905,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
         struct kcore_extract kce;
         bool delete_extract = false;
 
-        if (filename) {
-                snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
-                         symbol_conf.symfs, filename);
-        }
+        if (filename)
+                symbol__join_symfs(symfs_filename, filename);
 
         if (filename == NULL) {
                 if (dso->has_build_id) {
@@ -922,8 +926,7 @@ fallback:
                  * DSO is the same as when 'perf record' ran.
                  */
                 filename = (char *)dso->long_name;
-                snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
-                         symbol_conf.symfs, filename);
+                symbol__join_symfs(symfs_filename, filename);
                 free_filename = false;
         }
 
@@ -963,7 +966,7 @@ fallback:
                 kce.kcore_filename = symfs_filename;
                 kce.addr = map__rip_2objdump(map, sym->start);
                 kce.offs = sym->start;
-                kce.len = sym->end + 1 - sym->start;
+                kce.len = sym->end - sym->start;
                 if (!kcore_extract__create(&kce)) {
                         delete_extract = true;
                         strlcpy(symfs_filename, kce.extract_filename,
@@ -984,7 +987,7 @@ fallback:
                  disassembler_style ? "-M " : "",
                  disassembler_style ? disassembler_style : "",
                  map__rip_2objdump(map, sym->start),
-                 map__rip_2objdump(map, sym->end+1),
+                 map__rip_2objdump(map, sym->end),
                  symbol_conf.annotate_asm_raw ? "" : "--no-show-raw",
                  symbol_conf.annotate_src ? "-S" : "",
                  symfs_filename, filename);
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 7b176dd02e1a..5cf9e1b5989d 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -22,6 +22,7 @@ typedef int (*config_fn_t)(const char *, const char *, void *);
 extern int perf_default_config(const char *, const char *, void *);
 extern int perf_config(config_fn_t fn, void *);
 extern int perf_config_int(const char *, const char *);
+extern u64 perf_config_u64(const char *, const char *);
 extern int perf_config_bool(const char *, const char *);
 extern int config_error_nonbool(const char *);
 extern const char *perf_config_dirname(const char *, const char *);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 437ee09727e6..c84d3f8dcb75 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -25,77 +25,172 @@
 
 __thread struct callchain_cursor callchain_cursor;
 
-int
-parse_callchain_report_opt(const char *arg)
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+static int get_stack_size(const char *str, unsigned long *_size)
 {
-        char *tok, *tok2;
         char *endptr;
+        unsigned long size;
+        unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
 
-        symbol_conf.use_callchain = true;
+        size = strtoul(str, &endptr, 0);
 
-        if (!arg)
+        do {
+                if (*endptr)
+                        break;
+
+                size = round_up(size, sizeof(u64));
+                if (!size || size > max_size)
+                        break;
+
+                *_size = size;
                 return 0;
 
-        tok = strtok((char *)arg, ",");
-        if (!tok)
-                return -1;
+        } while (0);
 
-        /* get the output mode */
-        if (!strncmp(tok, "graph", strlen(arg))) {
-                callchain_param.mode = CHAIN_GRAPH_ABS;
+        pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
+               max_size, str);
+        return -1;
+}
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
 
-        } else if (!strncmp(tok, "flat", strlen(arg))) {
-                callchain_param.mode = CHAIN_FLAT;
-        } else if (!strncmp(tok, "fractal", strlen(arg))) {
-                callchain_param.mode = CHAIN_GRAPH_REL;
-        } else if (!strncmp(tok, "none", strlen(arg))) {
-                callchain_param.mode = CHAIN_NONE;
-                symbol_conf.use_callchain = false;
-                return 0;
-        } else {
-                return -1;
-        }
+int parse_callchain_record_opt(const char *arg)
+{
+        char *tok, *name, *saveptr = NULL;
+        char *buf;
+        int ret = -1;
+
+        /* We need buffer that we know we can write to. */
+        buf = malloc(strlen(arg) + 1);
+        if (!buf)
+                return -ENOMEM;
+
+        strcpy(buf, arg);
+
+        tok = strtok_r((char *)buf, ",", &saveptr);
+        name = tok ? : (char *)buf;
+
+        do {
+                /* Framepointer style */
+                if (!strncmp(name, "fp", sizeof("fp"))) {
+                        if (!strtok_r(NULL, ",", &saveptr)) {
+                                callchain_param.record_mode = CALLCHAIN_FP;
+                                ret = 0;
+                        } else
+                                pr_err("callchain: No more arguments "
+                                       "needed for -g fp\n");
+                        break;
 
-        /* get the min percentage */
-        tok = strtok(NULL, ",");
-        if (!tok)
-                goto setup;
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+                /* Dwarf style */
+                } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
+                        const unsigned long default_stack_dump_size = 8192;
 
-        callchain_param.min_percent = strtod(tok, &endptr);
-        if (tok == endptr)
-                return -1;
+                        ret = 0;
+                        callchain_param.record_mode = CALLCHAIN_DWARF;
+                        callchain_param.dump_size = default_stack_dump_size;
 
-        /* get the print limit */
-        tok2 = strtok(NULL, ",");
-        if (!tok2)
-                goto setup;
+                        tok = strtok_r(NULL, ",", &saveptr);
+                        if (tok) {
+                                unsigned long size = 0;
 
-        if (tok2[0] != 'c') {
-                callchain_param.print_limit = strtoul(tok2, &endptr, 0);
-                tok2 = strtok(NULL, ",");
-                if (!tok2)
-                        goto setup;
+                                ret = get_stack_size(tok, &size);
+                                callchain_param.dump_size = size;
+                        }
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
+                } else {
+                        pr_err("callchain: Unknown --call-graph option "
+                               "value: %s\n", arg);
+                        break;
+                }
+
+        } while (0);
+
+        free(buf);
+        return ret;
+}
+
+static int parse_callchain_mode(const char *value)
+{
+        if (!strncmp(value, "graph", strlen(value))) {
+                callchain_param.mode = CHAIN_GRAPH_ABS;
+                return 0;
+        }
+        if (!strncmp(value, "flat", strlen(value))) {
+                callchain_param.mode = CHAIN_FLAT;
+                return 0;
         }
+        if (!strncmp(value, "fractal", strlen(value))) {
+                callchain_param.mode = CHAIN_GRAPH_REL;
+                return 0;
+        }
+        return -1;
+}
 
-        /* get the call chain order */
-        if (!strncmp(tok2, "caller", strlen("caller")))
+static int parse_callchain_order(const char *value)
+{
+        if (!strncmp(value, "caller", strlen(value))) {
                 callchain_param.order = ORDER_CALLER;
-        else if (!strncmp(tok2, "callee", strlen("callee")))
+                return 0;
+        }
+        if (!strncmp(value, "callee", strlen(value))) {
                 callchain_param.order = ORDER_CALLEE;
-        else
-                return -1;
+                return 0;
+        }
+        return -1;
+}
 
-        /* Get the sort key */
-        tok2 = strtok(NULL, ",");
-        if (!tok2)
-                goto setup;
-        if (!strncmp(tok2, "function", strlen("function")))
+static int parse_callchain_sort_key(const char *value)
+{
+        if (!strncmp(value, "function", strlen(value))) {
                 callchain_param.key = CCKEY_FUNCTION;
-        else if (!strncmp(tok2, "address", strlen("address")))
+                return 0;
+        }
+        if (!strncmp(value, "address", strlen(value))) {
                 callchain_param.key = CCKEY_ADDRESS;
-        else
-                return -1;
-setup:
+                return 0;
+        }
+        return -1;
+}
+
+int
+parse_callchain_report_opt(const char *arg)
+{
+        char *tok;
+        char *endptr;
+        bool minpcnt_set = false;
+
+        symbol_conf.use_callchain = true;
+
+        if (!arg)
+                return 0;
+
+        while ((tok = strtok((char *)arg, ",")) != NULL) {
+                if (!strncmp(tok, "none", strlen(tok))) {
+                        callchain_param.mode = CHAIN_NONE;
+                        symbol_conf.use_callchain = false;
+                        return 0;
+                }
+
+                if (!parse_callchain_mode(tok) ||
+                    !parse_callchain_order(tok) ||
+                    !parse_callchain_sort_key(tok)) {
+                        /* parsing ok - move on to the next */
+                } else if (!minpcnt_set) {
+                        /* try to get the min percent */
+                        callchain_param.min_percent = strtod(tok, &endptr);
+                        if (tok == endptr)
+                                return -1;
+                        minpcnt_set = true;
+                } else {
+                        /* try print limit at last */
+                        callchain_param.print_limit = strtoul(tok, &endptr, 0);
+                        if (tok == endptr)
+                                return -1;
+                }
+
+                arg = NULL;
+        }
+
         if (callchain_register_param(&callchain_param) < 0) {
                 pr_err("Can't register callchain params\n");
                 return -1;
@@ -103,6 +198,47 @@ setup:
         return 0;
 }
 
+int perf_callchain_config(const char *var, const char *value)
+{
+        char *endptr;
+
+        if (prefixcmp(var, "call-graph."))
+                return 0;
+        var += sizeof("call-graph.") - 1;
+
+        if (!strcmp(var, "record-mode"))
+                return parse_callchain_record_opt(value);
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+        if (!strcmp(var, "dump-size")) {
+                unsigned long size = 0;
+                int ret;
+
+                ret = get_stack_size(value, &size);
+                callchain_param.dump_size = size;
+
+                return ret;
+        }
+#endif
+        if (!strcmp(var, "print-type"))
+                return parse_callchain_mode(value);
+        if (!strcmp(var, "order"))
+                return parse_callchain_order(value);
+        if (!strcmp(var, "sort-key"))
+                return parse_callchain_sort_key(value);
+        if (!strcmp(var, "threshold")) {
+                callchain_param.min_percent = strtod(value, &endptr);
+                if (value == endptr)
+                        return -1;
+        }
+        if (!strcmp(var, "print-limit")) {
+                callchain_param.print_limit = strtod(value, &endptr);
+                if (value == endptr)
+                        return -1;
+        }
+
+        return 0;
+}
+
 static void
 rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
                     enum chain_mode mode)
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index da43619d6173..94cfefddf4db 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -54,6 +54,9 @@ enum chain_key {
 };
 
 struct callchain_param {
+        bool                    enabled;
+        enum perf_call_graph_mode record_mode;
+        u32                     dump_size;
         enum chain_mode         mode;
         u32                     print_limit;
         double                  min_percent;
@@ -62,6 +65,8 @@ struct callchain_param {
         enum chain_key          key;
 };
 
+extern struct callchain_param callchain_param;
+
 struct callchain_list {
         u64                     ip;
         struct map_symbol       ms;
@@ -154,7 +159,6 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
 struct option;
 struct hist_entry;
 
-int record_parse_callchain(const char *arg, struct record_opts *opts);
 int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
 int record_callchain_opt(const struct option *opt, const char *arg, int unset);
 
@@ -166,7 +170,9 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *
                         bool hide_unresolved);
 
 extern const char record_callchain_help[];
+int parse_callchain_record_opt(const char *arg);
 int parse_callchain_report_opt(const char *arg);
+int perf_callchain_config(const char *var, const char *value);
 
 static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
                                              struct callchain_cursor *src)
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index c5d05ec17220..47b78b3f0325 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -1,7 +1,9 @@
+#include <sched.h>
 #include "util.h"
 #include "../perf.h"
 #include "cloexec.h"
 #include "asm/bug.h"
+#include "debug.h"
 
 static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
 
@@ -9,15 +11,30 @@ static int perf_flag_probe(void)
 {
         /* use 'safest' configuration as used in perf_evsel__fallback() */
         struct perf_event_attr attr = {
-                .type = PERF_COUNT_SW_CPU_CLOCK,
+                .type = PERF_TYPE_SOFTWARE,
                 .config = PERF_COUNT_SW_CPU_CLOCK,
+                .exclude_kernel = 1,
         };
         int fd;
         int err;
+        int cpu;
+        pid_t pid = -1;
+        char sbuf[STRERR_BUFSIZE];
 
-        /* check cloexec flag */
-        fd = sys_perf_event_open(&attr, 0, -1, -1,
-                                 PERF_FLAG_FD_CLOEXEC);
+        cpu = sched_getcpu();
+        if (cpu < 0)
+                cpu = 0;
+
+        while (1) {
+                /* check cloexec flag */
+                fd = sys_perf_event_open(&attr, pid, cpu, -1,
+                                         PERF_FLAG_FD_CLOEXEC);
+                if (fd < 0 && pid == -1 && errno == EACCES) {
+                        pid = 0;
+                        continue;
+                }
+                break;
+        }
         err = errno;
 
         if (fd >= 0) {
@@ -25,17 +42,17 @@ static int perf_flag_probe(void)
                 return 1;
         }
 
-        WARN_ONCE(err != EINVAL,
+        WARN_ONCE(err != EINVAL && err != EBUSY,
                   "perf_event_open(..., PERF_FLAG_FD_CLOEXEC) failed with unexpected error %d (%s)\n",
-                  err, strerror(err));
+                  err, strerror_r(err, sbuf, sizeof(sbuf)));
 
         /* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */
-        fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+        fd = sys_perf_event_open(&attr, pid, cpu, -1, 0);
         err = errno;
 
-        if (WARN_ONCE(fd < 0,
+        if (WARN_ONCE(fd < 0 && err != EBUSY,
                       "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n",
-                      err, strerror(err)))
+                      err, strerror_r(err, sbuf, sizeof(sbuf))))
                 return -1;
 
         close(fd);
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 87b8672eb413..f4654183d391 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -335,3 +335,19 @@ int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...)
         va_end(args);
         return value_color_snprintf(bf, size, fmt, percent);
 }
+
+int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...)
+{
+        va_list args;
+        int len;
+        double percent;
+        const char *color;
+
+        va_start(args, fmt);
+        len = va_arg(args, int);
+        percent = va_arg(args, double);
+        va_end(args);
+
+        color = get_percent_color(percent);
+        return color_snprintf(bf, size, color, fmt, len, percent);
+}
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index 7ff30a62a132..0a594b8a0c26 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -41,6 +41,7 @@ int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
 int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
 int value_color_snprintf(char *bf, size_t size, const char *fmt, double value);
 int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...);
+int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...);
 int percent_color_fprintf(FILE *fp, const char *fmt, double percent);
 const char *get_percent_color(double percent);
 
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index f9e777629e21..b2bb59df65e1 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -74,7 +74,7 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
         return new;
 }
 
-struct comm *comm__new(const char *str, u64 timestamp)
+struct comm *comm__new(const char *str, u64 timestamp, bool exec)
 {
         struct comm *comm = zalloc(sizeof(*comm));
 
@@ -82,6 +82,7 @@ struct comm *comm__new(const char *str, u64 timestamp)
                 return NULL;
 
         comm->start = timestamp;
+        comm->exec = exec;
 
         comm->comm_str = comm_str__findnew(str, &comm_str_root);
         if (!comm->comm_str) {
@@ -94,7 +95,7 @@ struct comm *comm__new(const char *str, u64 timestamp)
         return comm;
 }
 
-int comm__override(struct comm *comm, const char *str, u64 timestamp)
+int comm__override(struct comm *comm, const char *str, u64 timestamp, bool exec)
 {
         struct comm_str *new, *old = comm->comm_str;
 
@@ -106,6 +107,8 @@ int comm__override(struct comm *comm, const char *str, u64 timestamp)
         comm_str__put(old);
         comm->comm_str = new;
         comm->start = timestamp;
+        if (exec)
+                comm->exec = true;
 
         return 0;
 }
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
index fac5bd51befc..51c10ab257f8 100644
--- a/tools/perf/util/comm.h
+++ b/tools/perf/util/comm.h
@@ -11,11 +11,13 @@ struct comm {
         struct comm_str *comm_str;
         u64 start;
         struct list_head list;
+        bool exec;
 };
 
 void comm__free(struct comm *comm);
-struct comm *comm__new(const char *str, u64 timestamp);
+struct comm *comm__new(const char *str, u64 timestamp, bool exec);
 const char *comm__str(const struct comm *comm);
-int comm__override(struct comm *comm, const char *str, u64 timestamp);
+int comm__override(struct comm *comm, const char *str, u64 timestamp,
+                   bool exec);
 
 #endif  /* __PERF_COMM_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 1e5e2e5af6b1..57ff826f150b 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -222,7 +222,8 @@ static int perf_parse_file(config_fn_t fn, void *data)
         const unsigned char *bomptr = utf8_bom;
 
         for (;;) {
-                int c = get_next_char();
+                int line, c = get_next_char();
+
                 if (bomptr && *bomptr) {
                         /* We are at the file beginning; skip UTF8-encoded BOM
                          * if present. Sane editors won't put this in on their
@@ -261,8 +262,16 @@ static int perf_parse_file(config_fn_t fn, void *data)
                 if (!isalpha(c))
                         break;
                 var[baselen] = tolower(c);
-                if (get_value(fn, data, var, baselen+1) < 0)
+
+                /*
+                 * The get_value function might or might not reach the '\n',
+                 * so saving the current line number for error reporting.
+                 */
+                line = config_linenr;
+                if (get_value(fn, data, var, baselen+1) < 0) {
+                        config_linenr = line;
                         break;
+                }
         }
         die("bad config file line %d in %s", config_linenr, config_file_name);
 }
@@ -286,6 +295,21 @@ static int parse_unit_factor(const char *end, unsigned long *val)
         return 0;
 }
 
+static int perf_parse_llong(const char *value, long long *ret)
+{
+        if (value && *value) {
+                char *end;
+                long long val = strtoll(value, &end, 0);
+                unsigned long factor = 1;
+
+                if (!parse_unit_factor(end, &factor))
+                        return 0;
+                *ret = val * factor;
+                return 1;
+        }
+        return 0;
+}
+
 static int perf_parse_long(const char *value, long *ret)
 {
         if (value && *value) {
@@ -307,6 +331,15 @@ static void die_bad_config(const char *name)
         die("bad config value for '%s'", name);
 }
 
+u64 perf_config_u64(const char *name, const char *value)
+{
+        long long ret = 0;
+
+        if (!perf_parse_llong(value, &ret))
+                die_bad_config(name);
+        return (u64) ret;
+}
+
 int perf_config_int(const char *name, const char *value)
 {
         long ret = 0;
@@ -372,6 +405,9 @@ int perf_default_config(const char *var, const char *value,
         if (!prefixcmp(var, "ui."))
                 return perf_ui_config(var, value);
 
+        if (!prefixcmp(var, "call-graph."))
+                return perf_callchain_config(var, value);
+
         /* Add other config variables here. */
         return 0;
 }
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 29d720cf5844..1921942fc2e0 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -50,12 +50,14 @@ static int open_file_read(struct perf_data_file *file)
 {
         struct stat st;
         int fd;
+        char sbuf[STRERR_BUFSIZE];
 
         fd = open(file->path, O_RDONLY);
         if (fd < 0) {
                 int err = errno;
 
-                pr_err("failed to open %s: %s", file->path, strerror(err));
+                pr_err("failed to open %s: %s", file->path,
+                        strerror_r(err, sbuf, sizeof(sbuf)));
                 if (err == ENOENT && !strcmp(file->path, "perf.data"))
                         pr_err("  (try 'perf record' first)");
                 pr_err("\n");
@@ -88,6 +90,7 @@ static int open_file_read(struct perf_data_file *file)
 static int open_file_write(struct perf_data_file *file)
 {
         int fd;
+        char sbuf[STRERR_BUFSIZE];
 
         if (check_backup(file))
                 return -1;
@@ -95,7 +98,8 @@ static int open_file_write(struct perf_data_file *file)
         fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR);
 
         if (fd < 0)
-                pr_err("failed to open %s : %s\n", file->path, strerror(errno));
+                pr_err("failed to open %s : %s\n", file->path,
+                        strerror_r(errno, sbuf, sizeof(sbuf)));
 
         return fd;
 }
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 71d419362634..ba357f3226c6 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -13,8 +13,12 @@
 #include "util.h"
 #include "target.h"
 
+#define NSECS_PER_SEC  1000000000ULL
+#define NSECS_PER_USEC 1000ULL
+
 int verbose;
 bool dump_trace = false, quiet = false;
+int debug_ordered_events;
 
 static int _eprintf(int level, int var, const char *fmt, va_list args)
 {
@@ -42,6 +46,35 @@ int eprintf(int level, int var, const char *fmt, ...)
         return ret;
 }
 
+static int __eprintf_time(u64 t, const char *fmt, va_list args)
+{
+        int ret = 0;
+        u64 secs, usecs, nsecs = t;
+
+        secs   = nsecs / NSECS_PER_SEC;
+        nsecs -= secs  * NSECS_PER_SEC;
+        usecs  = nsecs / NSECS_PER_USEC;
+
+        ret = fprintf(stderr, "[%13" PRIu64 ".%06" PRIu64 "] ",
+                      secs, usecs);
+        ret += vfprintf(stderr, fmt, args);
+        return ret;
+}
+
+int eprintf_time(int level, int var, u64 t, const char *fmt, ...)
+{
+        int ret = 0;
+        va_list args;
+
+        if (var >= level) {
+                va_start(args, fmt);
+                ret = __eprintf_time(t, fmt, args);
+                va_end(args);
+        }
+
+        return ret;
+}
+
 /*
  * Overloading libtraceevent standard info print
  * function, display with -v in perf.
@@ -110,7 +143,8 @@ static struct debug_variable {
         const char *name;
         int *ptr;
 } debug_variables[] = {
-        { .name = "verbose", .ptr = &verbose },
+        { .name = "verbose",            .ptr = &verbose },
+        { .name = "ordered-events",     .ptr = &debug_ordered_events},
         { .name = NULL, }
 };
 
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 89fb6b0f7ab2..be264d6f3b30 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -3,6 +3,7 @@
 #define __PERF_DEBUG_H
 
 #include <stdbool.h>
+#include <string.h>
 #include "event.h"
 #include "../ui/helpline.h"
 #include "../ui/progress.h"
@@ -10,6 +11,7 @@
 
 extern int verbose;
 extern bool quiet, dump_trace;
+extern int debug_ordered_events;
 
 #ifndef pr_fmt
 #define pr_fmt(fmt) fmt
@@ -29,6 +31,14 @@ extern bool quiet, dump_trace;
 #define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
 
+#define pr_time_N(n, var, t, fmt, ...) \
+        eprintf_time(n, var, t, fmt, ##__VA_ARGS__)
+
+#define pr_oe_time(t, fmt, ...)  pr_time_N(1, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_oe_time2(t, fmt, ...) pr_time_N(2, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
+
+#define STRERR_BUFSIZE  128     /* For the buffer size of strerror_r */
+
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(union perf_event *event);
 
@@ -38,6 +48,7 @@ int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
 void pr_stat(const char *fmt, ...);
 
 int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4)));
+int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__((format(printf, 4, 5)));
 
 int perf_debug_option(const char *str);
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 90d02c661dd4..0247acfdfaca 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -37,6 +37,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
 {
         char build_id_hex[BUILD_ID_SIZE * 2 + 1];
         int ret = 0;
+        size_t len;
 
         switch (type) {
         case DSO_BINARY_TYPE__DEBUGLINK: {
@@ -60,26 +61,25 @@ int dso__read_binary_type_filename(const struct dso *dso,
                 break;
 
         case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
-                snprintf(filename, size, "%s/usr/lib/debug%s.debug",
-                         symbol_conf.symfs, dso->long_name);
+                len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
+                snprintf(filename + len, size - len, "%s.debug", dso->long_name);
                 break;
 
         case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
-                snprintf(filename, size, "%s/usr/lib/debug%s",
-                         symbol_conf.symfs, dso->long_name);
+                len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
+                snprintf(filename + len, size - len, "%s", dso->long_name);
                 break;
 
         case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
         {
                 const char *last_slash;
-                size_t len;
                 size_t dir_size;
 
                 last_slash = dso->long_name + dso->long_name_len;
                 while (last_slash != dso->long_name && *last_slash != '/')
                         last_slash--;
 
-                len = scnprintf(filename, size, "%s", symbol_conf.symfs);
+                len = __symbol__join_symfs(filename, size, "");
                 dir_size = last_slash - dso->long_name + 2;
                 if (dir_size > (size - len)) {
                         ret = -1;
@@ -100,26 +100,24 @@ int dso__read_binary_type_filename(const struct dso *dso,
                 build_id__sprintf(dso->build_id,
                                   sizeof(dso->build_id),
                                   build_id_hex);
-                snprintf(filename, size,
-                         "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
-                         symbol_conf.symfs, build_id_hex, build_id_hex + 2);
+                len = __symbol__join_symfs(filename, size, "/usr/lib/debug/.build-id/");
+                snprintf(filename + len, size - len, "%.2s/%s.debug",
+                         build_id_hex, build_id_hex + 2);
                 break;
 
         case DSO_BINARY_TYPE__VMLINUX:
         case DSO_BINARY_TYPE__GUEST_VMLINUX:
         case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
-                snprintf(filename, size, "%s%s",
-                         symbol_conf.symfs, dso->long_name);
+                __symbol__join_symfs(filename, size, dso->long_name);
                 break;
 
         case DSO_BINARY_TYPE__GUEST_KMODULE:
-                snprintf(filename, size, "%s%s%s", symbol_conf.symfs,
-                         root_dir, dso->long_name);
+                path__join3(filename, size, symbol_conf.symfs,
+                            root_dir, dso->long_name);
                 break;
 
         case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
-                snprintf(filename, size, "%s%s", symbol_conf.symfs,
-                         dso->long_name);
+                __symbol__join_symfs(filename, size, dso->long_name);
                 break;
 
         case DSO_BINARY_TYPE__KCORE:
@@ -164,13 +162,15 @@ static void close_first_dso(void);
 static int do_open(char *name)
 {
         int fd;
+        char sbuf[STRERR_BUFSIZE];
 
         do {
                 fd = open(name, O_RDONLY);
                 if (fd >= 0)
                         return fd;
 
-                pr_debug("dso open failed, mmap: %s\n", strerror(errno));
+                pr_debug("dso open failed, mmap: %s\n",
+                         strerror_r(errno, sbuf, sizeof(sbuf)));
                 if (!dso__data_open_cnt || errno != EMFILE)
                         break;
 
@@ -532,10 +532,12 @@ static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 static int data_file_size(struct dso *dso)
 {
         struct stat st;
+        char sbuf[STRERR_BUFSIZE];
 
         if (!dso->data.file_size) {
                 if (fstat(dso->data.fd, &st)) {
-                        pr_err("dso mmap failed, fstat: %s\n", strerror(errno));
+                        pr_err("dso mmap failed, fstat: %s\n",
+                                strerror_r(errno, sbuf, sizeof(sbuf)));
                         return -1;
                 }
                 dso->data.file_size = st.st_size;
@@ -651,6 +653,65 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
         return dso;
 }
 
+/*
+ * Find a matching entry and/or link current entry to RB tree.
+ * Either one of the dso or name parameter must be non-NULL or the
+ * function will not work.
+ */
+static struct dso *dso__findlink_by_longname(struct rb_root *root,
+                                             struct dso *dso, const char *name)
+{
+        struct rb_node **p = &root->rb_node;
+        struct rb_node  *parent = NULL;
+
+        if (!name)
+                name = dso->long_name;
+        /*
+         * Find node with the matching name
+         */
+        while (*p) {
+                struct dso *this = rb_entry(*p, struct dso, rb_node);
+                int rc = strcmp(name, this->long_name);
+
+                parent = *p;
+                if (rc == 0) {
+                        /*
+                         * In case the new DSO is a duplicate of an existing
+                         * one, print an one-time warning & put the new entry
+                         * at the end of the list of duplicates.
+                         */
+                        if (!dso || (dso == this))
+                                return this;    /* Find matching dso */
+                        /*
+                         * The core kernel DSOs may have duplicated long name.
+                         * In this case, the short name should be different.
+                         * Comparing the short names to differentiate the DSOs.
+                         */
+                        rc = strcmp(dso->short_name, this->short_name);
+                        if (rc == 0) {
+                                pr_err("Duplicated dso name: %s\n", name);
+                                return NULL;
+                        }
+                }
+                if (rc < 0)
+                        p = &parent->rb_left;
+                else
+                        p = &parent->rb_right;
+        }
+        if (dso) {
+                /* Add new node and rebalance tree */
+                rb_link_node(&dso->rb_node, parent, p);
+                rb_insert_color(&dso->rb_node, root);
+        }
+        return NULL;
+}
+
+static inline struct dso *
+dso__find_by_longname(const struct rb_root *root, const char *name)
+{
+        return dso__findlink_by_longname((struct rb_root *)root, NULL, name);
+}
+
 void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
 {
         if (name == NULL)
@@ -753,6 +814,7 @@ struct dso *dso__new(const char *name)
                 dso->a2l_fails = 1;
                 dso->kernel = DSO_TYPE_USER;
                 dso->needs_swap = DSO_SWAP__UNSET;
+                RB_CLEAR_NODE(&dso->rb_node);
                 INIT_LIST_HEAD(&dso->node);
                 INIT_LIST_HEAD(&dso->data.open_entry);
         }
@@ -763,6 +825,10 @@ struct dso *dso__new(const char *name)
 void dso__delete(struct dso *dso)
 {
         int i;
+
+        if (!RB_EMPTY_NODE(&dso->rb_node))
+                pr_err("DSO %s is still in rbtree when being deleted!\n",
+                       dso->long_name);
         for (i = 0; i < MAP__NR_TYPES; ++i)
                 symbols__delete(&dso->symbols[i]);
 
@@ -849,35 +915,34 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
         return have_build_id;
 }
 
-void dsos__add(struct list_head *head, struct dso *dso)
+void dsos__add(struct dsos *dsos, struct dso *dso)
 {
-        list_add_tail(&dso->node, head);
+        list_add_tail(&dso->node, &dsos->head);
+        dso__findlink_by_longname(&dsos->root, dso, NULL);
 }
 
-struct dso *dsos__find(const struct list_head *head, const char *name, bool cmp_short)
+struct dso *dsos__find(const struct dsos *dsos, const char *name,
+                       bool cmp_short)
 {
         struct dso *pos;
 
         if (cmp_short) {
-                list_for_each_entry(pos, head, node)
+                list_for_each_entry(pos, &dsos->head, node)
                         if (strcmp(pos->short_name, name) == 0)
                                 return pos;
                 return NULL;
         }
-        list_for_each_entry(pos, head, node)
-                if (strcmp(pos->long_name, name) == 0)
-                        return pos;
-        return NULL;
+        return dso__find_by_longname(&dsos->root, name);
 }
 
-struct dso *__dsos__findnew(struct list_head *head, const char *name)
+struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
 {
-        struct dso *dso = dsos__find(head, name, false);
+        struct dso *dso = dsos__find(dsos, name, false);
 
         if (!dso) {
                 dso = dso__new(name);
                 if (dso != NULL) {
-                        dsos__add(head, dso);
+                        dsos__add(dsos, dso);
                         dso__set_basename(dso);
                 }
         }
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 5e463c0964d4..acb651acc7fd 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -90,8 +90,18 @@ struct dso_cache {
         char data[0];
 };
 
+/*
+ * DSOs are put into both a list for fast iteration and rbtree for fast
+ * long name lookup.
+ */
+struct dsos {
+        struct list_head head;
+        struct rb_root   root;  /* rbtree root sorted by long name */
+};
+
 struct dso {
         struct list_head node;
+        struct rb_node   rb_node;       /* rbtree node sorted by long name */
         struct rb_root   symbols[MAP__NR_TYPES];
         struct rb_root   symbol_names[MAP__NR_TYPES];
         void             *a2l;
@@ -224,10 +234,10 @@ struct map *dso__new_map(const char *name);
 struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
                                 const char *short_name, int dso_type);
 
-void dsos__add(struct list_head *head, struct dso *dso);
-struct dso *dsos__find(const struct list_head *head, const char *name,
+void dsos__add(struct dsos *dsos, struct dso *dso);
+struct dso *dsos__find(const struct dsos *dsos, const char *name,
                        bool cmp_short);
-struct dso *__dsos__findnew(struct list_head *head, const char *name);
+struct dso *__dsos__findnew(struct dsos *dsos, const char *name);
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
 
 size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 1398c83d896d..4af6b279e34a 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -558,13 +558,17 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
         struct map *map;
         struct kmap *kmap;
         int err;
+        union perf_event *event;
+
+        if (machine->vmlinux_maps[0] == NULL)
+                return -1;
+
         /*
          * We should get this from /sys/kernel/sections/.text, but till that is
          * available use this, and after it is use this as a fallback for older
          * kernels.
          */
-        union perf_event *event = zalloc((sizeof(event->mmap) +
-                                          machine->id_hdr_size));
+        event = zalloc((sizeof(event->mmap) + machine->id_hdr_size));
         if (event == NULL) {
                 pr_debug("Not enough memory synthesizing mmap event "
                          "for kernel modules\n");
@@ -784,9 +788,9 @@ try_again:
                  * "[vdso]" dso, but for now lets use the old trick of looking
                  * in the whole kernel symbol list.
                  */
-                if ((long long)al->addr < 0 &&
-                    cpumode == PERF_RECORD_MISC_USER &&
-                    machine && mg != &machine->kmaps) {
+                if (cpumode == PERF_RECORD_MISC_USER && machine &&
+                    mg != &machine->kmaps &&
+                    machine__kernel_ip(machine, al->addr)) {
                         mg = &machine->kmaps;
                         load_map = true;
                         goto try_again;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 94d6976180da..5699e7e2a790 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -156,6 +156,8 @@ struct perf_sample {
         u32 cpu;
         u32 raw_size;
         u64 data_src;
+        u32 flags;
+        u16 insn_len;
         void *raw_data;
         struct ip_callchain *callchain;
         struct branch_stack *branch_stack;
@@ -188,6 +190,32 @@ enum perf_user_event_type { /* above any possible kernel type */
         PERF_RECORD_HEADER_MAX
 };
 
+/*
+ * The kernel collects the number of events it couldn't send in a stretch and
+ * when possible sends this number in a PERF_RECORD_LOST event. The number of
+ * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while
+ * total_lost tells exactly how many events the kernel in fact lost, i.e. it is
+ * the sum of all struct lost_event.lost fields reported.
+ *
+ * The total_period is needed because by default auto-freq is used, so
+ * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
+ * the total number of low level events, it is necessary to to sum all struct
+ * sample_event.period and stash the result in total_period.
+ */
+struct events_stats {
+        u64 total_period;
+        u64 total_non_filtered_period;
+        u64 total_lost;
+        u64 total_invalid_chains;
+        u32 nr_events[PERF_RECORD_HEADER_MAX];
+        u32 nr_non_filtered_samples;
+        u32 nr_lost_warned;
+        u32 nr_unknown_events;
+        u32 nr_invalid_chains;
+        u32 nr_unknown_id;
+        u32 nr_unprocessable_samples;
+};
+
 struct attr_event {
         struct perf_event_header header;
         struct perf_event_attr attr;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 814e954c1318..3c9e77d6b4c2 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -25,6 +25,9 @@
 #include <linux/bitops.h>
 #include <linux/hash.h>
 
+static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx);
+static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx);
+
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
 
@@ -37,6 +40,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
                 INIT_HLIST_HEAD(&evlist->heads[i]);
         INIT_LIST_HEAD(&evlist->entries);
         perf_evlist__set_maps(evlist, cpus, threads);
+        fdarray__init(&evlist->pollfd, 64);
         evlist->workload.pid = -1;
 }
 
@@ -102,7 +106,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
         zfree(&evlist->mmap);
-        zfree(&evlist->pollfd);
+        fdarray__exit(&evlist->pollfd);
 }
 
 void perf_evlist__delete(struct perf_evlist *evlist)
@@ -122,6 +126,7 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 {
         list_add_tail(&entry->node, &evlist->entries);
         entry->idx = evlist->nr_entries;
+        entry->tracking = !entry->idx;
 
         if (!evlist->nr_entries++)
                 perf_evlist__set_id_pos(evlist);
@@ -265,17 +270,27 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist,
         return 0;
 }
 
+static int perf_evlist__nr_threads(struct perf_evlist *evlist,
+                                   struct perf_evsel *evsel)
+{
+        if (evsel->system_wide)
+                return 1;
+        else
+                return thread_map__nr(evlist->threads);
+}
+
 void perf_evlist__disable(struct perf_evlist *evlist)
 {
         int cpu, thread;
         struct perf_evsel *pos;
         int nr_cpus = cpu_map__nr(evlist->cpus);
-        int nr_threads = thread_map__nr(evlist->threads);
+        int nr_threads;
 
         for (cpu = 0; cpu < nr_cpus; cpu++) {
                 evlist__for_each(evlist, pos) {
                         if (!perf_evsel__is_group_leader(pos) || !pos->fd)
                                 continue;
+                        nr_threads = perf_evlist__nr_threads(evlist, pos);
                         for (thread = 0; thread < nr_threads; thread++)
                                 ioctl(FD(pos, cpu, thread),
                                       PERF_EVENT_IOC_DISABLE, 0);
@@ -288,12 +303,13 @@ void perf_evlist__enable(struct perf_evlist *evlist)
         int cpu, thread;
         struct perf_evsel *pos;
         int nr_cpus = cpu_map__nr(evlist->cpus);
-        int nr_threads = thread_map__nr(evlist->threads);
+        int nr_threads;
 
         for (cpu = 0; cpu < nr_cpus; cpu++) {
                 evlist__for_each(evlist, pos) {
                         if (!perf_evsel__is_group_leader(pos) || !pos->fd)
                                 continue;
+                        nr_threads = perf_evlist__nr_threads(evlist, pos);
                         for (thread = 0; thread < nr_threads; thread++)
                                 ioctl(FD(pos, cpu, thread),
                                       PERF_EVENT_IOC_ENABLE, 0);
@@ -305,12 +321,14 @@ int perf_evlist__disable_event(struct perf_evlist *evlist,
                                struct perf_evsel *evsel)
 {
         int cpu, thread, err;
+        int nr_cpus = cpu_map__nr(evlist->cpus);
+        int nr_threads = perf_evlist__nr_threads(evlist, evsel);
 
         if (!evsel->fd)
                 return 0;
 
-        for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
-                for (thread = 0; thread < evlist->threads->nr; thread++) {
+        for (cpu = 0; cpu < nr_cpus; cpu++) {
+                for (thread = 0; thread < nr_threads; thread++) {
                         err = ioctl(FD(evsel, cpu, thread),
                                     PERF_EVENT_IOC_DISABLE, 0);
                         if (err)
@@ -324,12 +342,14 @@ int perf_evlist__enable_event(struct perf_evlist *evlist,
                               struct perf_evsel *evsel)
 {
         int cpu, thread, err;
+        int nr_cpus = cpu_map__nr(evlist->cpus);
+        int nr_threads = perf_evlist__nr_threads(evlist, evsel);
 
         if (!evsel->fd)
                 return -EINVAL;
 
-        for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
-                for (thread = 0; thread < evlist->threads->nr; thread++) {
+        for (cpu = 0; cpu < nr_cpus; cpu++) {
+                for (thread = 0; thread < nr_threads; thread++) {
                         err = ioctl(FD(evsel, cpu, thread),
                                     PERF_EVENT_IOC_ENABLE, 0);
                         if (err)
@@ -339,21 +359,111 @@ int perf_evlist__enable_event(struct perf_evlist *evlist,
         return 0;
 }
 
-static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
+static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist,
+                                         struct perf_evsel *evsel, int cpu)
+{
+        int thread, err;
+        int nr_threads = perf_evlist__nr_threads(evlist, evsel);
+
+        if (!evsel->fd)
+                return -EINVAL;
+
+        for (thread = 0; thread < nr_threads; thread++) {
+                err = ioctl(FD(evsel, cpu, thread),
+                            PERF_EVENT_IOC_ENABLE, 0);
+                if (err)
+                        return err;
+        }
+        return 0;
+}
+
+static int perf_evlist__enable_event_thread(struct perf_evlist *evlist,
+                                            struct perf_evsel *evsel,
+                                            int thread)
+{
+        int cpu, err;
+        int nr_cpus = cpu_map__nr(evlist->cpus);
+
+        if (!evsel->fd)
+                return -EINVAL;
+
+        for (cpu = 0; cpu < nr_cpus; cpu++) {
+                err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0);
+                if (err)
+                        return err;
+        }
+        return 0;
+}
+
+int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
+                                  struct perf_evsel *evsel, int idx)
+{
+        bool per_cpu_mmaps = !cpu_map__empty(evlist->cpus);
+
+        if (per_cpu_mmaps)
+                return perf_evlist__enable_event_cpu(evlist, evsel, idx);
+        else
+                return perf_evlist__enable_event_thread(evlist, evsel, idx);
+}
+
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
         int nr_cpus = cpu_map__nr(evlist->cpus);
         int nr_threads = thread_map__nr(evlist->threads);
-        int nfds = nr_cpus * nr_threads * evlist->nr_entries;
-        evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
-        return evlist->pollfd != NULL ? 0 : -ENOMEM;
+        int nfds = 0;
+        struct perf_evsel *evsel;
+
+        list_for_each_entry(evsel, &evlist->entries, node) {
+                if (evsel->system_wide)
+                        nfds += nr_cpus;
+                else
+                        nfds += nr_cpus * nr_threads;
+        }
+
+        if (fdarray__available_entries(&evlist->pollfd) < nfds &&
+            fdarray__grow(&evlist->pollfd, nfds) < 0)
+                return -ENOMEM;
+
+        return 0;
+}
+
+static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx)
+{
+        int pos = fdarray__add(&evlist->pollfd, fd, POLLIN | POLLERR | POLLHUP);
+        /*
+         * Save the idx so that when we filter out fds POLLHUP'ed we can
+         * close the associated evlist->mmap[] entry.
+         */
+        if (pos >= 0) {
+                evlist->pollfd.priv[pos].idx = idx;
+
+                fcntl(fd, F_SETFL, O_NONBLOCK);
+        }
+
+        return pos;
+}
+
+int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
+{
+        return __perf_evlist__add_pollfd(evlist, fd, -1);
+}
+
+static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd)
+{
+        struct perf_evlist *evlist = container_of(fda, struct perf_evlist, pollfd);
+
+        perf_evlist__mmap_put(evlist, fda->priv[fd].idx);
+}
+
+int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask)
+{
+        return fdarray__filter(&evlist->pollfd, revents_and_mask,
+                               perf_evlist__munmap_filtered);
 }
 
-void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
+int perf_evlist__poll(struct perf_evlist *evlist, int timeout)
 {
-        fcntl(fd, F_SETFL, O_NONBLOCK);
-        evlist->pollfd[evlist->nr_fds].fd = fd;
-        evlist->pollfd[evlist->nr_fds].events = POLLIN;
-        evlist->nr_fds++;
+        return fdarray__poll(&evlist->pollfd, timeout);
 }
 
 static void perf_evlist__id_hash(struct perf_evlist *evlist,
@@ -566,14 +676,36 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
         return event;
 }
 
+static bool perf_mmap__empty(struct perf_mmap *md)
+{
+        return perf_mmap__read_head(md) != md->prev;
+}
+
+static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
+{
+        ++evlist->mmap[idx].refcnt;
+}
+
+static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
+{
+        BUG_ON(evlist->mmap[idx].refcnt == 0);
+
+        if (--evlist->mmap[idx].refcnt == 0)
+                __perf_evlist__munmap(evlist, idx);
+}
+
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 {
+        struct perf_mmap *md = &evlist->mmap[idx];
+
         if (!evlist->overwrite) {
-                struct perf_mmap *md = &evlist->mmap[idx];
                 unsigned int old = md->prev;
 
                 perf_mmap__write_tail(md, old);
         }
+
+        if (md->refcnt == 1 && perf_mmap__empty(md))
+                perf_evlist__mmap_put(evlist, idx);
 }
 
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
@@ -581,6 +713,7 @@ static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
         if (evlist->mmap[idx].base != NULL) {
                 munmap(evlist->mmap[idx].base, evlist->mmap_len);
                 evlist->mmap[idx].base = NULL;
+                evlist->mmap[idx].refcnt = 0;
         }
 }
 
@@ -614,6 +747,20 @@ struct mmap_params {
 static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
                                struct mmap_params *mp, int fd)
 {
+        /*
+         * The last one will be done at perf_evlist__mmap_consume(), so that we
+         * make sure we don't prevent tools from consuming every last event in
+         * the ring buffer.
+         *
+         * I.e. we can get the POLLHUP meaning that the fd doesn't exist
+         * anymore, but the last events for it are still in the ring buffer,
+         * waiting to be consumed.
+         *
+         * Tools can chose to ignore this at their own discretion, but the
+         * evlist layer can't just drop it when filtering events in
+         * perf_evlist__filter_pollfd().
+         */
+        evlist->mmap[idx].refcnt = 2;
         evlist->mmap[idx].prev = 0;
         evlist->mmap[idx].mask = mp->mask;
         evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
@@ -625,7 +772,6 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
                 return -1;
         }
 
-        perf_evlist__add_pollfd(evlist, fd);
         return 0;
 }
 
@@ -636,7 +782,12 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
         struct perf_evsel *evsel;
 
         evlist__for_each(evlist, evsel) {
-                int fd = FD(evsel, cpu, thread);
+                int fd;
+
+                if (evsel->system_wide && thread)
+                        continue;
+
+                fd = FD(evsel, cpu, thread);
 
                 if (*output == -1) {
                         *output = fd;
@@ -645,6 +796,13 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
                 } else {
                         if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
                                 return -1;
+
+                        perf_evlist__mmap_get(evlist, idx);
+                }
+
+                if (__perf_evlist__add_pollfd(evlist, fd, idx) < 0) {
+                        perf_evlist__mmap_put(evlist, idx);
+                        return -1;
                 }
 
                 if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
@@ -804,7 +962,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
         if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
                 return -ENOMEM;
 
-        if (evlist->pollfd == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
+        if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
                 return -ENOMEM;
 
         evlist->overwrite = overwrite;
@@ -845,6 +1003,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 
 out_delete_threads:
         thread_map__delete(evlist->threads);
+        evlist->threads = NULL;
         return -1;
 }
 
@@ -1017,11 +1176,51 @@ void perf_evlist__close(struct perf_evlist *evlist)
         }
 }
 
+static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist)
+{
+        int err = -ENOMEM;
+
+        /*
+         * Try reading /sys/devices/system/cpu/online to get
+         * an all cpus map.
+         *
+         * FIXME: -ENOMEM is the best we can do here, the cpu_map
+         * code needs an overhaul to properly forward the
+         * error, and we may not want to do that fallback to a
+         * default cpu identity map :-\
+         */
+        evlist->cpus = cpu_map__new(NULL);
+        if (evlist->cpus == NULL)
+                goto out;
+
+        evlist->threads = thread_map__new_dummy();
+        if (evlist->threads == NULL)
+                goto out_free_cpus;
+
+        err = 0;
+out:
+        return err;
+out_free_cpus:
+        cpu_map__delete(evlist->cpus);
+        evlist->cpus = NULL;
+        goto out;
+}
+
 int perf_evlist__open(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
         int err;
 
+        /*
+         * Default: one fd per CPU, all threads, aka systemwide
+         * as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL
+         */
+        if (evlist->threads == NULL && evlist->cpus == NULL) {
+                err = perf_evlist__create_syswide_maps(evlist);
+                if (err < 0)
+                        goto out_err;
+        }
+
         perf_evlist__update_id_pos(evlist);
 
         evlist__for_each(evlist, evsel) {
@@ -1061,6 +1260,8 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
         }
 
         if (!evlist->workload.pid) {
+                int ret;
+
                 if (pipe_output)
                         dup2(2, 1);
 
@@ -1078,8 +1279,22 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
                 /*
                  * Wait until the parent tells us to go.
                  */
-                if (read(go_pipe[0], &bf, 1) == -1)
-                        perror("unable to read pipe");
+                ret = read(go_pipe[0], &bf, 1);
+                /*
+                 * The parent will ask for the execvp() to be performed by
+                 * writing exactly one byte, in workload.cork_fd, usually via
+                 * perf_evlist__start_workload().
+                 *
+                 * For cancelling the workload without actuallin running it,
+                 * the parent will just close workload.cork_fd, without writing
+                 * anything, i.e. read will return zero and we just exit()
+                 * here.
+                 */
+                if (ret != 1) {
+                        if (ret == -1)
+                                perror("unable to read pipe");
+                        exit(ret);
+                }
 
                 execvp(argv[0], (char **)argv);
 
@@ -1102,8 +1317,14 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
                 sigaction(SIGUSR1, &act, NULL);
         }
 
-        if (target__none(target))
+        if (target__none(target)) {
+                if (evlist->threads == NULL) {
+                        fprintf(stderr, "FATAL: evlist->threads need to be set at this point (%s:%d).\n",
+                                __func__, __LINE__);
+                        goto out_close_pipes;
+                }
                 evlist->threads->map[0] = evlist->workload.pid;
+        }
 
         close(child_ready_pipe[1]);
         close(go_pipe[0]);
@@ -1202,7 +1423,7 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
                                int err, char *buf, size_t size)
 {
         int printed, value;
-        char sbuf[128], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+        char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
 
         switch (err) {
         case EACCES:
@@ -1250,3 +1471,19 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 
         list_splice(&move, &evlist->entries);
 }
+
+void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
+                                     struct perf_evsel *tracking_evsel)
+{
+        struct perf_evsel *evsel;
+
+        if (tracking_evsel->tracking)
+                return;
+
+        evlist__for_each(evlist, evsel) {
+                if (evsel != tracking_evsel)
+                        evsel->tracking = false;
+        }
+
+        tracking_evsel->tracking = true;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index f5173cd63693..649b0c597283 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -2,6 +2,7 @@
 #define __PERF_EVLIST_H 1
 
 #include <linux/list.h>
+#include <api/fd/array.h>
 #include <stdio.h>
 #include "../perf.h"
 #include "event.h"
@@ -17,9 +18,15 @@ struct record_opts;
 #define PERF_EVLIST__HLIST_BITS 8
 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
 
+/**
+ * struct perf_mmap - perf's ring buffer mmap details
+ *
+ * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this
+ */
 struct perf_mmap {
         void             *base;
         int              mask;
+        int              refcnt;
         unsigned int     prev;
         char             event_copy[PERF_SAMPLE_MAX_SIZE];
 };
@@ -29,7 +36,6 @@ struct perf_evlist {
         struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
         int              nr_entries;
         int              nr_groups;
-        int              nr_fds;
         int              nr_mmaps;
         size_t           mmap_len;
         int              id_pos;
@@ -40,8 +46,8 @@ struct perf_evlist {
                 pid_t   pid;
         } workload;
         bool             overwrite;
+        struct fdarray   pollfd;
         struct perf_mmap *mmap;
-        struct pollfd    *pollfd;
         struct thread_map *threads;
         struct cpu_map    *cpus;
         struct perf_evsel *selected;
@@ -82,7 +88,11 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
 void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
                          int cpu, int thread, u64 id);
 
-void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
+int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);
+int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask);
+
+int perf_evlist__poll(struct perf_evlist *evlist, int timeout);
 
 struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
 
@@ -107,6 +117,8 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
                                                      void *ucontext));
 int perf_evlist__start_workload(struct perf_evlist *evlist);
 
+struct option;
+
 int perf_evlist__parse_mmap_pages(const struct option *opt,
                                   const char *str,
                                   int unset);
@@ -122,6 +134,8 @@ int perf_evlist__disable_event(struct perf_evlist *evlist,
                                struct perf_evsel *evsel);
 int perf_evlist__enable_event(struct perf_evlist *evlist,
                               struct perf_evsel *evsel);
+int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
+                                  struct perf_evsel *evsel, int idx);
 
 void perf_evlist__set_selected(struct perf_evlist *evlist,
                                struct perf_evsel *evsel);
@@ -262,4 +276,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 #define evlist__for_each_safe(evlist, tmp, evsel) \
         __evlist__for_each_safe(&(evlist)->entries, tmp, evsel)
 
+void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
+                                     struct perf_evsel *tracking_evsel);
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 21a373ebea22..2f9e68025ede 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -15,6 +15,8 @@
 #include <linux/perf_event.h>
 #include <sys/resource.h>
 #include "asm/bug.h"
+#include "callchain.h"
+#include "cgroup.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "util.h"
@@ -32,6 +34,48 @@ static struct {
         bool cloexec;
 } perf_missing_features;
 
+static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused)
+{
+        return 0;
+}
+
+static void perf_evsel__no_extra_fini(struct perf_evsel *evsel __maybe_unused)
+{
+}
+
+static struct {
+        size_t  size;
+        int     (*init)(struct perf_evsel *evsel);
+        void    (*fini)(struct perf_evsel *evsel);
+} perf_evsel__object = {
+        .size = sizeof(struct perf_evsel),
+        .init = perf_evsel__no_extra_init,
+        .fini = perf_evsel__no_extra_fini,
+};
+
+int perf_evsel__object_config(size_t object_size,
+                              int (*init)(struct perf_evsel *evsel),
+                              void (*fini)(struct perf_evsel *evsel))
+{
+
+        if (object_size == 0)
+                goto set_methods;
+
+        if (perf_evsel__object.size > object_size)
+                return -EINVAL;
+
+        perf_evsel__object.size = object_size;
+
+set_methods:
+        if (init != NULL)
+                perf_evsel__object.init = init;
+
+        if (fini != NULL)
+                perf_evsel__object.fini = fini;
+
+        return 0;
+}
+
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
 int __perf_evsel__sample_size(u64 sample_type)
@@ -116,16 +160,6 @@ void perf_evsel__calc_id_pos(struct perf_evsel *evsel)
         evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type);
 }
 
-void hists__init(struct hists *hists)
-{
-        memset(hists, 0, sizeof(*hists));
-        hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
-        hists->entries_in = &hists->entries_in_array[0];
-        hists->entries_collapsed = RB_ROOT;
-        hists->entries = RB_ROOT;
-        pthread_mutex_init(&hists->lock, NULL);
-}
-
 void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
                                   enum perf_event_sample_format bit)
 {
@@ -162,19 +196,20 @@ void perf_evsel__init(struct perf_evsel *evsel,
                       struct perf_event_attr *attr, int idx)
 {
         evsel->idx         = idx;
+        evsel->tracking    = !idx;
         evsel->attr        = *attr;
         evsel->leader      = evsel;
         evsel->unit        = "";
         evsel->scale       = 1.0;
         INIT_LIST_HEAD(&evsel->node);
-        hists__init(&evsel->hists);
+        perf_evsel__object.init(evsel);
         evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
         perf_evsel__calc_id_pos(evsel);
 }
 
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 {
-        struct perf_evsel *evsel = zalloc(sizeof(*evsel));
+        struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
 
         if (evsel != NULL)
                 perf_evsel__init(evsel, attr, idx);
@@ -184,7 +219,7 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 
 struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx)
 {
-        struct perf_evsel *evsel = zalloc(sizeof(*evsel));
+        struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
 
         if (evsel != NULL) {
                 struct perf_event_attr attr = {
@@ -502,20 +537,19 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
 }
 
 static void
-perf_evsel__config_callgraph(struct perf_evsel *evsel,
-                             struct record_opts *opts)
+perf_evsel__config_callgraph(struct perf_evsel *evsel)
 {
         bool function = perf_evsel__is_function_event(evsel);
         struct perf_event_attr *attr = &evsel->attr;
 
         perf_evsel__set_sample_bit(evsel, CALLCHAIN);
 
-        if (opts->call_graph == CALLCHAIN_DWARF) {
+        if (callchain_param.record_mode == CALLCHAIN_DWARF) {
                 if (!function) {
                         perf_evsel__set_sample_bit(evsel, REGS_USER);
                         perf_evsel__set_sample_bit(evsel, STACK_USER);
                         attr->sample_regs_user = PERF_REGS_MASK;
-                        attr->sample_stack_user = opts->stack_dump_size;
+                        attr->sample_stack_user = callchain_param.dump_size;
                         attr->exclude_callchain_user = 1;
                 } else {
                         pr_info("Cannot use DWARF unwind for function trace event,"
@@ -561,7 +595,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 {
         struct perf_evsel *leader = evsel->leader;
         struct perf_event_attr *attr = &evsel->attr;
-        int track = !evsel->idx; /* only the first counter needs these */
+        int track = evsel->tracking;
         bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
 
         attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
@@ -624,8 +658,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
                 attr->mmap_data = track;
         }
 
-        if (opts->call_graph_enabled && !evsel->no_aux_samples)
-                perf_evsel__config_callgraph(evsel, opts);
+        if (callchain_param.enabled && !evsel->no_aux_samples)
+                perf_evsel__config_callgraph(evsel);
 
         if (target__has_cpu(&opts->target))
                 perf_evsel__set_sample_bit(evsel, CPU);
@@ -633,9 +667,12 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
         if (opts->period)
                 perf_evsel__set_sample_bit(evsel, PERIOD);
 
-        if (!perf_missing_features.sample_id_all &&
-            (opts->sample_time || !opts->no_inherit ||
-             target__has_cpu(&opts->target) || per_cpu))
+        /*
+         * When the user explicitely disabled time don't force it here.
+         */
+        if (opts->sample_time &&
+            (!perf_missing_features.sample_id_all &&
+            (!opts->no_inherit || target__has_cpu(&opts->target) || per_cpu)))
                 perf_evsel__set_sample_bit(evsel, TIME);
 
         if (opts->raw_samples && !evsel->no_aux_samples) {
@@ -689,9 +726,13 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
         }
 }
 
-int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
+static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
         int cpu, thread;
+
+        if (evsel->system_wide)
+                nthreads = 1;
+
         evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
 
         if (evsel->fd) {
@@ -710,6 +751,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthrea
 {
         int cpu, thread;
 
+        if (evsel->system_wide)
+                nthreads = 1;
+
         for (cpu = 0; cpu < ncpus; cpu++) {
                 for (thread = 0; thread < nthreads; thread++) {
                         int fd = FD(evsel, cpu, thread),
@@ -740,6 +784,9 @@ int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads)
 
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
+        if (evsel->system_wide)
+                nthreads = 1;
+
         evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
         if (evsel->sample_id == NULL)
                 return -ENOMEM;
@@ -767,13 +814,13 @@ int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
         return evsel->counts != NULL ? 0 : -ENOMEM;
 }
 
-void perf_evsel__free_fd(struct perf_evsel *evsel)
+static void perf_evsel__free_fd(struct perf_evsel *evsel)
 {
         xyarray__delete(evsel->fd);
         evsel->fd = NULL;
 }
 
-void perf_evsel__free_id(struct perf_evsel *evsel)
+static void perf_evsel__free_id(struct perf_evsel *evsel)
 {
         xyarray__delete(evsel->sample_id);
         evsel->sample_id = NULL;
@@ -784,6 +831,9 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
         int cpu, thread;
 
+        if (evsel->system_wide)
+                nthreads = 1;
+
         for (cpu = 0; cpu < ncpus; cpu++)
                 for (thread = 0; thread < nthreads; ++thread) {
                         close(FD(evsel, cpu, thread));
@@ -801,16 +851,17 @@ void perf_evsel__exit(struct perf_evsel *evsel)
         assert(list_empty(&evsel->node));
         perf_evsel__free_fd(evsel);
         perf_evsel__free_id(evsel);
-}
-
-void perf_evsel__delete(struct perf_evsel *evsel)
-{
-        perf_evsel__exit(evsel);
         close_cgroup(evsel->cgrp);
         zfree(&evsel->group_name);
         if (evsel->tp_format)
                 pevent_free_format(evsel->tp_format);
         zfree(&evsel->name);
+        perf_evsel__object.fini(evsel);
+}
+
+void perf_evsel__delete(struct perf_evsel *evsel)
+{
+        perf_evsel__exit(evsel);
         free(evsel);
 }
 
@@ -872,6 +923,9 @@ int __perf_evsel__read(struct perf_evsel *evsel,
         int cpu, thread;
         struct perf_counts_values *aggr = &evsel->counts->aggr, count;
 
+        if (evsel->system_wide)
+                nthreads = 1;
+
         aggr->val = aggr->ena = aggr->run = 0;
 
         for (cpu = 0; cpu < ncpus; cpu++) {
@@ -994,13 +1048,18 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
                               struct thread_map *threads)
 {
-        int cpu, thread;
+        int cpu, thread, nthreads;
         unsigned long flags = PERF_FLAG_FD_CLOEXEC;
         int pid = -1, err;
         enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
 
+        if (evsel->system_wide)
+                nthreads = 1;
+        else
+                nthreads = threads->nr;
+
         if (evsel->fd == NULL &&
-            perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
+            perf_evsel__alloc_fd(evsel, cpus->nr, nthreads) < 0)
                 return -ENOMEM;
 
         if (evsel->cgrp) {
@@ -1024,10 +1083,10 @@ retry_sample_id:
 
         for (cpu = 0; cpu < cpus->nr; cpu++) {
 
-                for (thread = 0; thread < threads->nr; thread++) {
+                for (thread = 0; thread < nthreads; thread++) {
                         int group_fd;
 
-                        if (!evsel->cgrp)
+                        if (!evsel->cgrp && !evsel->system_wide)
                                 pid = threads->map[thread];
 
                         group_fd = get_group_fd(evsel, cpu, thread);
@@ -1100,7 +1159,7 @@ out_close:
                         close(FD(evsel, cpu, thread));
                         FD(evsel, cpu, thread) = -1;
                 }
-                thread = threads->nr;
+                thread = nthreads;
         } while (--cpu >= 0);
         return err;
 }
@@ -2002,6 +2061,8 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
                               int err, char *msg, size_t size)
 {
+        char sbuf[STRERR_BUFSIZE];
+
         switch (err) {
         case EPERM:
         case EACCES:
@@ -2036,13 +2097,20 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
         "No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.");
 #endif
                 break;
+        case EBUSY:
+                if (find_process("oprofiled"))
+                        return scnprintf(msg, size,
+        "The PMU counters are busy/taken by another profiler.\n"
+        "We found oprofile daemon running, please stop it and try again.");
+                break;
         default:
                 break;
         }
 
         return scnprintf(msg, size,
-        "The sys_perf_event_open() syscall returned with %d (%s) for event (%s).  \n"
+        "The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
         "/bin/dmesg may provide additional information.\n"
         "No CONFIG_PERF_EVENTS=y kernel support configured?\n",
-                         err, strerror(err), perf_evsel__name(evsel));
+                         err, strerror_r(err, sbuf, sizeof(sbuf)),
+                         perf_evsel__name(evsel));
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d7f93ce0ebc1..163c5604e5d1 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -7,8 +7,6 @@
 #include <linux/perf_event.h>
 #include <linux/types.h>
 #include "xyarray.h"
-#include "cgroup.h"
-#include "hist.h"
 #include "symbol.h"
 
 struct perf_counts_values {
@@ -43,6 +41,8 @@ struct perf_sample_id {
         u64                     period;
 };
 
+struct cgroup_sel;
+
 /** struct perf_evsel - event selector
  *
  * @name - Can be set to retain the original event name passed by the user,
@@ -66,7 +66,6 @@ struct perf_evsel {
         struct perf_counts      *prev_raw_counts;
         int                     idx;
         u32                     ids;
-        struct hists            hists;
         char                    *name;
         double                  scale;
         const char              *unit;
@@ -85,6 +84,8 @@ struct perf_evsel {
         bool                    needs_swap;
         bool                    no_aux_samples;
         bool                    immediate;
+        bool                    system_wide;
+        bool                    tracking;
         /* parse modifier helper */
         int                     exclude_GH;
         int                     nr_members;
@@ -98,13 +99,16 @@ union u64_swap {
         u32 val32[2];
 };
 
-#define hists_to_evsel(h) container_of(h, struct perf_evsel, hists)
-
 struct cpu_map;
+struct target;
 struct thread_map;
 struct perf_evlist;
 struct record_opts;
 
+int perf_evsel__object_config(size_t object_size,
+                              int (*init)(struct perf_evsel *evsel),
+                              void (*fini)(struct perf_evsel *evsel));
+
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx);
 
 static inline struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr)
@@ -151,12 +155,9 @@ const char *perf_evsel__name(struct perf_evsel *evsel);
 const char *perf_evsel__group_name(struct perf_evsel *evsel);
 int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 
-int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
 void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
-void perf_evsel__free_fd(struct perf_evsel *evsel);
-void perf_evsel__free_id(struct perf_evsel *evsel);
 void perf_evsel__free_counts(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
@@ -279,8 +280,6 @@ static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
         return __perf_evsel__read(evsel, ncpus, nthreads, true);
 }
 
-void hists__init(struct hists *hists);
-
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                              struct perf_sample *sample);
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 158c787ce0c4..26f5b2fe5dc8 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -214,11 +214,11 @@ static int machine__hit_all_dsos(struct machine *machine)
 {
         int err;
 
-        err = __dsos__hit_all(&machine->kernel_dsos);
+        err = __dsos__hit_all(&machine->kernel_dsos.head);
         if (err)
                 return err;
 
-        return __dsos__hit_all(&machine->user_dsos);
+        return __dsos__hit_all(&machine->user_dsos.head);
 }
 
 int dsos__hit_all(struct perf_session *session)
@@ -288,11 +288,12 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
                 umisc = PERF_RECORD_MISC_GUEST_USER;
         }
 
-        err = __dsos__write_buildid_table(&machine->kernel_dsos, machine,
+        err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine,
                                           machine->pid, kmisc, fd);
         if (err == 0)
-                err = __dsos__write_buildid_table(&machine->user_dsos, machine,
-                                                  machine->pid, umisc, fd);
+                err = __dsos__write_buildid_table(&machine->user_dsos.head,
+                                                  machine, machine->pid, umisc,
+                                                  fd);
         return err;
 }
 
@@ -455,9 +456,10 @@ static int __dsos__cache_build_ids(struct list_head *head,
 
 static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
 {
-        int ret = __dsos__cache_build_ids(&machine->kernel_dsos, machine,
+        int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine,
                                           debugdir);
-        ret |= __dsos__cache_build_ids(&machine->user_dsos, machine, debugdir);
+        ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine,
+                                       debugdir);
         return ret;
 }
 
@@ -483,8 +485,10 @@ static int perf_session__cache_build_ids(struct perf_session *session)
 
 static bool machine__read_build_ids(struct machine *machine, bool with_hits)
 {
-        bool ret = __dsos__read_build_ids(&machine->kernel_dsos, with_hits);
-        ret |= __dsos__read_build_ids(&machine->user_dsos, with_hits);
+        bool ret;
+
+        ret  = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits);
+        ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits);
         return ret;
 }
 
@@ -575,16 +579,12 @@ static int write_version(int fd, struct perf_header *h __maybe_unused,
         return do_write_string(fd, perf_version_string);
 }
 
-static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
-                       struct perf_evlist *evlist __maybe_unused)
+static int __write_cpudesc(int fd, const char *cpuinfo_proc)
 {
-#ifndef CPUINFO_PROC
-#define CPUINFO_PROC NULL
-#endif
         FILE *file;
         char *buf = NULL;
         char *s, *p;
-        const char *search = CPUINFO_PROC;
+        const char *search = cpuinfo_proc;
         size_t len = 0;
         int ret = -1;
 
@@ -634,6 +634,25 @@ done:
         return ret;
 }
 
+static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
+                       struct perf_evlist *evlist __maybe_unused)
+{
+#ifndef CPUINFO_PROC
+#define CPUINFO_PROC {"model name", }
+#endif
+        const char *cpuinfo_procs[] = CPUINFO_PROC;
+        unsigned int i;
+
+        for (i = 0; i < ARRAY_SIZE(cpuinfo_procs); i++) {
+                int ret;
+                ret = __write_cpudesc(fd, cpuinfo_procs[i]);
+                if (ret >= 0)
+                        return ret;
+        }
+        return -1;
+}
+
+
 static int write_nrcpus(int fd, struct perf_header *h __maybe_unused,
                         struct perf_evlist *evlist __maybe_unused)
 {
@@ -1548,7 +1567,7 @@ static int __event_process_build_id(struct build_id_event *bev,
                                     struct perf_session *session)
 {
         int err = -1;
-        struct list_head *head;
+        struct dsos *dsos;
         struct machine *machine;
         u16 misc;
         struct dso *dso;
@@ -1563,22 +1582,22 @@ static int __event_process_build_id(struct build_id_event *bev,
         switch (misc) {
         case PERF_RECORD_MISC_KERNEL:
                 dso_type = DSO_TYPE_KERNEL;
-                head = &machine->kernel_dsos;
+                dsos = &machine->kernel_dsos;
                 break;
         case PERF_RECORD_MISC_GUEST_KERNEL:
                 dso_type = DSO_TYPE_GUEST_KERNEL;
-                head = &machine->kernel_dsos;
+                dsos = &machine->kernel_dsos;
                 break;
         case PERF_RECORD_MISC_USER:
         case PERF_RECORD_MISC_GUEST_USER:
                 dso_type = DSO_TYPE_USER;
-                head = &machine->user_dsos;
+                dsos = &machine->user_dsos;
                 break;
         default:
                 goto out;
         }
 
-        dso = __dsos__findnew(head, filename);
+        dso = __dsos__findnew(dsos, filename);
         if (dso != NULL) {
                 char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 30df6187ee02..6e88b9e395df 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -3,6 +3,7 @@
 #include "hist.h"
 #include "session.h"
 #include "sort.h"
+#include "evlist.h"
 #include "evsel.h"
 #include "annotate.h"
 #include <math.h>
@@ -14,13 +15,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists,
 static bool hists__filter_entry_by_symbol(struct hists *hists,
                                           struct hist_entry *he);
 
-struct callchain_param  callchain_param = {
-        .mode   = CHAIN_GRAPH_REL,
-        .min_percent = 0.5,
-        .order  = ORDER_CALLEE,
-        .key    = CCKEY_FUNCTION
-};
-
 u16 hists__col_len(struct hists *hists, enum hist_column col)
 {
         return hists->col_len[col];
@@ -277,6 +271,28 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
         }
 }
 
+void hists__delete_entries(struct hists *hists)
+{
+        struct rb_node *next = rb_first(&hists->entries);
+        struct hist_entry *n;
+
+        while (next) {
+                n = rb_entry(next, struct hist_entry, rb_node);
+                next = rb_next(&n->rb_node);
+
+                rb_erase(&n->rb_node, &hists->entries);
+
+                if (sort__need_collapse)
+                        rb_erase(&n->rb_node_in, &hists->entries_collapsed);
+
+                --hists->nr_entries;
+                if (!n->filtered)
+                        --hists->nr_non_filtered_entries;
+
+                hist_entry__free(n);
+        }
+}
+
 /*
  * histogram, sorted on item, collects periods
  */
@@ -494,6 +510,7 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al
 {
         u64 cost;
         struct mem_info *mi = iter->priv;
+        struct hists *hists = evsel__hists(iter->evsel);
         struct hist_entry *he;
 
         if (mi == NULL)
@@ -510,7 +527,7 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al
          * and this is indirectly achieved by passing period=weight here
          * and the he_stat__add_period() function.
          */
-        he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi,
+        he = __hists__add_entry(hists, al, iter->parent, NULL, mi,
                                 cost, cost, 0, true);
         if (!he)
                 return -ENOMEM;
@@ -524,13 +541,14 @@ iter_finish_mem_entry(struct hist_entry_iter *iter,
                       struct addr_location *al __maybe_unused)
 {
         struct perf_evsel *evsel = iter->evsel;
+        struct hists *hists = evsel__hists(evsel);
         struct hist_entry *he = iter->he;
         int err = -EINVAL;
 
         if (he == NULL)
                 goto out;
 
-        hists__inc_nr_samples(&evsel->hists, he->filtered);
+        hists__inc_nr_samples(hists, he->filtered);
 
         err = hist_entry__append_callchain(he, iter->sample);
 
@@ -596,6 +614,7 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
 {
         struct branch_info *bi;
         struct perf_evsel *evsel = iter->evsel;
+        struct hists *hists = evsel__hists(evsel);
         struct hist_entry *he = NULL;
         int i = iter->curr;
         int err = 0;
@@ -609,12 +628,12 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
          * The report shows the percentage of total branches captured
          * and not events sampled. Thus we use a pseudo period of 1.
          */
-        he = __hists__add_entry(&evsel->hists, al, iter->parent, &bi[i], NULL,
+        he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL,
                                 1, 1, 0, true);
         if (he == NULL)
                 return -ENOMEM;
 
-        hists__inc_nr_samples(&evsel->hists, he->filtered);
+        hists__inc_nr_samples(hists, he->filtered);
 
 out:
         iter->he = he;
@@ -646,7 +665,7 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location
         struct perf_sample *sample = iter->sample;
         struct hist_entry *he;
 
-        he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+        he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
                                 sample->period, sample->weight,
                                 sample->transaction, true);
         if (he == NULL)
@@ -669,7 +688,7 @@ iter_finish_normal_entry(struct hist_entry_iter *iter,
 
         iter->he = NULL;
 
-        hists__inc_nr_samples(&evsel->hists, he->filtered);
+        hists__inc_nr_samples(evsel__hists(evsel), he->filtered);
 
         return hist_entry__append_callchain(he, sample);
 }
@@ -702,12 +721,13 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
                                  struct addr_location *al)
 {
         struct perf_evsel *evsel = iter->evsel;
+        struct hists *hists = evsel__hists(evsel);
         struct perf_sample *sample = iter->sample;
         struct hist_entry **he_cache = iter->priv;
         struct hist_entry *he;
         int err = 0;
 
-        he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+        he = __hists__add_entry(hists, al, iter->parent, NULL, NULL,
                                 sample->period, sample->weight,
                                 sample->transaction, true);
         if (he == NULL)
@@ -724,7 +744,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
          */
         callchain_cursor_commit(&callchain_cursor);
 
-        hists__inc_nr_samples(&evsel->hists, he->filtered);
+        hists__inc_nr_samples(hists, he->filtered);
 
         return err;
 }
@@ -780,7 +800,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
                 }
         }
 
-        he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+        he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
                                 sample->period, sample->weight,
                                 sample->transaction, false);
         if (he == NULL)
@@ -1386,6 +1406,21 @@ int hists__link(struct hists *leader, struct hists *other)
         return 0;
 }
 
+
+size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp)
+{
+        struct perf_evsel *pos;
+        size_t ret = 0;
+
+        evlist__for_each(evlist, pos) {
+                ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
+                ret += events_stats__fprintf(&evsel__hists(pos)->stats, fp);
+        }
+
+        return ret;
+}
+
+
 u64 hists__total_period(struct hists *hists)
 {
         return symbol_conf.filter_relative ? hists->stats.total_non_filtered_period :
@@ -1412,3 +1447,31 @@ int perf_hist_config(const char *var, const char *value)
 
         return 0;
 }
+
+static int hists_evsel__init(struct perf_evsel *evsel)
+{
+        struct hists *hists = evsel__hists(evsel);
+
+        memset(hists, 0, sizeof(*hists));
+        hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
+        hists->entries_in = &hists->entries_in_array[0];
+        hists->entries_collapsed = RB_ROOT;
+        hists->entries = RB_ROOT;
+        pthread_mutex_init(&hists->lock, NULL);
+        return 0;
+}
+
+/*
+ * XXX We probably need a hists_evsel__exit() to free the hist_entries
+ * stored in the rbtree...
+ */
+
+int hists__init(void)
+{
+        int err = perf_evsel__object_config(sizeof(struct hists_evsel),
+                                            hists_evsel__init, NULL);
+        if (err)
+                fputs("FATAL ERROR: Couldn't setup hists class\n", stderr);
+
+        return err;
+}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 742f49a85725..d0ef9a19a744 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -4,12 +4,11 @@
 #include <linux/types.h>
 #include <pthread.h>
 #include "callchain.h"
+#include "evsel.h"
 #include "header.h"
 #include "color.h"
 #include "ui/progress.h"
 
-extern struct callchain_param callchain_param;
-
 struct hist_entry;
 struct addr_location;
 struct symbol;
@@ -23,32 +22,6 @@ enum hist_filter {
         HIST_FILTER__HOST,
 };
 
-/*
- * The kernel collects the number of events it couldn't send in a stretch and
- * when possible sends this number in a PERF_RECORD_LOST event. The number of
- * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while
- * total_lost tells exactly how many events the kernel in fact lost, i.e. it is
- * the sum of all struct lost_event.lost fields reported.
- *
- * The total_period is needed because by default auto-freq is used, so
- * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
- * the total number of low level events, it is necessary to to sum all struct
- * sample_event.period and stash the result in total_period.
- */
-struct events_stats {
-        u64 total_period;
-        u64 total_non_filtered_period;
-        u64 total_lost;
-        u64 total_invalid_chains;
-        u32 nr_events[PERF_RECORD_HEADER_MAX];
-        u32 nr_non_filtered_samples;
-        u32 nr_lost_warned;
-        u32 nr_unknown_events;
-        u32 nr_invalid_chains;
-        u32 nr_unknown_id;
-        u32 nr_unprocessable_samples;
-};
-
 enum hist_column {
         HISTC_SYMBOL,
         HISTC_DSO,
@@ -152,6 +125,7 @@ void hists__output_resort(struct hists *hists);
 void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
+void hists__delete_entries(struct hists *hists);
 void hists__output_recalc_col_len(struct hists *hists, int max_rows);
 
 u64 hists__total_period(struct hists *hists);
@@ -164,6 +138,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
                       int max_cols, float min_pcnt, FILE *fp);
+size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
 
 void hists__filter_by_dso(struct hists *hists);
 void hists__filter_by_thread(struct hists *hists);
@@ -184,6 +159,25 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *he);
 void hists__match(struct hists *leader, struct hists *other);
 int hists__link(struct hists *leader, struct hists *other);
 
+struct hists_evsel {
+        struct perf_evsel evsel;
+        struct hists      hists;
+};
+
+static inline struct perf_evsel *hists_to_evsel(struct hists *hists)
+{
+        struct hists_evsel *hevsel = container_of(hists, struct hists_evsel, hists);
+        return &hevsel->evsel;
+}
+
+static inline struct hists *evsel__hists(struct perf_evsel *evsel)
+{
+        struct hists_evsel *hevsel = (struct hists_evsel *)evsel;
+        return &hevsel->hists;
+}
+
+int hists__init(void);
+
 struct perf_hpp {
         char *buf;
         size_t size;
@@ -192,6 +186,7 @@ struct perf_hpp {
 };
 
 struct perf_hpp_fmt {
+        const char *name;
         int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
                       struct perf_evsel *evsel);
         int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
@@ -207,6 +202,8 @@ struct perf_hpp_fmt {
         struct list_head list;
         struct list_head sort_list;
         bool elide;
+        int len;
+        int user_len;
 };
 
 extern struct list_head perf_hpp__list;
@@ -261,17 +258,19 @@ static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
 }
 
 void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
+void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists);
+void perf_hpp__set_user_width(const char *width_list_str);
 
 typedef u64 (*hpp_field_fn)(struct hist_entry *he);
 typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front);
 typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
 
-int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
-               hpp_field_fn get_field, const char *fmt,
-               hpp_snprint_fn print_fn, bool fmt_percent);
-int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
-                   hpp_field_fn get_field, const char *fmt,
-                   hpp_snprint_fn print_fn, bool fmt_percent);
+int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+             struct hist_entry *he, hpp_field_fn get_field,
+             const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
+int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+                 struct hist_entry *he, hpp_field_fn get_field,
+                 const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
 
 static inline void advance_hpp(struct perf_hpp *hpp, int inc)
 {
diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h
index 97a800738226..6f19c548ecc0 100644
--- a/tools/perf/util/include/linux/string.h
+++ b/tools/perf/util/include/linux/string.h
@@ -1,4 +1,3 @@
 #include <string.h>
 
 void *memdup(const void *src, size_t len);
-int str_append(char **s, int *len, const char *a);
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
index 0b5a8cd2ee79..cf1d7913783b 100644
--- a/tools/perf/util/kvm-stat.h
+++ b/tools/perf/util/kvm-stat.h
@@ -92,7 +92,6 @@ struct perf_kvm_stat {
         u64 lost_events;
         u64 duration;
 
-        const char *pid_str;
         struct intlist *pid_list;
 
         struct rb_root result;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 16bba9fff2c8..34fc7c8672e4 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -13,12 +13,18 @@
 #include <symbol/kallsyms.h>
 #include "unwind.h"
 
+static void dsos__init(struct dsos *dsos)
+{
+        INIT_LIST_HEAD(&dsos->head);
+        dsos->root = RB_ROOT;
+}
+
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
         map_groups__init(&machine->kmaps);
         RB_CLEAR_NODE(&machine->rb_node);
-        INIT_LIST_HEAD(&machine->user_dsos);
-        INIT_LIST_HEAD(&machine->kernel_dsos);
+        dsos__init(&machine->user_dsos);
+        dsos__init(&machine->kernel_dsos);
 
         machine->threads = RB_ROOT;
         INIT_LIST_HEAD(&machine->dead_threads);
@@ -31,6 +37,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
         machine->symbol_filter = NULL;
         machine->id_hdr_size = 0;
+        machine->comm_exec = false;
+        machine->kernel_start = 0;
 
         machine->root_dir = strdup(root_dir);
         if (machine->root_dir == NULL)
@@ -70,11 +78,12 @@ out_delete:
         return NULL;
 }
 
-static void dsos__delete(struct list_head *dsos)
+static void dsos__delete(struct dsos *dsos)
 {
         struct dso *pos, *n;
 
-        list_for_each_entry_safe(pos, n, dsos, node) {
+        list_for_each_entry_safe(pos, n, &dsos->head, node) {
+                RB_CLEAR_NODE(&pos->rb_node);
                 list_del(&pos->node);
                 dso__delete(pos);
         }
@@ -179,6 +188,19 @@ void machines__set_symbol_filter(struct machines *machines,
         }
 }
 
+void machines__set_comm_exec(struct machines *machines, bool comm_exec)
+{
+        struct rb_node *nd;
+
+        machines->host.comm_exec = comm_exec;
+
+        for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+                struct machine *machine = rb_entry(nd, struct machine, rb_node);
+
+                machine->comm_exec = comm_exec;
+        }
+}
+
 struct machine *machines__find(struct machines *machines, pid_t pid)
 {
         struct rb_node **p = &machines->guests.rb_node;
@@ -398,17 +420,31 @@ struct thread *machine__find_thread(struct machine *machine, pid_t pid,
         return __machine__findnew_thread(machine, pid, tid, false);
 }
 
+struct comm *machine__thread_exec_comm(struct machine *machine,
+                                       struct thread *thread)
+{
+        if (machine->comm_exec)
+                return thread__exec_comm(thread);
+        else
+                return thread__comm(thread);
+}
+
 int machine__process_comm_event(struct machine *machine, union perf_event *event,
                                 struct perf_sample *sample)
 {
         struct thread *thread = machine__findnew_thread(machine,
                                                         event->comm.pid,
                                                         event->comm.tid);
+        bool exec = event->header.misc & PERF_RECORD_MISC_COMM_EXEC;
+
+        if (exec)
+                machine->comm_exec = true;
 
         if (dump_trace)
                 perf_event__fprintf_comm(event, stdout);
 
-        if (thread == NULL || thread__set_comm(thread, event->comm.comm, sample->time)) {
+        if (thread == NULL ||
+            __thread__set_comm(thread, event->comm.comm, sample->time, exec)) {
                 dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
                 return -1;
         }
@@ -448,23 +484,23 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
 {
         struct rb_node *nd;
-        size_t ret = __dsos__fprintf(&machines->host.kernel_dsos, fp) +
-                     __dsos__fprintf(&machines->host.user_dsos, fp);
+        size_t ret = __dsos__fprintf(&machines->host.kernel_dsos.head, fp) +
+                     __dsos__fprintf(&machines->host.user_dsos.head, fp);
 
         for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
                 struct machine *pos = rb_entry(nd, struct machine, rb_node);
-                ret += __dsos__fprintf(&pos->kernel_dsos, fp);
-                ret += __dsos__fprintf(&pos->user_dsos, fp);
+                ret += __dsos__fprintf(&pos->kernel_dsos.head, fp);
+                ret += __dsos__fprintf(&pos->user_dsos.head, fp);
         }
 
         return ret;
 }
 
-size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
+size_t machine__fprintf_dsos_buildid(struct machine *m, FILE *fp,
                                      bool (skip)(struct dso *dso, int parm), int parm)
 {
-        return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, skip, parm) +
-               __dsos__fprintf_buildid(&machine->user_dsos, fp, skip, parm);
+        return __dsos__fprintf_buildid(&m->kernel_dsos.head, fp, skip, parm) +
+               __dsos__fprintf_buildid(&m->user_dsos.head, fp, skip, parm);
 }
 
 size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
@@ -565,8 +601,8 @@ const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
  * Returns the name of the start symbol in *symbol_name. Pass in NULL as
  * symbol_name if it's not that important.
  */
-static u64 machine__get_kernel_start_addr(struct machine *machine,
-                                          const char **symbol_name)
+static u64 machine__get_running_kernel_start(struct machine *machine,
+                                             const char **symbol_name)
 {
         char filename[PATH_MAX];
         int i;
@@ -593,7 +629,7 @@ static u64 machine__get_kernel_start_addr(struct machine *machine,
 int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
         enum map_type type;
-        u64 start = machine__get_kernel_start_addr(machine, NULL);
+        u64 start = machine__get_running_kernel_start(machine, NULL);
 
         for (type = 0; type < MAP__NR_TYPES; ++type) {
                 struct kmap *kmap;
@@ -912,7 +948,7 @@ int machine__create_kernel_maps(struct machine *machine)
 {
         struct dso *kernel = machine__get_kernel(machine);
         const char *name;
-        u64 addr = machine__get_kernel_start_addr(machine, &name);
+        u64 addr = machine__get_running_kernel_start(machine, &name);
         if (!addr)
                 return -1;
 
@@ -965,7 +1001,7 @@ static bool machine__uses_kcore(struct machine *machine)
 {
         struct dso *dso;
 
-        list_for_each_entry(dso, &machine->kernel_dsos, node) {
+        list_for_each_entry(dso, &machine->kernel_dsos.head, node) {
                 if (dso__is_kcore(dso))
                         return true;
         }
@@ -1285,6 +1321,16 @@ static void ip__resolve_data(struct machine *machine, struct thread *thread,
 
         thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr,
                                    &al);
+        if (al.map == NULL) {
+                /*
+                 * some shared data regions have execute bit set which puts
+                 * their mapping in the MAP__FUNCTION type array.
+                 * Check there as a fallback option before dropping the sample.
+                 */
+                thread__find_addr_location(thread, machine, m, MAP__FUNCTION, addr,
+                                           &al);
+        }
+
         ams->addr = addr;
         ams->al_addr = al.addr;
         ams->sym = al.sym;
@@ -1531,3 +1577,25 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 
         return 0;
 }
+
+int machine__get_kernel_start(struct machine *machine)
+{
+        struct map *map = machine__kernel_map(machine, MAP__FUNCTION);
+        int err = 0;
+
+        /*
+         * The only addresses above 2^63 are kernel addresses of a 64-bit
+         * kernel.  Note that addresses are unsigned so that on a 32-bit system
+         * all addresses including kernel addresses are less than 2^32.  In
+         * that case (32-bit system), if the kernel mapping is unknown, all
+         * addresses will be assumed to be in user space - see
+         * machine__kernel_ip().
+         */
+        machine->kernel_start = 1ULL << 63;
+        if (map) {
+                err = map__load(map, machine->symbol_filter);
+                if (map->start)
+                        machine->kernel_start = map->start;
+        }
+        return err;
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index b972824e6294..2b651a7f5d0d 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -4,6 +4,7 @@
 #include <sys/types.h>
 #include <linux/rbtree.h>
 #include "map.h"
+#include "dso.h"
 #include "event.h"
 
 struct addr_location;
@@ -26,15 +27,17 @@ struct machine {
         struct rb_node    rb_node;
         pid_t             pid;
         u16               id_hdr_size;
+        bool              comm_exec;
         char              *root_dir;
         struct rb_root    threads;
         struct list_head  dead_threads;
         struct thread     *last_match;
         struct vdso_info  *vdso_info;
-        struct list_head  user_dsos;
-        struct list_head  kernel_dsos;
+        struct dsos       user_dsos;
+        struct dsos       kernel_dsos;
         struct map_groups kmaps;
         struct map        *vmlinux_maps[MAP__NR_TYPES];
+        u64               kernel_start;
         symbol_filter_t   symbol_filter;
         pid_t             *current_tid;
 };
@@ -45,8 +48,26 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type)
         return machine->vmlinux_maps[type];
 }
 
+int machine__get_kernel_start(struct machine *machine);
+
+static inline u64 machine__kernel_start(struct machine *machine)
+{
+        if (!machine->kernel_start)
+                machine__get_kernel_start(machine);
+        return machine->kernel_start;
+}
+
+static inline bool machine__kernel_ip(struct machine *machine, u64 ip)
+{
+        u64 kernel_start = machine__kernel_start(machine);
+
+        return ip >= kernel_start;
+}
+
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
                                     pid_t tid);
+struct comm *machine__thread_exec_comm(struct machine *machine,
+                                       struct thread *thread);
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event,
                                 struct perf_sample *sample);
@@ -88,6 +109,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
 
 void machines__set_symbol_filter(struct machines *machines,
                                  symbol_filter_t symbol_filter);
+void machines__set_comm_exec(struct machines *machines, bool comm_exec);
 
 struct machine *machine__new_host(void);
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 31b8905dd863..2137c4596ec7 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -31,6 +31,7 @@ static inline int is_anon_memory(const char *filename)
 static inline int is_no_dso_memory(const char *filename)
 {
         return !strncmp(filename, "[stack", 6) ||
+               !strncmp(filename, "/SYSV",5)   ||
                !strcmp(filename, "[heap]");
 }
 
@@ -555,7 +556,7 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 
 int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
 {
-        if (ams->addr < ams->map->start || ams->addr > ams->map->end) {
+        if (ams->addr < ams->map->start || ams->addr >= ams->map->end) {
                 if (ams->map->groups == NULL)
                         return -1;
                 ams->map = map_groups__find(ams->map->groups, ams->map->type,
@@ -663,7 +664,7 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
                                 goto move_map;
                         }
 
-                        before->end = map->start - 1;
+                        before->end = map->start;
                         map_groups__insert(mg, before);
                         if (verbose >= 2)
                                 map__fprintf(before, fp);
@@ -677,7 +678,7 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
                                 goto move_map;
                         }
 
-                        after->start = map->end + 1;
+                        after->start = map->end;
                         map_groups__insert(mg, after);
                         if (verbose >= 2)
                                 map__fprintf(after, fp);
@@ -751,7 +752,7 @@ struct map *maps__find(struct rb_root *maps, u64 ip)
                 m = rb_entry(parent, struct map, rb_node);
                 if (ip < m->start)
                         p = &(*p)->rb_left;
-                else if (ip > m->end)
+                else if (ip >= m->end)
                         p = &(*p)->rb_right;
                 else
                         return m;
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
new file mode 100644
index 000000000000..fd4be94125fb
--- /dev/null
+++ b/tools/perf/util/ordered-events.c
@@ -0,0 +1,286 @@
+#include <linux/list.h>
+#include <linux/compiler.h>
+#include <linux/string.h>
+#include "ordered-events.h"
+#include "evlist.h"
+#include "session.h"
+#include "asm/bug.h"
+#include "debug.h"
+
+#define pr_N(n, fmt, ...) \
+        eprintf(n, debug_ordered_events, fmt, ##__VA_ARGS__)
+
+#define pr(fmt, ...) pr_N(1, pr_fmt(fmt), ##__VA_ARGS__)
+
+static void queue_event(struct ordered_events *oe, struct ordered_event *new)
+{
+        struct ordered_event *last = oe->last;
+        u64 timestamp = new->timestamp;
+        struct list_head *p;
+
+        ++oe->nr_events;
+        oe->last = new;
+
+        pr_oe_time2(timestamp, "queue_event nr_events %u\n", oe->nr_events);
+
+        if (!last) {
+                list_add(&new->list, &oe->events);
+                oe->max_timestamp = timestamp;
+                return;
+        }
+
+        /*
+         * last event might point to some random place in the list as it's
+         * the last queued event. We expect that the new event is close to
+         * this.
+         */
+        if (last->timestamp <= timestamp) {
+                while (last->timestamp <= timestamp) {
+                        p = last->list.next;
+                        if (p == &oe->events) {
+                                list_add_tail(&new->list, &oe->events);
+                                oe->max_timestamp = timestamp;
+                                return;
+                        }
+                        last = list_entry(p, struct ordered_event, list);
+                }
+                list_add_tail(&new->list, &last->list);
+        } else {
+                while (last->timestamp > timestamp) {
+                        p = last->list.prev;
+                        if (p == &oe->events) {
+                                list_add(&new->list, &oe->events);
+                                return;
+                        }
+                        last = list_entry(p, struct ordered_event, list);
+                }
+                list_add(&new->list, &last->list);
+        }
+}
+
+static union perf_event *__dup_event(struct ordered_events *oe,
+                                     union perf_event *event)
+{
+        union perf_event *new_event = NULL;
+
+        if (oe->cur_alloc_size < oe->max_alloc_size) {
+                new_event = memdup(event, event->header.size);
+                if (new_event)
+                        oe->cur_alloc_size += event->header.size;
+        }
+
+        return new_event;
+}
+
+static union perf_event *dup_event(struct ordered_events *oe,
+                                   union perf_event *event)
+{
+        return oe->copy_on_queue ? __dup_event(oe, event) : event;
+}
+
+static void free_dup_event(struct ordered_events *oe, union perf_event *event)
+{
+        if (oe->copy_on_queue) {
+                oe->cur_alloc_size -= event->header.size;
+                free(event);
+        }
+}
+
+#define MAX_SAMPLE_BUFFER       (64 * 1024 / sizeof(struct ordered_event))
+static struct ordered_event *alloc_event(struct ordered_events *oe,
+                                         union perf_event *event)
+{
+        struct list_head *cache = &oe->cache;
+        struct ordered_event *new = NULL;
+        union perf_event *new_event;
+
+        new_event = dup_event(oe, event);
+        if (!new_event)
+                return NULL;
+
+        if (!list_empty(cache)) {
+                new = list_entry(cache->next, struct ordered_event, list);
+                list_del(&new->list);
+        } else if (oe->buffer) {
+                new = oe->buffer + oe->buffer_idx;
+                if (++oe->buffer_idx == MAX_SAMPLE_BUFFER)
+                        oe->buffer = NULL;
+        } else if (oe->cur_alloc_size < oe->max_alloc_size) {
+                size_t size = MAX_SAMPLE_BUFFER * sizeof(*new);
+
+                oe->buffer = malloc(size);
+                if (!oe->buffer) {
+                        free_dup_event(oe, new_event);
+                        return NULL;
+                }
+
+                pr("alloc size %" PRIu64 "B (+%zu), max %" PRIu64 "B\n",
+                   oe->cur_alloc_size, size, oe->max_alloc_size);
+
+                oe->cur_alloc_size += size;
+                list_add(&oe->buffer->list, &oe->to_free);
+
+                /* First entry is abused to maintain the to_free list. */
+                oe->buffer_idx = 2;
+                new = oe->buffer + 1;
+        } else {
+                pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size);
+        }
+
+        new->event = new_event;
+        return new;
+}
+
+struct ordered_event *
+ordered_events__new(struct ordered_events *oe, u64 timestamp,
+                    union perf_event *event)
+{
+        struct ordered_event *new;
+
+        new = alloc_event(oe, event);
+        if (new) {
+                new->timestamp = timestamp;
+                queue_event(oe, new);
+        }
+
+        return new;
+}
+
+void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event)
+{
+        list_move(&event->list, &oe->cache);
+        oe->nr_events--;
+        free_dup_event(oe, event->event);
+}
+
+static int __ordered_events__flush(struct perf_session *s,
+                                   struct perf_tool *tool)
+{
+        struct ordered_events *oe = &s->ordered_events;
+        struct list_head *head = &oe->events;
+        struct ordered_event *tmp, *iter;
+        struct perf_sample sample;
+        u64 limit = oe->next_flush;
+        u64 last_ts = oe->last ? oe->last->timestamp : 0ULL;
+        bool show_progress = limit == ULLONG_MAX;
+        struct ui_progress prog;
+        int ret;
+
+        if (!tool->ordered_events || !limit)
+                return 0;
+
+        if (show_progress)
+                ui_progress__init(&prog, oe->nr_events, "Processing time ordered events...");
+
+        list_for_each_entry_safe(iter, tmp, head, list) {
+                if (session_done())
+                        return 0;
+
+                if (iter->timestamp > limit)
+                        break;
+
+                ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample);
+                if (ret)
+                        pr_err("Can't parse sample, err = %d\n", ret);
+                else {
+                        ret = perf_session__deliver_event(s, iter->event, &sample, tool,
+                                                          iter->file_offset);
+                        if (ret)
+                                return ret;
+                }
+
+                ordered_events__delete(oe, iter);
+                oe->last_flush = iter->timestamp;
+
+                if (show_progress)
+                        ui_progress__update(&prog, 1);
+        }
+
+        if (list_empty(head))
+                oe->last = NULL;
+        else if (last_ts <= limit)
+                oe->last = list_entry(head->prev, struct ordered_event, list);
+
+        return 0;
+}
+
+int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
+                          enum oe_flush how)
+{
+        struct ordered_events *oe = &s->ordered_events;
+        static const char * const str[] = {
+                "NONE",
+                "FINAL",
+                "ROUND",
+                "HALF ",
+        };
+        int err;
+
+        switch (how) {
+        case OE_FLUSH__FINAL:
+                oe->next_flush = ULLONG_MAX;
+                break;
+
+        case OE_FLUSH__HALF:
+        {
+                struct ordered_event *first, *last;
+                struct list_head *head = &oe->events;
+
+                first = list_entry(head->next, struct ordered_event, list);
+                last = oe->last;
+
+                /* Warn if we are called before any event got allocated. */
+                if (WARN_ONCE(!last || list_empty(head), "empty queue"))
+                        return 0;
+
+                oe->next_flush  = first->timestamp;
+                oe->next_flush += (last->timestamp - first->timestamp) / 2;
+                break;
+        }
+
+        case OE_FLUSH__ROUND:
+        case OE_FLUSH__NONE:
+        default:
+                break;
+        };
+
+        pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush PRE  %s, nr_events %u\n",
+                   str[how], oe->nr_events);
+        pr_oe_time(oe->max_timestamp, "max_timestamp\n");
+
+        err = __ordered_events__flush(s, tool);
+
+        if (!err) {
+                if (how == OE_FLUSH__ROUND)
+                        oe->next_flush = oe->max_timestamp;
+
+                oe->last_flush_type = how;
+        }
+
+        pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush POST %s, nr_events %u\n",
+                   str[how], oe->nr_events);
+        pr_oe_time(oe->last_flush, "last_flush\n");
+
+        return err;
+}
+
+void ordered_events__init(struct ordered_events *oe)
+{
+        INIT_LIST_HEAD(&oe->events);
+        INIT_LIST_HEAD(&oe->cache);
+        INIT_LIST_HEAD(&oe->to_free);
+        oe->max_alloc_size = (u64) -1;
+        oe->cur_alloc_size = 0;
+}
+
+void ordered_events__free(struct ordered_events *oe)
+{
+        while (!list_empty(&oe->to_free)) {
+                struct ordered_event *event;
+
+                event = list_entry(oe->to_free.next, struct ordered_event, list);
+                list_del(&event->list);
+                free_dup_event(oe, event->event);
+                free(event);
+        }
+}
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
new file mode 100644
index 000000000000..7b8f9b011f38
--- /dev/null
+++ b/tools/perf/util/ordered-events.h
@@ -0,0 +1,59 @@
+#ifndef __ORDERED_EVENTS_H
+#define __ORDERED_EVENTS_H
+
+#include <linux/types.h>
+#include "tool.h"
+
+struct perf_session;
+
+struct ordered_event {
+        u64                     timestamp;
+        u64                     file_offset;
+        union perf_event        *event;
+        struct list_head        list;
+};
+
+enum oe_flush {
+        OE_FLUSH__NONE,
+        OE_FLUSH__FINAL,
+        OE_FLUSH__ROUND,
+        OE_FLUSH__HALF,
+};
+
+struct ordered_events {
+        u64                     last_flush;
+        u64                     next_flush;
+        u64                     max_timestamp;
+        u64                     max_alloc_size;
+        u64                     cur_alloc_size;
+        struct list_head        events;
+        struct list_head        cache;
+        struct list_head        to_free;
+        struct ordered_event    *buffer;
+        struct ordered_event    *last;
+        int                     buffer_idx;
+        unsigned int            nr_events;
+        enum oe_flush           last_flush_type;
+        bool                    copy_on_queue;
+};
+
+struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp,
+                                          union perf_event *event);
+void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event);
+int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
+                          enum oe_flush how);
+void ordered_events__init(struct ordered_events *oe);
+void ordered_events__free(struct ordered_events *oe);
+
+static inline
+void ordered_events__set_alloc_size(struct ordered_events *oe, u64 size)
+{
+        oe->max_alloc_size = size;
+}
+
+static inline
+void ordered_events__set_copy_on_queue(struct ordered_events *oe, bool copy)
+{
+        oe->copy_on_queue = copy;
+}
+#endif /* __ORDERED_EVENTS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 1e15df10a88c..c659a3ca1283 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -6,10 +6,11 @@
 #include "parse-options.h"
 #include "parse-events.h"
 #include "exec_cmd.h"
-#include "linux/string.h"
+#include "string.h"
 #include "symbol.h"
 #include "cache.h"
 #include "header.h"
+#include "debug.h"
 #include <api/fs/debugfs.h>
 #include "parse-events-bison.h"
 #define YY_EXTRA_TYPE int
@@ -29,6 +30,15 @@ extern int parse_events_debug;
 #endif
 int parse_events_parse(void *data, void *scanner);
 
+static struct perf_pmu_event_symbol *perf_pmu_events_list;
+/*
+ * The variable indicates the number of supported pmu event symbols.
+ * 0 means not initialized and ready to init
+ * -1 means failed to init, don't try anymore
+ * >0 is the number of supported pmu event symbols
+ */
+static int perf_pmu_events_list_num;
+
 static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
         [PERF_COUNT_HW_CPU_CYCLES] = {
                 .symbol = "cpu-cycles",
@@ -633,18 +643,28 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
                          char *name, struct list_head *head_config)
 {
         struct perf_event_attr attr;
+        struct perf_pmu_info info;
         struct perf_pmu *pmu;
         struct perf_evsel *evsel;
-        const char *unit;
-        double scale;
 
         pmu = perf_pmu__find(name);
         if (!pmu)
                 return -EINVAL;
 
-        memset(&attr, 0, sizeof(attr));
+        if (pmu->default_config) {
+                memcpy(&attr, pmu->default_config,
+                       sizeof(struct perf_event_attr));
+        } else {
+                memset(&attr, 0, sizeof(attr));
+        }
 
-        if (perf_pmu__check_alias(pmu, head_config, &unit, &scale))
+        if (!head_config) {
+                attr.type = pmu->type;
+                evsel = __add_event(list, idx, &attr, NULL, pmu->cpus);
+                return evsel ? 0 : -ENOMEM;
+        }
+
+        if (perf_pmu__check_alias(pmu, head_config, &info))
                 return -EINVAL;
 
         /*
@@ -659,8 +679,8 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
         evsel = __add_event(list, idx, &attr, pmu_event_name(head_config),
                             pmu->cpus);
         if (evsel) {
-                evsel->unit = unit;
-                evsel->scale = scale;
+                evsel->unit = info.unit;
+                evsel->scale = info.scale;
         }
 
         return evsel ? 0 : -ENOMEM;
@@ -852,30 +872,111 @@ int parse_events_name(struct list_head *list, char *name)
         return 0;
 }
 
-static int parse_events__scanner(const char *str, void *data, int start_token);
+static int
+comp_pmu(const void *p1, const void *p2)
+{
+        struct perf_pmu_event_symbol *pmu1 = (struct perf_pmu_event_symbol *) p1;
+        struct perf_pmu_event_symbol *pmu2 = (struct perf_pmu_event_symbol *) p2;
 
-static int parse_events_fixup(int ret, const char *str, void *data,
-                              int start_token)
+        return strcmp(pmu1->symbol, pmu2->symbol);
+}
+
+static void perf_pmu__parse_cleanup(void)
 {
-        char *o = strdup(str);
-        char *s = NULL;
-        char *t = o;
-        char *p;
+        if (perf_pmu_events_list_num > 0) {
+                struct perf_pmu_event_symbol *p;
+                int i;
+
+                for (i = 0; i < perf_pmu_events_list_num; i++) {
+                        p = perf_pmu_events_list + i;
+                        free(p->symbol);
+                }
+                free(perf_pmu_events_list);
+                perf_pmu_events_list = NULL;
+                perf_pmu_events_list_num = 0;
+        }
+}
+
+#define SET_SYMBOL(str, stype)          \
+do {                                    \
+        p->symbol = str;                \
+        if (!p->symbol)                 \
+                goto err;               \
+        p->type = stype;                \
+} while (0)
+
+/*
+ * Read the pmu events list from sysfs
+ * Save it into perf_pmu_events_list
+ */
+static void perf_pmu__parse_init(void)
+{
+
+        struct perf_pmu *pmu = NULL;
+        struct perf_pmu_alias *alias;
         int len = 0;
 
-        if (!o)
-                return ret;
-        while ((p = strsep(&t, ",")) != NULL) {
-                if (s)
-                        str_append(&s, &len, ",");
-                str_append(&s, &len, "cpu/");
-                str_append(&s, &len, p);
-                str_append(&s, &len, "/");
+        pmu = perf_pmu__find("cpu");
+        if ((pmu == NULL) || list_empty(&pmu->aliases)) {
+                perf_pmu_events_list_num = -1;
+                return;
         }
-        free(o);
-        if (!s)
-                return -ENOMEM;
-        return parse_events__scanner(s, data, start_token);
+        list_for_each_entry(alias, &pmu->aliases, list) {
+                if (strchr(alias->name, '-'))
+                        len++;
+                len++;
+        }
+        perf_pmu_events_list = malloc(sizeof(struct perf_pmu_event_symbol) * len);
+        if (!perf_pmu_events_list)
+                return;
+        perf_pmu_events_list_num = len;
+
+        len = 0;
+        list_for_each_entry(alias, &pmu->aliases, list) {
+                struct perf_pmu_event_symbol *p = perf_pmu_events_list + len;
+                char *tmp = strchr(alias->name, '-');
+
+                if (tmp != NULL) {
+                        SET_SYMBOL(strndup(alias->name, tmp - alias->name),
+                                        PMU_EVENT_SYMBOL_PREFIX);
+                        p++;
+                        SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX);
+                        len += 2;
+                } else {
+                        SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL);
+                        len++;
+                }
+        }
+        qsort(perf_pmu_events_list, len,
+                sizeof(struct perf_pmu_event_symbol), comp_pmu);
+
+        return;
+err:
+        perf_pmu__parse_cleanup();
+}
+
+enum perf_pmu_event_symbol_type
+perf_pmu__parse_check(const char *name)
+{
+        struct perf_pmu_event_symbol p, *r;
+
+        /* scan kernel pmu events from sysfs if needed */
+        if (perf_pmu_events_list_num == 0)
+                perf_pmu__parse_init();
+        /*
+         * name "cpu" could be prefix of cpu-cycles or cpu// events.
+         * cpu-cycles has been handled by hardcode.
+         * So it must be cpu// events, not kernel pmu event.
+         */
+        if ((perf_pmu_events_list_num <= 0) || !strcmp(name, "cpu"))
+                return PMU_EVENT_SYMBOL_ERR;
+
+        p.symbol = strdup(name);
+        r = bsearch(&p, perf_pmu_events_list,
+                        (size_t) perf_pmu_events_list_num,
+                        sizeof(struct perf_pmu_event_symbol), comp_pmu);
+        free(p.symbol);
+        return r ? r->type : PMU_EVENT_SYMBOL_ERR;
 }
 
 static int parse_events__scanner(const char *str, void *data, int start_token)
@@ -898,8 +999,6 @@ static int parse_events__scanner(const char *str, void *data, int start_token)
         parse_events__flush_buffer(buffer, scanner);
         parse_events__delete_buffer(buffer, scanner);
         parse_events_lex_destroy(scanner);
-        if (ret && !strchr(str, '/'))
-                ret = parse_events_fixup(ret, str, data, start_token);
         return ret;
 }
 
@@ -934,6 +1033,7 @@ int parse_events(struct perf_evlist *evlist, const char *str)
         int ret;
 
         ret = parse_events__scanner(str, &data, PE_START_EVENTS);
+        perf_pmu__parse_cleanup();
         if (!ret) {
                 int entries = data.idx - evlist->nr_entries;
                 perf_evlist__splice_list_tail(evlist, &data.list, entries);
@@ -973,7 +1073,7 @@ int parse_filter(const struct option *opt, const char *str,
 
         if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) {
                 fprintf(stderr,
-                        "-F option should follow a -e tracepoint option\n");
+                        "--filter option should follow a -e tracepoint option\n");
                 return -1;
         }
 
@@ -1006,9 +1106,11 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
         struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
         char evt_path[MAXPATHLEN];
         char dir_path[MAXPATHLEN];
+        char sbuf[STRERR_BUFSIZE];
 
         if (debugfs_valid_mountpoint(tracing_events_path)) {
-                printf("  [ Tracepoints not available: %s ]\n", strerror(errno));
+                printf("  [ Tracepoints not available: %s ]\n",
+                        strerror_r(errno, sbuf, sizeof(sbuf)));
                 return;
         }
 
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index df094b4ed5ed..db2cf78ff0f3 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -35,6 +35,18 @@ extern int parse_filter(const struct option *opt, const char *str, int unset);
 
 #define EVENTS_HELP_MAX (128*1024)
 
+enum perf_pmu_event_symbol_type {
+        PMU_EVENT_SYMBOL_ERR,           /* not a PMU EVENT */
+        PMU_EVENT_SYMBOL,               /* normal style PMU event */
+        PMU_EVENT_SYMBOL_PREFIX,        /* prefix of pre-suf style event */
+        PMU_EVENT_SYMBOL_SUFFIX,        /* suffix of pre-suf style event */
+};
+
+struct perf_pmu_event_symbol {
+        char    *symbol;
+        enum perf_pmu_event_symbol_type type;
+};
+
 enum {
         PARSE_EVENTS__TERM_TYPE_NUM,
         PARSE_EVENTS__TERM_TYPE_STR,
@@ -95,6 +107,8 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
                                 void *ptr, char *type);
 int parse_events_add_pmu(struct list_head *list, int *idx,
                          char *pmu , struct list_head *head_config);
+enum perf_pmu_event_symbol_type
+perf_pmu__parse_check(const char *name);
 void parse_events__set_leader(char *name, struct list_head *list);
 void parse_events_update_lists(struct list_head *list_event,
                                struct list_head *list_all);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 343299575b30..906630bbf8eb 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -51,6 +51,24 @@ static int str(yyscan_t scanner, int token)
         return token;
 }
 
+static int pmu_str_check(yyscan_t scanner)
+{
+        YYSTYPE *yylval = parse_events_get_lval(scanner);
+        char *text = parse_events_get_text(scanner);
+
+        yylval->str = strdup(text);
+        switch (perf_pmu__parse_check(text)) {
+                case PMU_EVENT_SYMBOL_PREFIX:
+                        return PE_PMU_EVENT_PRE;
+                case PMU_EVENT_SYMBOL_SUFFIX:
+                        return PE_PMU_EVENT_SUF;
+                case PMU_EVENT_SYMBOL:
+                        return PE_KERNEL_PMU_EVENT;
+                default:
+                        return PE_NAME;
+        }
+}
+
 static int sym(yyscan_t scanner, int type, int config)
 {
         YYSTYPE *yylval = parse_events_get_lval(scanner);
@@ -178,6 +196,16 @@ alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_AL
 emulation-faults                                { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy                                           { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
 
+        /*
+         * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately.
+         * Because the prefix cycles is mixed up with cpu-cycles.
+         * loads and stores are mixed up with cache event
+         */
+cycles-ct                                       { return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+cycles-t                                        { return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+mem-loads                                       { return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+mem-stores                                      { return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+
 L1-dcache|l1-d|l1d|L1-data              |
 L1-icache|l1-i|l1i|L1-instruction       |
 LLC|L2                                  |
@@ -199,7 +227,7 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 {num_hex}               { return value(yyscanner, 16); }
 
 {modifier_event}        { return str(yyscanner, PE_MODIFIER_EVENT); }
-{name}                  { return str(yyscanner, PE_NAME); }
+{name}                  { return pmu_str_check(yyscanner); }
 "/"                     { BEGIN(config); return '/'; }
 -                       { return '-'; }
 ,                       { BEGIN(event); return ','; }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 0bc87ba46bf3..93c4c9fbc922 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -47,6 +47,7 @@ static inc_group_count(struct list_head *list,
 %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT
 %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
 %token PE_ERROR
+%token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
@@ -58,6 +59,7 @@ static inc_group_count(struct list_head *list,
 %type <str> PE_MODIFIER_EVENT
 %type <str> PE_MODIFIER_BP
 %type <str> PE_EVENT_NAME
+%type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
 %type <num> value_sym
 %type <head> event_config
 %type <term> event_term
@@ -210,6 +212,54 @@ PE_NAME '/' event_config '/'
         parse_events__free_terms($3);
         $$ = list;
 }
+|
+PE_NAME '/' '/'
+{
+        struct parse_events_evlist *data = _data;
+        struct list_head *list;
+
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, NULL));
+        $$ = list;
+}
+|
+PE_KERNEL_PMU_EVENT sep_dc
+{
+        struct parse_events_evlist *data = _data;
+        struct list_head *head;
+        struct parse_events_term *term;
+        struct list_head *list;
+
+        ALLOC_LIST(head);
+        ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+                                        $1, 1));
+        list_add_tail(&term->list, head);
+
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+        parse_events__free_terms(head);
+        $$ = list;
+}
+|
+PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
+{
+        struct parse_events_evlist *data = _data;
+        struct list_head *head;
+        struct parse_events_term *term;
+        struct list_head *list;
+        char pmu_name[128];
+        snprintf(&pmu_name, 128, "%s-%s", $1, $3);
+
+        ALLOC_LIST(head);
+        ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+                                        &pmu_name, 1));
+        list_add_tail(&term->list, head);
+
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+        parse_events__free_terms(head);
+        $$ = list;
+}
 
 value_sym:
 PE_VALUE_SYM_HW
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 7a811eb61f75..e243ad962a4d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -2,6 +2,8 @@
 #include <sys/types.h>
 #include <unistd.h>
 #include <stdio.h>
+#include <stdbool.h>
+#include <stdarg.h>
 #include <dirent.h>
 #include <api/fs/fs.h>
 #include <locale.h>
@@ -10,16 +12,6 @@
 #include "parse-events.h"
 #include "cpumap.h"
 
-#define UNIT_MAX_LEN    31 /* max length for event unit name */
-
-struct perf_pmu_alias {
-        char *name;
-        struct list_head terms;
-        struct list_head list;
-        char unit[UNIT_MAX_LEN+1];
-        double scale;
-};
-
 struct perf_pmu_format {
         char *name;
         int value;
@@ -208,6 +200,19 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
         return 0;
 }
 
+static inline bool pmu_alias_info_file(char *name)
+{
+        size_t len;
+
+        len = strlen(name);
+        if (len > 5 && !strcmp(name + len - 5, ".unit"))
+                return true;
+        if (len > 6 && !strcmp(name + len - 6, ".scale"))
+                return true;
+
+        return false;
+}
+
 /*
  * Process all the sysfs attributes located under the directory
  * specified in 'dir' parameter.
@@ -216,7 +221,6 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 {
         struct dirent *evt_ent;
         DIR *event_dir;
-        size_t len;
         int ret = 0;
 
         event_dir = opendir(dir);
@@ -232,13 +236,9 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
                         continue;
 
                 /*
-                 * skip .unit and .scale info files
-                 * parsed in perf_pmu__new_alias()
+                 * skip info files parsed in perf_pmu__new_alias()
                  */
-                len = strlen(name);
-                if (len > 5 && !strcmp(name + len - 5, ".unit"))
-                        continue;
-                if (len > 6 && !strcmp(name + len - 6, ".scale"))
+                if (pmu_alias_info_file(name))
                         continue;
 
                 snprintf(path, PATH_MAX, "%s/%s", dir, name);
@@ -387,6 +387,12 @@ static struct cpu_map *pmu_cpumask(const char *name)
         return cpus;
 }
 
+struct perf_event_attr *__attribute__((weak))
+perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
+{
+        return NULL;
+}
+
 static struct perf_pmu *pmu_lookup(const char *name)
 {
         struct perf_pmu *pmu;
@@ -421,6 +427,9 @@ static struct perf_pmu *pmu_lookup(const char *name)
         pmu->name = strdup(name);
         pmu->type = type;
         list_add_tail(&pmu->list, &pmus);
+
+        pmu->default_config = perf_pmu__get_default_config(pmu);
+
         return pmu;
 }
 
@@ -479,28 +488,24 @@ pmu_find_format(struct list_head *formats, char *name)
 }
 
 /*
- * Returns value based on the format definition (format parameter)
+ * Sets value based on the format definition (format parameter)
  * and unformated value (value parameter).
- *
- * TODO maybe optimize a little ;)
  */
-static __u64 pmu_format_value(unsigned long *format, __u64 value)
+static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v,
+                             bool zero)
 {
         unsigned long fbit, vbit;
-        __u64 v = 0;
 
         for (fbit = 0, vbit = 0; fbit < PERF_PMU_FORMAT_BITS; fbit++) {
 
                 if (!test_bit(fbit, format))
                         continue;
 
-                if (!(value & (1llu << vbit++)))
-                        continue;
-
-                v |= (1llu << fbit);
+                if (value & (1llu << vbit++))
+                        *v |= (1llu << fbit);
+                else if (zero)
+                        *v &= ~(1llu << fbit);
         }
-
-        return v;
 }
 
 /*
@@ -509,7 +514,8 @@ static __u64 pmu_format_value(unsigned long *format, __u64 value)
  */
 static int pmu_config_term(struct list_head *formats,
                            struct perf_event_attr *attr,
-                           struct parse_events_term *term)
+                           struct parse_events_term *term,
+                           bool zero)
 {
         struct perf_pmu_format *format;
         __u64 *vp;
@@ -548,18 +554,19 @@ static int pmu_config_term(struct list_head *formats,
          * non-hardcoded terms, here's the place to translate
          * them into value.
          */
-        *vp |= pmu_format_value(format->bits, term->val.num);
+        pmu_format_value(format->bits, term->val.num, vp, zero);
         return 0;
 }
 
 int perf_pmu__config_terms(struct list_head *formats,
                            struct perf_event_attr *attr,
-                           struct list_head *head_terms)
+                           struct list_head *head_terms,
+                           bool zero)
 {
         struct parse_events_term *term;
 
         list_for_each_entry(term, head_terms, list)
-                if (pmu_config_term(formats, attr, term))
+                if (pmu_config_term(formats, attr, term, zero))
                         return -EINVAL;
 
         return 0;
@@ -573,8 +580,10 @@ int perf_pmu__config_terms(struct list_head *formats,
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
                      struct list_head *head_terms)
 {
+        bool zero = !!pmu->default_config;
+
         attr->type = pmu->type;
-        return perf_pmu__config_terms(&pmu->format, attr, head_terms);
+        return perf_pmu__config_terms(&pmu->format, attr, head_terms, zero);
 }
 
 static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
@@ -634,7 +643,7 @@ static int check_unit_scale(struct perf_pmu_alias *alias,
  * defined for the alias
  */
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
-                          const char **unit, double *scale)
+                          struct perf_pmu_info *info)
 {
         struct parse_events_term *term, *h;
         struct perf_pmu_alias *alias;
@@ -644,8 +653,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
          * Mark unit and scale as not set
          * (different from default values, see below)
          */
-        *unit   = NULL;
-        *scale  = 0.0;
+        info->unit   = NULL;
+        info->scale  = 0.0;
 
         list_for_each_entry_safe(term, h, head_terms, list) {
                 alias = pmu_find_alias(pmu, term);
@@ -655,7 +664,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
                 if (ret)
                         return ret;
 
-                ret = check_unit_scale(alias, unit, scale);
+                ret = check_unit_scale(alias, &info->unit, &info->scale);
                 if (ret)
                         return ret;
 
@@ -668,11 +677,11 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
          * set defaults as for evsel
          * unit cannot left to NULL
          */
-        if (*unit == NULL)
-                *unit   = "";
+        if (info->unit == NULL)
+                info->unit   = "";
 
-        if (*scale == 0.0)
-                *scale  = 1.0;
+        if (info->scale == 0.0)
+                info->scale  = 1.0;
 
         return 0;
 }
@@ -794,3 +803,39 @@ bool pmu_have_event(const char *pname, const char *name)
         }
         return false;
 }
+
+static FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name)
+{
+        struct stat st;
+        char path[PATH_MAX];
+        const char *sysfs;
+
+        sysfs = sysfs__mountpoint();
+        if (!sysfs)
+                return NULL;
+
+        snprintf(path, PATH_MAX,
+                 "%s" EVENT_SOURCE_DEVICE_PATH "%s/%s", sysfs, pmu->name, name);
+
+        if (stat(path, &st) < 0)
+                return NULL;
+
+        return fopen(path, "r");
+}
+
+int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
+                        ...)
+{
+        va_list args;
+        FILE *file;
+        int ret = EOF;
+
+        va_start(args, fmt);
+        file = perf_pmu__open_file(pmu, name);
+        if (file) {
+                ret = vfscanf(file, fmt, args);
+                fclose(file);
+        }
+        va_end(args);
+        return ret;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index c14a543ce1f3..fe9dfbee8eed 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -13,13 +13,31 @@ enum {
 
 #define PERF_PMU_FORMAT_BITS 64
 
+struct perf_event_attr;
+
 struct perf_pmu {
         char *name;
         __u32 type;
+        struct perf_event_attr *default_config;
         struct cpu_map *cpus;
-        struct list_head format;
-        struct list_head aliases;
-        struct list_head list;
+        struct list_head format;  /* HEAD struct perf_pmu_format -> list */
+        struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */
+        struct list_head list;    /* ELEM */
+};
+
+struct perf_pmu_info {
+        const char *unit;
+        double scale;
+};
+
+#define UNIT_MAX_LEN    31 /* max length for event unit name */
+
+struct perf_pmu_alias {
+        char *name;
+        struct list_head terms; /* HEAD struct parse_events_term -> list */
+        struct list_head list;  /* ELEM */
+        char unit[UNIT_MAX_LEN+1];
+        double scale;
 };
 
 struct perf_pmu *perf_pmu__find(const char *name);
@@ -27,9 +45,10 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
                      struct list_head *head_terms);
 int perf_pmu__config_terms(struct list_head *formats,
                            struct perf_event_attr *attr,
-                           struct list_head *head_terms);
+                           struct list_head *head_terms,
+                           bool zero);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
-                          const char **unit, double *scale);
+                          struct perf_pmu_info *info);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
                                   struct list_head *head_terms);
 int perf_pmu_wrap(void);
@@ -45,5 +64,11 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 void print_pmu_events(const char *event_glob, bool name_only);
 bool pmu_have_event(const char *pname, const char *name);
 
+int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
+                        ...) __attribute__((format(scanf, 3, 4)));
+
 int perf_pmu__test(void);
+
+struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
+
 #endif /* __PMU_H */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 9a0a1839a377..c150ca4343eb 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -79,7 +79,7 @@ static int init_symbol_maps(bool user_only)
         int ret;
 
         symbol_conf.sort_by_name = true;
-        ret = symbol__init();
+        ret = symbol__init(NULL);
         if (ret < 0) {
                 pr_debug("Failed to init symbol map.\n");
                 goto out;
@@ -184,7 +184,8 @@ static struct dso *kernel_get_module_dso(const char *module)
         const char *vmlinux_name;
 
         if (module) {
-                list_for_each_entry(dso, &host_machine->kernel_dsos, node) {
+                list_for_each_entry(dso, &host_machine->kernel_dsos.head,
+                                    node) {
                         if (strncmp(dso->short_name + 1, module,
                                     dso->short_name_len - 2) == 0)
                                 goto found;
@@ -258,21 +259,33 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 #ifdef HAVE_DWARF_SUPPORT
 
 /* Open new debuginfo of given module */
-static struct debuginfo *open_debuginfo(const char *module)
+static struct debuginfo *open_debuginfo(const char *module, bool silent)
 {
         const char *path = module;
+        struct debuginfo *ret;
 
         if (!module || !strchr(module, '/')) {
                 path = kernel_get_module_path(module);
                 if (!path) {
-                        pr_err("Failed to find path of %s module.\n",
-                               module ?: "kernel");
+                        if (!silent)
+                                pr_err("Failed to find path of %s module.\n",
+                                       module ?: "kernel");
                         return NULL;
                 }
         }
-        return debuginfo__new(path);
+        ret = debuginfo__new(path);
+        if (!ret && !silent) {
+                pr_warning("The %s file has no debug information.\n", path);
+                if (!module || !strtailcmp(path, ".ko"))
+                        pr_warning("Rebuild with CONFIG_DEBUG_INFO=y, ");
+                else
+                        pr_warning("Rebuild with -g, ");
+                pr_warning("or install an appropriate debuginfo package.\n");
+        }
+        return ret;
 }
 
+
 static int get_text_start_address(const char *exec, unsigned long *address)
 {
         Elf *elf;
@@ -333,15 +346,13 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
         pr_debug("try to find information at %" PRIx64 " in %s\n", addr,
                  tp->module ? : "kernel");
 
-        dinfo = open_debuginfo(tp->module);
+        dinfo = open_debuginfo(tp->module, verbose == 0);
         if (dinfo) {
                 ret = debuginfo__find_probe_point(dinfo,
                                                  (unsigned long)addr, pp);
                 debuginfo__delete(dinfo);
-        } else {
-                pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n", addr);
+        } else
                 ret = -ENOENT;
-        }
 
         if (ret > 0) {
                 pp->retprobe = tp->retprobe;
@@ -457,13 +468,11 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
         struct debuginfo *dinfo;
         int ntevs, ret = 0;
 
-        dinfo = open_debuginfo(target);
+        dinfo = open_debuginfo(target, !need_dwarf);
 
         if (!dinfo) {
-                if (need_dwarf) {
-                        pr_warning("Failed to open debuginfo file.\n");
+                if (need_dwarf)
                         return -ENOENT;
-                }
                 pr_debug("Could not open debuginfo. Try to use symbols.\n");
                 return 0;
         }
@@ -565,7 +574,7 @@ static int get_real_path(const char *raw_path, const char *comp_dir,
 
 static int __show_one_line(FILE *fp, int l, bool skip, bool show_num)
 {
-        char buf[LINEBUF_SIZE];
+        char buf[LINEBUF_SIZE], sbuf[STRERR_BUFSIZE];
         const char *color = show_num ? "" : PERF_COLOR_BLUE;
         const char *prefix = NULL;
 
@@ -585,7 +594,8 @@ static int __show_one_line(FILE *fp, int l, bool skip, bool show_num)
         return 1;
 error:
         if (ferror(fp)) {
-                pr_warning("File read error: %s\n", strerror(errno));
+                pr_warning("File read error: %s\n",
+                           strerror_r(errno, sbuf, sizeof(sbuf)));
                 return -1;
         }
         return 0;
@@ -618,13 +628,12 @@ static int __show_line_range(struct line_range *lr, const char *module)
         FILE *fp;
         int ret;
         char *tmp;
+        char sbuf[STRERR_BUFSIZE];
 
         /* Search a line range */
-        dinfo = open_debuginfo(module);
-        if (!dinfo) {
-                pr_warning("Failed to open debuginfo file.\n");
+        dinfo = open_debuginfo(module, false);
+        if (!dinfo)
                 return -ENOENT;
-        }
 
         ret = debuginfo__find_line_range(dinfo, lr);
         debuginfo__delete(dinfo);
@@ -656,7 +665,7 @@ static int __show_line_range(struct line_range *lr, const char *module)
         fp = fopen(lr->path, "r");
         if (fp == NULL) {
                 pr_warning("Failed to open %s: %s\n", lr->path,
-                           strerror(errno));
+                           strerror_r(errno, sbuf, sizeof(sbuf)));
                 return -errno;
         }
         /* Skip to starting line number */
@@ -689,11 +698,11 @@ end:
         return ret;
 }
 
-int show_line_range(struct line_range *lr, const char *module)
+int show_line_range(struct line_range *lr, const char *module, bool user)
 {
         int ret;
 
-        ret = init_symbol_maps(false);
+        ret = init_symbol_maps(user);
         if (ret < 0)
                 return ret;
         ret = __show_line_range(lr, module);
@@ -768,13 +777,12 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
         int i, ret = 0;
         struct debuginfo *dinfo;
 
-        ret = init_symbol_maps(false);
+        ret = init_symbol_maps(pevs->uprobes);
         if (ret < 0)
                 return ret;
 
-        dinfo = open_debuginfo(module);
+        dinfo = open_debuginfo(module, false);
         if (!dinfo) {
-                pr_warning("Failed to open debuginfo file.\n");
                 ret = -ENOENT;
                 goto out;
         }
@@ -815,7 +823,8 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 }
 
 int show_line_range(struct line_range *lr __maybe_unused,
-                    const char *module __maybe_unused)
+                    const char *module __maybe_unused,
+                    bool user __maybe_unused)
 {
         pr_warning("Debuginfo-analysis is not supported.\n");
         return -ENOSYS;
@@ -1405,8 +1414,7 @@ int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len)
 
         return tmp - buf;
 error:
-        pr_debug("Failed to synthesize perf probe argument: %s\n",
-                 strerror(-ret));
+        pr_debug("Failed to synthesize perf probe argument: %d\n", ret);
         return ret;
 }
 
@@ -1455,8 +1463,7 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 
         return buf;
 error:
-        pr_debug("Failed to synthesize perf probe point: %s\n",
-                 strerror(-ret));
+        pr_debug("Failed to synthesize perf probe point: %d\n", ret);
         free(buf);
         return NULL;
 }
@@ -1780,10 +1787,11 @@ static void clear_probe_trace_event(struct probe_trace_event *tev)
         memset(tev, 0, sizeof(*tev));
 }
 
-static void print_warn_msg(const char *file, bool is_kprobe)
+static void print_open_warning(int err, bool is_kprobe)
 {
+        char sbuf[STRERR_BUFSIZE];
 
-        if (errno == ENOENT) {
+        if (err == -ENOENT) {
                 const char *config;
 
                 if (!is_kprobe)
@@ -1791,25 +1799,43 @@ static void print_warn_msg(const char *file, bool is_kprobe)
                 else
                         config = "CONFIG_KPROBE_EVENTS";
 
-                pr_warning("%s file does not exist - please rebuild kernel"
-                                " with %s.\n", file, config);
-        } else
-                pr_warning("Failed to open %s file: %s\n", file,
-                                strerror(errno));
+                pr_warning("%cprobe_events file does not exist"
+                           " - please rebuild kernel with %s.\n",
+                           is_kprobe ? 'k' : 'u', config);
+        } else if (err == -ENOTSUP)
+                pr_warning("Debugfs is not mounted.\n");
+        else
+                pr_warning("Failed to open %cprobe_events: %s\n",
+                           is_kprobe ? 'k' : 'u',
+                           strerror_r(-err, sbuf, sizeof(sbuf)));
+}
+
+static void print_both_open_warning(int kerr, int uerr)
+{
+        /* Both kprobes and uprobes are disabled, warn it. */
+        if (kerr == -ENOTSUP && uerr == -ENOTSUP)
+                pr_warning("Debugfs is not mounted.\n");
+        else if (kerr == -ENOENT && uerr == -ENOENT)
+                pr_warning("Please rebuild kernel with CONFIG_KPROBE_EVENTS "
+                           "or/and CONFIG_UPROBE_EVENTS.\n");
+        else {
+                char sbuf[STRERR_BUFSIZE];
+                pr_warning("Failed to open kprobe events: %s.\n",
+                           strerror_r(-kerr, sbuf, sizeof(sbuf)));
+                pr_warning("Failed to open uprobe events: %s.\n",
+                           strerror_r(-uerr, sbuf, sizeof(sbuf)));
+        }
 }
 
-static int open_probe_events(const char *trace_file, bool readwrite,
-                                bool is_kprobe)
+static int open_probe_events(const char *trace_file, bool readwrite)
 {
         char buf[PATH_MAX];
         const char *__debugfs;
         int ret;
 
         __debugfs = debugfs_find_mountpoint();
-        if (__debugfs == NULL) {
-                pr_warning("Debugfs is not mounted.\n");
-                return -ENOENT;
-        }
+        if (__debugfs == NULL)
+                return -ENOTSUP;
 
         ret = e_snprintf(buf, PATH_MAX, "%s/%s", __debugfs, trace_file);
         if (ret >= 0) {
@@ -1820,19 +1846,19 @@ static int open_probe_events(const char *trace_file, bool readwrite,
                         ret = open(buf, O_RDONLY, 0);
 
                 if (ret < 0)
-                        print_warn_msg(buf, is_kprobe);
+                        ret = -errno;
         }
         return ret;
 }
 
 static int open_kprobe_events(bool readwrite)
 {
-        return open_probe_events("tracing/kprobe_events", readwrite, true);
+        return open_probe_events("tracing/kprobe_events", readwrite);
 }
 
 static int open_uprobe_events(bool readwrite)
 {
-        return open_probe_events("tracing/uprobe_events", readwrite, false);
+        return open_probe_events("tracing/uprobe_events", readwrite);
 }
 
 /* Get raw string list of current kprobe_events  or uprobe_events */
@@ -1857,7 +1883,7 @@ static struct strlist *get_probe_trace_command_rawlist(int fd)
                         p[idx] = '\0';
                 ret = strlist__add(sl, buf);
                 if (ret < 0) {
-                        pr_debug("strlist__add failed: %s\n", strerror(-ret));
+                        pr_debug("strlist__add failed (%d)\n", ret);
                         strlist__delete(sl);
                         return NULL;
                 }
@@ -1916,7 +1942,7 @@ static int __show_perf_probe_events(int fd, bool is_kprobe)
 
         rawlist = get_probe_trace_command_rawlist(fd);
         if (!rawlist)
-                return -ENOENT;
+                return -ENOMEM;
 
         strlist__for_each(ent, rawlist) {
                 ret = parse_probe_trace_command(ent->s, &tev);
@@ -1940,27 +1966,34 @@ static int __show_perf_probe_events(int fd, bool is_kprobe)
 /* List up current perf-probe events */
 int show_perf_probe_events(void)
 {
-        int fd, ret;
+        int kp_fd, up_fd, ret;
 
         setup_pager();
-        fd = open_kprobe_events(false);
-
-        if (fd < 0)
-                return fd;
 
         ret = init_symbol_maps(false);
         if (ret < 0)
                 return ret;
 
-        ret = __show_perf_probe_events(fd, true);
-        close(fd);
+        kp_fd = open_kprobe_events(false);
+        if (kp_fd >= 0) {
+                ret = __show_perf_probe_events(kp_fd, true);
+                close(kp_fd);
+                if (ret < 0)
+                        goto out;
+        }
 
-        fd = open_uprobe_events(false);
-        if (fd >= 0) {
-                ret = __show_perf_probe_events(fd, false);
-                close(fd);
+        up_fd = open_uprobe_events(false);
+        if (kp_fd < 0 && up_fd < 0) {
+                print_both_open_warning(kp_fd, up_fd);
+                ret = kp_fd;
+                goto out;
         }
 
+        if (up_fd >= 0) {
+                ret = __show_perf_probe_events(up_fd, false);
+                close(up_fd);
+        }
+out:
         exit_symbol_maps();
         return ret;
 }
@@ -1976,6 +2009,8 @@ static struct strlist *get_probe_trace_event_names(int fd, bool include_group)
 
         memset(&tev, 0, sizeof(tev));
         rawlist = get_probe_trace_command_rawlist(fd);
+        if (!rawlist)
+                return NULL;
         sl = strlist__new(true, NULL);
         strlist__for_each(ent, rawlist) {
                 ret = parse_probe_trace_command(ent->s, &tev);
@@ -2005,6 +2040,7 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev)
 {
         int ret = 0;
         char *buf = synthesize_probe_trace_command(tev);
+        char sbuf[STRERR_BUFSIZE];
 
         if (!buf) {
                 pr_debug("Failed to synthesize probe trace event.\n");
@@ -2016,7 +2052,7 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev)
                 ret = write(fd, buf, strlen(buf));
                 if (ret <= 0)
                         pr_warning("Failed to write event: %s\n",
-                                   strerror(errno));
+                                   strerror_r(errno, sbuf, sizeof(sbuf)));
         }
         free(buf);
         return ret;
@@ -2030,7 +2066,7 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
         /* Try no suffix */
         ret = e_snprintf(buf, len, "%s", base);
         if (ret < 0) {
-                pr_debug("snprintf() failed: %s\n", strerror(-ret));
+                pr_debug("snprintf() failed: %d\n", ret);
                 return ret;
         }
         if (!strlist__has_entry(namelist, buf))
@@ -2046,7 +2082,7 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
         for (i = 1; i < MAX_EVENT_INDEX; i++) {
                 ret = e_snprintf(buf, len, "%s_%d", base, i);
                 if (ret < 0) {
-                        pr_debug("snprintf() failed: %s\n", strerror(-ret));
+                        pr_debug("snprintf() failed: %d\n", ret);
                         return ret;
                 }
                 if (!strlist__has_entry(namelist, buf))
@@ -2075,8 +2111,11 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
         else
                 fd = open_kprobe_events(true);
 
-        if (fd < 0)
+        if (fd < 0) {
+                print_open_warning(fd, !pev->uprobes);
                 return fd;
+        }
+
         /* Get current event names */
         namelist = get_probe_trace_event_names(fd, false);
         if (!namelist) {
@@ -2408,7 +2447,8 @@ static int __del_trace_probe_event(int fd, struct str_node *ent)
         printf("Removed event: %s\n", ent->s);
         return 0;
 error:
-        pr_warning("Failed to delete event: %s\n", strerror(-ret));
+        pr_warning("Failed to delete event: %s\n",
+                   strerror_r(-ret, buf, sizeof(buf)));
         return ret;
 }
 
@@ -2449,15 +2489,18 @@ int del_perf_probe_events(struct strlist *dellist)
 
         /* Get current event names */
         kfd = open_kprobe_events(true);
-        if (kfd < 0)
-                return kfd;
+        if (kfd >= 0)
+                namelist = get_probe_trace_event_names(kfd, true);
 
-        namelist = get_probe_trace_event_names(kfd, true);
         ufd = open_uprobe_events(true);
-
         if (ufd >= 0)
                 unamelist = get_probe_trace_event_names(ufd, true);
 
+        if (kfd < 0 && ufd < 0) {
+                print_both_open_warning(kfd, ufd);
+                goto error;
+        }
+
         if (namelist == NULL && unamelist == NULL)
                 goto error;
 
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 776c9347a3b6..e01e9943139f 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -128,7 +128,8 @@ extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
                                  bool force_add);
 extern int del_perf_probe_events(struct strlist *dellist);
 extern int show_perf_probe_events(void);
-extern int show_line_range(struct line_range *lr, const char *module);
+extern int show_line_range(struct line_range *lr, const char *module,
+                           bool user);
 extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
                                int max_probe_points, const char *module,
                                struct strfilter *filter, bool externs);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index dca9145d704c..c7918f83b300 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -281,6 +281,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
         struct probe_trace_arg_ref **ref_ptr = &tvar->ref;
         Dwarf_Die type;
         char buf[16];
+        char sbuf[STRERR_BUFSIZE];
         int bsize, boffs, total;
         int ret;
 
@@ -367,7 +368,7 @@ formatted:
                 if (ret >= 16)
                         ret = -E2BIG;
                 pr_warning("Failed to convert variable type: %s\n",
-                           strerror(-ret));
+                           strerror_r(-ret, sbuf, sizeof(sbuf)));
                 return ret;
         }
         tvar->type = strdup(buf);
@@ -608,14 +609,18 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
                 return -EINVAL;
         }
 
-        /* Get an appropriate symbol from symtab */
-        symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+        symbol = dwarf_diename(sp_die);
         if (!symbol) {
-                pr_warning("Failed to find symbol at 0x%lx\n",
-                           (unsigned long)paddr);
-                return -ENOENT;
+                /* Try to get the symbol name from symtab */
+                symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+                if (!symbol) {
+                        pr_warning("Failed to find symbol at 0x%lx\n",
+                                   (unsigned long)paddr);
+                        return -ENOENT;
+                }
+                eaddr = sym.st_value;
         }
-        tp->offset = (unsigned long)(paddr - sym.st_value);
+        tp->offset = (unsigned long)(paddr - eaddr);
         tp->address = (unsigned long)paddr;
         tp->symbol = strdup(symbol);
         if (!tp->symbol)
@@ -779,10 +784,12 @@ static int find_lazy_match_lines(struct intlist *list,
         size_t line_len;
         ssize_t len;
         int count = 0, linenum = 1;
+        char sbuf[STRERR_BUFSIZE];
 
         fp = fopen(fname, "r");
         if (!fp) {
-                pr_warning("Failed to open %s: %s\n", fname, strerror(errno));
+                pr_warning("Failed to open %s: %s\n", fname,
+                           strerror_r(errno, sbuf, sizeof(sbuf)));
                 return -errno;
         }
 
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 12aa9b0d0ba1..3dda85ca50c1 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -736,7 +736,7 @@ static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist,
         if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i", kwlist, &timeout))
                 return NULL;
 
-        n = poll(evlist->pollfd, evlist->nr_fds, timeout);
+        n = perf_evlist__poll(evlist, timeout);
         if (n < 0) {
                 PyErr_SetFromErrno(PyExc_OSError);
                 return NULL;
@@ -753,9 +753,9 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist,
         PyObject *list = PyList_New(0);
         int i;
 
-        for (i = 0; i < evlist->nr_fds; ++i) {
+        for (i = 0; i < evlist->pollfd.nr; ++i) {
                 PyObject *file;
-                FILE *fp = fdopen(evlist->pollfd[i].fd, "r");
+                FILE *fp = fdopen(evlist->pollfd.entries[i].fd, "r");
 
                 if (fp == NULL)
                         goto free_list;
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index fe8079edbdc1..cf69325b985f 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -14,6 +14,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
         struct perf_evsel *evsel;
         unsigned long flags = perf_event_open_cloexec_flag();
         int err = -EAGAIN, fd;
+        static pid_t pid = -1;
 
         evlist = perf_evlist__new();
         if (!evlist)
@@ -24,14 +25,22 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
 
         evsel = perf_evlist__first(evlist);
 
-        fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, flags);
-        if (fd < 0)
-                goto out_delete;
+        while (1) {
+                fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags);
+                if (fd < 0) {
+                        if (pid == -1 && errno == EACCES) {
+                                pid = 0;
+                                continue;
+                        }
+                        goto out_delete;
+                }
+                break;
+        }
         close(fd);
 
         fn(evsel);
 
-        fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, flags);
+        fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags);
         if (fd < 0) {
                 if (errno == EINVAL)
                         err = -EINVAL;
@@ -47,7 +56,7 @@ out_delete:
 
 static bool perf_probe_api(setup_probe_fn_t fn)
 {
-        const char *try[] = {"cycles:u", "instructions:u", "cpu-clock", NULL};
+        const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL};
         struct cpu_map *cpus;
         int cpu, ret, i = 0;
 
@@ -106,7 +115,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 
         evlist__for_each(evlist, evsel) {
                 perf_evsel__config(evsel, opts);
-                if (!evsel->idx && use_comm_exec)
+                if (evsel->tracking && use_comm_exec)
                         evsel->attr.comm_exec = 1;
         }
 
@@ -201,6 +210,7 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
         struct perf_evsel *evsel;
         int err, fd, cpu;
         bool ret = false;
+        pid_t pid = -1;
 
         temp_evlist = perf_evlist__new();
         if (!temp_evlist)
@@ -221,12 +231,20 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
                 cpu = evlist->cpus->map[0];
         }
 
-        fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1,
-                                 perf_event_open_cloexec_flag());
-        if (fd >= 0) {
-                close(fd);
-                ret = true;
+        while (1) {
+                fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1,
+                                         perf_event_open_cloexec_flag());
+                if (fd < 0) {
+                        if (pid == -1 && errno == EACCES) {
+                                pid = 0;
+                                continue;
+                        }
+                        goto out_delete;
+                }
+                break;
         }
+        close(fd);
+        ret = true;
 
 out_delete:
         perf_evlist__delete(temp_evlist);
diff --git a/tools/perf/util/run-command.c b/tools/perf/util/run-command.c
index da8e9b285f51..34622b53e733 100644
--- a/tools/perf/util/run-command.c
+++ b/tools/perf/util/run-command.c
@@ -1,6 +1,7 @@
 #include "cache.h"
 #include "run-command.h"
 #include "exec_cmd.h"
+#include "debug.h"
 
 static inline void close_pair(int fd[2])
 {
@@ -19,6 +20,7 @@ int start_command(struct child_process *cmd)
 {
         int need_in, need_out, need_err;
         int fdin[2], fdout[2], fderr[2];
+        char sbuf[STRERR_BUFSIZE];
 
         /*
          * In case of errors we must keep the promise to close FDs
@@ -99,7 +101,7 @@ int start_command(struct child_process *cmd)
 
                 if (cmd->dir && chdir(cmd->dir))
                         die("exec %s: cd to %s failed (%s)", cmd->argv[0],
-                            cmd->dir, strerror(errno));
+                            cmd->dir, strerror_r(errno, sbuf, sizeof(sbuf)));
                 if (cmd->env) {
                         for (; *cmd->env; cmd->env++) {
                                 if (strchr(*cmd->env, '='))
@@ -153,6 +155,8 @@ int start_command(struct child_process *cmd)
 
 static int wait_or_whine(pid_t pid)
 {
+        char sbuf[STRERR_BUFSIZE];
+
         for (;;) {
                 int status, code;
                 pid_t waiting = waitpid(pid, &status, 0);
@@ -160,7 +164,8 @@ static int wait_or_whine(pid_t pid)
                 if (waiting < 0) {
                         if (errno == EINTR)
                                 continue;
-                        error("waitpid failed (%s)", strerror(errno));
+                        error("waitpid failed (%s)",
+                              strerror_r(errno, sbuf, sizeof(sbuf)));
                         return -ERR_RUN_COMMAND_WAITPID;
                 }
                 if (waiting != pid)
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b2dba9c0a3a1..0a01bac4ce02 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -432,6 +432,11 @@ error:
         return err;
 }
 
+static int perl_flush_script(void)
+{
+        return 0;
+}
+
 /*
  * Stop trace script
  */
@@ -633,6 +638,7 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile)
 struct scripting_ops perl_scripting_ops = {
         .name = "Perl",
         .start_script = perl_start_script,
+        .flush_script = perl_flush_script,
         .stop_script = perl_stop_script,
         .process_event = perl_process_event,
         .generate_script = perl_generate_script,
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index cbce2545da45..496f21cadd97 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -28,6 +28,7 @@
 
 #include "../../perf.h"
 #include "../debug.h"
+#include "../callchain.h"
 #include "../evsel.h"
 #include "../util.h"
 #include "../event.h"
@@ -73,6 +74,35 @@ static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObj
         Py_DECREF(val);
 }
 
+static PyObject *get_handler(const char *handler_name)
+{
+        PyObject *handler;
+
+        handler = PyDict_GetItemString(main_dict, handler_name);
+        if (handler && !PyCallable_Check(handler))
+                return NULL;
+        return handler;
+}
+
+static void call_object(PyObject *handler, PyObject *args, const char *die_msg)
+{
+        PyObject *retval;
+
+        retval = PyObject_CallObject(handler, args);
+        if (retval == NULL)
+                handler_call_die(die_msg);
+        Py_DECREF(retval);
+}
+
+static void try_call_object(const char *handler_name, PyObject *args)
+{
+        PyObject *handler;
+
+        handler = get_handler(handler_name);
+        if (handler)
+                call_object(handler, args, handler_name);
+}
+
 static void define_value(enum print_arg_type field_type,
                          const char *ev_name,
                          const char *field_name,
@@ -80,7 +110,7 @@ static void define_value(enum print_arg_type field_type,
                          const char *field_str)
 {
         const char *handler_name = "define_flag_value";
-        PyObject *handler, *t, *retval;
+        PyObject *t;
         unsigned long long value;
         unsigned n = 0;
 
@@ -98,13 +128,7 @@ static void define_value(enum print_arg_type field_type,
         PyTuple_SetItem(t, n++, PyInt_FromLong(value));
         PyTuple_SetItem(t, n++, PyString_FromString(field_str));
 
-        handler = PyDict_GetItemString(main_dict, handler_name);
-        if (handler && PyCallable_Check(handler)) {
-                retval = PyObject_CallObject(handler, t);
-                if (retval == NULL)
-                        handler_call_die(handler_name);
-                Py_DECREF(retval);
-        }
+        try_call_object(handler_name, t);
 
         Py_DECREF(t);
 }
@@ -127,7 +151,7 @@ static void define_field(enum print_arg_type field_type,
                          const char *delim)
 {
         const char *handler_name = "define_flag_field";
-        PyObject *handler, *t, *retval;
+        PyObject *t;
         unsigned n = 0;
 
         if (field_type == PRINT_SYMBOL)
@@ -145,13 +169,7 @@ static void define_field(enum print_arg_type field_type,
         if (field_type == PRINT_FLAGS)
                 PyTuple_SetItem(t, n++, PyString_FromString(delim));
 
-        handler = PyDict_GetItemString(main_dict, handler_name);
-        if (handler && PyCallable_Check(handler)) {
-                retval = PyObject_CallObject(handler, t);
-                if (retval == NULL)
-                        handler_call_die(handler_name);
-                Py_DECREF(retval);
-        }
+        try_call_object(handler_name, t);
 
         Py_DECREF(t);
 }
@@ -362,7 +380,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
                                       struct thread *thread,
                                       struct addr_location *al)
 {
-        PyObject *handler, *retval, *context, *t, *obj, *callchain;
+        PyObject *handler, *context, *t, *obj, *callchain;
         PyObject *dict = NULL;
         static char handler_name[256];
         struct format_field *field;
@@ -387,9 +405,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 
         sprintf(handler_name, "%s__%s", event->system, event->name);
 
-        handler = PyDict_GetItemString(main_dict, handler_name);
-        if (handler && !PyCallable_Check(handler))
-                handler = NULL;
+        handler = get_handler(handler_name);
         if (!handler) {
                 dict = PyDict_New();
                 if (!dict)
@@ -450,19 +466,9 @@ static void python_process_tracepoint(struct perf_sample *sample,
                 Py_FatalError("error resizing Python tuple");
 
         if (handler) {
-                retval = PyObject_CallObject(handler, t);
-                if (retval == NULL)
-                        handler_call_die(handler_name);
-                Py_DECREF(retval);
+                call_object(handler, t, handler_name);
         } else {
-                handler = PyDict_GetItemString(main_dict, "trace_unhandled");
-                if (handler && PyCallable_Check(handler)) {
-
-                        retval = PyObject_CallObject(handler, t);
-                        if (retval == NULL)
-                                handler_call_die("trace_unhandled");
-                        Py_DECREF(retval);
-                }
+                try_call_object("trace_unhandled", t);
                 Py_DECREF(dict);
         }
 
@@ -474,7 +480,7 @@ static void python_process_general_event(struct perf_sample *sample,
                                          struct thread *thread,
                                          struct addr_location *al)
 {
-        PyObject *handler, *retval, *t, *dict, *callchain, *dict_sample;
+        PyObject *handler, *t, *dict, *callchain, *dict_sample;
         static char handler_name[64];
         unsigned n = 0;
 
@@ -496,8 +502,8 @@ static void python_process_general_event(struct perf_sample *sample,
 
         snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
 
-        handler = PyDict_GetItemString(main_dict, handler_name);
-        if (!handler || !PyCallable_Check(handler))
+        handler = get_handler(handler_name);
+        if (!handler)
                 goto exit;
 
         pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
@@ -539,10 +545,7 @@ static void python_process_general_event(struct perf_sample *sample,
         if (_PyTuple_Resize(&t, n) == -1)
                 Py_FatalError("error resizing Python tuple");
 
-        retval = PyObject_CallObject(handler, t);
-        if (retval == NULL)
-                handler_call_die(handler_name);
-        Py_DECREF(retval);
+        call_object(handler, t, handler_name);
 exit:
         Py_DECREF(dict);
         Py_DECREF(t);
@@ -566,36 +569,24 @@ static void python_process_event(union perf_event *event __maybe_unused,
 
 static int run_start_sub(void)
 {
-        PyObject *handler, *retval;
-        int err = 0;
-
         main_module = PyImport_AddModule("__main__");
         if (main_module == NULL)
                 return -1;
         Py_INCREF(main_module);
 
         main_dict = PyModule_GetDict(main_module);
-        if (main_dict == NULL) {
-                err = -1;
+        if (main_dict == NULL)
                 goto error;
-        }
         Py_INCREF(main_dict);
 
-        handler = PyDict_GetItemString(main_dict, "trace_begin");
-        if (handler == NULL || !PyCallable_Check(handler))
-                goto out;
+        try_call_object("trace_begin", NULL);
 
-        retval = PyObject_CallObject(handler, NULL);
-        if (retval == NULL)
-                handler_call_die("trace_begin");
+        return 0;
 
-        Py_DECREF(retval);
-        return err;
 error:
         Py_XDECREF(main_dict);
         Py_XDECREF(main_module);
-out:
-        return err;
+        return -1;
 }
 
 /*
@@ -649,28 +640,23 @@ error:
         return err;
 }
 
+static int python_flush_script(void)
+{
+        return 0;
+}
+
 /*
  * Stop trace script
  */
 static int python_stop_script(void)
 {
-        PyObject *handler, *retval;
-        int err = 0;
+        try_call_object("trace_end", NULL);
 
-        handler = PyDict_GetItemString(main_dict, "trace_end");
-        if (handler == NULL || !PyCallable_Check(handler))
-                goto out;
-
-        retval = PyObject_CallObject(handler, NULL);
-        if (retval == NULL)
-                handler_call_die("trace_end");
-        Py_DECREF(retval);
-out:
         Py_XDECREF(main_dict);
         Py_XDECREF(main_module);
         Py_Finalize();
 
-        return err;
+        return 0;
 }
 
 static int python_generate_script(struct pevent *pevent, const char *outfile)
@@ -843,6 +829,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 struct scripting_ops python_scripting_ops = {
         .name = "Python",
         .start_script = python_start_script,
+        .flush_script = python_flush_script,
         .stop_script = python_stop_script,
         .process_event = python_process_event,
         .generate_script = python_generate_script,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 88dfef70c13d..6702ac28754b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -14,6 +14,7 @@
 #include "util.h"
 #include "cpumap.h"
 #include "perf_regs.h"
+#include "asm/bug.h"
 
 static int perf_session__open(struct perf_session *session)
 {
@@ -66,6 +67,25 @@ static void perf_session__destroy_kernel_maps(struct perf_session *session)
         machines__destroy_kernel_maps(&session->machines);
 }
 
+static bool perf_session__has_comm_exec(struct perf_session *session)
+{
+        struct perf_evsel *evsel;
+
+        evlist__for_each(session->evlist, evsel) {
+                if (evsel->attr.comm_exec)
+                        return true;
+        }
+
+        return false;
+}
+
+static void perf_session__set_comm_exec(struct perf_session *session)
+{
+        bool comm_exec = perf_session__has_comm_exec(session);
+
+        machines__set_comm_exec(&session->machines, comm_exec);
+}
+
 struct perf_session *perf_session__new(struct perf_data_file *file,
                                        bool repipe, struct perf_tool *tool)
 {
@@ -75,9 +95,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
                 goto out;
 
         session->repipe = repipe;
-        INIT_LIST_HEAD(&session->ordered_samples.samples);
-        INIT_LIST_HEAD(&session->ordered_samples.sample_cache);
-        INIT_LIST_HEAD(&session->ordered_samples.to_free);
+        ordered_events__init(&session->ordered_events);
         machines__init(&session->machines);
 
         if (file) {
@@ -91,6 +109,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
                                 goto out_close;
 
                         perf_session__set_id_hdr_size(session);
+                        perf_session__set_comm_exec(session);
                 }
         }
 
@@ -100,13 +119,13 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
                  * kernel MMAP event, in perf_event__process_mmap().
                  */
                 if (perf_session__create_kernel_maps(session) < 0)
-                        goto out_delete;
+                        pr_warning("Cannot read kernel map\n");
         }
 
         if (tool && tool->ordering_requires_timestamps &&
-            tool->ordered_samples && !perf_evlist__sample_id_all(session->evlist)) {
+            tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) {
                 dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
-                tool->ordered_samples = false;
+                tool->ordered_events = false;
         }
 
         return session;
@@ -238,7 +257,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
         if (tool->build_id == NULL)
                 tool->build_id = process_finished_round_stub;
         if (tool->finished_round == NULL) {
-                if (tool->ordered_samples)
+                if (tool->ordered_events)
                         tool->finished_round = process_finished_round;
                 else
                         tool->finished_round = process_finished_round_stub;
@@ -444,87 +463,6 @@ static perf_event__swap_op perf_event__swap_ops[] = {
         [PERF_RECORD_HEADER_MAX]          = NULL,
 };
 
-struct sample_queue {
-        u64                     timestamp;
-        u64                     file_offset;
-        union perf_event        *event;
-        struct list_head        list;
-};
-
-static void perf_session_free_sample_buffers(struct perf_session *session)
-{
-        struct ordered_samples *os = &session->ordered_samples;
-
-        while (!list_empty(&os->to_free)) {
-                struct sample_queue *sq;
-
-                sq = list_entry(os->to_free.next, struct sample_queue, list);
-                list_del(&sq->list);
-                free(sq);
-        }
-}
-
-static int perf_session_deliver_event(struct perf_session *session,
-                                      union perf_event *event,
-                                      struct perf_sample *sample,
-                                      struct perf_tool *tool,
-                                      u64 file_offset);
-
-static int flush_sample_queue(struct perf_session *s,
-                       struct perf_tool *tool)
-{
-        struct ordered_samples *os = &s->ordered_samples;
-        struct list_head *head = &os->samples;
-        struct sample_queue *tmp, *iter;
-        struct perf_sample sample;
-        u64 limit = os->next_flush;
-        u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
-        bool show_progress = limit == ULLONG_MAX;
-        struct ui_progress prog;
-        int ret;
-
-        if (!tool->ordered_samples || !limit)
-                return 0;
-
-        if (show_progress)
-                ui_progress__init(&prog, os->nr_samples, "Processing time ordered events...");
-
-        list_for_each_entry_safe(iter, tmp, head, list) {
-                if (session_done())
-                        return 0;
-
-                if (iter->timestamp > limit)
-                        break;
-
-                ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample);
-                if (ret)
-                        pr_err("Can't parse sample, err = %d\n", ret);
-                else {
-                        ret = perf_session_deliver_event(s, iter->event, &sample, tool,
-                                                         iter->file_offset);
-                        if (ret)
-                                return ret;
-                }
-
-                os->last_flush = iter->timestamp;
-                list_del(&iter->list);
-                list_add(&iter->list, &os->sample_cache);
-                os->nr_samples--;
-
-                if (show_progress)
-                        ui_progress__update(&prog, 1);
-        }
-
-        if (list_empty(head)) {
-                os->last_sample = NULL;
-        } else if (last_ts <= limit) {
-                os->last_sample =
-                        list_entry(head->prev, struct sample_queue, list);
-        }
-
-        return 0;
-}
-
 /*
  * When perf record finishes a pass on every buffers, it records this pseudo
  * event.
@@ -568,99 +506,42 @@ static int process_finished_round(struct perf_tool *tool,
                                   union perf_event *event __maybe_unused,
                                   struct perf_session *session)
 {
-        int ret = flush_sample_queue(session, tool);
-        if (!ret)
-                session->ordered_samples.next_flush = session->ordered_samples.max_timestamp;
-
-        return ret;
-}
-
-/* The queue is ordered by time */
-static void __queue_event(struct sample_queue *new, struct perf_session *s)
-{
-        struct ordered_samples *os = &s->ordered_samples;
-        struct sample_queue *sample = os->last_sample;
-        u64 timestamp = new->timestamp;
-        struct list_head *p;
-
-        ++os->nr_samples;
-        os->last_sample = new;
-
-        if (!sample) {
-                list_add(&new->list, &os->samples);
-                os->max_timestamp = timestamp;
-                return;
-        }
-
-        /*
-         * last_sample might point to some random place in the list as it's
-         * the last queued event. We expect that the new event is close to
-         * this.
-         */
-        if (sample->timestamp <= timestamp) {
-                while (sample->timestamp <= timestamp) {
-                        p = sample->list.next;
-                        if (p == &os->samples) {
-                                list_add_tail(&new->list, &os->samples);
-                                os->max_timestamp = timestamp;
-                                return;
-                        }
-                        sample = list_entry(p, struct sample_queue, list);
-                }
-                list_add_tail(&new->list, &sample->list);
-        } else {
-                while (sample->timestamp > timestamp) {
-                        p = sample->list.prev;
-                        if (p == &os->samples) {
-                                list_add(&new->list, &os->samples);
-                                return;
-                        }
-                        sample = list_entry(p, struct sample_queue, list);
-                }
-                list_add(&new->list, &sample->list);
-        }
+        return ordered_events__flush(session, tool, OE_FLUSH__ROUND);
 }
 
-#define MAX_SAMPLE_BUFFER       (64 * 1024 / sizeof(struct sample_queue))
-
 int perf_session_queue_event(struct perf_session *s, union perf_event *event,
-                                    struct perf_sample *sample, u64 file_offset)
+                             struct perf_tool *tool, struct perf_sample *sample,
+                             u64 file_offset)
 {
-        struct ordered_samples *os = &s->ordered_samples;
-        struct list_head *sc = &os->sample_cache;
+        struct ordered_events *oe = &s->ordered_events;
         u64 timestamp = sample->time;
-        struct sample_queue *new;
+        struct ordered_event *new;
 
         if (!timestamp || timestamp == ~0ULL)
                 return -ETIME;
 
-        if (timestamp < s->ordered_samples.last_flush) {
-                printf("Warning: Timestamp below last timeslice flush\n");
-                return -EINVAL;
-        }
+        if (timestamp < oe->last_flush) {
+                WARN_ONCE(1, "Timestamp below last timeslice flush\n");
 
-        if (!list_empty(sc)) {
-                new = list_entry(sc->next, struct sample_queue, list);
-                list_del(&new->list);
-        } else if (os->sample_buffer) {
-                new = os->sample_buffer + os->sample_buffer_idx;
-                if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER)
-                        os->sample_buffer = NULL;
-        } else {
-                os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new));
-                if (!os->sample_buffer)
-                        return -ENOMEM;
-                list_add(&os->sample_buffer->list, &os->to_free);
-                os->sample_buffer_idx = 2;
-                new = os->sample_buffer + 1;
+                pr_oe_time(timestamp,      "out of order event");
+                pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n",
+                           oe->last_flush_type);
+
+                /* We could get out of order messages after forced flush. */
+                if (oe->last_flush_type != OE_FLUSH__HALF)
+                        return -EINVAL;
         }
 
-        new->timestamp = timestamp;
-        new->file_offset = file_offset;
-        new->event = event;
+        new = ordered_events__new(oe, timestamp, event);
+        if (!new) {
+                ordered_events__flush(s, tool, OE_FLUSH__HALF);
+                new = ordered_events__new(oe, timestamp, event);
+        }
 
-        __queue_event(new, s);
+        if (!new)
+                return -ENOMEM;
 
+        new->file_offset = file_offset;
         return 0;
 }
 
@@ -920,11 +801,10 @@ perf_session__deliver_sample(struct perf_session *session,
                                             &sample->read.one, machine);
 }
 
-static int perf_session_deliver_event(struct perf_session *session,
-                                      union perf_event *event,
-                                      struct perf_sample *sample,
-                                      struct perf_tool *tool,
-                                      u64 file_offset)
+int perf_session__deliver_event(struct perf_session *session,
+                                union perf_event *event,
+                                struct perf_sample *sample,
+                                struct perf_tool *tool, u64 file_offset)
 {
         struct perf_evsel *evsel;
         struct machine *machine;
@@ -932,22 +812,6 @@ static int perf_session_deliver_event(struct perf_session *session,
         dump_event(session, event, file_offset, sample);
 
         evsel = perf_evlist__id2evsel(session->evlist, sample->id);
-        if (evsel != NULL && event->header.type != PERF_RECORD_SAMPLE) {
-                /*
-                 * XXX We're leaving PERF_RECORD_SAMPLE unnacounted here
-                 * because the tools right now may apply filters, discarding
-                 * some of the samples. For consistency, in the future we
-                 * should have something like nr_filtered_samples and remove
-                 * the sample->period from total_sample_period, etc, KISS for
-                 * now tho.
-                 *
-                 * Also testing against NULL allows us to handle files without
-                 * attr.sample_id_all and/or without PERF_SAMPLE_ID. In the
-                 * future probably it'll be a good idea to restrict event
-                 * processing via perf_session to files with both set.
-                 */
-                hists__inc_nr_events(&evsel->hists, event->header.type);
-        }
 
         machine = perf_session__find_machine_for_cpumode(session, event,
                                                          sample);
@@ -1005,8 +869,10 @@ static s64 perf_session__process_user_event(struct perf_session *session,
         switch (event->header.type) {
         case PERF_RECORD_HEADER_ATTR:
                 err = tool->attr(tool, event, &session->evlist);
-                if (err == 0)
+                if (err == 0) {
                         perf_session__set_id_hdr_size(session);
+                        perf_session__set_comm_exec(session);
+                }
                 return err;
         case PERF_RECORD_HEADER_EVENT_TYPE:
                 /*
@@ -1036,6 +902,61 @@ static void event_swap(union perf_event *event, bool sample_id_all)
                 swap(event, sample_id_all);
 }
 
+int perf_session__peek_event(struct perf_session *session, off_t file_offset,
+                             void *buf, size_t buf_sz,
+                             union perf_event **event_ptr,
+                             struct perf_sample *sample)
+{
+        union perf_event *event;
+        size_t hdr_sz, rest;
+        int fd;
+
+        if (session->one_mmap && !session->header.needs_swap) {
+                event = file_offset - session->one_mmap_offset +
+                        session->one_mmap_addr;
+                goto out_parse_sample;
+        }
+
+        if (perf_data_file__is_pipe(session->file))
+                return -1;
+
+        fd = perf_data_file__fd(session->file);
+        hdr_sz = sizeof(struct perf_event_header);
+
+        if (buf_sz < hdr_sz)
+                return -1;
+
+        if (lseek(fd, file_offset, SEEK_SET) == (off_t)-1 ||
+            readn(fd, &buf, hdr_sz) != (ssize_t)hdr_sz)
+                return -1;
+
+        event = (union perf_event *)buf;
+
+        if (session->header.needs_swap)
+                perf_event_header__bswap(&event->header);
+
+        if (event->header.size < hdr_sz)
+                return -1;
+
+        rest = event->header.size - hdr_sz;
+
+        if (readn(fd, &buf, rest) != (ssize_t)rest)
+                return -1;
+
+        if (session->header.needs_swap)
+                event_swap(event, perf_evlist__sample_id_all(session->evlist));
+
+out_parse_sample:
+
+        if (sample && event->header.type < PERF_RECORD_USER_TYPE_START &&
+            perf_evlist__parse_sample(session->evlist, event, sample))
+                return -1;
+
+        *event_ptr = event;
+
+        return 0;
+}
+
 static s64 perf_session__process_event(struct perf_session *session,
                                        union perf_event *event,
                                        struct perf_tool *tool,
@@ -1062,15 +983,15 @@ static s64 perf_session__process_event(struct perf_session *session,
         if (ret)
                 return ret;
 
-        if (tool->ordered_samples) {
-                ret = perf_session_queue_event(session, event, &sample,
+        if (tool->ordered_events) {
+                ret = perf_session_queue_event(session, event, tool, &sample,
                                                file_offset);
                 if (ret != -ETIME)
                         return ret;
         }
 
-        return perf_session_deliver_event(session, event, &sample, tool,
-                                          file_offset);
+        return perf_session__deliver_event(session, event, &sample, tool,
+                                           file_offset);
 }
 
 void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -1222,12 +1143,11 @@ more:
                 goto more;
 done:
         /* do the final flush for ordered samples */
-        session->ordered_samples.next_flush = ULLONG_MAX;
-        err = flush_sample_queue(session, tool);
+        err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
 out_err:
         free(buf);
         perf_session__warn_about_errors(session, tool);
-        perf_session_free_sample_buffers(session);
+        ordered_events__free(&session->ordered_events);
         return err;
 }
 
@@ -1368,12 +1288,11 @@ more:
 
 out:
         /* do the final flush for ordered samples */
-        session->ordered_samples.next_flush = ULLONG_MAX;
-        err = flush_sample_queue(session, tool);
+        err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
 out_err:
         ui_progress__finish();
         perf_session__warn_about_errors(session, tool);
-        perf_session_free_sample_buffers(session);
+        ordered_events__free(&session->ordered_events);
         session->one_mmap = false;
         return err;
 }
@@ -1455,16 +1374,9 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp
 
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 {
-        struct perf_evsel *pos;
         size_t ret = fprintf(fp, "Aggregated stats:\n");
 
         ret += events_stats__fprintf(&session->stats, fp);
-
-        evlist__for_each(session->evlist, pos) {
-                ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
-                ret += events_stats__fprintf(&pos->hists.stats, fp);
-        }
-
         return ret;
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 0321013bd9fd..a4be851f1a90 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -2,33 +2,19 @@
 #define __PERF_SESSION_H
 
 #include "trace-event.h"
-#include "hist.h"
 #include "event.h"
 #include "header.h"
 #include "machine.h"
 #include "symbol.h"
 #include "thread.h"
 #include "data.h"
+#include "ordered-events.h"
 #include <linux/rbtree.h>
 #include <linux/perf_event.h>
 
-struct sample_queue;
 struct ip_callchain;
 struct thread;
 
-struct ordered_samples {
-        u64                     last_flush;
-        u64                     next_flush;
-        u64                     max_timestamp;
-        struct list_head        samples;
-        struct list_head        sample_cache;
-        struct list_head        to_free;
-        struct sample_queue     *sample_buffer;
-        struct sample_queue     *last_sample;
-        int                     sample_buffer_idx;
-        unsigned int            nr_samples;
-};
-
 struct perf_session {
         struct perf_header      header;
         struct machines         machines;
@@ -39,7 +25,7 @@ struct perf_session {
         bool                    one_mmap;
         void                    *one_mmap_addr;
         u64                     one_mmap_offset;
-        struct ordered_samples  ordered_samples;
+        struct ordered_events   ordered_events;
         struct perf_data_file   *file;
 };
 
@@ -58,6 +44,11 @@ void perf_session__delete(struct perf_session *session);
 
 void perf_event_header__bswap(struct perf_event_header *hdr);
 
+int perf_session__peek_event(struct perf_session *session, off_t file_offset,
+                             void *buf, size_t buf_sz,
+                             union perf_event **event_ptr,
+                             struct perf_sample *sample);
+
 int __perf_session__process_events(struct perf_session *session,
                                    u64 data_offset, u64 data_size, u64 size,
                                    struct perf_tool *tool);
@@ -65,10 +56,16 @@ int perf_session__process_events(struct perf_session *session,
                                  struct perf_tool *tool);
 
 int perf_session_queue_event(struct perf_session *s, union perf_event *event,
-                             struct perf_sample *sample, u64 file_offset);
+                             struct perf_tool *tool, struct perf_sample *sample,
+                             u64 file_offset);
 
 void perf_tool__fill_defaults(struct perf_tool *tool);
 
+int perf_session__deliver_event(struct perf_session *session,
+                                union perf_event *event,
+                                struct perf_sample *sample,
+                                struct perf_tool *tool, u64 file_offset);
+
 int perf_session__resolve_callchain(struct perf_session *session,
                                     struct perf_evsel *evsel,
                                     struct thread *thread,
@@ -128,5 +125,5 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 
 extern volatile int session_done;
 
-#define session_done()  (*(volatile int *)(&session_done))
+#define session_done()  ACCESS_ONCE(session_done)
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 14e5a039bc45..9402885a77f3 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -70,12 +70,14 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
                                        size_t size, unsigned int width)
 {
         const char *comm = thread__comm_str(he->thread);
-        return repsep_snprintf(bf, size, "%*s:%5d", width - 6,
-                               comm ?: "", he->thread->tid);
+
+        width = max(7U, width) - 6;
+        return repsep_snprintf(bf, size, "%5d:%-*.*s", he->thread->tid,
+                               width, width, comm ?: "");
 }
 
 struct sort_entry sort_thread = {
-        .se_header      = "Command:  Pid",
+        .se_header      = "  Pid:Command",
         .se_cmp         = sort__thread_cmp,
         .se_snprintf    = hist_entry__thread_snprintf,
         .se_width_idx   = HISTC_THREAD,
@@ -106,7 +108,7 @@ sort__comm_sort(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf,
                                      size_t size, unsigned int width)
 {
-        return repsep_snprintf(bf, size, "%*s", width, comm__str(he->comm));
+        return repsep_snprintf(bf, size, "%-*.*s", width, width, comm__str(he->comm));
 }
 
 struct sort_entry sort_comm = {
@@ -152,10 +154,10 @@ static int _hist_entry__dso_snprintf(struct map *map, char *bf,
         if (map && map->dso) {
                 const char *dso_name = !verbose ? map->dso->short_name :
                         map->dso->long_name;
-                return repsep_snprintf(bf, size, "%-*s", width, dso_name);
+                return repsep_snprintf(bf, size, "%-*.*s", width, width, dso_name);
         }
 
-        return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
+        return repsep_snprintf(bf, size, "%-*.*s", width, width, "[unknown]");
 }
 
 static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf,
@@ -257,7 +259,10 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
                                        width - ret, "");
         }
 
-        return ret;
+        if (ret > width)
+                bf[width] = '\0';
+
+        return width;
 }
 
 static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
@@ -302,10 +307,9 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 }
 
 static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
-                                        size_t size,
-                                        unsigned int width __maybe_unused)
+                                        size_t size, unsigned int width)
 {
-        return repsep_snprintf(bf, size, "%s", he->srcline);
+        return repsep_snprintf(bf, size, "%*.*-s", width, width, he->srcline);
 }
 
 struct sort_entry sort_srcline = {
@@ -332,7 +336,7 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf,
                                        size_t size, unsigned int width)
 {
-        return repsep_snprintf(bf, size, "%-*s", width,
+        return repsep_snprintf(bf, size, "%-*.*s", width, width,
                               he->parent ? he->parent->name : "[other]");
 }
 
@@ -354,7 +358,7 @@ sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__cpu_snprintf(struct hist_entry *he, char *bf,
                                     size_t size, unsigned int width)
 {
-        return repsep_snprintf(bf, size, "%*d", width, he->cpu);
+        return repsep_snprintf(bf, size, "%*.*d", width, width, he->cpu);
 }
 
 struct sort_entry sort_cpu = {
@@ -369,6 +373,9 @@ struct sort_entry sort_cpu = {
 static int64_t
 sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+        if (!left->branch_info || !right->branch_info)
+                return cmp_null(left->branch_info, right->branch_info);
+
         return _sort__dso_cmp(left->branch_info->from.map,
                               right->branch_info->from.map);
 }
@@ -376,13 +383,19 @@ sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf,
                                     size_t size, unsigned int width)
 {
-        return _hist_entry__dso_snprintf(he->branch_info->from.map,
-                                         bf, size, width);
+        if (he->branch_info)
+                return _hist_entry__dso_snprintf(he->branch_info->from.map,
+                                                 bf, size, width);
+        else
+                return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
 static int64_t
 sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+        if (!left->branch_info || !right->branch_info)
+                return cmp_null(left->branch_info, right->branch_info);
+
         return _sort__dso_cmp(left->branch_info->to.map,
                               right->branch_info->to.map);
 }
@@ -390,8 +403,11 @@ sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf,
                                        size_t size, unsigned int width)
 {
-        return _hist_entry__dso_snprintf(he->branch_info->to.map,
-                                         bf, size, width);
+        if (he->branch_info)
+                return _hist_entry__dso_snprintf(he->branch_info->to.map,
+                                                 bf, size, width);
+        else
+                return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
 static int64_t
@@ -400,6 +416,12 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
         struct addr_map_symbol *from_l = &left->branch_info->from;
         struct addr_map_symbol *from_r = &right->branch_info->from;
 
+        if (!left->branch_info || !right->branch_info)
+                return cmp_null(left->branch_info, right->branch_info);
+
+        from_l = &left->branch_info->from;
+        from_r = &right->branch_info->from;
+
         if (!from_l->sym && !from_r->sym)
                 return _sort__addr_cmp(from_l->addr, from_r->addr);
 
@@ -409,8 +431,13 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
 static int64_t
 sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-        struct addr_map_symbol *to_l = &left->branch_info->to;
-        struct addr_map_symbol *to_r = &right->branch_info->to;
+        struct addr_map_symbol *to_l, *to_r;
+
+        if (!left->branch_info || !right->branch_info)
+                return cmp_null(left->branch_info, right->branch_info);
+
+        to_l = &left->branch_info->to;
+        to_r = &right->branch_info->to;
 
         if (!to_l->sym && !to_r->sym)
                 return _sort__addr_cmp(to_l->addr, to_r->addr);
@@ -421,19 +448,27 @@ sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf,
                                          size_t size, unsigned int width)
 {
-        struct addr_map_symbol *from = &he->branch_info->from;
-        return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
-                                         he->level, bf, size, width);
+        if (he->branch_info) {
+                struct addr_map_symbol *from = &he->branch_info->from;
 
+                return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
+                                                 he->level, bf, size, width);
+        }
+
+        return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
 static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf,
                                        size_t size, unsigned int width)
 {
-        struct addr_map_symbol *to = &he->branch_info->to;
-        return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
-                                         he->level, bf, size, width);
+        if (he->branch_info) {
+                struct addr_map_symbol *to = &he->branch_info->to;
 
+                return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
+                                                 he->level, bf, size, width);
+        }
+
+        return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
 struct sort_entry sort_dso_from = {
@@ -467,11 +502,13 @@ struct sort_entry sort_sym_to = {
 static int64_t
 sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-        const unsigned char mp = left->branch_info->flags.mispred !=
-                                        right->branch_info->flags.mispred;
-        const unsigned char p = left->branch_info->flags.predicted !=
-                                        right->branch_info->flags.predicted;
+        unsigned char mp, p;
 
+        if (!left->branch_info || !right->branch_info)
+                return cmp_null(left->branch_info, right->branch_info);
+
+        mp = left->branch_info->flags.mispred != right->branch_info->flags.mispred;
+        p  = left->branch_info->flags.predicted != right->branch_info->flags.predicted;
         return mp || p;
 }
 
@@ -479,12 +516,14 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf,
                                     size_t size, unsigned int width){
         static const char *out = "N/A";
 
-        if (he->branch_info->flags.predicted)
-                out = "N";
-        else if (he->branch_info->flags.mispred)
-                out = "Y";
+        if (he->branch_info) {
+                if (he->branch_info->flags.predicted)
+                        out = "N";
+                else if (he->branch_info->flags.mispred)
+                        out = "Y";
+        }
 
-        return repsep_snprintf(bf, size, "%-*s", width, out);
+        return repsep_snprintf(bf, size, "%-*.*s", width, width, out);
 }
 
 /* --sort daddr_sym */
@@ -985,6 +1024,9 @@ struct sort_entry sort_mem_dcacheline = {
 static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+        if (!left->branch_info || !right->branch_info)
+                return cmp_null(left->branch_info, right->branch_info);
+
         return left->branch_info->flags.abort !=
                 right->branch_info->flags.abort;
 }
@@ -992,10 +1034,15 @@ sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__abort_snprintf(struct hist_entry *he, char *bf,
                                     size_t size, unsigned int width)
 {
-        static const char *out = ".";
+        static const char *out = "N/A";
+
+        if (he->branch_info) {
+                if (he->branch_info->flags.abort)
+                        out = "A";
+                else
+                        out = ".";
+        }
 
-        if (he->branch_info->flags.abort)
-                out = "A";
         return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
@@ -1009,6 +1056,9 @@ struct sort_entry sort_abort = {
 static int64_t
 sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+        if (!left->branch_info || !right->branch_info)
+                return cmp_null(left->branch_info, right->branch_info);
+
         return left->branch_info->flags.in_tx !=
                 right->branch_info->flags.in_tx;
 }
@@ -1016,10 +1066,14 @@ sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__in_tx_snprintf(struct hist_entry *he, char *bf,
                                     size_t size, unsigned int width)
 {
-        static const char *out = ".";
+        static const char *out = "N/A";
 
-        if (he->branch_info->flags.in_tx)
-                out = "T";
+        if (he->branch_info) {
+                if (he->branch_info->flags.in_tx)
+                        out = "T";
+                else
+                        out = ".";
+        }
 
         return repsep_snprintf(bf, size, "%-*s", width, out);
 }
@@ -1194,7 +1248,7 @@ bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
         return hse_a->se == hse_b->se;
 }
 
-void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 {
         struct hpp_sort_entry *hse;
 
@@ -1202,20 +1256,21 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
                 return;
 
         hse = container_of(fmt, struct hpp_sort_entry, hpp);
-        hists__new_col_len(hists, hse->se->se_width_idx,
-                           strlen(hse->se->se_header));
+        hists__new_col_len(hists, hse->se->se_width_idx, strlen(fmt->name));
 }
 
 static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
                               struct perf_evsel *evsel)
 {
         struct hpp_sort_entry *hse;
-        size_t len;
+        size_t len = fmt->user_len;
 
         hse = container_of(fmt, struct hpp_sort_entry, hpp);
-        len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
 
-        return scnprintf(hpp->buf, hpp->size, "%-*s", len, hse->se->se_header);
+        if (!len)
+                len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx);
+
+        return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name);
 }
 
 static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
@@ -1223,20 +1278,26 @@ static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
                              struct perf_evsel *evsel)
 {
         struct hpp_sort_entry *hse;
+        size_t len = fmt->user_len;
 
         hse = container_of(fmt, struct hpp_sort_entry, hpp);
 
-        return hists__col_len(&evsel->hists, hse->se->se_width_idx);
+        if (!len)
+                len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx);
+
+        return len;
 }
 
 static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
                              struct hist_entry *he)
 {
         struct hpp_sort_entry *hse;
-        size_t len;
+        size_t len = fmt->user_len;
 
         hse = container_of(fmt, struct hpp_sort_entry, hpp);
-        len = hists__col_len(he->hists, hse->se->se_width_idx);
+
+        if (!len)
+                len = hists__col_len(he->hists, hse->se->se_width_idx);
 
         return hse->se->se_snprintf(he, hpp->buf, hpp->size, len);
 }
@@ -1253,6 +1314,7 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
         }
 
         hse->se = sd->entry;
+        hse->hpp.name = sd->entry->se_header;
         hse->hpp.header = __sort__hpp_header;
         hse->hpp.width = __sort__hpp_width;
         hse->hpp.entry = __sort__hpp_entry;
@@ -1265,6 +1327,8 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
         INIT_LIST_HEAD(&hse->hpp.list);
         INIT_LIST_HEAD(&hse->hpp.sort_list);
         hse->hpp.elide = false;
+        hse->hpp.len = 0;
+        hse->hpp.user_len = 0;
 
         return hse;
 }
@@ -1432,14 +1496,49 @@ static const char *get_default_sort_order(void)
         return default_sort_orders[sort__mode];
 }
 
+static int setup_sort_order(void)
+{
+        char *new_sort_order;
+
+        /*
+         * Append '+'-prefixed sort order to the default sort
+         * order string.
+         */
+        if (!sort_order || is_strict_order(sort_order))
+                return 0;
+
+        if (sort_order[1] == '\0') {
+                error("Invalid --sort key: `+'");
+                return -EINVAL;
+        }
+
+        /*
+         * We allocate new sort_order string, but we never free it,
+         * because it's checked over the rest of the code.
+         */
+        if (asprintf(&new_sort_order, "%s,%s",
+                     get_default_sort_order(), sort_order + 1) < 0) {
+                error("Not enough memory to set up --sort");
+                return -ENOMEM;
+        }
+
+        sort_order = new_sort_order;
+        return 0;
+}
+
 static int __setup_sorting(void)
 {
         char *tmp, *tok, *str;
-        const char *sort_keys = sort_order;
+        const char *sort_keys;
         int ret = 0;
 
+        ret = setup_sort_order();
+        if (ret)
+                return ret;
+
+        sort_keys = sort_order;
         if (sort_keys == NULL) {
-                if (field_order) {
+                if (is_strict_order(field_order)) {
                         /*
                          * If user specified field order but no sort order,
                          * we'll honor it and not add default sort orders.
@@ -1625,23 +1724,36 @@ static void reset_dimensions(void)
                 memory_sort_dimensions[i].taken = 0;
 }
 
+bool is_strict_order(const char *order)
+{
+        return order && (*order != '+');
+}
+
 static int __setup_output_field(void)
 {
-        char *tmp, *tok, *str;
-        int ret = 0;
+        char *tmp, *tok, *str, *strp;
+        int ret = -EINVAL;
 
         if (field_order == NULL)
                 return 0;
 
         reset_dimensions();
 
-        str = strdup(field_order);
+        strp = str = strdup(field_order);
         if (str == NULL) {
                 error("Not enough memory to setup output fields");
                 return -ENOMEM;
         }
 
-        for (tok = strtok_r(str, ", ", &tmp);
+        if (!is_strict_order(field_order))
+                strp++;
+
+        if (!strlen(strp)) {
+                error("Invalid --fields key: `+'");
+                goto out;
+        }
+
+        for (tok = strtok_r(strp, ", ", &tmp);
                         tok; tok = strtok_r(NULL, ", ", &tmp)) {
                 ret = output_field_add(tok);
                 if (ret == -EINVAL) {
@@ -1653,6 +1765,7 @@ static int __setup_output_field(void)
                 }
         }
 
+out:
         free(str);
         return ret;
 }
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 041f0c9cea2b..c03e4ff8beff 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -218,4 +218,5 @@ void perf_hpp__set_elide(int idx, bool elide);
 
 int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
 
+bool is_strict_order(const char *order);
 #endif  /* __PERF_SORT_H */
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 2553e5b55b89..6afd6106ceb5 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -9,78 +9,48 @@
  */
 s64 perf_atoll(const char *str)
 {
-        unsigned int i;
-        s64 length = -1, unit = 1;
+        s64 length;
+        char *p;
+        char c;
 
         if (!isdigit(str[0]))
                 goto out_err;
 
-        for (i = 1; i < strlen(str); i++) {
-                switch (str[i]) {
-                case 'B':
-                case 'b':
-                        break;
-                case 'K':
-                        if (str[i + 1] != 'B')
-                                goto out_err;
-                        else
-                                goto kilo;
-                case 'k':
-                        if (str[i + 1] != 'b')
-                                goto out_err;
-kilo:
-                        unit = K;
-                        break;
-                case 'M':
-                        if (str[i + 1] != 'B')
-                                goto out_err;
-                        else
-                                goto mega;
-                case 'm':
-                        if (str[i + 1] != 'b')
-                                goto out_err;
-mega:
-                        unit = K * K;
-                        break;
-                case 'G':
-                        if (str[i + 1] != 'B')
+        length = strtoll(str, &p, 10);
+        switch (c = *p++) {
+                case 'b': case 'B':
+                        if (*p)
                                 goto out_err;
-                        else
-                                goto giga;
-                case 'g':
-                        if (str[i + 1] != 'b')
-                                goto out_err;
-giga:
-                        unit = K * K * K;
+                case '\0':
+                        return length;
+                default:
+                        goto out_err;
+                /* two-letter suffices */
+                case 'k': case 'K':
+                        length <<= 10;
                         break;
-                case 'T':
-                        if (str[i + 1] != 'B')
-                                goto out_err;
-                        else
-                                goto tera;
-                case 't':
-                        if (str[i + 1] != 'b')
-                                goto out_err;
-tera:
-                        unit = K * K * K * K;
+                case 'm': case 'M':
+                        length <<= 20;
                         break;
-                case '\0':      /* only specified figures */
-                        unit = 1;
+                case 'g': case 'G':
+                        length <<= 30;
                         break;
-                default:
-                        if (!isdigit(str[i]))
-                                goto out_err;
+                case 't': case 'T':
+                        length <<= 40;
                         break;
-                }
         }
-
-        length = atoll(str) * unit;
-        goto out;
+        /* we want the cases to match */
+        if (islower(c)) {
+                if (strcmp(p, "b") != 0)
+                        goto out_err;
+        } else {
+                if (strcmp(p, "B") != 0)
+                        goto out_err;
+        }
+        return length;
 
 out_err:
-        length = -1;
-out:
-        return length;
+        return -1;
 }
 
 /*
@@ -387,27 +357,3 @@ void *memdup(const void *src, size_t len)
 
         return p;
 }
-
-/**
- * str_append - reallocate string and append another
- * @s: pointer to string pointer
- * @len: pointer to len (initialized)
- * @a: string to append.
- */
-int str_append(char **s, int *len, const char *a)
-{
-        int olen = *s ? strlen(*s) : 0;
-        int nlen = olen + strlen(a) + 1;
-        if (*len < nlen) {
-                *len = *len * 2;
-                if (*len < nlen)
-                        *len = nlen;
-                *s = realloc(*s, *len);
-                if (!*s)
-                        return -ENOMEM;
-                if (olen == 0)
-                        **s = 0;
-        }
-        strcat(*s, a);
-        return 0;
-}
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index d75349979e65..1e23a5bfb044 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -6,6 +6,7 @@
 #include <inttypes.h>
 
 #include "symbol.h"
+#include "machine.h"
 #include "vdso.h"
 #include <symbol/kallsyms.h>
 #include "debug.h"
@@ -680,6 +681,11 @@ static u64 ref_reloc(struct kmap *kmap)
         return 0;
 }
 
+static bool want_demangle(bool is_kernel_sym)
+{
+        return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
+}
+
 int dso__load_sym(struct dso *dso, struct map *map,
                   struct symsrc *syms_ss, struct symsrc *runtime_ss,
                   symbol_filter_t filter, int kmodule)
@@ -712,6 +718,14 @@ int dso__load_sym(struct dso *dso, struct map *map,
                 symbols__delete(&dso->symbols[map->type]);
 
         if (!syms_ss->symtab) {
+                /*
+                 * If the vmlinux is stripped, fail so we will fall back
+                 * to using kallsyms. The vmlinux runtime symbols aren't
+                 * of much use.
+                 */
+                if (dso->kernel)
+                        goto out_elf_end;
+
                 syms_ss->symtab  = syms_ss->dynsym;
                 syms_ss->symshdr = syms_ss->dynshdr;
         }
@@ -736,7 +750,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
         if (symstrs == NULL)
                 goto out_elf_end;
 
-        sec_strndx = elf_getscn(elf, ehdr.e_shstrndx);
+        sec_strndx = elf_getscn(runtime_ss->elf, runtime_ss->ehdr.e_shstrndx);
         if (sec_strndx == NULL)
                 goto out_elf_end;
 
@@ -916,7 +930,11 @@ int dso__load_sym(struct dso *dso, struct map *map,
                                 }
                                 curr_dso->symtab_type = dso->symtab_type;
                                 map_groups__insert(kmap->kmaps, curr_map);
-                                dsos__add(&dso->node, curr_dso);
+                                /*
+                                 * The new DSO should go to the kernel DSOS
+                                 */
+                                dsos__add(&map->groups->machine->kernel_dsos,
+                                          curr_dso);
                                 dso__set_loaded(curr_dso, map->type);
                         } else
                                 curr_dso = curr_map->dso;
@@ -938,9 +956,12 @@ new_symbol:
                  * DWARF DW_compile_unit has this, but we don't always have access
                  * to it...
                  */
-                if (symbol_conf.demangle) {
-                        demangled = bfd_demangle(NULL, elf_name,
-                                                 DMGL_PARAMS | DMGL_ANSI);
+                if (want_demangle(dso->kernel || kmodule)) {
+                        int demangle_flags = DMGL_NO_OPTS;
+                        if (verbose)
+                                demangle_flags = DMGL_PARAMS | DMGL_ANSI;
+
+                        demangled = bfd_demangle(NULL, elf_name, demangle_flags);
                         if (demangled != NULL)
                                 elf_name = demangled;
                 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index eb06746b06b2..078331140d8c 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -15,6 +15,7 @@
 #include "machine.h"
 #include "symbol.h"
 #include "strlist.h"
+#include "header.h"
 
 #include <elf.h>
 #include <limits.h>
@@ -33,6 +34,7 @@ struct symbol_conf symbol_conf = {
         .try_vmlinux_path       = true,
         .annotate_src           = true,
         .demangle               = true,
+        .demangle_kernel        = false,
         .cumulate_callchain     = true,
         .show_hist_headers      = true,
         .symfs                  = "",
@@ -184,7 +186,7 @@ void symbols__fixup_end(struct rb_root *symbols)
                 curr = rb_entry(nd, struct symbol, rb_node);
 
                 if (prev->end == prev->start && prev->end != curr->start)
-                        prev->end = curr->start - 1;
+                        prev->end = curr->start;
         }
 
         /* Last entry */
@@ -205,7 +207,7 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
         for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) {
                 prev = curr;
                 curr = rb_entry(nd, struct map, rb_node);
-                prev->end = curr->start - 1;
+                prev->end = curr->start;
         }
 
         /*
@@ -227,7 +229,7 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
                 sym = ((void *)sym) + symbol_conf.priv_size;
 
         sym->start   = start;
-        sym->end     = len ? start + len - 1 : start;
+        sym->end     = len ? start + len : start;
         sym->binding = binding;
         sym->namelen = namelen - 1;
 
@@ -323,7 +325,7 @@ static struct symbol *symbols__find(struct rb_root *symbols, u64 ip)
 
                 if (ip < s->start)
                         n = n->rb_left;
-                else if (ip > s->end)
+                else if (ip >= s->end)
                         n = n->rb_right;
                 else
                         return s;
@@ -523,10 +525,15 @@ struct process_kallsyms_args {
         struct dso *dso;
 };
 
+/*
+ * These are symbols in the kernel image, so make sure that
+ * sym is from a kernel DSO.
+ */
 bool symbol__is_idle(struct symbol *sym)
 {
         const char * const idle_symbols[] = {
                 "cpu_idle",
+                "cpu_startup_entry",
                 "intel_idle",
                 "default_idle",
                 "native_safe_halt",
@@ -1468,8 +1475,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
         if (vmlinux[0] == '/')
                 snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s", vmlinux);
         else
-                snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s",
-                         symbol_conf.symfs, vmlinux);
+                symbol__join_symfs(symfs_vmlinux, vmlinux);
 
         if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
                 symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
@@ -1745,12 +1751,13 @@ static void vmlinux_path__exit(void)
         zfree(&vmlinux_path);
 }
 
-static int vmlinux_path__init(void)
+static int vmlinux_path__init(struct perf_session_env *env)
 {
         struct utsname uts;
         char bf[PATH_MAX];
+        char *kernel_version;
 
-        vmlinux_path = malloc(sizeof(char *) * 5);
+        vmlinux_path = malloc(sizeof(char *) * 6);
         if (vmlinux_path == NULL)
                 return -1;
 
@@ -1763,25 +1770,37 @@ static int vmlinux_path__init(void)
                 goto out_fail;
         ++vmlinux_path__nr_entries;
 
-        /* only try running kernel version if no symfs was given */
+        /* only try kernel version if no symfs was given */
         if (symbol_conf.symfs[0] != 0)
                 return 0;
 
-        if (uname(&uts) < 0)
-                return -1;
+        if (env) {
+                kernel_version = env->os_release;
+        } else {
+                if (uname(&uts) < 0)
+                        goto out_fail;
 
-        snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", uts.release);
+                kernel_version = uts.release;
+        }
+
+        snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", kernel_version);
         vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
         if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
                 goto out_fail;
         ++vmlinux_path__nr_entries;
-        snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", uts.release);
+        snprintf(bf, sizeof(bf), "/usr/lib/debug/boot/vmlinux-%s",
+                 kernel_version);
+        vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
+        if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
+                goto out_fail;
+        ++vmlinux_path__nr_entries;
+        snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", kernel_version);
         vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
         if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
                 goto out_fail;
         ++vmlinux_path__nr_entries;
         snprintf(bf, sizeof(bf), "/usr/lib/debug/lib/modules/%s/vmlinux",
-                 uts.release);
+                 kernel_version);
         vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
         if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
                 goto out_fail;
@@ -1827,7 +1846,7 @@ static bool symbol__read_kptr_restrict(void)
         return value;
 }
 
-int symbol__init(void)
+int symbol__init(struct perf_session_env *env)
 {
         const char *symfs;
 
@@ -1842,7 +1861,7 @@ int symbol__init(void)
                 symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -
                                           sizeof(struct symbol));
 
-        if (symbol_conf.try_vmlinux_path && vmlinux_path__init() < 0)
+        if (symbol_conf.try_vmlinux_path && vmlinux_path__init(env) < 0)
                 return -1;
 
         if (symbol_conf.field_sep && *symbol_conf.field_sep == '.') {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index e7295e93cff9..eb2c19bf8d90 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -13,6 +13,7 @@
 #include <libgen.h>
 #include "build-id.h"
 #include "event.h"
+#include "util.h"
 
 #ifdef HAVE_LIBELF_SUPPORT
 #include <libelf.h>
@@ -59,6 +60,7 @@ extern Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 #endif
 
 #ifndef DMGL_PARAMS
+#define DMGL_NO_OPTS     0              /* For readability... */
 #define DMGL_PARAMS      (1 << 0)       /* Include function args */
 #define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
 #endif
@@ -93,7 +95,7 @@ void symbols__delete(struct rb_root *symbols);
 
 static inline size_t symbol__size(const struct symbol *sym)
 {
-        return sym->end - sym->start + 1;
+        return sym->end - sym->start;
 }
 
 struct strlist;
@@ -118,6 +120,7 @@ struct symbol_conf {
                         annotate_src,
                         event_group,
                         demangle,
+                        demangle_kernel,
                         filter_relative,
                         show_hist_headers;
         const char      *vmlinux_name,
@@ -143,6 +146,14 @@ struct symbol_conf {
 };
 
 extern struct symbol_conf symbol_conf;
+
+static inline int __symbol__join_symfs(char *bf, size_t size, const char *path)
+{
+        return path__join(bf, size, symbol_conf.symfs, path);
+}
+
+#define symbol__join_symfs(bf, path) __symbol__join_symfs(bf, sizeof(bf), path)
+
 extern int vmlinux_path__nr_entries;
 extern char **vmlinux_path;
 
@@ -253,7 +264,8 @@ int modules__parse(const char *filename, void *arg,
 int filename__read_debuglink(const char *filename, char *debuglink,
                              size_t size);
 
-int symbol__init(void);
+struct perf_session_env;
+int symbol__init(struct perf_session_env *env);
 void symbol__exit(void);
 void symbol__elf_init(void);
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 12c7a253a63c..c41411726c7a 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,6 +7,7 @@
 #include "util.h"
 #include "debug.h"
 #include "comm.h"
+#include "unwind.h"
 
 int thread__init_map_groups(struct thread *thread, struct machine *machine)
 {
@@ -37,17 +38,21 @@ struct thread *thread__new(pid_t pid, pid_t tid)
                 thread->cpu = -1;
                 INIT_LIST_HEAD(&thread->comm_list);
 
+                if (unwind__prepare_access(thread) < 0)
+                        goto err_thread;
+
                 comm_str = malloc(32);
                 if (!comm_str)
                         goto err_thread;
 
                 snprintf(comm_str, 32, ":%d", tid);
-                comm = comm__new(comm_str, 0);
+                comm = comm__new(comm_str, 0, false);
                 free(comm_str);
                 if (!comm)
                         goto err_thread;
 
                 list_add(&comm->list, &thread->comm_list);
+
         }
 
         return thread;
@@ -69,6 +74,7 @@ void thread__delete(struct thread *thread)
                 list_del(&comm->list);
                 comm__free(comm);
         }
+        unwind__finish_access(thread);
 
         free(thread);
 }
@@ -81,22 +87,39 @@ struct comm *thread__comm(const struct thread *thread)
         return list_first_entry(&thread->comm_list, struct comm, list);
 }
 
+struct comm *thread__exec_comm(const struct thread *thread)
+{
+        struct comm *comm, *last = NULL;
+
+        list_for_each_entry(comm, &thread->comm_list, list) {
+                if (comm->exec)
+                        return comm;
+                last = comm;
+        }
+
+        return last;
+}
+
 /* CHECKME: time should always be 0 if event aren't ordered */
-int thread__set_comm(struct thread *thread, const char *str, u64 timestamp)
+int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
+                       bool exec)
 {
         struct comm *new, *curr = thread__comm(thread);
         int err;
 
         /* Override latest entry if it had no specific time coverage */
-        if (!curr->start) {
-                err = comm__override(curr, str, timestamp);
+        if (!curr->start && !curr->exec) {
+                err = comm__override(curr, str, timestamp, exec);
                 if (err)
                         return err;
         } else {
-                new = comm__new(str, timestamp);
+                new = comm__new(str, timestamp, exec);
                 if (!new)
                         return -ENOMEM;
                 list_add(&new->list, &thread->comm_list);
+
+                if (exec)
+                        unwind__flush_access(thread);
         }
 
         thread->comm_set = true;
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 716b7723cce2..8c75fa774706 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -38,9 +38,17 @@ static inline void thread__exited(struct thread *thread)
         thread->dead = true;
 }
 
-int thread__set_comm(struct thread *thread, const char *comm, u64 timestamp);
+int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp,
+                       bool exec);
+static inline int thread__set_comm(struct thread *thread, const char *comm,
+                                   u64 timestamp)
+{
+        return __thread__set_comm(thread, comm, timestamp, false);
+}
+
 int thread__comm_len(struct thread *thread);
 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);
 void thread__insert_map(struct thread *thread, struct map *map);
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 5d3215912105..f93b9734735b 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -214,6 +214,17 @@ out_free_threads:
         goto out;
 }
 
+struct thread_map *thread_map__new_dummy(void)
+{
+        struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+
+        if (threads != NULL) {
+                threads->map[0] = -1;
+                threads->nr     = 1;
+        }
+        return threads;
+}
+
 static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 {
         struct thread_map *threads = NULL, *nt;
@@ -224,14 +235,8 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
         struct strlist *slist;
 
         /* perf-stat expects threads to be generated even if tid not given */
-        if (!tid_str) {
-                threads = malloc(sizeof(*threads) + sizeof(pid_t));
-                if (threads != NULL) {
-                        threads->map[0] = -1;
-                        threads->nr     = 1;
-                }
-                return threads;
-        }
+        if (!tid_str)
+                return thread_map__new_dummy();
 
         slist = strlist__new(false, tid_str);
         if (!slist)
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 0cd8b3108084..95313f43cc0f 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -9,6 +9,7 @@ struct thread_map {
         pid_t map[];
 };
 
+struct thread_map *thread_map__new_dummy(void);
 struct thread_map *thread_map__new_by_pid(pid_t pid);
 struct thread_map *thread_map__new_by_tid(pid_t tid);
 struct thread_map *thread_map__new_by_uid(uid_t uid);
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 4385816d3d49..f11636966a0f 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -40,7 +40,7 @@ struct perf_tool {
         event_op2       tracing_data;
         event_op2       finished_round,
                         build_id;
-        bool            ordered_samples;
+        bool            ordered_events;
         bool            ordering_requires_timestamps;
 };
 
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 57aaccc1692e..5c9bdd1591a9 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -30,6 +30,11 @@
 
 struct scripting_context *scripting_context;
 
+static int flush_script_unsupported(void)
+{
+        return 0;
+}
+
 static int stop_script_unsupported(void)
 {
         return 0;
@@ -74,6 +79,7 @@ static int python_generate_script_unsupported(struct pevent *pevent
 struct scripting_ops python_scripting_unsupported_ops = {
         .name = "Python",
         .start_script = python_start_script_unsupported,
+        .flush_script = flush_script_unsupported,
         .stop_script = stop_script_unsupported,
         .process_event = process_event_unsupported,
         .generate_script = python_generate_script_unsupported,
@@ -137,6 +143,7 @@ static int perl_generate_script_unsupported(struct pevent *pevent
 struct scripting_ops perl_scripting_unsupported_ops = {
         .name = "Perl",
         .start_script = perl_start_script_unsupported,
+        .flush_script = flush_script_unsupported,
         .stop_script = stop_script_unsupported,
         .process_event = process_event_unsupported,
         .generate_script = perl_generate_script_unsupported,
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 7b6d68688327..52aaa19e1eb1 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -64,6 +64,7 @@ struct perf_session;
 struct scripting_ops {
         const char *name;
         int (*start_script) (const char *script, int argc, const char **argv);
+        int (*flush_script) (void);
         int (*stop_script) (void);
         void (*process_event) (union perf_event *event,
                                struct perf_sample *sample,
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 92b56db52471..4d45c0dfe343 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -24,6 +24,7 @@
 #include <linux/list.h>
 #include <libunwind.h>
 #include <libunwind-ptrace.h>
+#include "callchain.h"
 #include "thread.h"
 #include "session.h"
 #include "perf_regs.h"
@@ -525,12 +526,12 @@ static unw_accessors_t accessors = {
         .get_proc_name          = get_proc_name,
 };
 
-static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
-                       void *arg, int max_stack)
+int unwind__prepare_access(struct thread *thread)
 {
         unw_addr_space_t addr_space;
-        unw_cursor_t c;
-        int ret;
+
+        if (callchain_param.record_mode != CALLCHAIN_DWARF)
+                return 0;
 
         addr_space = unw_create_addr_space(&accessors, 0);
         if (!addr_space) {
@@ -538,6 +539,45 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
                 return -ENOMEM;
         }
 
+        unw_set_caching_policy(addr_space, UNW_CACHE_GLOBAL);
+        thread__set_priv(thread, addr_space);
+
+        return 0;
+}
+
+void unwind__flush_access(struct thread *thread)
+{
+        unw_addr_space_t addr_space;
+
+        if (callchain_param.record_mode != CALLCHAIN_DWARF)
+                return;
+
+        addr_space = thread__priv(thread);
+        unw_flush_cache(addr_space, 0, 0);
+}
+
+void unwind__finish_access(struct thread *thread)
+{
+        unw_addr_space_t addr_space;
+
+        if (callchain_param.record_mode != CALLCHAIN_DWARF)
+                return;
+
+        addr_space = thread__priv(thread);
+        unw_destroy_addr_space(addr_space);
+}
+
+static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
+                       void *arg, int max_stack)
+{
+        unw_addr_space_t addr_space;
+        unw_cursor_t c;
+        int ret;
+
+        addr_space = thread__priv(ui->thread);
+        if (addr_space == NULL)
+                return -1;
+
         ret = unw_init_remote(&c, addr_space, ui);
         if (ret)
                 display_error(ret);
@@ -549,7 +589,6 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
                 ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0;
         }
 
-        unw_destroy_addr_space(addr_space);
         return ret;
 }
 
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index f03061260b4e..f50b737235eb 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include "event.h"
 #include "symbol.h"
+#include "thread.h"
 
 struct unwind_entry {
         struct map      *map;
@@ -21,6 +22,17 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 /* libunwind specific */
 #ifdef HAVE_LIBUNWIND_SUPPORT
 int libunwind__arch_reg_id(int regnum);
+int unwind__prepare_access(struct thread *thread);
+void unwind__flush_access(struct thread *thread);
+void unwind__finish_access(struct thread *thread);
+#else
+static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
+{
+        return 0;
+}
+
+static inline void unwind__flush_access(struct thread *thread __maybe_unused) {}
+static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
 #endif
 #else
 static inline int
@@ -33,5 +45,13 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
 {
         return 0;
 }
+
+static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
+{
+        return 0;
+}
+
+static inline void unwind__flush_access(struct thread *thread __maybe_unused) {}
+static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
 #endif /* HAVE_DWARF_UNWIND_SUPPORT */
 #endif /* __UNWIND_H */
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index e52e7461911b..d5eab3f3323f 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -13,6 +13,15 @@
 #include <limits.h>
 #include <byteswap.h>
 #include <linux/kernel.h>
+#include <unistd.h>
+#include "callchain.h"
+
+struct callchain_param  callchain_param = {
+        .mode   = CHAIN_GRAPH_REL,
+        .min_percent = 0.5,
+        .order  = ORDER_CALLEE,
+        .key    = CCKEY_FUNCTION
+};
 
 /*
  * XXX We need to find a better place for these things...
@@ -282,6 +291,18 @@ void get_term_dimensions(struct winsize *ws)
         ws->ws_col = 80;
 }
 
+void set_term_quiet_input(struct termios *old)
+{
+        struct termios tc;
+
+        tcgetattr(0, old);
+        tc = *old;
+        tc.c_lflag &= ~(ICANON | ECHO);
+        tc.c_cc[VMIN] = 0;
+        tc.c_cc[VTIME] = 0;
+        tcsetattr(0, TCSANOW, &tc);
+}
+
 static void set_tracing_events_path(const char *mountpoint)
 {
         snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s",
@@ -443,6 +464,7 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep)
         size_t size = 0, alloc_size = 0;
         void *bf = NULL, *nbf;
         int fd, n, err = 0;
+        char sbuf[STRERR_BUFSIZE];
 
         fd = open(filename, O_RDONLY);
         if (fd < 0)
@@ -463,8 +485,8 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep)
                 n = read(fd, bf + size, alloc_size - size);
                 if (n < 0) {
                         if (size) {
-                                pr_warning("read failed %d: %s\n",
-                                           errno, strerror(errno));
+                                pr_warning("read failed %d: %s\n", errno,
+                                         strerror_r(errno, sbuf, sizeof(sbuf)));
                                 err = 0;
                         } else
                                 err = -errno;
@@ -536,3 +558,39 @@ void mem_bswap_64(void *src, int byte_size)
                 ++m;
         }
 }
+
+bool find_process(const char *name)
+{
+        size_t len = strlen(name);
+        DIR *dir;
+        struct dirent *d;
+        int ret = -1;
+
+        dir = opendir(procfs__mountpoint());
+        if (!dir)
+                return -1;
+
+        /* Walk through the directory. */
+        while (ret && (d = readdir(dir)) != NULL) {
+                char path[PATH_MAX];
+                char *data;
+                size_t size;
+
+                if ((d->d_type != DT_DIR) ||
+                     !strcmp(".", d->d_name) ||
+                     !strcmp("..", d->d_name))
+                        continue;
+
+                scnprintf(path, sizeof(path), "%s/%s/comm",
+                          procfs__mountpoint(), d->d_name);
+
+                if (filename__read_str(path, &data, &size))
+                        continue;
+
+                ret = strncmp(name, data, len);
+                free(data);
+        }
+
+        closedir(dir);
+        return ret ? false : true;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 66864364ccb4..80bfdaa0e2a4 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -39,6 +39,8 @@
 
 #define _ALL_SOURCE 1
 #define _BSD_SOURCE 1
+/* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
+#define _DEFAULT_SOURCE 1
 #define HAS_BOOL
 
 #include <unistd.h>
@@ -64,16 +66,18 @@
 #include <regex.h>
 #include <utime.h>
 #include <sys/wait.h>
-#include <sys/poll.h>
+#include <poll.h>
 #include <sys/socket.h>
 #include <sys/ioctl.h>
 #include <inttypes.h>
+#include <linux/kernel.h>
 #include <linux/magic.h>
 #include <linux/types.h>
 #include <sys/ttydefaults.h>
 #include <api/fs/debugfs.h>
 #include <termios.h>
 #include <linux/bitops.h>
+#include <termios.h>
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
@@ -307,6 +311,7 @@ extern unsigned int page_size;
 extern int cacheline_size;
 
 void get_term_dimensions(struct winsize *ws);
+void set_term_quiet_input(struct termios *old);
 
 struct parse_tag {
         char tag;
@@ -317,6 +322,21 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags);
 
 #define SRCLINE_UNKNOWN  ((char *) "??:0")
 
+static inline int path__join(char *bf, size_t size,
+                             const char *path1, const char *path2)
+{
+        return scnprintf(bf, size, "%s%s%s", path1, path1[0] ? "/" : "", path2);
+}
+
+static inline int path__join3(char *bf, size_t size,
+                              const char *path1, const char *path2,
+                              const char *path3)
+{
+        return scnprintf(bf, size, "%s%s%s%s%s",
+                         path1, path1[0] ? "/" : "",
+                         path2, path2[0] ? "/" : "", path3);
+}
+
 struct dso;
 
 char *get_srcline(struct dso *dso, unsigned long addr);
@@ -330,4 +350,5 @@ void mem_bswap_64(void *src, int byte_size);
 void mem_bswap_32(void *src, int byte_size);
 
 const char *get_filename_for_perf_kvm(void);
+bool find_process(const char *name);
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/power/acpi/os_specific/service_layers/osunixxf.c b/tools/power/acpi/os_specific/service_layers/osunixxf.c
index 60b58cd18410..7ccb073f8316 100644
--- a/tools/power/acpi/os_specific/service_layers/osunixxf.c
+++ b/tools/power/acpi/os_specific/service_layers/osunixxf.c
@@ -122,6 +122,14 @@ static void os_enter_line_edit_mode(void)
 {
         struct termios local_term_attributes;
 
+        term_attributes_were_set = 0;
+
+        /* STDIN must be a terminal */
+
+        if (!isatty(STDIN_FILENO)) {
+                return;
+        }
+
         /* Get and keep the original attributes */
 
         if (tcgetattr(STDIN_FILENO, &original_term_attributes)) {
diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c
index 53cee781e24e..24d32968802d 100644
--- a/tools/power/acpi/tools/acpidump/apdump.c
+++ b/tools/power/acpi/tools/acpidump/apdump.c
@@ -146,7 +146,7 @@ u32 ap_get_table_length(struct acpi_table_header *table)
 
         if (ACPI_VALIDATE_RSDP_SIG(table->signature)) {
                 rsdp = ACPI_CAST_PTR(struct acpi_table_rsdp, table);
-                return (rsdp->length);
+                return (acpi_tb_get_rsdp_length(rsdp));
         }
 
         /* Normal ACPI table */
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index d0396af99fa0..5b1b807265a1 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -267,90 +267,90 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 /*
  * Example Format w/ field column widths:
  *
- * Package    Core     CPU Avg_MHz Bzy_MHz TSC_MHz     SMI   %Busy CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 CoreTmp  PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
- * 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567
+ *  Package    Core     CPU Avg_MHz Bzy_MHz TSC_MHz     SMI   %Busy CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 CoreTmp  PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
+ * 123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678
  */
 
 void print_header(void)
 {
         if (show_pkg)
-                outp += sprintf(outp, "Package ");
+                outp += sprintf(outp, " Package");
         if (show_core)
-                outp += sprintf(outp, "    Core ");
+                outp += sprintf(outp, "    Core");
         if (show_cpu)
-                outp += sprintf(outp, "    CPU ");
+                outp += sprintf(outp, "     CPU");
         if (has_aperf)
-                outp += sprintf(outp, "Avg_MHz ");
+                outp += sprintf(outp, " Avg_MHz");
         if (do_nhm_cstates)
-                outp += sprintf(outp, "  %%Busy ");
+                outp += sprintf(outp, "   %%Busy");
         if (has_aperf)
-                outp += sprintf(outp, "Bzy_MHz ");
-        outp += sprintf(outp, "TSC_MHz ");
+                outp += sprintf(outp, " Bzy_MHz");
+        outp += sprintf(outp, " TSC_MHz");
         if (do_smi)
-                outp += sprintf(outp, "    SMI ");
+                outp += sprintf(outp, "     SMI");
         if (extra_delta_offset32)
-                outp += sprintf(outp, " count 0x%03X ", extra_delta_offset32);
+                outp += sprintf(outp, "  count 0x%03X", extra_delta_offset32);
         if (extra_delta_offset64)
-                outp += sprintf(outp, " COUNT 0x%03X ", extra_delta_offset64);
+                outp += sprintf(outp, "  COUNT 0x%03X", extra_delta_offset64);
         if (extra_msr_offset32)
-                outp += sprintf(outp, "  MSR 0x%03X ", extra_msr_offset32);
+                outp += sprintf(outp, "   MSR 0x%03X", extra_msr_offset32);
         if (extra_msr_offset64)
-                outp += sprintf(outp, "          MSR 0x%03X ", extra_msr_offset64);
+                outp += sprintf(outp, "           MSR 0x%03X", extra_msr_offset64);
         if (do_nhm_cstates)
-                outp += sprintf(outp, " CPU%%c1 ");
+                outp += sprintf(outp, "  CPU%%c1");
         if (do_nhm_cstates && !do_slm_cstates)
-                outp += sprintf(outp, " CPU%%c3 ");
+                outp += sprintf(outp, "  CPU%%c3");
         if (do_nhm_cstates)
-                outp += sprintf(outp, " CPU%%c6 ");
+                outp += sprintf(outp, "  CPU%%c6");
         if (do_snb_cstates)
-                outp += sprintf(outp, " CPU%%c7 ");
+                outp += sprintf(outp, "  CPU%%c7");
 
         if (do_dts)
-                outp += sprintf(outp, "CoreTmp ");
+                outp += sprintf(outp, " CoreTmp");
         if (do_ptm)
-                outp += sprintf(outp, " PkgTmp ");
+                outp += sprintf(outp, "  PkgTmp");
 
         if (do_snb_cstates)
-                outp += sprintf(outp, "Pkg%%pc2 ");
+                outp += sprintf(outp, " Pkg%%pc2");
         if (do_nhm_cstates && !do_slm_cstates)
-                outp += sprintf(outp, "Pkg%%pc3 ");
+                outp += sprintf(outp, " Pkg%%pc3");
         if (do_nhm_cstates && !do_slm_cstates)
-                outp += sprintf(outp, "Pkg%%pc6 ");
+                outp += sprintf(outp, " Pkg%%pc6");
         if (do_snb_cstates)
-                outp += sprintf(outp, "Pkg%%pc7 ");
+                outp += sprintf(outp, " Pkg%%pc7");
         if (do_c8_c9_c10) {
-                outp += sprintf(outp, "Pkg%%pc8 ");
-                outp += sprintf(outp, "Pkg%%pc9 ");
-                outp += sprintf(outp, "Pk%%pc10 ");
+                outp += sprintf(outp, " Pkg%%pc8");
+                outp += sprintf(outp, " Pkg%%pc9");
+                outp += sprintf(outp, " Pk%%pc10");
         }
 
         if (do_rapl && !rapl_joules) {
                 if (do_rapl & RAPL_PKG)
-                        outp += sprintf(outp, "PkgWatt ");
+                        outp += sprintf(outp, " PkgWatt");
                 if (do_rapl & RAPL_CORES)
-                        outp += sprintf(outp, "CorWatt ");
+                        outp += sprintf(outp, " CorWatt");
                 if (do_rapl & RAPL_GFX)
-                        outp += sprintf(outp, "GFXWatt ");
+                        outp += sprintf(outp, " GFXWatt");
                 if (do_rapl & RAPL_DRAM)
-                        outp += sprintf(outp, "RAMWatt ");
+                        outp += sprintf(outp, " RAMWatt");
                 if (do_rapl & RAPL_PKG_PERF_STATUS)
-                        outp += sprintf(outp, "  PKG_%% ");
+                        outp += sprintf(outp, "   PKG_%%");
                 if (do_rapl & RAPL_DRAM_PERF_STATUS)
-                        outp += sprintf(outp, "  RAM_%% ");
+                        outp += sprintf(outp, "   RAM_%%");
         } else {
                 if (do_rapl & RAPL_PKG)
-                        outp += sprintf(outp, "  Pkg_J ");
+                        outp += sprintf(outp, "   Pkg_J");
                 if (do_rapl & RAPL_CORES)
-                        outp += sprintf(outp, "  Cor_J ");
+                        outp += sprintf(outp, "   Cor_J");
                 if (do_rapl & RAPL_GFX)
-                        outp += sprintf(outp, "  GFX_J ");
+                        outp += sprintf(outp, "   GFX_J");
                 if (do_rapl & RAPL_DRAM)
-                        outp += sprintf(outp, "  RAM_W ");
+                        outp += sprintf(outp, "   RAM_W");
                 if (do_rapl & RAPL_PKG_PERF_STATUS)
-                        outp += sprintf(outp, "  PKG_%% ");
+                        outp += sprintf(outp, "   PKG_%%");
                 if (do_rapl & RAPL_DRAM_PERF_STATUS)
-                        outp += sprintf(outp, "  RAM_%% ");
-                outp += sprintf(outp, "  time ");
+                        outp += sprintf(outp, "   RAM_%%");
+                outp += sprintf(outp, "   time");
 
         }
         outp += sprintf(outp, "\n");
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 55ab700f6ba5..bf1398180785 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -194,6 +194,7 @@ my $config_bisect_check;
 
 my $patchcheck_type;
 my $patchcheck_start;
+my $patchcheck_cherry;
 my $patchcheck_end;
 
 # set when a test is something other that just building or install
@@ -320,6 +321,7 @@ my %option_map = (
 
     "PATCHCHECK_TYPE"           => \$patchcheck_type,
     "PATCHCHECK_START"          => \$patchcheck_start,
+    "PATCHCHECK_CHERRY"         => \$patchcheck_cherry,
     "PATCHCHECK_END"            => \$patchcheck_end,
 );
 
@@ -1448,6 +1450,12 @@ sub wait_for_monitor {
         }
     }
     print "** Monitor flushed **\n";
+
+    # if stop is defined but wasn't hit, return error
+    # used by reboot (which wants to see a reboot)
+    if (defined($stop) && !$booted) {
+        $bug = 1;
+    }
     return $bug;
 }
 
@@ -2336,15 +2344,17 @@ sub success {
 
 sub answer_bisect {
     for (;;) {
-        doprint "Pass or fail? [p/f]";
+        doprint "Pass, fail, or skip? [p/f/s]";
         my $ans = <STDIN>;
         chomp $ans;
         if ($ans eq "p" || $ans eq "P") {
             return 1;
         } elsif ($ans eq "f" || $ans eq "F") {
             return 0;
+        } elsif ($ans eq "s" || $ans eq "S") {
+            return -1;
         } else {
-            print "Please answer 'P' or 'F'\n";
+            print "Please answer 'p', 'f', or 's'\n";
         }
     }
 }
@@ -2726,15 +2736,17 @@ sub bisect {
     run_command "git bisect start$start_files" or
         dodie "could not start bisect";
 
-    run_command "git bisect good $good" or
-        dodie "could not set bisect good to $good";
-
-    run_git_bisect "git bisect bad $bad" or
-        dodie "could not set bisect bad to $bad";
-
     if (defined($replay)) {
         run_command "git bisect replay $replay" or
             dodie "failed to run replay";
+    } else {
+
+        run_command "git bisect good $good" or
+            dodie "could not set bisect good to $good";
+
+        run_git_bisect "git bisect bad $bad" or
+            dodie "could not set bisect bad to $bad";
+
     }
 
     if (defined($start)) {
@@ -3181,9 +3193,16 @@ sub patchcheck {
 
     my $start = $patchcheck_start;
 
+    my $cherry = $patchcheck_cherry;
+    if (!defined($cherry)) {
+        $cherry = 0;
+    }
+
     my $end = "HEAD";
     if (defined($patchcheck_end)) {
         $end = $patchcheck_end;
+    } elsif ($cherry) {
+        die "PATCHCHECK_END must be defined with PATCHCHECK_CHERRY\n";
     }
 
     # Get the true sha1's since we can use things like HEAD~3
@@ -3197,24 +3216,38 @@ sub patchcheck {
         $type = "boot";
     }
 
-    open (IN, "git log --pretty=oneline $end|") or
-        dodie "could not get git list";
+    if ($cherry) {
+        open (IN, "git cherry -v $start $end|") or
+            dodie "could not get git list";
+    } else {
+        open (IN, "git log --pretty=oneline $end|") or
+            dodie "could not get git list";
+    }
 
     my @list;
 
     while (<IN>) {
         chomp;
+        # git cherry adds a '+' we want to remove
+        s/^\+ //;
         $list[$#list+1] = $_;
         last if (/^$start/);
     }
     close(IN);
 
-    if ($list[$#list] !~ /^$start/) {
-        fail "SHA1 $start not found";
+    if (!$cherry) {
+        if ($list[$#list] !~ /^$start/) {
+            fail "SHA1 $start not found";
+        }
+
+        # go backwards in the list
+        @list = reverse @list;
     }
 
-    # go backwards in the list
-    @list = reverse @list;
+    doprint("Going to test the following commits:\n");
+    foreach my $l (@list) {
+        doprint "$l\n";
+    }
 
     my $save_clean = $noclean;
     my %ignored_warnings;
diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf
index 911e45ad657a..6c58cd8bbbae 100644
--- a/tools/testing/ktest/sample.conf
+++ b/tools/testing/ktest/sample.conf
@@ -906,6 +906,16 @@
 #
 #  PATCHCHECK_END is the last patch to check (default HEAD)
 #
+#  PATCHCHECK_CHERRY if set to non zero, then git cherry will be
+#      performed against PATCHCHECK_START and PATCHCHECK_END. That is
+#
+#      git cherry ${PATCHCHECK_START} ${PATCHCHECK_END}
+#
+#      Then the changes found will be tested.
+#
+#      Note, PATCHCHECK_CHERRY requires PATCHCHECK_END to be defined.
+#      (default 0)
+#
 #  PATCHCHECK_TYPE is required and is the type of test to run:
 #      build, boot, test.
 #
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index d10f95ce2ea4..45f145c6f843 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -2,8 +2,10 @@ TARGETS = breakpoints
 TARGETS += cpu-hotplug
 TARGETS += efivarfs
 TARGETS += kcmp
+TARGETS += memfd
 TARGETS += memory-hotplug
 TARGETS += mqueue
+TARGETS += mount
 TARGETS += net
 TARGETS += ptrace
 TARGETS += timers
@@ -12,6 +14,7 @@ TARGETS += powerpc
 TARGETS += user
 TARGETS += sysctl
 TARGETS += firmware
+TARGETS += ftrace
 
 TARGETS_HOTPLUG = cpu-hotplug
 TARGETS_HOTPLUG += memory-hotplug
diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile
new file mode 100644
index 000000000000..76cc9f156267
--- /dev/null
+++ b/tools/testing/selftests/ftrace/Makefile
@@ -0,0 +1,7 @@
+all:
+
+run_tests:
+        @/bin/sh ./ftracetest || echo "ftrace selftests: [FAIL]"
+
+clean:
+        rm -rf logs/*
diff --git a/tools/testing/selftests/ftrace/README b/tools/testing/selftests/ftrace/README
new file mode 100644
index 000000000000..182e76fa4b82
--- /dev/null
+++ b/tools/testing/selftests/ftrace/README
@@ -0,0 +1,82 @@
+Linux Ftrace Testcases
+
+This is a collection of testcases for ftrace tracing feature in the Linux
+kernel. Since ftrace exports interfaces via the debugfs, we just need
+shell scripts for testing. Feel free to add new test cases.
+
+Running the ftrace testcases
+============================
+
+At first, you need to be the root user to run this script.
+To run all testcases:
+
+  $ sudo ./ftracetest
+
+To run specific testcases:
+
+  # ./ftracetest test.d/basic3.tc
+
+Or you can also run testcases under given directory:
+
+  # ./ftracetest test.d/kprobe/
+
+Contributing new testcases
+==========================
+
+Copy test.d/template to your testcase (whose filename must have *.tc
+extension) and rewrite the test description line.
+
+ * The working directory of the script is <debugfs>/tracing/.
+
+ * Take care with side effects as the tests are run with root privilege.
+
+ * The tests should not run for a long period of time (more than 1 min.)
+   These are to be unit tests.
+
+ * You can add a directory for your testcases under test.d/ if needed.
+
+ * The test cases should run on dash (busybox shell) for testing on
+   minimal cross-build environments.
+
+ * Note that the tests are run with "set -e" (errexit) option. If any
+   command fails, the test will be terminated immediately.
+
+ * The tests can return some result codes instead of pass or fail by
+   using exit_unresolved, exit_untested, exit_unsupported and exit_xfail.
+
+Result code
+===========
+
+Ftracetest supports following result codes.
+
+ * PASS: The test succeeded as expected. The test which exits with 0 is
+         counted as passed test.
+
+ * FAIL: The test failed, but was expected to succeed. The test which exits
+         with !0 is counted as failed test.
+
+ * UNRESOLVED: The test produced unclear or intermidiate results.
+             for example, the test was interrupted
+                       or the test depends on a previous test, which failed.
+                       or the test was set up incorrectly
+             The test which is in above situation, must call exit_unresolved.
+
+ * UNTESTED: The test was not run, currently just a placeholder.
+             In this case, the test must call exit_untested.
+
+ * UNSUPPORTED: The test failed because of lack of feature.
+               In this case, the test must call exit_unsupported.
+
+ * XFAIL: The test failed, and was expected to fail.
+          To return XFAIL, call exit_xfail from the test.
+
+There are some sample test scripts for result code under samples/.
+You can also run samples as below:
+
+  # ./ftracetest samples/
+
+TODO
+====
+
+ * Fancy colored output :)
+
diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
new file mode 100755
index 000000000000..515247601df4
--- /dev/null
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -0,0 +1,253 @@
+#!/bin/sh
+
+# ftracetest - Ftrace test shell scripts
+#
+# Copyright (C) Hitachi Ltd., 2014
+#  Written by Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
+#
+# Released under the terms of the GPL v2.
+
+usage() { # errno [message]
+[ "$2" ] && echo $2
+echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]"
+echo " Options:"
+echo "          -h|--help  Show help message"
+echo "          -k|--keep  Keep passed test logs"
+echo "          -d|--debug Debug mode (trace all shell commands)"
+exit $1
+}
+
+errexit() { # message
+  echo "Error: $1" 1>&2
+  exit 1
+}
+
+# Ensuring user privilege
+if [ `id -u` -ne 0 ]; then
+  errexit "this must be run by root user"
+fi
+
+# Utilities
+absdir() { # file_path
+  (cd `dirname $1`; pwd)
+}
+
+abspath() {
+  echo `absdir $1`/`basename $1`
+}
+
+find_testcases() { #directory
+  echo `find $1 -name \*.tc`
+}
+
+parse_opts() { # opts
+  local OPT_TEST_CASES=
+  local OPT_TEST_DIR=
+
+  while [ "$1" ]; do
+    case "$1" in
+    --help|-h)
+      usage 0
+    ;;
+    --keep|-k)
+      KEEP_LOG=1
+      shift 1
+    ;;
+    --debug|-d)
+      DEBUG=1
+      shift 1
+    ;;
+    *.tc)
+      if [ -f "$1" ]; then
+        OPT_TEST_CASES="$OPT_TEST_CASES `abspath $1`"
+        shift 1
+      else
+        usage 1 "$1 is not a testcase"
+      fi
+      ;;
+    *)
+      if [ -d "$1" ]; then
+        OPT_TEST_DIR=`abspath $1`
+        OPT_TEST_CASES="$OPT_TEST_CASES `find_testcases $OPT_TEST_DIR`"
+        shift 1
+      else
+        usage 1 "Invalid option ($1)"
+      fi
+    ;;
+    esac
+  done
+  if [ "$OPT_TEST_CASES" ]; then
+    TEST_CASES=$OPT_TEST_CASES
+  fi
+}
+
+# Parameters
+DEBUGFS_DIR=`grep debugfs /proc/mounts | cut -f2 -d' ' | head -1`
+TRACING_DIR=$DEBUGFS_DIR/tracing
+TOP_DIR=`absdir $0`
+TEST_DIR=$TOP_DIR/test.d
+TEST_CASES=`find_testcases $TEST_DIR`
+LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`/
+KEEP_LOG=0
+DEBUG=0
+# Parse command-line options
+parse_opts $*
+
+[ $DEBUG -ne 0 ] && set -x
+
+# Verify parameters
+if [ -z "$DEBUGFS_DIR" -o ! -d "$TRACING_DIR" ]; then
+  errexit "No ftrace directory found"
+fi
+
+# Preparing logs
+LOG_FILE=$LOG_DIR/ftracetest.log
+mkdir -p $LOG_DIR || errexit "Failed to make a log directory: $LOG_DIR"
+date > $LOG_FILE
+prlog() { # messages
+  echo "$@" | tee -a $LOG_FILE
+}
+catlog() { #file
+  cat $1 | tee -a $LOG_FILE
+}
+prlog "=== Ftrace unit tests ==="
+
+
+# Testcase management
+# Test result codes - Dejagnu extended code
+PASS=0  # The test succeeded.
+FAIL=1  # The test failed, but was expected to succeed.
+UNRESOLVED=2  # The test produced indeterminate results. (e.g. interrupted)
+UNTESTED=3    # The test was not run, currently just a placeholder.
+UNSUPPORTED=4 # The test failed because of lack of feature.
+XFAIL=5 # The test failed, and was expected to fail.
+
+# Accumulations
+PASSED_CASES=
+FAILED_CASES=
+UNRESOLVED_CASES=
+UNTESTED_CASES=
+UNSUPPORTED_CASES=
+XFAILED_CASES=
+UNDEFINED_CASES=
+TOTAL_RESULT=0
+
+CASENO=0
+testcase() { # testfile
+  CASENO=$((CASENO+1))
+  prlog -n "[$CASENO]"`grep "^#[ \t]*description:" $1 | cut -f2 -d:`
+}
+
+eval_result() { # retval sigval
+  local retval=$2
+  if [ $2 -eq 0 ]; then
+    test $1 -ne 0 && retval=$FAIL
+  fi
+  case $retval in
+    $PASS)
+      prlog "   [PASS]"
+      PASSED_CASES="$PASSED_CASES $CASENO"
+      return 0
+    ;;
+    $FAIL)
+      prlog "   [FAIL]"
+      FAILED_CASES="$FAILED_CASES $CASENO"
+      return 1 # this is a bug.
+    ;;
+    $UNRESOLVED)
+      prlog "   [UNRESOLVED]"
+      UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO"
+      return 1 # this is a kind of bug.. something happened.
+    ;;
+    $UNTESTED)
+      prlog "   [UNTESTED]"
+      UNTESTED_CASES="$UNTESTED_CASES $CASENO"
+      return 0
+    ;;
+    $UNSUPPORTED)
+      prlog "   [UNSUPPORTED]"
+      UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO"
+      return 1 # this is not a bug, but the result should be reported.
+    ;;
+    $XFAIL)
+      prlog "   [XFAIL]"
+      XFAILED_CASES="$XFAILED_CASES $CASENO"
+      return 0
+    ;;
+    *)
+      prlog "   [UNDEFINED]"
+      UNDEFINED_CASES="$UNDEFINED_CASES $CASENO"
+      return 1 # this must be a test bug
+    ;;
+  esac
+}
+
+# Signal handling for result codes
+SIG_RESULT=
+SIG_BASE=36     # Use realtime signals
+SIG_PID=$$
+
+SIG_UNRESOLVED=$((SIG_BASE + UNRESOLVED))
+exit_unresolved () {
+  kill -s $SIG_UNRESOLVED $SIG_PID
+  exit 0
+}
+trap 'SIG_RESULT=$UNRESOLVED' $SIG_UNRESOLVED
+
+SIG_UNTESTED=$((SIG_BASE + UNTESTED))
+exit_untested () {
+  kill -s $SIG_UNTESTED $SIG_PID
+  exit 0
+}
+trap 'SIG_RESULT=$UNTESTED' $SIG_UNTESTED
+
+SIG_UNSUPPORTED=$((SIG_BASE + UNSUPPORTED))
+exit_unsupported () {
+  kill -s $SIG_UNSUPPORTED $SIG_PID
+  exit 0
+}
+trap 'SIG_RESULT=$UNSUPPORTED' $SIG_UNSUPPORTED
+
+SIG_XFAIL=$((SIG_BASE + XFAIL))
+exit_xfail () {
+  kill -s $SIG_XFAIL $SIG_PID
+  exit 0
+}
+trap 'SIG_RESULT=$XFAIL' $SIG_XFAIL
+
+# Run one test case
+run_test() { # testfile
+  local testname=`basename $1`
+  local testlog=`mktemp --tmpdir=$LOG_DIR ${testname}-XXXXXX.log`
+  testcase $1
+  echo "execute: "$1 > $testlog
+  SIG_RESULT=0
+  # setup PID and PPID, $$ is not updated.
+  (cd $TRACING_DIR; read PID _ < /proc/self/stat ;
+   set -e; set -x; . $1) >> $testlog 2>&1
+  eval_result $? $SIG_RESULT
+  if [ $? -eq 0 ]; then
+    # Remove test log if the test was done as it was expected.
+    [ $KEEP_LOG -eq 0 ] && rm $testlog
+  else
+    catlog $testlog
+    TOTAL_RESULT=1
+  fi
+}
+
+# Main loop
+for t in $TEST_CASES; do
+  run_test $t
+done
+
+prlog ""
+prlog "# of passed: " `echo $PASSED_CASES | wc -w`
+prlog "# of failed: " `echo $FAILED_CASES | wc -w`
+prlog "# of unresolved: " `echo $UNRESOLVED_CASES | wc -w`
+prlog "# of untested: " `echo $UNTESTED_CASES | wc -w`
+prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w`
+prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w`
+prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w`
+
+# if no error, return 0
+exit $TOTAL_RESULT
diff --git a/tools/testing/selftests/ftrace/samples/fail.tc b/tools/testing/selftests/ftrace/samples/fail.tc
new file mode 100644
index 000000000000..15e35b956e05
--- /dev/null
+++ b/tools/testing/selftests/ftrace/samples/fail.tc
@@ -0,0 +1,4 @@
+#!/bin/sh
+# description: failure-case example
+cat non-exist-file
+echo "this is not executed"
diff --git a/tools/testing/selftests/ftrace/samples/pass.tc b/tools/testing/selftests/ftrace/samples/pass.tc
new file mode 100644
index 000000000000..d01549370041
--- /dev/null
+++ b/tools/testing/selftests/ftrace/samples/pass.tc
@@ -0,0 +1,3 @@
+#!/bin/sh
+# description: pass-case example
+return 0
diff --git a/tools/testing/selftests/ftrace/samples/unresolved.tc b/tools/testing/selftests/ftrace/samples/unresolved.tc
new file mode 100644
index 000000000000..41e99d3358d1
--- /dev/null
+++ b/tools/testing/selftests/ftrace/samples/unresolved.tc
@@ -0,0 +1,4 @@
+#!/bin/sh
+# description: unresolved-case example
+trap exit_unresolved INT
+kill -INT $PID
diff --git a/tools/testing/selftests/ftrace/samples/unsupported.tc b/tools/testing/selftests/ftrace/samples/unsupported.tc
new file mode 100644
index 000000000000..45910ff13328
--- /dev/null
+++ b/tools/testing/selftests/ftrace/samples/unsupported.tc
@@ -0,0 +1,3 @@
+#!/bin/sh
+# description: unsupported-case example
+exit_unsupported
diff --git a/tools/testing/selftests/ftrace/samples/untested.tc b/tools/testing/selftests/ftrace/samples/untested.tc
new file mode 100644
index 000000000000..35a45946ec60
--- /dev/null
+++ b/tools/testing/selftests/ftrace/samples/untested.tc
@@ -0,0 +1,3 @@
+#!/bin/sh
+# description: untested-case example
+exit_untested
diff --git a/tools/testing/selftests/ftrace/samples/xfail.tc b/tools/testing/selftests/ftrace/samples/xfail.tc
new file mode 100644
index 000000000000..9dd395323259
--- /dev/null
+++ b/tools/testing/selftests/ftrace/samples/xfail.tc
@@ -0,0 +1,3 @@
+#!/bin/sh
+# description: xfail-case example
+cat non-exist-file || exit_xfail
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic1.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic1.tc
new file mode 100644
index 000000000000..9980ff14ae44
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/basic1.tc
@@ -0,0 +1,3 @@
+#!/bin/sh
+# description: Basic trace file check
+test -f README -a -f trace -a -f tracing_on -a -f trace_pipe
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc
new file mode 100644
index 000000000000..bf9a7b037924
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc
@@ -0,0 +1,7 @@
+#!/bin/sh
+# description: Basic test for tracers
+test -f available_tracers
+for t in `cat available_tracers`; do
+  echo $t > current_tracer
+done
+echo nop > current_tracer
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc
new file mode 100644
index 000000000000..bde6625d9785
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc
@@ -0,0 +1,8 @@
+#!/bin/sh
+# description: Basic trace clock test
+test -f trace_clock
+for c in `cat trace_clock | tr  -d \[\]`; do
+  echo $c > trace_clock
+  grep '\['$c'\]' trace_clock
+done
+echo local > trace_clock
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
new file mode 100644
index 000000000000..1b8b665ab2b3
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
@@ -0,0 +1,11 @@
+#!/bin/sh
+# description: Kprobe dynamic event - adding and removing
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+echo 0 > events/enable
+echo > kprobe_events
+echo p:myevent do_fork > kprobe_events
+grep myevent kprobe_events
+test -d events/kprobes/myevent
+echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
new file mode 100644
index 000000000000..b55c84003587
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
@@ -0,0 +1,13 @@
+#!/bin/sh
+# description: Kprobe dynamic event - busy event check
+
+[ -f kprobe_events ] || exit_unsupported
+
+echo 0 > events/enable
+echo > kprobe_events
+echo p:myevent do_fork > kprobe_events
+test -d events/kprobes/myevent
+echo 1 > events/kprobes/myevent/enable
+echo > kprobe_events && exit 1 # this must fail
+echo 0 > events/kprobes/myevent/enable
+echo > kprobe_events # this must succeed
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
new file mode 100644
index 000000000000..a603d3f8db7b
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
@@ -0,0 +1,16 @@
+#!/bin/sh
+# description: Kprobe dynamic event with arguments
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+echo 0 > events/enable
+echo > kprobe_events
+echo 'p:testprobe do_fork $stack $stack0 +0($stack)' > kprobe_events
+grep testprobe kprobe_events
+test -d events/kprobes/testprobe
+echo 1 > events/kprobes/testprobe/enable
+( echo "forked")
+echo 0 > events/kprobes/testprobe/enable
+echo "-:testprobe" >> kprobe_events
+test -d events/kprobes/testprobe && exit 1 || exit 0
+
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
new file mode 100644
index 000000000000..283c29e7f7c4
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
@@ -0,0 +1,15 @@
+#!/bin/sh
+# description: Kretprobe dynamic event with arguments
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+echo 0 > events/enable
+echo > kprobe_events
+echo 'r:testprobe2 do_fork $retval' > kprobe_events
+grep testprobe2 kprobe_events
+test -d events/kprobes/testprobe2
+echo 1 > events/kprobes/testprobe2/enable
+( echo "forked")
+echo 0 > events/kprobes/testprobe2/enable
+echo '-:testprobe2' >> kprobe_events
+test -d events/kprobes/testprobe2 && exit 1 || exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/template b/tools/testing/selftests/ftrace/test.d/template
new file mode 100644
index 000000000000..5448f7abad5f
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/template
@@ -0,0 +1,9 @@
+#!/bin/sh
+# description: %HERE DESCRIBE WHAT THIS DOES%
+# you have to add ".tc" extention for your testcase file
+# Note that all tests are run with "errexit" option.
+
+exit 0 # Return 0 if the test is passed, otherwise return !0
+# If the test could not run because of lack of feature, call exit_unsupported
+# If the test returned unclear results, call exit_unresolved
+# If the test is a dummy, or a placeholder, call exit_untested
diff --git a/tools/testing/selftests/ipc/Makefile b/tools/testing/selftests/ipc/Makefile
index 5386fd7c43ae..74bbefdeaf4c 100644
--- a/tools/testing/selftests/ipc/Makefile
+++ b/tools/testing/selftests/ipc/Makefile
@@ -1,18 +1,18 @@
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/)
 ifeq ($(ARCH),i386)
-        ARCH := X86
+        ARCH := x86
         CFLAGS := -DCONFIG_X86_32 -D__i386__
 endif
 ifeq ($(ARCH),x86_64)
-        ARCH := X86
+        ARCH := x86
         CFLAGS := -DCONFIG_X86_64 -D__x86_64__
 endif
 
 CFLAGS += -I../../../../usr/include/
 
 all:
-ifeq ($(ARCH),X86)
+ifeq ($(ARCH),x86)
         gcc $(CFLAGS) msgque.c -o msgque_test
 else
         echo "Not an x86 target, can't build msgque selftest"
diff --git a/tools/testing/selftests/kcmp/Makefile b/tools/testing/selftests/kcmp/Makefile
index d7d6bbeeff2f..8aabd82db9e4 100644
--- a/tools/testing/selftests/kcmp/Makefile
+++ b/tools/testing/selftests/kcmp/Makefile
@@ -1,11 +1,11 @@
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/)
 ifeq ($(ARCH),i386)
-        ARCH := X86
+        ARCH := x86
         CFLAGS := -DCONFIG_X86_32 -D__i386__
 endif
 ifeq ($(ARCH),x86_64)
-        ARCH := X86
+        ARCH := x86
         CFLAGS := -DCONFIG_X86_64 -D__x86_64__
 endif
 
@@ -15,7 +15,7 @@ CFLAGS += -I../../../../usr/include/
 CFLAGS += -I../../../../arch/x86/include/
 
 all:
-ifeq ($(ARCH),X86)
+ifeq ($(ARCH),x86)
         gcc $(CFLAGS) kcmp_test.c -o kcmp_test
 else
         echo "Not an x86 target, can't build kcmp selftest"
diff --git a/tools/testing/selftests/memfd/.gitignore b/tools/testing/selftests/memfd/.gitignore
new file mode 100644
index 000000000000..afe87c40ac80
--- /dev/null
+++ b/tools/testing/selftests/memfd/.gitignore
@@ -0,0 +1,4 @@
+fuse_mnt
+fuse_test
+memfd_test
+memfd-test-file
diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile
new file mode 100644
index 000000000000..b80cd10d53ba
--- /dev/null
+++ b/tools/testing/selftests/memfd/Makefile
@@ -0,0 +1,20 @@
+CFLAGS += -D_FILE_OFFSET_BITS=64
+CFLAGS += -I../../../../include/uapi/
+CFLAGS += -I../../../../include/
+
+all:
+        gcc $(CFLAGS) memfd_test.c -o memfd_test
+
+run_tests: all
+        gcc $(CFLAGS) memfd_test.c -o memfd_test
+        @./memfd_test || echo "memfd_test: [FAIL]"
+
+build_fuse:
+        gcc $(CFLAGS) fuse_mnt.c `pkg-config fuse --cflags --libs` -o fuse_mnt
+        gcc $(CFLAGS) fuse_test.c -o fuse_test
+
+run_fuse: build_fuse
+        @./run_fuse_test.sh || echo "fuse_test: [FAIL]"
+
+clean:
+        $(RM) memfd_test fuse_test
diff --git a/tools/testing/selftests/memfd/fuse_mnt.c b/tools/testing/selftests/memfd/fuse_mnt.c
new file mode 100644
index 000000000000..feacf1280fcd
--- /dev/null
+++ b/tools/testing/selftests/memfd/fuse_mnt.c
@@ -0,0 +1,110 @@
+/*
+ * memfd test file-system
+ * This file uses FUSE to create a dummy file-system with only one file /memfd.
+ * This file is read-only and takes 1s per read.
+ *
+ * This file-system is used by the memfd test-cases to force the kernel to pin
+ * pages during reads(). Due to the 1s delay of this file-system, this is a
+ * nice way to test race-conditions against get_user_pages() in the kernel.
+ *
+ * We use direct_io==1 to force the kernel to use direct-IO for this
+ * file-system.
+ */
+
+#define FUSE_USE_VERSION 26
+
+#include <fuse.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <unistd.h>
+
+static const char memfd_content[] = "memfd-example-content";
+static const char memfd_path[] = "/memfd";
+
+static int memfd_getattr(const char *path, struct stat *st)
+{
+        memset(st, 0, sizeof(*st));
+
+        if (!strcmp(path, "/")) {
+                st->st_mode = S_IFDIR | 0755;
+                st->st_nlink = 2;
+        } else if (!strcmp(path, memfd_path)) {
+                st->st_mode = S_IFREG | 0444;
+                st->st_nlink = 1;
+                st->st_size = strlen(memfd_content);
+        } else {
+                return -ENOENT;
+        }
+
+        return 0;
+}
+
+static int memfd_readdir(const char *path,
+                         void *buf,
+                         fuse_fill_dir_t filler,
+                         off_t offset,
+                         struct fuse_file_info *fi)
+{
+        if (strcmp(path, "/"))
+                return -ENOENT;
+
+        filler(buf, ".", NULL, 0);
+        filler(buf, "..", NULL, 0);
+        filler(buf, memfd_path + 1, NULL, 0);
+
+        return 0;
+}
+
+static int memfd_open(const char *path, struct fuse_file_info *fi)
+{
+        if (strcmp(path, memfd_path))
+                return -ENOENT;
+
+        if ((fi->flags & 3) != O_RDONLY)
+                return -EACCES;
+
+        /* force direct-IO */
+        fi->direct_io = 1;
+
+        return 0;
+}
+
+static int memfd_read(const char *path,
+                      char *buf,
+                      size_t size,
+                      off_t offset,
+                      struct fuse_file_info *fi)
+{
+        size_t len;
+
+        if (strcmp(path, memfd_path) != 0)
+                return -ENOENT;
+
+        sleep(1);
+
+        len = strlen(memfd_content);
+        if (offset < len) {
+                if (offset + size > len)
+                        size = len - offset;
+
+                memcpy(buf, memfd_content + offset, size);
+        } else {
+                size = 0;
+        }
+
+        return size;
+}
+
+static struct fuse_operations memfd_ops = {
+        .getattr        = memfd_getattr,
+        .readdir        = memfd_readdir,
+        .open           = memfd_open,
+        .read           = memfd_read,
+};
+
+int main(int argc, char *argv[])
+{
+        return fuse_main(argc, argv, &memfd_ops, NULL);
+}
diff --git a/tools/testing/selftests/memfd/fuse_test.c b/tools/testing/selftests/memfd/fuse_test.c
new file mode 100644
index 000000000000..67908b18f035
--- /dev/null
+++ b/tools/testing/selftests/memfd/fuse_test.c
@@ -0,0 +1,311 @@
+/*
+ * memfd GUP test-case
+ * This tests memfd interactions with get_user_pages(). We require the
+ * fuse_mnt.c program to provide a fake direct-IO FUSE mount-point for us. This
+ * file-system delays _all_ reads by 1s and forces direct-IO. This means, any
+ * read() on files in that file-system will pin the receive-buffer pages for at
+ * least 1s via get_user_pages().
+ *
+ * We use this trick to race ADD_SEALS against a write on a memfd object. The
+ * ADD_SEALS must fail if the memfd pages are still pinned. Note that we use
+ * the read() syscall with our memory-mapped memfd object as receive buffer to
+ * force the kernel to write into our memfd object.
+ */
+
+#define _GNU_SOURCE
+#define __EXPORTED_HEADERS__
+
+#include <errno.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <linux/falloc.h>
+#include <linux/fcntl.h>
+#include <linux/memfd.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#define MFD_DEF_SIZE 8192
+#define STACK_SIZE 65535
+
+static int sys_memfd_create(const char *name,
+                            unsigned int flags)
+{
+        return syscall(__NR_memfd_create, name, flags);
+}
+
+static int mfd_assert_new(const char *name, loff_t sz, unsigned int flags)
+{
+        int r, fd;
+
+        fd = sys_memfd_create(name, flags);
+        if (fd < 0) {
+                printf("memfd_create(\"%s\", %u) failed: %m\n",
+                       name, flags);
+                abort();
+        }
+
+        r = ftruncate(fd, sz);
+        if (r < 0) {
+                printf("ftruncate(%llu) failed: %m\n", (unsigned long long)sz);
+                abort();
+        }
+
+        return fd;
+}
+
+static __u64 mfd_assert_get_seals(int fd)
+{
+        long r;
+
+        r = fcntl(fd, F_GET_SEALS);
+        if (r < 0) {
+                printf("GET_SEALS(%d) failed: %m\n", fd);
+                abort();
+        }
+
+        return r;
+}
+
+static void mfd_assert_has_seals(int fd, __u64 seals)
+{
+        __u64 s;
+
+        s = mfd_assert_get_seals(fd);
+        if (s != seals) {
+                printf("%llu != %llu = GET_SEALS(%d)\n",
+                       (unsigned long long)seals, (unsigned long long)s, fd);
+                abort();
+        }
+}
+
+static void mfd_assert_add_seals(int fd, __u64 seals)
+{
+        long r;
+        __u64 s;
+
+        s = mfd_assert_get_seals(fd);
+        r = fcntl(fd, F_ADD_SEALS, seals);
+        if (r < 0) {
+                printf("ADD_SEALS(%d, %llu -> %llu) failed: %m\n",
+                       fd, (unsigned long long)s, (unsigned long long)seals);
+                abort();
+        }
+}
+
+static int mfd_busy_add_seals(int fd, __u64 seals)
+{
+        long r;
+        __u64 s;
+
+        r = fcntl(fd, F_GET_SEALS);
+        if (r < 0)
+                s = 0;
+        else
+                s = r;
+
+        r = fcntl(fd, F_ADD_SEALS, seals);
+        if (r < 0 && errno != EBUSY) {
+                printf("ADD_SEALS(%d, %llu -> %llu) didn't fail as expected with EBUSY: %m\n",
+                       fd, (unsigned long long)s, (unsigned long long)seals);
+                abort();
+        }
+
+        return r;
+}
+
+static void *mfd_assert_mmap_shared(int fd)
+{
+        void *p;
+
+        p = mmap(NULL,
+                 MFD_DEF_SIZE,
+                 PROT_READ | PROT_WRITE,
+                 MAP_SHARED,
+                 fd,
+                 0);
+        if (p == MAP_FAILED) {
+                printf("mmap() failed: %m\n");
+                abort();
+        }
+
+        return p;
+}
+
+static void *mfd_assert_mmap_private(int fd)
+{
+        void *p;
+
+        p = mmap(NULL,
+                 MFD_DEF_SIZE,
+                 PROT_READ | PROT_WRITE,
+                 MAP_PRIVATE,
+                 fd,
+                 0);
+        if (p == MAP_FAILED) {
+                printf("mmap() failed: %m\n");
+                abort();
+        }
+
+        return p;
+}
+
+static int global_mfd = -1;
+static void *global_p = NULL;
+
+static int sealing_thread_fn(void *arg)
+{
+        int sig, r;
+
+        /*
+         * This thread first waits 200ms so any pending operation in the parent
+         * is correctly started. After that, it tries to seal @global_mfd as
+         * SEAL_WRITE. This _must_ fail as the parent thread has a read() into
+         * that memory mapped object still ongoing.
+         * We then wait one more second and try sealing again. This time it
+         * must succeed as there shouldn't be anyone else pinning the pages.
+         */
+
+        /* wait 200ms for FUSE-request to be active */
+        usleep(200000);
+
+        /* unmount mapping before sealing to avoid i_mmap_writable failures */
+        munmap(global_p, MFD_DEF_SIZE);
+
+        /* Try sealing the global file; expect EBUSY or success. Current
+         * kernels will never succeed, but in the future, kernels might
+         * implement page-replacements or other fancy ways to avoid racing
+         * writes. */
+        r = mfd_busy_add_seals(global_mfd, F_SEAL_WRITE);
+        if (r >= 0) {
+                printf("HURRAY! This kernel fixed GUP races!\n");
+        } else {
+                /* wait 1s more so the FUSE-request is done */
+                sleep(1);
+
+                /* try sealing the global file again */
+                mfd_assert_add_seals(global_mfd, F_SEAL_WRITE);
+        }
+
+        return 0;
+}
+
+static pid_t spawn_sealing_thread(void)
+{
+        uint8_t *stack;
+        pid_t pid;
+
+        stack = malloc(STACK_SIZE);
+        if (!stack) {
+                printf("malloc(STACK_SIZE) failed: %m\n");
+                abort();
+        }
+
+        pid = clone(sealing_thread_fn,
+                    stack + STACK_SIZE,
+                    SIGCHLD | CLONE_FILES | CLONE_FS | CLONE_VM,
+                    NULL);
+        if (pid < 0) {
+                printf("clone() failed: %m\n");
+                abort();
+        }
+
+        return pid;
+}
+
+static void join_sealing_thread(pid_t pid)
+{
+        waitpid(pid, NULL, 0);
+}
+
+int main(int argc, char **argv)
+{
+        static const char zero[MFD_DEF_SIZE];
+        int fd, mfd, r;
+        void *p;
+        int was_sealed;
+        pid_t pid;
+
+        if (argc < 2) {
+                printf("error: please pass path to file in fuse_mnt mount-point\n");
+                abort();
+        }
+
+        /* open FUSE memfd file for GUP testing */
+        printf("opening: %s\n", argv[1]);
+        fd = open(argv[1], O_RDONLY | O_CLOEXEC);
+        if (fd < 0) {
+                printf("cannot open(\"%s\"): %m\n", argv[1]);
+                abort();
+        }
+
+        /* create new memfd-object */
+        mfd = mfd_assert_new("kern_memfd_fuse",
+                             MFD_DEF_SIZE,
+                             MFD_CLOEXEC | MFD_ALLOW_SEALING);
+
+        /* mmap memfd-object for writing */
+        p = mfd_assert_mmap_shared(mfd);
+
+        /* pass mfd+mapping to a separate sealing-thread which tries to seal
+         * the memfd objects with SEAL_WRITE while we write into it */
+        global_mfd = mfd;
+        global_p = p;
+        pid = spawn_sealing_thread();
+
+        /* Use read() on the FUSE file to read into our memory-mapped memfd
+         * object. This races the other thread which tries to seal the
+         * memfd-object.
+         * If @fd is on the memfd-fake-FUSE-FS, the read() is delayed by 1s.
+         * This guarantees that the receive-buffer is pinned for 1s until the
+         * data is written into it. The racing ADD_SEALS should thus fail as
+         * the pages are still pinned. */
+        r = read(fd, p, MFD_DEF_SIZE);
+        if (r < 0) {
+                printf("read() failed: %m\n");
+                abort();
+        } else if (!r) {
+                printf("unexpected EOF on read()\n");
+                abort();
+        }
+
+        was_sealed = mfd_assert_get_seals(mfd) & F_SEAL_WRITE;
+
+        /* Wait for sealing-thread to finish and verify that it
+         * successfully sealed the file after the second try. */
+        join_sealing_thread(pid);
+        mfd_assert_has_seals(mfd, F_SEAL_WRITE);
+
+        /* *IF* the memfd-object was sealed at the time our read() returned,
+         * then the kernel did a page-replacement or canceled the read() (or
+         * whatever magic it did..). In that case, the memfd object is still
+         * all zero.
+         * In case the memfd-object was *not* sealed, the read() was successfull
+         * and the memfd object must *not* be all zero.
+         * Note that in real scenarios, there might be a mixture of both, but
+         * in this test-cases, we have explicit 200ms delays which should be
+         * enough to avoid any in-flight writes. */
+
+        p = mfd_assert_mmap_private(mfd);
+        if (was_sealed && memcmp(p, zero, MFD_DEF_SIZE)) {
+                printf("memfd sealed during read() but data not discarded\n");
+                abort();
+        } else if (!was_sealed && !memcmp(p, zero, MFD_DEF_SIZE)) {
+                printf("memfd sealed after read() but data discarded\n");
+                abort();
+        }
+
+        close(mfd);
+        close(fd);
+
+        printf("fuse: DONE\n");
+
+        return 0;
+}
diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
new file mode 100644
index 000000000000..0b9eafb7ab7b
--- /dev/null
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -0,0 +1,911 @@
+#define _GNU_SOURCE
+#define __EXPORTED_HEADERS__
+
+#include <errno.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <linux/falloc.h>
+#include <linux/fcntl.h>
+#include <linux/memfd.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#define MFD_DEF_SIZE 8192
+#define STACK_SIZE 65535
+
+static int sys_memfd_create(const char *name,
+                            unsigned int flags)
+{
+        return syscall(__NR_memfd_create, name, flags);
+}
+
+static int mfd_assert_new(const char *name, loff_t sz, unsigned int flags)
+{
+        int r, fd;
+
+        fd = sys_memfd_create(name, flags);
+        if (fd < 0) {
+                printf("memfd_create(\"%s\", %u) failed: %m\n",
+                       name, flags);
+                abort();
+        }
+
+        r = ftruncate(fd, sz);
+        if (r < 0) {
+                printf("ftruncate(%llu) failed: %m\n", (unsigned long long)sz);
+                abort();
+        }
+
+        return fd;
+}
+
+static void mfd_fail_new(const char *name, unsigned int flags)
+{
+        int r;
+
+        r = sys_memfd_create(name, flags);
+        if (r >= 0) {
+                printf("memfd_create(\"%s\", %u) succeeded, but failure expected\n",
+                       name, flags);
+                close(r);
+                abort();
+        }
+}
+
+static unsigned int mfd_assert_get_seals(int fd)
+{
+        int r;
+
+        r = fcntl(fd, F_GET_SEALS);
+        if (r < 0) {
+                printf("GET_SEALS(%d) failed: %m\n", fd);
+                abort();
+        }
+
+        return (unsigned int)r;
+}
+
+static void mfd_assert_has_seals(int fd, unsigned int seals)
+{
+        unsigned int s;
+
+        s = mfd_assert_get_seals(fd);
+        if (s != seals) {
+                printf("%u != %u = GET_SEALS(%d)\n", seals, s, fd);
+                abort();
+        }
+}
+
+static void mfd_assert_add_seals(int fd, unsigned int seals)
+{
+        int r;
+        unsigned int s;
+
+        s = mfd_assert_get_seals(fd);
+        r = fcntl(fd, F_ADD_SEALS, seals);
+        if (r < 0) {
+                printf("ADD_SEALS(%d, %u -> %u) failed: %m\n", fd, s, seals);
+                abort();
+        }
+}
+
+static void mfd_fail_add_seals(int fd, unsigned int seals)
+{
+        int r;
+        unsigned int s;
+
+        r = fcntl(fd, F_GET_SEALS);
+        if (r < 0)
+                s = 0;
+        else
+                s = (unsigned int)r;
+
+        r = fcntl(fd, F_ADD_SEALS, seals);
+        if (r >= 0) {
+                printf("ADD_SEALS(%d, %u -> %u) didn't fail as expected\n",
+                                fd, s, seals);
+                abort();
+        }
+}
+
+static void mfd_assert_size(int fd, size_t size)
+{
+        struct stat st;
+        int r;
+
+        r = fstat(fd, &st);
+        if (r < 0) {
+                printf("fstat(%d) failed: %m\n", fd);
+                abort();
+        } else if (st.st_size != size) {
+                printf("wrong file size %lld, but expected %lld\n",
+                       (long long)st.st_size, (long long)size);
+                abort();
+        }
+}
+
+static int mfd_assert_dup(int fd)
+{
+        int r;
+
+        r = dup(fd);
+        if (r < 0) {
+                printf("dup(%d) failed: %m\n", fd);
+                abort();
+        }
+
+        return r;
+}
+
+static void *mfd_assert_mmap_shared(int fd)
+{
+        void *p;
+
+        p = mmap(NULL,
+                 MFD_DEF_SIZE,
+                 PROT_READ | PROT_WRITE,
+                 MAP_SHARED,
+                 fd,
+                 0);
+        if (p == MAP_FAILED) {
+                printf("mmap() failed: %m\n");
+                abort();
+        }
+
+        return p;
+}
+
+static void *mfd_assert_mmap_private(int fd)
+{
+        void *p;
+
+        p = mmap(NULL,
+                 MFD_DEF_SIZE,
+                 PROT_READ,
+                 MAP_PRIVATE,
+                 fd,
+                 0);
+        if (p == MAP_FAILED) {
+                printf("mmap() failed: %m\n");
+                abort();
+        }
+
+        return p;
+}
+
+static int mfd_assert_open(int fd, int flags, mode_t mode)
+{
+        char buf[512];
+        int r;
+
+        sprintf(buf, "/proc/self/fd/%d", fd);
+        r = open(buf, flags, mode);
+        if (r < 0) {
+                printf("open(%s) failed: %m\n", buf);
+                abort();
+        }
+
+        return r;
+}
+
+static void mfd_fail_open(int fd, int flags, mode_t mode)
+{
+        char buf[512];
+        int r;
+
+        sprintf(buf, "/proc/self/fd/%d", fd);
+        r = open(buf, flags, mode);
+        if (r >= 0) {
+                printf("open(%s) didn't fail as expected\n", buf);
+                abort();
+        }
+}
+
+static void mfd_assert_read(int fd)
+{
+        char buf[16];
+        void *p;
+        ssize_t l;
+
+        l = read(fd, buf, sizeof(buf));
+        if (l != sizeof(buf)) {
+                printf("read() failed: %m\n");
+                abort();
+        }
+
+        /* verify PROT_READ *is* allowed */
+        p = mmap(NULL,
+                 MFD_DEF_SIZE,
+                 PROT_READ,
+                 MAP_PRIVATE,
+                 fd,
+                 0);
+        if (p == MAP_FAILED) {
+                printf("mmap() failed: %m\n");
+                abort();
+        }
+        munmap(p, MFD_DEF_SIZE);
+
+        /* verify MAP_PRIVATE is *always* allowed (even writable) */
+        p = mmap(NULL,
+                 MFD_DEF_SIZE,
+                 PROT_READ | PROT_WRITE,
+                 MAP_PRIVATE,
+                 fd,
+                 0);
+        if (p == MAP_FAILED) {
+                printf("mmap() failed: %m\n");
+                abort();
+        }
+        munmap(p, MFD_DEF_SIZE);
+}
+
+static void mfd_assert_write(int fd)
+{
+        ssize_t l;
+        void *p;
+        int r;
+
+        /* verify write() succeeds */
+        l = write(fd, "\0\0\0\0", 4);
+        if (l != 4) {
+                printf("write() failed: %m\n");
+                abort();
+        }
+
+        /* verify PROT_READ | PROT_WRITE is allowed */
+        p = mmap(NULL,
+                 MFD_DEF_SIZE,
+                 PROT_READ | PROT_WRITE,
+                 MAP_SHARED,
+                 fd,
+                 0);
+        if (p == MAP_FAILED) {
+                printf("mmap() failed: %m\n");
+                abort();
+        }
+        *(char *)p = 0;
+        munmap(p, MFD_DEF_SIZE);
+
+        /* verify PROT_WRITE is allowed */
+        p = mmap(NULL,
+                 MFD_DEF_SIZE,
+                 PROT_WRITE,
+                 MAP_SHARED,
+                 fd,
+                 0);
+        if (p == MAP_FAILED) {
+                printf("mmap() failed: %m\n");
+                abort();
+        }
+        *(char *)p = 0;
+        munmap(p, MFD_DEF_SIZE);
+
+        /* verify PROT_READ with MAP_SHARED is allowed and a following
+         * mprotect(PROT_WRITE) allows writing */
+        p = mmap(NULL,
+                 MFD_DEF_SIZE,
+                 PROT_READ,
+                 MAP_SHARED,
+                 fd,
+                 0);
+        if (p == MAP_FAILED) {
+                printf("mmap() failed: %m\n");
+                abort();
+        }
+
+        r = mprotect(p, MFD_DEF_SIZE, PROT_READ | PROT_WRITE);
+        if (r < 0) {
+                printf("mprotect() failed: %m\n");
+                abort();
+        }
+
+        *(char *)p = 0;
+        munmap(p, MFD_DEF_SIZE);
+
+        /* verify PUNCH_HOLE works */
+        r = fallocate(fd,
+                      FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+                      0,
+                      MFD_DEF_SIZE);
+        if (r < 0) {
+                printf("fallocate(PUNCH_HOLE) failed: %m\n");
+                abort();
+        }
+}
+
+static void mfd_fail_write(int fd)
+{
+        ssize_t l;
+        void *p;
+        int r;
+
+        /* verify write() fails */
+        l = write(fd, "data", 4);
+        if (l != -EPERM) {
+                printf("expected EPERM on write(), but got %d: %m\n", (int)l);
+                abort();
+        }
+
+        /* verify PROT_READ | PROT_WRITE is not allowed */
+        p = mmap(NULL,
+                 MFD_DEF_SIZE,
+                 PROT_READ | PROT_WRITE,
+                 MAP_SHARED,
+                 fd,
+                 0);
+        if (p != MAP_FAILED) {
+                printf("mmap() didn't fail as expected\n");
+                abort();
+        }
+
+        /* verify PROT_WRITE is not allowed */
+        p = mmap(NULL,
+                 MFD_DEF_SIZE,
+                 PROT_WRITE,
+                 MAP_SHARED,
+                 fd,
+                 0);
+        if (p != MAP_FAILED) {
+                printf("mmap() didn't fail as expected\n");
+                abort();
+        }
+
+        /* Verify PROT_READ with MAP_SHARED with a following mprotect is not
+         * allowed. Note that for r/w the kernel already prevents the mmap. */
+        p = mmap(NULL,
+                 MFD_DEF_SIZE,
+                 PROT_READ,
+                 MAP_SHARED,
+                 fd,
+                 0);
+        if (p != MAP_FAILED) {
+                r = mprotect(p, MFD_DEF_SIZE, PROT_READ | PROT_WRITE);
+                if (r >= 0) {
+                        printf("mmap()+mprotect() didn't fail as expected\n");
+                        abort();
+                }
+        }
+
+        /* verify PUNCH_HOLE fails */
+        r = fallocate(fd,
+                      FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+                      0,
+                      MFD_DEF_SIZE);
+        if (r >= 0) {
+                printf("fallocate(PUNCH_HOLE) didn't fail as expected\n");
+                abort();
+        }
+}
+
+static void mfd_assert_shrink(int fd)
+{
+        int r, fd2;
+
+        r = ftruncate(fd, MFD_DEF_SIZE / 2);
+        if (r < 0) {
+                printf("ftruncate(SHRINK) failed: %m\n");
+                abort();
+        }
+
+        mfd_assert_size(fd, MFD_DEF_SIZE / 2);
+
+        fd2 = mfd_assert_open(fd,
+                              O_RDWR | O_CREAT | O_TRUNC,
+                              S_IRUSR | S_IWUSR);
+        close(fd2);
+
+        mfd_assert_size(fd, 0);
+}
+
+static void mfd_fail_shrink(int fd)
+{
+        int r;
+
+        r = ftruncate(fd, MFD_DEF_SIZE / 2);
+        if (r >= 0) {
+                printf("ftruncate(SHRINK) didn't fail as expected\n");
+                abort();
+        }
+
+        mfd_fail_open(fd,
+                      O_RDWR | O_CREAT | O_TRUNC,
+                      S_IRUSR | S_IWUSR);
+}
+
+static void mfd_assert_grow(int fd)
+{
+        int r;
+
+        r = ftruncate(fd, MFD_DEF_SIZE * 2);
+        if (r < 0) {
+                printf("ftruncate(GROW) failed: %m\n");
+                abort();
+        }
+
+        mfd_assert_size(fd, MFD_DEF_SIZE * 2);
+
+        r = fallocate(fd,
+                      0,
+                      0,
+                      MFD_DEF_SIZE * 4);
+        if (r < 0) {
+                printf("fallocate(ALLOC) failed: %m\n");
+                abort();
+        }
+
+        mfd_assert_size(fd, MFD_DEF_SIZE * 4);
+}
+
+static void mfd_fail_grow(int fd)
+{
+        int r;
+
+        r = ftruncate(fd, MFD_DEF_SIZE * 2);
+        if (r >= 0) {
+                printf("ftruncate(GROW) didn't fail as expected\n");
+                abort();
+        }
+
+        r = fallocate(fd,
+                      0,
+                      0,
+                      MFD_DEF_SIZE * 4);
+        if (r >= 0) {
+                printf("fallocate(ALLOC) didn't fail as expected\n");
+                abort();
+        }
+}
+
+static void mfd_assert_grow_write(int fd)
+{
+        static char buf[MFD_DEF_SIZE * 8];
+        ssize_t l;
+
+        l = pwrite(fd, buf, sizeof(buf), 0);
+        if (l != sizeof(buf)) {
+                printf("pwrite() failed: %m\n");
+                abort();
+        }
+
+        mfd_assert_size(fd, MFD_DEF_SIZE * 8);
+}
+
+static void mfd_fail_grow_write(int fd)
+{
+        static char buf[MFD_DEF_SIZE * 8];
+        ssize_t l;
+
+        l = pwrite(fd, buf, sizeof(buf), 0);
+        if (l == sizeof(buf)) {
+                printf("pwrite() didn't fail as expected\n");
+                abort();
+        }
+}
+
+static int idle_thread_fn(void *arg)
+{
+        sigset_t set;
+        int sig;
+
+        /* dummy waiter; SIGTERM terminates us anyway */
+        sigemptyset(&set);
+        sigaddset(&set, SIGTERM);
+        sigwait(&set, &sig);
+
+        return 0;
+}
+
+static pid_t spawn_idle_thread(unsigned int flags)
+{
+        uint8_t *stack;
+        pid_t pid;
+
+        stack = malloc(STACK_SIZE);
+        if (!stack) {
+                printf("malloc(STACK_SIZE) failed: %m\n");
+                abort();
+        }
+
+        pid = clone(idle_thread_fn,
+                    stack + STACK_SIZE,
+                    SIGCHLD | flags,
+                    NULL);
+        if (pid < 0) {
+                printf("clone() failed: %m\n");
+                abort();
+        }
+
+        return pid;
+}
+
+static void join_idle_thread(pid_t pid)
+{
+        kill(pid, SIGTERM);
+        waitpid(pid, NULL, 0);
+}
+
+/*
+ * Test memfd_create() syscall
+ * Verify syscall-argument validation, including name checks, flag validation
+ * and more.
+ */
+static void test_create(void)
+{
+        char buf[2048];
+        int fd;
+
+        /* test NULL name */
+        mfd_fail_new(NULL, 0);
+
+        /* test over-long name (not zero-terminated) */
+        memset(buf, 0xff, sizeof(buf));
+        mfd_fail_new(buf, 0);
+
+        /* test over-long zero-terminated name */
+        memset(buf, 0xff, sizeof(buf));
+        buf[sizeof(buf) - 1] = 0;
+        mfd_fail_new(buf, 0);
+
+        /* verify "" is a valid name */
+        fd = mfd_assert_new("", 0, 0);
+        close(fd);
+
+        /* verify invalid O_* open flags */
+        mfd_fail_new("", 0x0100);
+        mfd_fail_new("", ~MFD_CLOEXEC);
+        mfd_fail_new("", ~MFD_ALLOW_SEALING);
+        mfd_fail_new("", ~0);
+        mfd_fail_new("", 0x80000000U);
+
+        /* verify MFD_CLOEXEC is allowed */
+        fd = mfd_assert_new("", 0, MFD_CLOEXEC);
+        close(fd);
+
+        /* verify MFD_ALLOW_SEALING is allowed */
+        fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING);
+        close(fd);
+
+        /* verify MFD_ALLOW_SEALING | MFD_CLOEXEC is allowed */
+        fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING | MFD_CLOEXEC);
+        close(fd);
+}
+
+/*
+ * Test basic sealing
+ * A very basic sealing test to see whether setting/retrieving seals works.
+ */
+static void test_basic(void)
+{
+        int fd;
+
+        fd = mfd_assert_new("kern_memfd_basic",
+                            MFD_DEF_SIZE,
+                            MFD_CLOEXEC | MFD_ALLOW_SEALING);
+
+        /* add basic seals */
+        mfd_assert_has_seals(fd, 0);
+        mfd_assert_add_seals(fd, F_SEAL_SHRINK |
+                                 F_SEAL_WRITE);
+        mfd_assert_has_seals(fd, F_SEAL_SHRINK |
+                                 F_SEAL_WRITE);
+
+        /* add them again */
+        mfd_assert_add_seals(fd, F_SEAL_SHRINK |
+                                 F_SEAL_WRITE);
+        mfd_assert_has_seals(fd, F_SEAL_SHRINK |
+                                 F_SEAL_WRITE);
+
+        /* add more seals and seal against sealing */
+        mfd_assert_add_seals(fd, F_SEAL_GROW | F_SEAL_SEAL);
+        mfd_assert_has_seals(fd, F_SEAL_SHRINK |
+                                 F_SEAL_GROW |
+                                 F_SEAL_WRITE |
+                                 F_SEAL_SEAL);
+
+        /* verify that sealing no longer works */
+        mfd_fail_add_seals(fd, F_SEAL_GROW);
+        mfd_fail_add_seals(fd, 0);
+
+        close(fd);
+
+        /* verify sealing does not work without MFD_ALLOW_SEALING */
+        fd = mfd_assert_new("kern_memfd_basic",
+                            MFD_DEF_SIZE,
+                            MFD_CLOEXEC);
+        mfd_assert_has_seals(fd, F_SEAL_SEAL);
+        mfd_fail_add_seals(fd, F_SEAL_SHRINK |
+                               F_SEAL_GROW |
+                               F_SEAL_WRITE);
+        mfd_assert_has_seals(fd, F_SEAL_SEAL);
+        close(fd);
+}
+
+/*
+ * Test SEAL_WRITE
+ * Test whether SEAL_WRITE actually prevents modifications.
+ */
+static void test_seal_write(void)
+{
+        int fd;
+
+        fd = mfd_assert_new("kern_memfd_seal_write",
+                            MFD_DEF_SIZE,
+                            MFD_CLOEXEC | MFD_ALLOW_SEALING);
+        mfd_assert_has_seals(fd, 0);
+        mfd_assert_add_seals(fd, F_SEAL_WRITE);
+        mfd_assert_has_seals(fd, F_SEAL_WRITE);
+
+        mfd_assert_read(fd);
+        mfd_fail_write(fd);
+        mfd_assert_shrink(fd);
+        mfd_assert_grow(fd);
+        mfd_fail_grow_write(fd);
+
+        close(fd);
+}
+
+/*
+ * Test SEAL_SHRINK
+ * Test whether SEAL_SHRINK actually prevents shrinking
+ */
+static void test_seal_shrink(void)
+{
+        int fd;
+
+        fd = mfd_assert_new("kern_memfd_seal_shrink",
+                            MFD_DEF_SIZE,
+                            MFD_CLOEXEC | MFD_ALLOW_SEALING);
+        mfd_assert_has_seals(fd, 0);
+        mfd_assert_add_seals(fd, F_SEAL_SHRINK);
+        mfd_assert_has_seals(fd, F_SEAL_SHRINK);
+
+        mfd_assert_read(fd);
+        mfd_assert_write(fd);
+        mfd_fail_shrink(fd);
+        mfd_assert_grow(fd);
+        mfd_assert_grow_write(fd);
+
+        close(fd);
+}
+
+/*
+ * Test SEAL_GROW
+ * Test whether SEAL_GROW actually prevents growing
+ */
+static void test_seal_grow(void)
+{
+        int fd;
+
+        fd = mfd_assert_new("kern_memfd_seal_grow",
+                            MFD_DEF_SIZE,
+                            MFD_CLOEXEC | MFD_ALLOW_SEALING);
+        mfd_assert_has_seals(fd, 0);
+        mfd_assert_add_seals(fd, F_SEAL_GROW);
+        mfd_assert_has_seals(fd, F_SEAL_GROW);
+
+        mfd_assert_read(fd);
+        mfd_assert_write(fd);
+        mfd_assert_shrink(fd);
+        mfd_fail_grow(fd);
+        mfd_fail_grow_write(fd);
+
+        close(fd);
+}
+
+/*
+ * Test SEAL_SHRINK | SEAL_GROW
+ * Test whether SEAL_SHRINK | SEAL_GROW actually prevents resizing
+ */
+static void test_seal_resize(void)
+{
+        int fd;
+
+        fd = mfd_assert_new("kern_memfd_seal_resize",
+                            MFD_DEF_SIZE,
+                            MFD_CLOEXEC | MFD_ALLOW_SEALING);
+        mfd_assert_has_seals(fd, 0);
+        mfd_assert_add_seals(fd, F_SEAL_SHRINK | F_SEAL_GROW);
+        mfd_assert_has_seals(fd, F_SEAL_SHRINK | F_SEAL_GROW);
+
+        mfd_assert_read(fd);
+        mfd_assert_write(fd);
+        mfd_fail_shrink(fd);
+        mfd_fail_grow(fd);
+        mfd_fail_grow_write(fd);
+
+        close(fd);
+}
+
+/*
+ * Test sharing via dup()
+ * Test that seals are shared between dupped FDs and they're all equal.
+ */
+static void test_share_dup(void)
+{
+        int fd, fd2;
+
+        fd = mfd_assert_new("kern_memfd_share_dup",
+                            MFD_DEF_SIZE,
+                            MFD_CLOEXEC | MFD_ALLOW_SEALING);
+        mfd_assert_has_seals(fd, 0);
+
+        fd2 = mfd_assert_dup(fd);
+        mfd_assert_has_seals(fd2, 0);
+
+        mfd_assert_add_seals(fd, F_SEAL_WRITE);
+        mfd_assert_has_seals(fd, F_SEAL_WRITE);
+        mfd_assert_has_seals(fd2, F_SEAL_WRITE);
+
+        mfd_assert_add_seals(fd2, F_SEAL_SHRINK);
+        mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK);
+        mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK);
+
+        mfd_assert_add_seals(fd, F_SEAL_SEAL);
+        mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_SEAL);
+        mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_SEAL);
+
+        mfd_fail_add_seals(fd, F_SEAL_GROW);
+        mfd_fail_add_seals(fd2, F_SEAL_GROW);
+        mfd_fail_add_seals(fd, F_SEAL_SEAL);
+        mfd_fail_add_seals(fd2, F_SEAL_SEAL);
+
+        close(fd2);
+
+        mfd_fail_add_seals(fd, F_SEAL_GROW);
+        close(fd);
+}
+
+/*
+ * Test sealing with active mmap()s
+ * Modifying seals is only allowed if no other mmap() refs exist.
+ */
+static void test_share_mmap(void)
+{
+        int fd;
+        void *p;
+
+        fd = mfd_assert_new("kern_memfd_share_mmap",
+                            MFD_DEF_SIZE,
+                            MFD_CLOEXEC | MFD_ALLOW_SEALING);
+        mfd_assert_has_seals(fd, 0);
+
+        /* shared/writable ref prevents sealing WRITE, but allows others */
+        p = mfd_assert_mmap_shared(fd);
+        mfd_fail_add_seals(fd, F_SEAL_WRITE);
+        mfd_assert_has_seals(fd, 0);
+        mfd_assert_add_seals(fd, F_SEAL_SHRINK);
+        mfd_assert_has_seals(fd, F_SEAL_SHRINK);
+        munmap(p, MFD_DEF_SIZE);
+
+        /* readable ref allows sealing */
+        p = mfd_assert_mmap_private(fd);
+        mfd_assert_add_seals(fd, F_SEAL_WRITE);
+        mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK);
+        munmap(p, MFD_DEF_SIZE);
+
+        close(fd);
+}
+
+/*
+ * Test sealing with open(/proc/self/fd/%d)
+ * Via /proc we can get access to a separate file-context for the same memfd.
+ * This is *not* like dup(), but like a real separate open(). Make sure the
+ * semantics are as expected and we correctly check for RDONLY / WRONLY / RDWR.
+ */
+static void test_share_open(void)
+{
+        int fd, fd2;
+
+        fd = mfd_assert_new("kern_memfd_share_open",
+                            MFD_DEF_SIZE,
+                            MFD_CLOEXEC | MFD_ALLOW_SEALING);
+        mfd_assert_has_seals(fd, 0);
+
+        fd2 = mfd_assert_open(fd, O_RDWR, 0);
+        mfd_assert_add_seals(fd, F_SEAL_WRITE);
+        mfd_assert_has_seals(fd, F_SEAL_WRITE);
+        mfd_assert_has_seals(fd2, F_SEAL_WRITE);
+
+        mfd_assert_add_seals(fd2, F_SEAL_SHRINK);
+        mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK);
+        mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK);
+
+        close(fd);
+        fd = mfd_assert_open(fd2, O_RDONLY, 0);
+
+        mfd_fail_add_seals(fd, F_SEAL_SEAL);
+        mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK);
+        mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK);
+
+        close(fd2);
+        fd2 = mfd_assert_open(fd, O_RDWR, 0);
+
+        mfd_assert_add_seals(fd2, F_SEAL_SEAL);
+        mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_SEAL);
+        mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_SEAL);
+
+        close(fd2);
+        close(fd);
+}
+
+/*
+ * Test sharing via fork()
+ * Test whether seal-modifications work as expected with forked childs.
+ */
+static void test_share_fork(void)
+{
+        int fd;
+        pid_t pid;
+
+        fd = mfd_assert_new("kern_memfd_share_fork",
+                            MFD_DEF_SIZE,
+                            MFD_CLOEXEC | MFD_ALLOW_SEALING);
+        mfd_assert_has_seals(fd, 0);
+
+        pid = spawn_idle_thread(0);
+        mfd_assert_add_seals(fd, F_SEAL_SEAL);
+        mfd_assert_has_seals(fd, F_SEAL_SEAL);
+
+        mfd_fail_add_seals(fd, F_SEAL_WRITE);
+        mfd_assert_has_seals(fd, F_SEAL_SEAL);
+
+        join_idle_thread(pid);
+
+        mfd_fail_add_seals(fd, F_SEAL_WRITE);
+        mfd_assert_has_seals(fd, F_SEAL_SEAL);
+
+        close(fd);
+}
+
+int main(int argc, char **argv)
+{
+        pid_t pid;
+
+        printf("memfd: CREATE\n");
+        test_create();
+        printf("memfd: BASIC\n");
+        test_basic();
+
+        printf("memfd: SEAL-WRITE\n");
+        test_seal_write();
+        printf("memfd: SEAL-SHRINK\n");
+        test_seal_shrink();
+        printf("memfd: SEAL-GROW\n");
+        test_seal_grow();
+        printf("memfd: SEAL-RESIZE\n");
+        test_seal_resize();
+
+        printf("memfd: SHARE-DUP\n");
+        test_share_dup();
+        printf("memfd: SHARE-MMAP\n");
+        test_share_mmap();
+        printf("memfd: SHARE-OPEN\n");
+        test_share_open();
+        printf("memfd: SHARE-FORK\n");
+        test_share_fork();
+
+        /* Run test-suite in a multi-threaded environment with a shared
+         * file-table. */
+        pid = spawn_idle_thread(CLONE_FILES | CLONE_FS | CLONE_VM);
+        printf("memfd: SHARE-DUP (shared file-table)\n");
+        test_share_dup();
+        printf("memfd: SHARE-MMAP (shared file-table)\n");
+        test_share_mmap();
+        printf("memfd: SHARE-OPEN (shared file-table)\n");
+        test_share_open();
+        printf("memfd: SHARE-FORK (shared file-table)\n");
+        test_share_fork();
+        join_idle_thread(pid);
+
+        printf("memfd: DONE\n");
+
+        return 0;
+}
diff --git a/tools/testing/selftests/memfd/run_fuse_test.sh b/tools/testing/selftests/memfd/run_fuse_test.sh
new file mode 100644
index 000000000000..69b930e1e041
--- /dev/null
+++ b/tools/testing/selftests/memfd/run_fuse_test.sh
@@ -0,0 +1,14 @@
+#!/bin/sh
+
+if test -d "./mnt" ; then
+        fusermount -u ./mnt
+        rmdir ./mnt
+fi
+
+set -e
+
+mkdir mnt
+./fuse_mnt ./mnt
+./fuse_test ./mnt/memfd
+fusermount -u ./mnt
+rmdir ./mnt
diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile
new file mode 100644
index 000000000000..337d853c2b72
--- /dev/null
+++ b/tools/testing/selftests/mount/Makefile
@@ -0,0 +1,17 @@
+# Makefile for mount selftests.
+
+all: unprivileged-remount-test
+
+unprivileged-remount-test: unprivileged-remount-test.c
+        gcc -Wall -O2 unprivileged-remount-test.c -o unprivileged-remount-test
+
+# Allow specific tests to be selected.
+test_unprivileged_remount: unprivileged-remount-test
+        @if [ -f /proc/self/uid_map ] ; then ./unprivileged-remount-test ; fi
+
+run_tests: all test_unprivileged_remount
+
+clean:
+        rm -f unprivileged-remount-test
+
+.PHONY: all test_unprivileged_remount
diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c
new file mode 100644
index 000000000000..1b3ff2fda4d0
--- /dev/null
+++ b/tools/testing/selftests/mount/unprivileged-remount-test.c
@@ -0,0 +1,242 @@
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/mount.h>
+#include <sys/wait.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <grp.h>
+#include <stdbool.h>
+#include <stdarg.h>
+
+#ifndef CLONE_NEWNS
+# define CLONE_NEWNS 0x00020000
+#endif
+#ifndef CLONE_NEWUTS
+# define CLONE_NEWUTS 0x04000000
+#endif
+#ifndef CLONE_NEWIPC
+# define CLONE_NEWIPC 0x08000000
+#endif
+#ifndef CLONE_NEWNET
+# define CLONE_NEWNET 0x40000000
+#endif
+#ifndef CLONE_NEWUSER
+# define CLONE_NEWUSER 0x10000000
+#endif
+#ifndef CLONE_NEWPID
+# define CLONE_NEWPID 0x20000000
+#endif
+
+#ifndef MS_RELATIME
+#define MS_RELATIME (1 << 21)
+#endif
+#ifndef MS_STRICTATIME
+#define MS_STRICTATIME (1 << 24)
+#endif
+
+static void die(char *fmt, ...)
+{
+        va_list ap;
+        va_start(ap, fmt);
+        vfprintf(stderr, fmt, ap);
+        va_end(ap);
+        exit(EXIT_FAILURE);
+}
+
+static void write_file(char *filename, char *fmt, ...)
+{
+        char buf[4096];
+        int fd;
+        ssize_t written;
+        int buf_len;
+        va_list ap;
+
+        va_start(ap, fmt);
+        buf_len = vsnprintf(buf, sizeof(buf), fmt, ap);
+        va_end(ap);
+        if (buf_len < 0) {
+                die("vsnprintf failed: %s\n",
+                    strerror(errno));
+        }
+        if (buf_len >= sizeof(buf)) {
+                die("vsnprintf output truncated\n");
+        }
+
+        fd = open(filename, O_WRONLY);
+        if (fd < 0) {
+                die("open of %s failed: %s\n",
+                    filename, strerror(errno));
+        }
+        written = write(fd, buf, buf_len);
+        if (written != buf_len) {
+                if (written >= 0) {
+                        die("short write to %s\n", filename);
+                } else {
+                        die("write to %s failed: %s\n",
+                                filename, strerror(errno));
+                }
+        }
+        if (close(fd) != 0) {
+                die("close of %s failed: %s\n",
+                        filename, strerror(errno));
+        }
+}
+
+static void create_and_enter_userns(void)
+{
+        uid_t uid;
+        gid_t gid;
+
+        uid = getuid();
+        gid = getgid();
+
+        if (unshare(CLONE_NEWUSER) !=0) {
+                die("unshare(CLONE_NEWUSER) failed: %s\n",
+                        strerror(errno));
+        }
+
+        write_file("/proc/self/uid_map", "0 %d 1", uid);
+        write_file("/proc/self/gid_map", "0 %d 1", gid);
+
+        if (setgroups(0, NULL) != 0) {
+                die("setgroups failed: %s\n",
+                        strerror(errno));
+        }
+        if (setgid(0) != 0) {
+                die ("setgid(0) failed %s\n",
+                        strerror(errno));
+        }
+        if (setuid(0) != 0) {
+                die("setuid(0) failed %s\n",
+                        strerror(errno));
+        }
+}
+
+static
+bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags)
+{
+        pid_t child;
+
+        child = fork();
+        if (child == -1) {
+                die("fork failed: %s\n",
+                        strerror(errno));
+        }
+        if (child != 0) { /* parent */
+                pid_t pid;
+                int status;
+                pid = waitpid(child, &status, 0);
+                if (pid == -1) {
+                        die("waitpid failed: %s\n",
+                                strerror(errno));
+                }
+                if (pid != child) {
+                        die("waited for %d got %d\n",
+                                child, pid);
+                }
+                if (!WIFEXITED(status)) {
+                        die("child did not terminate cleanly\n");
+                }
+                return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false;
+        }
+
+        create_and_enter_userns();
+        if (unshare(CLONE_NEWNS) != 0) {
+                die("unshare(CLONE_NEWNS) failed: %s\n",
+                        strerror(errno));
+        }
+
+        if (mount("testing", "/tmp", "ramfs", mount_flags, NULL) != 0) {
+                die("mount of /tmp failed: %s\n",
+                        strerror(errno));
+        }
+
+        create_and_enter_userns();
+
+        if (unshare(CLONE_NEWNS) != 0) {
+                die("unshare(CLONE_NEWNS) failed: %s\n",
+                        strerror(errno));
+        }
+
+        if (mount("/tmp", "/tmp", "none",
+                  MS_REMOUNT | MS_BIND | remount_flags, NULL) != 0) {
+                /* system("cat /proc/self/mounts"); */
+                die("remount of /tmp failed: %s\n",
+                    strerror(errno));
+        }
+
+        if (mount("/tmp", "/tmp", "none",
+                  MS_REMOUNT | MS_BIND | invalid_flags, NULL) == 0) {
+                /* system("cat /proc/self/mounts"); */
+                die("remount of /tmp with invalid flags "
+                    "succeeded unexpectedly\n");
+        }
+        exit(EXIT_SUCCESS);
+}
+
+static bool test_unpriv_remount_simple(int mount_flags)
+{
+        return test_unpriv_remount(mount_flags, mount_flags, 0);
+}
+
+static bool test_unpriv_remount_atime(int mount_flags, int invalid_flags)
+{
+        return test_unpriv_remount(mount_flags, mount_flags, invalid_flags);
+}
+
+int main(int argc, char **argv)
+{
+        if (!test_unpriv_remount_simple(MS_RDONLY|MS_NODEV)) {
+                die("MS_RDONLY malfunctions\n");
+        }
+        if (!test_unpriv_remount_simple(MS_NODEV)) {
+                die("MS_NODEV malfunctions\n");
+        }
+        if (!test_unpriv_remount_simple(MS_NOSUID|MS_NODEV)) {
+                die("MS_NOSUID malfunctions\n");
+        }
+        if (!test_unpriv_remount_simple(MS_NOEXEC|MS_NODEV)) {
+                die("MS_NOEXEC malfunctions\n");
+        }
+        if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODEV,
+                                       MS_NOATIME|MS_NODEV))
+        {
+                die("MS_RELATIME malfunctions\n");
+        }
+        if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODEV,
+                                       MS_NOATIME|MS_NODEV))
+        {
+                die("MS_STRICTATIME malfunctions\n");
+        }
+        if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODEV,
+                                       MS_STRICTATIME|MS_NODEV))
+        {
+                die("MS_RELATIME malfunctions\n");
+        }
+        if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME|MS_NODEV,
+                                       MS_NOATIME|MS_NODEV))
+        {
+                die("MS_RELATIME malfunctions\n");
+        }
+        if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME|MS_NODEV,
+                                       MS_NOATIME|MS_NODEV))
+        {
+                die("MS_RELATIME malfunctions\n");
+        }
+        if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME|MS_NODEV,
+                                       MS_STRICTATIME|MS_NODEV))
+        {
+                die("MS_RELATIME malfunctions\n");
+        }
+        if (!test_unpriv_remount(MS_STRICTATIME|MS_NODEV, MS_NODEV,
+                                 MS_NOATIME|MS_NODEV))
+        {
+                die("Default atime malfunctions\n");
+        }
+        return EXIT_SUCCESS;
+}
diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c
index 57b9c2b7c4ff..6f6733331d95 100644
--- a/tools/testing/selftests/net/psock_fanout.c
+++ b/tools/testing/selftests/net/psock_fanout.c
@@ -128,7 +128,7 @@ static int sock_fanout_read_ring(int fd, void *ring)
         struct tpacket2_hdr *header = ring;
         int count = 0;
 
-        while (header->tp_status & TP_STATUS_USER && count < RING_NUM_FRAMES) {
+        while (count < RING_NUM_FRAMES && header->tp_status & TP_STATUS_USER) {
                 count++;
                 header = ring + (count * getpagesize());
         }
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 54833a791a44..f6ff90a76bd7 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -13,14 +13,14 @@ CFLAGS := -Wall -O2 -flto -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CUR
 
 export CC CFLAGS
 
-TARGETS = pmu copyloops mm tm
+TARGETS = pmu copyloops mm tm primitives
 
 endif
 
-all:
-        @for TARGET in $(TARGETS); do \
-                $(MAKE) -C $$TARGET all; \
-        done;
+all: $(TARGETS)
+
+$(TARGETS):
+        $(MAKE) -k -C $@ all
 
 run_tests: all
         @for TARGET in $(TARGETS); do \
@@ -36,4 +36,4 @@ clean:
 tags:
         find . -name '*.c' -o -name '*.h' | xargs ctags
 
-.PHONY: all run_tests clean tags
+.PHONY: all run_tests clean tags $(TARGETS)
diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile
index b9ff0db42c79..c9f4263906a5 100644
--- a/tools/testing/selftests/powerpc/pmu/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/Makefile
@@ -1,10 +1,12 @@
 noarg:
         $(MAKE) -C ../
 
-PROGS := count_instructions
-EXTRA_SOURCES := ../harness.c event.c
+PROGS := count_instructions l3_bank_test per_event_excludes
+EXTRA_SOURCES := ../harness.c event.c lib.c
 
-all: $(PROGS) sub_all
+SUB_TARGETS = ebb
+
+all: $(PROGS) $(SUB_TARGETS)
 
 $(PROGS): $(EXTRA_SOURCES)
 
@@ -20,13 +22,8 @@ run_tests: all sub_run_tests
 clean: sub_clean
         rm -f $(PROGS) loop.o
 
-
-SUB_TARGETS = ebb
-
-sub_all:
-        @for TARGET in $(SUB_TARGETS); do \
-                $(MAKE) -C $$TARGET all; \
-        done;
+$(SUB_TARGETS):
+        $(MAKE) -k -C $@ all
 
 sub_run_tests: all
         @for TARGET in $(SUB_TARGETS); do \
@@ -38,4 +35,4 @@ sub_clean:
                 $(MAKE) -C $$TARGET clean; \
         done;
 
-.PHONY: all run_tests clean sub_all sub_run_tests sub_clean
+.PHONY: all run_tests clean sub_run_tests sub_clean $(SUB_TARGETS)
diff --git a/tools/testing/selftests/powerpc/pmu/count_instructions.c b/tools/testing/selftests/powerpc/pmu/count_instructions.c
index 312b4f0fd27c..4622117b24c0 100644
--- a/tools/testing/selftests/powerpc/pmu/count_instructions.c
+++ b/tools/testing/selftests/powerpc/pmu/count_instructions.c
@@ -12,6 +12,7 @@
 
 #include "event.h"
 #include "utils.h"
+#include "lib.h"
 
 extern void thirty_two_instruction_loop(u64 loops);
 
@@ -90,7 +91,7 @@ static u64 determine_overhead(struct event *events)
         return overhead;
 }
 
-static int count_instructions(void)
+static int test_body(void)
 {
         struct event events[2];
         u64 overhead;
@@ -111,17 +112,23 @@ static int count_instructions(void)
         overhead = determine_overhead(events);
         printf("Overhead of null loop: %llu instructions\n", overhead);
 
-        /* Run for 1M instructions */
-        FAIL_IF(do_count_loop(events, 0x100000, overhead, true));
+        /* Run for 1Mi instructions */
+        FAIL_IF(do_count_loop(events, 1000000, overhead, true));
+
+        /* Run for 10Mi instructions */
+        FAIL_IF(do_count_loop(events, 10000000, overhead, true));
+
+        /* Run for 100Mi instructions */
+        FAIL_IF(do_count_loop(events, 100000000, overhead, true));
 
-        /* Run for 10M instructions */
-        FAIL_IF(do_count_loop(events, 0xa00000, overhead, true));
+        /* Run for 1Bi instructions */
+        FAIL_IF(do_count_loop(events, 1000000000, overhead, true));
 
-        /* Run for 100M instructions */
-        FAIL_IF(do_count_loop(events, 0x6400000, overhead, true));
+        /* Run for 16Bi instructions */
+        FAIL_IF(do_count_loop(events, 16000000000, overhead, true));
 
-        /* Run for 1G instructions */
-        FAIL_IF(do_count_loop(events, 0x40000000, overhead, true));
+        /* Run for 64Bi instructions */
+        FAIL_IF(do_count_loop(events, 64000000000, overhead, true));
 
         event_close(&events[0]);
         event_close(&events[1]);
@@ -129,6 +136,11 @@ static int count_instructions(void)
         return 0;
 }
 
+static int count_instructions(void)
+{
+        return eat_cpu(test_body);
+}
+
 int main(void)
 {
         return test_harness(count_instructions, "count_instructions");
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
index edbba2affc2c..3dc4332698cb 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
@@ -13,11 +13,12 @@ PROGS := reg_access_test event_attributes_test cycles_test	\
          close_clears_pmcc_test instruction_count_test          \
          fork_cleanup_test ebb_on_child_test                    \
          ebb_on_willing_child_test back_to_back_ebbs_test       \
-         lost_exception_test no_handler_test
+         lost_exception_test no_handler_test                    \
+         cycles_with_mmcr2_test
 
 all: $(PROGS)
 
-$(PROGS): ../../harness.c ../event.c ../lib.c ebb.c ebb_handler.S trace.c
+$(PROGS): ../../harness.c ../event.c ../lib.c ebb.c ebb_handler.S trace.c busy_loop.S
 
 instruction_count_test: ../loop.S
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/busy_loop.S b/tools/testing/selftests/powerpc/pmu/ebb/busy_loop.S
new file mode 100644
index 000000000000..c7e4093f1cd3
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/busy_loop.S
@@ -0,0 +1,271 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <ppc-asm.h>
+
+        .text
+
+FUNC_START(core_busy_loop)
+        stdu    %r1, -168(%r1)
+        std     r14, 160(%r1)
+        std     r15, 152(%r1)
+        std     r16, 144(%r1)
+        std     r17, 136(%r1)
+        std     r18, 128(%r1)
+        std     r19, 120(%r1)
+        std     r20, 112(%r1)
+        std     r21, 104(%r1)
+        std     r22, 96(%r1)
+        std     r23, 88(%r1)
+        std     r24, 80(%r1)
+        std     r25, 72(%r1)
+        std     r26, 64(%r1)
+        std     r27, 56(%r1)
+        std     r28, 48(%r1)
+        std     r29, 40(%r1)
+        std     r30, 32(%r1)
+        std     r31, 24(%r1)
+
+        li       r3, 0x3030
+        std      r3, -96(%r1)
+        li       r4, 0x4040
+        std      r4, -104(%r1)
+        li       r5, 0x5050
+        std      r5, -112(%r1)
+        li       r6, 0x6060
+        std      r6, -120(%r1)
+        li       r7, 0x7070
+        std      r7, -128(%r1)
+        li       r8, 0x0808
+        std      r8, -136(%r1)
+        li       r9, 0x0909
+        std      r9, -144(%r1)
+        li      r10, 0x1010
+        std     r10, -152(%r1)
+        li      r11, 0x1111
+        std     r11, -160(%r1)
+        li      r14, 0x1414
+        std     r14, -168(%r1)
+        li      r15, 0x1515
+        std     r15, -176(%r1)
+        li      r16, 0x1616
+        std     r16, -184(%r1)
+        li      r17, 0x1717
+        std     r17, -192(%r1)
+        li      r18, 0x1818
+        std     r18, -200(%r1)
+        li      r19, 0x1919
+        std     r19, -208(%r1)
+        li      r20, 0x2020
+        std     r20, -216(%r1)
+        li      r21, 0x2121
+        std     r21, -224(%r1)
+        li      r22, 0x2222
+        std     r22, -232(%r1)
+        li      r23, 0x2323
+        std     r23, -240(%r1)
+        li      r24, 0x2424
+        std     r24, -248(%r1)
+        li      r25, 0x2525
+        std     r25, -256(%r1)
+        li      r26, 0x2626
+        std     r26, -264(%r1)
+        li      r27, 0x2727
+        std     r27, -272(%r1)
+        li      r28, 0x2828
+        std     r28, -280(%r1)
+        li      r29, 0x2929
+        std     r29, -288(%r1)
+        li      r30, 0x3030
+        li      r31, 0x3131
+
+        li      r3, 0
+0:      addi    r3, r3, 1
+        cmpwi   r3, 100
+        blt     0b
+
+        /* Return 1 (fail) unless we get through all the checks */
+        li      r3, 1
+
+        /* Check none of our registers have been corrupted */
+        cmpwi   r4,  0x4040
+        bne     1f
+        cmpwi   r5,  0x5050
+        bne     1f
+        cmpwi   r6,  0x6060
+        bne     1f
+        cmpwi   r7,  0x7070
+        bne     1f
+        cmpwi   r8,  0x0808
+        bne     1f
+        cmpwi   r9,  0x0909
+        bne     1f
+        cmpwi   r10, 0x1010
+        bne     1f
+        cmpwi   r11, 0x1111
+        bne     1f
+        cmpwi   r14, 0x1414
+        bne     1f
+        cmpwi   r15, 0x1515
+        bne     1f
+        cmpwi   r16, 0x1616
+        bne     1f
+        cmpwi   r17, 0x1717
+        bne     1f
+        cmpwi   r18, 0x1818
+        bne     1f
+        cmpwi   r19, 0x1919
+        bne     1f
+        cmpwi   r20, 0x2020
+        bne     1f
+        cmpwi   r21, 0x2121
+        bne     1f
+        cmpwi   r22, 0x2222
+        bne     1f
+        cmpwi   r23, 0x2323
+        bne     1f
+        cmpwi   r24, 0x2424
+        bne     1f
+        cmpwi   r25, 0x2525
+        bne     1f
+        cmpwi   r26, 0x2626
+        bne     1f
+        cmpwi   r27, 0x2727
+        bne     1f
+        cmpwi   r28, 0x2828
+        bne     1f
+        cmpwi   r29, 0x2929
+        bne     1f
+        cmpwi   r30, 0x3030
+        bne     1f
+        cmpwi   r31, 0x3131
+        bne     1f
+
+        /* Load junk into all our registers before we reload them from the stack. */
+        li      r3,  0xde
+        li      r4,  0xad
+        li      r5,  0xbe
+        li      r6,  0xef
+        li      r7,  0xde
+        li      r8,  0xad
+        li      r9,  0xbe
+        li      r10, 0xef
+        li      r11, 0xde
+        li      r14, 0xad
+        li      r15, 0xbe
+        li      r16, 0xef
+        li      r17, 0xde
+        li      r18, 0xad
+        li      r19, 0xbe
+        li      r20, 0xef
+        li      r21, 0xde
+        li      r22, 0xad
+        li      r23, 0xbe
+        li      r24, 0xef
+        li      r25, 0xde
+        li      r26, 0xad
+        li      r27, 0xbe
+        li      r28, 0xef
+        li      r29, 0xdd
+
+        ld      r3,     -96(%r1)
+        cmpwi   r3,  0x3030
+        bne     1f
+        ld      r4,     -104(%r1)
+        cmpwi   r4,  0x4040
+        bne     1f
+        ld      r5,     -112(%r1)
+        cmpwi   r5,  0x5050
+        bne     1f
+        ld      r6,     -120(%r1)
+        cmpwi   r6,  0x6060
+        bne     1f
+        ld      r7,     -128(%r1)
+        cmpwi   r7,  0x7070
+        bne     1f
+        ld      r8,     -136(%r1)
+        cmpwi   r8,  0x0808
+        bne     1f
+        ld      r9,     -144(%r1)
+        cmpwi   r9,  0x0909
+        bne     1f
+        ld      r10, -152(%r1)
+        cmpwi   r10, 0x1010
+        bne     1f
+        ld      r11, -160(%r1)
+        cmpwi   r11, 0x1111
+        bne     1f
+        ld      r14, -168(%r1)
+        cmpwi   r14, 0x1414
+        bne     1f
+        ld      r15, -176(%r1)
+        cmpwi   r15, 0x1515
+        bne     1f
+        ld      r16, -184(%r1)
+        cmpwi   r16, 0x1616
+        bne     1f
+        ld      r17, -192(%r1)
+        cmpwi   r17, 0x1717
+        bne     1f
+        ld      r18, -200(%r1)
+        cmpwi   r18, 0x1818
+        bne     1f
+        ld      r19, -208(%r1)
+        cmpwi   r19, 0x1919
+        bne     1f
+        ld      r20, -216(%r1)
+        cmpwi   r20, 0x2020
+        bne     1f
+        ld      r21, -224(%r1)
+        cmpwi   r21, 0x2121
+        bne     1f
+        ld      r22, -232(%r1)
+        cmpwi   r22, 0x2222
+        bne     1f
+        ld      r23, -240(%r1)
+        cmpwi   r23, 0x2323
+        bne     1f
+        ld      r24, -248(%r1)
+        cmpwi   r24, 0x2424
+        bne     1f
+        ld      r25, -256(%r1)
+        cmpwi   r25, 0x2525
+        bne     1f
+        ld      r26, -264(%r1)
+        cmpwi   r26, 0x2626
+        bne     1f
+        ld      r27, -272(%r1)
+        cmpwi   r27, 0x2727
+        bne     1f
+        ld      r28, -280(%r1)
+        cmpwi   r28, 0x2828
+        bne     1f
+        ld      r29, -288(%r1)
+        cmpwi   r29, 0x2929
+        bne     1f
+
+        /* Load 0 (success) to return */
+        li      r3, 0
+
+1:      ld      r14, 160(%r1)
+        ld      r15, 152(%r1)
+        ld      r16, 144(%r1)
+        ld      r17, 136(%r1)
+        ld      r18, 128(%r1)
+        ld      r19, 120(%r1)
+        ld      r20, 112(%r1)
+        ld      r21, 104(%r1)
+        ld      r22, 96(%r1)
+        ld      r23, 88(%r1)
+        ld      r24, 80(%r1)
+        ld      r25, 72(%r1)
+        ld      r26, 64(%r1)
+        ld      r27, 56(%r1)
+        ld      r28, 48(%r1)
+        ld      r29, 40(%r1)
+        ld      r30, 32(%r1)
+        ld      r31, 24(%r1)
+        addi    %r1, %r1, 168
+        blr
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
new file mode 100644
index 000000000000..d43029b0800c
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
@@ -0,0 +1,91 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+#include "ebb.h"
+
+
+/*
+ * Test of counting cycles while manipulating the user accessible bits in MMCR2.
+ */
+
+/* We use two values because the first freezes PMC1 and so we would get no EBBs */
+#define MMCR2_EXPECTED_1 0x4020100804020000UL /* (FC1P|FC2P|FC3P|FC4P|FC5P|FC6P) */
+#define MMCR2_EXPECTED_2 0x0020100804020000UL /* (     FC2P|FC3P|FC4P|FC5P|FC6P) */
+
+
+int cycles_with_mmcr2(void)
+{
+        struct event event;
+        uint64_t val, expected[2], actual;
+        int i;
+        bool bad_mmcr2;
+
+        event_init_named(&event, 0x1001e, "cycles");
+        event_leader_ebb_init(&event);
+
+        event.attr.exclude_kernel = 1;
+        event.attr.exclude_hv = 1;
+        event.attr.exclude_idle = 1;
+
+        FAIL_IF(event_open(&event));
+
+        ebb_enable_pmc_counting(1);
+        setup_ebb_handler(standard_ebb_callee);
+        ebb_global_enable();
+
+        FAIL_IF(ebb_event_enable(&event));
+
+        mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+
+        /* XXX Set of MMCR2 must be after enable */
+        expected[0] = MMCR2_EXPECTED_1;
+        expected[1] = MMCR2_EXPECTED_2;
+        i = 0;
+        bad_mmcr2 = false;
+
+        /* Make sure we loop until we take at least one EBB */
+        while ((ebb_state.stats.ebb_count < 20 && !bad_mmcr2) ||
+                ebb_state.stats.ebb_count < 1)
+        {
+                mtspr(SPRN_MMCR2, expected[i % 2]);
+
+                FAIL_IF(core_busy_loop());
+
+                val = mfspr(SPRN_MMCR2);
+                if (val != expected[i % 2]) {
+                        bad_mmcr2 = true;
+                        actual = val;
+                }
+
+                i++;
+        }
+
+        ebb_global_disable();
+        ebb_freeze_pmcs();
+
+        count_pmc(1, sample_period);
+
+        dump_ebb_state();
+
+        event_close(&event);
+
+        FAIL_IF(ebb_state.stats.ebb_count == 0);
+
+        if (bad_mmcr2)
+                printf("Bad MMCR2 value seen is 0x%lx\n", actual);
+
+        FAIL_IF(bad_mmcr2);
+
+        return 0;
+}
+
+int main(void)
+{
+        return test_harness(cycles_with_mmcr2, "cycles_with_mmcr2");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
index 1b46be94b64c..d7a72ce696b5 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -224,6 +224,7 @@ void dump_ebb_hw_state(void)
 
         printf("HW state:\n"            \
                "MMCR0 0x%016x %s\n"     \
+               "MMCR2 0x%016lx\n"       \
                "EBBHR 0x%016lx\n"       \
                "BESCR 0x%016llx %s\n"   \
                "PMC1  0x%016lx\n"       \
@@ -233,10 +234,11 @@ void dump_ebb_hw_state(void)
                "PMC5  0x%016lx\n"       \
                "PMC6  0x%016lx\n"       \
                "SIAR  0x%016lx\n",
-               mmcr0, decode_mmcr0(mmcr0), mfspr(SPRN_EBBHR), bescr,
-               decode_bescr(bescr), mfspr(SPRN_PMC1), mfspr(SPRN_PMC2),
-               mfspr(SPRN_PMC3), mfspr(SPRN_PMC4), mfspr(SPRN_PMC5),
-               mfspr(SPRN_PMC6), mfspr(SPRN_SIAR));
+               mmcr0, decode_mmcr0(mmcr0), mfspr(SPRN_MMCR2),
+               mfspr(SPRN_EBBHR), bescr, decode_bescr(bescr),
+               mfspr(SPRN_PMC1), mfspr(SPRN_PMC2), mfspr(SPRN_PMC3),
+               mfspr(SPRN_PMC4), mfspr(SPRN_PMC5), mfspr(SPRN_PMC6),
+               mfspr(SPRN_SIAR));
 }
 
 void dump_ebb_state(void)
@@ -335,257 +337,6 @@ void event_leader_ebb_init(struct event *e)
         e->attr.pinned = 1;
 }
 
-int core_busy_loop(void)
-{
-        int rc;
-
-        asm volatile (
-                "li  3,  0x3030\n"
-                "std 3,  -96(1)\n"
-                "li  4,  0x4040\n"
-                "std 4,  -104(1)\n"
-                "li  5,  0x5050\n"
-                "std 5,  -112(1)\n"
-                "li  6,  0x6060\n"
-                "std 6,  -120(1)\n"
-                "li  7,  0x7070\n"
-                "std 7,  -128(1)\n"
-                "li  8,  0x0808\n"
-                "std 8,  -136(1)\n"
-                "li  9,  0x0909\n"
-                "std 9,  -144(1)\n"
-                "li  10, 0x1010\n"
-                "std 10, -152(1)\n"
-                "li  11, 0x1111\n"
-                "std 11, -160(1)\n"
-                "li  14, 0x1414\n"
-                "std 14, -168(1)\n"
-                "li  15, 0x1515\n"
-                "std 15, -176(1)\n"
-                "li  16, 0x1616\n"
-                "std 16, -184(1)\n"
-                "li  17, 0x1717\n"
-                "std 17, -192(1)\n"
-                "li  18, 0x1818\n"
-                "std 18, -200(1)\n"
-                "li  19, 0x1919\n"
-                "std 19, -208(1)\n"
-                "li  20, 0x2020\n"
-                "std 20, -216(1)\n"
-                "li  21, 0x2121\n"
-                "std 21, -224(1)\n"
-                "li  22, 0x2222\n"
-                "std 22, -232(1)\n"
-                "li  23, 0x2323\n"
-                "std 23, -240(1)\n"
-                "li  24, 0x2424\n"
-                "std 24, -248(1)\n"
-                "li  25, 0x2525\n"
-                "std 25, -256(1)\n"
-                "li  26, 0x2626\n"
-                "std 26, -264(1)\n"
-                "li  27, 0x2727\n"
-                "std 27, -272(1)\n"
-                "li  28, 0x2828\n"
-                "std 28, -280(1)\n"
-                "li  29, 0x2929\n"
-                "std 29, -288(1)\n"
-                "li  30, 0x3030\n"
-                "li  31, 0x3131\n"
-
-                "li    3,  0\n"
-                "0: "
-                "addi  3, 3, 1\n"
-                "cmpwi 3, 100\n"
-                "blt   0b\n"
-
-                /* Return 1 (fail) unless we get through all the checks */
-                "li     0, 1\n"
-
-                /* Check none of our registers have been corrupted */
-                "cmpwi  4,  0x4040\n"
-                "bne    1f\n"
-                "cmpwi  5,  0x5050\n"
-                "bne    1f\n"
-                "cmpwi  6,  0x6060\n"
-                "bne    1f\n"
-                "cmpwi  7,  0x7070\n"
-                "bne    1f\n"
-                "cmpwi  8,  0x0808\n"
-                "bne    1f\n"
-                "cmpwi  9,  0x0909\n"
-                "bne    1f\n"
-                "cmpwi  10, 0x1010\n"
-                "bne    1f\n"
-                "cmpwi  11, 0x1111\n"
-                "bne    1f\n"
-                "cmpwi  14, 0x1414\n"
-                "bne    1f\n"
-                "cmpwi  15, 0x1515\n"
-                "bne    1f\n"
-                "cmpwi  16, 0x1616\n"
-                "bne    1f\n"
-                "cmpwi  17, 0x1717\n"
-                "bne    1f\n"
-                "cmpwi  18, 0x1818\n"
-                "bne    1f\n"
-                "cmpwi  19, 0x1919\n"
-                "bne    1f\n"
-                "cmpwi  20, 0x2020\n"
-                "bne    1f\n"
-                "cmpwi  21, 0x2121\n"
-                "bne    1f\n"
-                "cmpwi  22, 0x2222\n"
-                "bne    1f\n"
-                "cmpwi  23, 0x2323\n"
-                "bne    1f\n"
-                "cmpwi  24, 0x2424\n"
-                "bne    1f\n"
-                "cmpwi  25, 0x2525\n"
-                "bne    1f\n"
-                "cmpwi  26, 0x2626\n"
-                "bne    1f\n"
-                "cmpwi  27, 0x2727\n"
-                "bne    1f\n"
-                "cmpwi  28, 0x2828\n"
-                "bne    1f\n"
-                "cmpwi  29, 0x2929\n"
-                "bne    1f\n"
-                "cmpwi  30, 0x3030\n"
-                "bne    1f\n"
-                "cmpwi  31, 0x3131\n"
-                "bne    1f\n"
-
-                /* Load junk into all our registers before we reload them from the stack. */
-                "li  3,  0xde\n"
-                "li  4,  0xad\n"
-                "li  5,  0xbe\n"
-                "li  6,  0xef\n"
-                "li  7,  0xde\n"
-                "li  8,  0xad\n"
-                "li  9,  0xbe\n"
-                "li  10, 0xef\n"
-                "li  11, 0xde\n"
-                "li  14, 0xad\n"
-                "li  15, 0xbe\n"
-                "li  16, 0xef\n"
-                "li  17, 0xde\n"
-                "li  18, 0xad\n"
-                "li  19, 0xbe\n"
-                "li  20, 0xef\n"
-                "li  21, 0xde\n"
-                "li  22, 0xad\n"
-                "li  23, 0xbe\n"
-                "li  24, 0xef\n"
-                "li  25, 0xde\n"
-                "li  26, 0xad\n"
-                "li  27, 0xbe\n"
-                "li  28, 0xef\n"
-                "li  29, 0xdd\n"
-
-                "ld     3,  -96(1)\n"
-                "cmpwi  3,  0x3030\n"
-                "bne    1f\n"
-                "ld     4,  -104(1)\n"
-                "cmpwi  4,  0x4040\n"
-                "bne    1f\n"
-                "ld     5,  -112(1)\n"
-                "cmpwi  5,  0x5050\n"
-                "bne    1f\n"
-                "ld     6,  -120(1)\n"
-                "cmpwi  6,  0x6060\n"
-                "bne    1f\n"
-                "ld     7,  -128(1)\n"
-                "cmpwi  7,  0x7070\n"
-                "bne    1f\n"
-                "ld     8,  -136(1)\n"
-                "cmpwi  8,  0x0808\n"
-                "bne    1f\n"
-                "ld     9,  -144(1)\n"
-                "cmpwi  9,  0x0909\n"
-                "bne    1f\n"
-                "ld     10, -152(1)\n"
-                "cmpwi  10, 0x1010\n"
-                "bne    1f\n"
-                "ld     11, -160(1)\n"
-                "cmpwi  11, 0x1111\n"
-                "bne    1f\n"
-                "ld     14, -168(1)\n"
-                "cmpwi  14, 0x1414\n"
-                "bne    1f\n"
-                "ld     15, -176(1)\n"
-                "cmpwi  15, 0x1515\n"
-                "bne    1f\n"
-                "ld     16, -184(1)\n"
-                "cmpwi  16, 0x1616\n"
-                "bne    1f\n"
-                "ld     17, -192(1)\n"
-                "cmpwi  17, 0x1717\n"
-                "bne    1f\n"
-                "ld     18, -200(1)\n"
-                "cmpwi  18, 0x1818\n"
-                "bne    1f\n"
-                "ld     19, -208(1)\n"
-                "cmpwi  19, 0x1919\n"
-                "bne    1f\n"
-                "ld     20, -216(1)\n"
-                "cmpwi  20, 0x2020\n"
-                "bne    1f\n"
-                "ld     21, -224(1)\n"
-                "cmpwi  21, 0x2121\n"
-                "bne    1f\n"
-                "ld     22, -232(1)\n"
-                "cmpwi  22, 0x2222\n"
-                "bne    1f\n"
-                "ld     23, -240(1)\n"
-                "cmpwi  23, 0x2323\n"
-                "bne    1f\n"
-                "ld     24, -248(1)\n"
-                "cmpwi  24, 0x2424\n"
-                "bne    1f\n"
-                "ld     25, -256(1)\n"
-                "cmpwi  25, 0x2525\n"
-                "bne    1f\n"
-                "ld     26, -264(1)\n"
-                "cmpwi  26, 0x2626\n"
-                "bne    1f\n"
-                "ld     27, -272(1)\n"
-                "cmpwi  27, 0x2727\n"
-                "bne    1f\n"
-                "ld     28, -280(1)\n"
-                "cmpwi  28, 0x2828\n"
-                "bne    1f\n"
-                "ld     29, -288(1)\n"
-                "cmpwi  29, 0x2929\n"
-                "bne    1f\n"
-
-                /* Load 0 (success) to return */
-                "li     0, 0\n"
-
-                "1:     mr %0, 0\n"
-
-                : "=r" (rc)
-                : /* no inputs */
-                : "3", "4", "5", "6", "7", "8", "9", "10", "11", "14",
-                  "15", "16", "17", "18", "19", "20", "21", "22", "23",
-                   "24", "25", "26", "27", "28", "29", "30", "31",
-                   "memory"
-        );
-
-        return rc;
-}
-
-int core_busy_loop_with_freeze(void)
-{
-        int rc;
-
-        mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~MMCR0_FC);
-        rc = core_busy_loop();
-        mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) |  MMCR0_FC);
-
-        return rc;
-}
-
 int ebb_child(union pipe read_pipe, union pipe write_pipe)
 {
         struct event event;
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.h b/tools/testing/selftests/powerpc/pmu/ebb/ebb.h
index e62bde05bf78..e44eee5d97ca 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.h
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.h
@@ -70,7 +70,6 @@ int ebb_check_mmcr0(void);
 extern u64 sample_period;
 
 int core_busy_loop(void);
-int core_busy_loop_with_freeze(void);
 int ebb_child(union pipe read_pipe, union pipe write_pipe);
 int catch_sigill(void (*func)(void));
 void write_pmc1(void);
diff --git a/tools/testing/selftests/powerpc/pmu/l3_bank_test.c b/tools/testing/selftests/powerpc/pmu/l3_bank_test.c
new file mode 100644
index 000000000000..77472f31441e
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/l3_bank_test.c
@@ -0,0 +1,48 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "event.h"
+#include "utils.h"
+
+#define MALLOC_SIZE     (0x10000 * 10)  /* Ought to be enough .. */
+
+/*
+ * Tests that the L3 bank handling is correct. We fixed it in commit e9aaac1.
+ */
+static int l3_bank_test(void)
+{
+        struct event event;
+        char *p;
+        int i;
+
+        p = malloc(MALLOC_SIZE);
+        FAIL_IF(!p);
+
+        event_init(&event, 0x84918F);
+
+        FAIL_IF(event_open(&event));
+
+        for (i = 0; i < MALLOC_SIZE; i += 0x10000)
+                p[i] = i;
+
+        event_read(&event);
+        event_report(&event);
+
+        FAIL_IF(event.result.running == 0);
+        FAIL_IF(event.result.enabled == 0);
+
+        event_close(&event);
+        free(p);
+
+        return 0;
+}
+
+int main(void)
+{
+        return test_harness(l3_bank_test, "l3_bank_test");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/lib.c b/tools/testing/selftests/powerpc/pmu/lib.c
index 0f6a4731d546..9768dea37bf3 100644
--- a/tools/testing/selftests/powerpc/pmu/lib.c
+++ b/tools/testing/selftests/powerpc/pmu/lib.c
@@ -5,10 +5,15 @@
 
 #define _GNU_SOURCE     /* For CPU_ZERO etc. */
 
+#include <elf.h>
 #include <errno.h>
+#include <fcntl.h>
+#include <link.h>
 #include <sched.h>
 #include <setjmp.h>
 #include <stdlib.h>
+#include <sys/stat.h>
+#include <sys/types.h>
 #include <sys/wait.h>
 
 #include "utils.h"
@@ -177,8 +182,8 @@ struct addr_range libc, vdso;
 
 int parse_proc_maps(void)
 {
+        unsigned long start, end;
         char execute, name[128];
-        uint64_t start, end;
         FILE *f;
         int rc;
 
@@ -250,3 +255,46 @@ out_close:
 out:
         return rc;
 }
+
+static char auxv[4096];
+
+void *get_auxv_entry(int type)
+{
+        ElfW(auxv_t) *p;
+        void *result;
+        ssize_t num;
+        int fd;
+
+        fd = open("/proc/self/auxv", O_RDONLY);
+        if (fd == -1) {
+                perror("open");
+                return NULL;
+        }
+
+        result = NULL;
+
+        num = read(fd, auxv, sizeof(auxv));
+        if (num < 0) {
+                perror("read");
+                goto out;
+        }
+
+        if (num > sizeof(auxv)) {
+                printf("Overflowed auxv buffer\n");
+                goto out;
+        }
+
+        p = (ElfW(auxv_t) *)auxv;
+
+        while (p->a_type != AT_NULL) {
+                if (p->a_type == type) {
+                        result = (void *)p->a_un.a_val;
+                        break;
+                }
+
+                p++;
+        }
+out:
+        close(fd);
+        return result;
+}
diff --git a/tools/testing/selftests/powerpc/pmu/lib.h b/tools/testing/selftests/powerpc/pmu/lib.h
index ca5d72ae3be6..0f0339c8a6f6 100644
--- a/tools/testing/selftests/powerpc/pmu/lib.h
+++ b/tools/testing/selftests/powerpc/pmu/lib.h
@@ -29,6 +29,7 @@ extern int notify_parent(union pipe write_pipe);
 extern int notify_parent_of_error(union pipe write_pipe);
 extern pid_t eat_cpu(int (test_function)(void));
 extern bool require_paranoia_below(int level);
+extern void *get_auxv_entry(int type);
 
 struct addr_range {
         uint64_t first, last;
diff --git a/tools/testing/selftests/powerpc/pmu/per_event_excludes.c b/tools/testing/selftests/powerpc/pmu/per_event_excludes.c
new file mode 100644
index 000000000000..fddbbc9cae2f
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/per_event_excludes.c
@@ -0,0 +1,114 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#define _GNU_SOURCE
+
+#include <elf.h>
+#include <limits.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <string.h>
+#include <sys/prctl.h>
+
+#include "event.h"
+#include "lib.h"
+#include "utils.h"
+
+/*
+ * Test that per-event excludes work.
+ */
+
+static int per_event_excludes(void)
+{
+        struct event *e, events[4];
+        char *platform;
+        int i;
+
+        platform = (char *)get_auxv_entry(AT_BASE_PLATFORM);
+        FAIL_IF(!platform);
+        SKIP_IF(strcmp(platform, "power8") != 0);
+
+        /*
+         * We need to create the events disabled, otherwise the running/enabled
+         * counts don't match up.
+         */
+        e = &events[0];
+        event_init_opts(e, PERF_COUNT_HW_INSTRUCTIONS,
+                        PERF_TYPE_HARDWARE, "instructions");
+        e->attr.disabled = 1;
+
+        e = &events[1];
+        event_init_opts(e, PERF_COUNT_HW_INSTRUCTIONS,
+                        PERF_TYPE_HARDWARE, "instructions(k)");
+        e->attr.disabled = 1;
+        e->attr.exclude_user = 1;
+        e->attr.exclude_hv = 1;
+
+        e = &events[2];
+        event_init_opts(e, PERF_COUNT_HW_INSTRUCTIONS,
+                        PERF_TYPE_HARDWARE, "instructions(h)");
+        e->attr.disabled = 1;
+        e->attr.exclude_user = 1;
+        e->attr.exclude_kernel = 1;
+
+        e = &events[3];
+        event_init_opts(e, PERF_COUNT_HW_INSTRUCTIONS,
+                        PERF_TYPE_HARDWARE, "instructions(u)");
+        e->attr.disabled = 1;
+        e->attr.exclude_hv = 1;
+        e->attr.exclude_kernel = 1;
+
+        FAIL_IF(event_open(&events[0]));
+
+        /*
+         * The open here will fail if we don't have per event exclude support,
+         * because the second event has an incompatible set of exclude settings
+         * and we're asking for the events to be in a group.
+         */
+        for (i = 1; i < 4; i++)
+                FAIL_IF(event_open_with_group(&events[i], events[0].fd));
+
+        /*
+         * Even though the above will fail without per-event excludes we keep
+         * testing in order to be thorough.
+         */
+        prctl(PR_TASK_PERF_EVENTS_ENABLE);
+
+        /* Spin for a while */
+        for (i = 0; i < INT_MAX; i++)
+                asm volatile("" : : : "memory");
+
+        prctl(PR_TASK_PERF_EVENTS_DISABLE);
+
+        for (i = 0; i < 4; i++) {
+                FAIL_IF(event_read(&events[i]));
+                event_report(&events[i]);
+        }
+
+        /*
+         * We should see that all events have enabled == running. That
+         * shows that they were all on the PMU at once.
+         */
+        for (i = 0; i < 4; i++)
+                FAIL_IF(events[i].result.running != events[i].result.enabled);
+
+        /*
+         * We can also check that the result for instructions is >= all the
+         * other counts. That's because it is counting all instructions while
+         * the others are counting a subset.
+         */
+        for (i = 1; i < 4; i++)
+                FAIL_IF(events[0].result.value < events[i].result.value);
+
+        for (i = 0; i < 4; i++)
+                event_close(&events[i]);
+
+        return 0;
+}
+
+int main(void)
+{
+        return test_harness(per_event_excludes, "per_event_excludes");
+}
diff --git a/tools/testing/selftests/powerpc/primitives/Makefile b/tools/testing/selftests/powerpc/primitives/Makefile
new file mode 100644
index 000000000000..ea737ca01732
--- /dev/null
+++ b/tools/testing/selftests/powerpc/primitives/Makefile
@@ -0,0 +1,17 @@
+CFLAGS += -I$(CURDIR)
+
+PROGS := load_unaligned_zeropad
+
+all: $(PROGS)
+
+$(PROGS): ../harness.c
+
+run_tests: all
+        @-for PROG in $(PROGS); do \
+                ./$$PROG; \
+        done;
+
+clean:
+        rm -f $(PROGS) *.o
+
+.PHONY: all run_tests clean
diff --git a/tools/testing/selftests/powerpc/primitives/asm/asm-compat.h b/tools/testing/selftests/powerpc/primitives/asm/asm-compat.h
new file mode 120000
index 000000000000..b14255e15a25
--- /dev/null
+++ b/tools/testing/selftests/powerpc/primitives/asm/asm-compat.h
@@ -0,0 +1 @@
+../.././../../../../arch/powerpc/include/asm/asm-compat.h
\ No newline at end of file
diff --git a/tools/testing/selftests/powerpc/primitives/asm/ppc-opcode.h b/tools/testing/selftests/powerpc/primitives/asm/ppc-opcode.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/testing/selftests/powerpc/primitives/asm/ppc-opcode.h
diff --git a/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c
new file mode 100644
index 000000000000..d1b647509596
--- /dev/null
+++ b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c
@@ -0,0 +1,147 @@
+/*
+ * Userspace test harness for load_unaligned_zeropad. Creates two
+ * pages and uses mprotect to prevent access to the second page and
+ * a SEGV handler that walks the exception tables and runs the fixup
+ * routine.
+ *
+ * The results are compared against a normal load that is that is
+ * performed while access to the second page is enabled via mprotect.
+ *
+ * Copyright (C) 2014 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <signal.h>
+#include <unistd.h>
+#include <sys/mman.h>
+
+#define FIXUP_SECTION ".ex_fixup"
+
+#include "word-at-a-time.h"
+
+#include "utils.h"
+
+
+static int page_size;
+static char *mem_region;
+
+static int protect_region(void)
+{
+        if (mprotect(mem_region + page_size, page_size, PROT_NONE)) {
+                perror("mprotect");
+                return 1;
+        }
+
+        return 0;
+}
+
+static int unprotect_region(void)
+{
+        if (mprotect(mem_region + page_size, page_size, PROT_READ|PROT_WRITE)) {
+                perror("mprotect");
+                return 1;
+        }
+
+        return 0;
+}
+
+extern char __start___ex_table[];
+extern char __stop___ex_table[];
+
+#if defined(__powerpc64__)
+#define UCONTEXT_NIA(UC)        (UC)->uc_mcontext.gp_regs[PT_NIP]
+#elif defined(__powerpc__)
+#define UCONTEXT_NIA(UC)        (UC)->uc_mcontext.uc_regs->gregs[PT_NIP]
+#else
+#error implement UCONTEXT_NIA
+#endif
+
+static int segv_error;
+
+static void segv_handler(int signr, siginfo_t *info, void *ptr)
+{
+        ucontext_t *uc = (ucontext_t *)ptr;
+        unsigned long addr = (unsigned long)info->si_addr;
+        unsigned long *ip = &UCONTEXT_NIA(uc);
+        unsigned long *ex_p = (unsigned long *)__start___ex_table;
+
+        while (ex_p < (unsigned long *)__stop___ex_table) {
+                unsigned long insn, fixup;
+
+                insn = *ex_p++;
+                fixup = *ex_p++;
+
+                if (insn == *ip) {
+                        *ip = fixup;
+                        return;
+                }
+        }
+
+        printf("No exception table match for NIA %lx ADDR %lx\n", *ip, addr);
+        segv_error++;
+}
+
+static void setup_segv_handler(void)
+{
+        struct sigaction action;
+
+        memset(&action, 0, sizeof(action));
+        action.sa_sigaction = segv_handler;
+        action.sa_flags = SA_SIGINFO;
+        sigaction(SIGSEGV, &action, NULL);
+}
+
+static int do_one_test(char *p, int page_offset)
+{
+        unsigned long should;
+        unsigned long got;
+
+        FAIL_IF(unprotect_region());
+        should = *(unsigned long *)p;
+        FAIL_IF(protect_region());
+
+        got = load_unaligned_zeropad(p);
+
+        if (should != got)
+                printf("offset %u load_unaligned_zeropad returned 0x%lx, should be 0x%lx\n", page_offset, got, should);
+
+        return 0;
+}
+
+static int test_body(void)
+{
+        unsigned long i;
+
+        page_size = getpagesize();
+        mem_region = mmap(NULL, page_size * 2, PROT_READ|PROT_WRITE,
+                MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);
+
+        FAIL_IF(mem_region == MAP_FAILED);
+
+        for (i = 0; i < page_size; i++)
+                mem_region[i] = i;
+
+        memset(mem_region+page_size, 0, page_size);
+
+        setup_segv_handler();
+
+        for (i = 0; i < page_size; i++)
+                FAIL_IF(do_one_test(mem_region+i, i));
+
+        FAIL_IF(segv_error);
+
+        return 0;
+}
+
+int main(void)
+{
+        return test_harness(test_body, "load_unaligned_zeropad");
+}
diff --git a/tools/testing/selftests/powerpc/primitives/word-at-a-time.h b/tools/testing/selftests/powerpc/primitives/word-at-a-time.h
new file mode 120000
index 000000000000..eb74401b591f
--- /dev/null
+++ b/tools/testing/selftests/powerpc/primitives/word-at-a-time.h
@@ -0,0 +1 @@
+../../../../../arch/powerpc/include/asm/word-at-a-time.h
\ No newline at end of file
diff --git a/tools/testing/selftests/ptrace/peeksiginfo.c b/tools/testing/selftests/ptrace/peeksiginfo.c
index d46558b1f58d..c34cd8ac8aaa 100644
--- a/tools/testing/selftests/ptrace/peeksiginfo.c
+++ b/tools/testing/selftests/ptrace/peeksiginfo.c
@@ -31,6 +31,10 @@ static int sys_ptrace(int request, pid_t pid, void *addr, void *data)
 #define TEST_SICODE_PRIV        -1
 #define TEST_SICODE_SHARE       -2
 
+#ifndef PAGE_SIZE
+#define PAGE_SIZE sysconf(_SC_PAGESIZE)
+#endif
+
 #define err(fmt, ...)                                           \
                 fprintf(stderr,                                 \
                         "Error (%s:%d): " fmt,                  \
diff --git a/tools/testing/selftests/rcutorture/bin/config2frag.sh b/tools/testing/selftests/rcutorture/bin/config2frag.sh
index 9f9ffcd427d3..56f51ae13d73 100644..100755
--- a/tools/testing/selftests/rcutorture/bin/config2frag.sh
+++ b/tools/testing/selftests/rcutorture/bin/config2frag.sh
@@ -1,5 +1,5 @@
-#!/bin/sh
-# Usage: sh config2frag.sh < .config > configfrag
+#!/bin/bash
+# Usage: config2frag.sh < .config > configfrag
 #
 # Converts the "# CONFIG_XXX is not set" to "CONFIG_XXX=n" so that the
 # resulting file becomes a legitimate Kconfig fragment.
diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh
index d686537dd55c..eee31e261bf7 100755
--- a/tools/testing/selftests/rcutorture/bin/configcheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh
@@ -1,5 +1,5 @@
-#!/bin/sh
-# Usage: sh configcheck.sh .config .config-template
+#!/bin/bash
+# Usage: configcheck.sh .config .config-template
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index 9c3f3d39b934..15f1a17ca96e 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -1,6 +1,6 @@
-#!/bin/sh
+#!/bin/bash
 #
-# sh configinit.sh config-spec-file [ build output dir ]
+# Usage: configinit.sh config-spec-file [ build output dir ]
 #
 # Create a .config file from the spec file.  Run from the kernel source tree.
 # Exits with 0 if all went well, with 1 if all went well but the config
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index d01b865bb100..b325470c01b3 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -64,6 +64,26 @@ configfrag_boot_params () {
         fi
 }
 
+# configfrag_boot_cpus bootparam-string config-fragment-file config-cpus
+#
+# Decreases number of CPUs based on any maxcpus= boot parameters specified.
+configfrag_boot_cpus () {
+        local bootargs="`configfrag_boot_params "$1" "$2"`"
+        local maxcpus
+        if echo "${bootargs}" | grep -q 'maxcpus=[0-9]'
+        then
+                maxcpus="`echo "${bootargs}" | sed -e 's/^.*maxcpus=\([0-9]*\).*$/\1/'`"
+                if test "$3" -gt "$maxcpus"
+                then
+                        echo $maxcpus
+                else
+                        echo $3
+                fi
+        else
+                echo $3
+        fi
+}
+
 # configfrag_hotplug_cpu config-fragment-file
 #
 # Returns 1 if the config fragment specifies hotplug CPU.
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index 7c1e56b46de4..00cb0db2643d 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -2,7 +2,7 @@
 #
 # Build a kvm-ready Linux kernel from the tree in the current directory.
 #
-# Usage: sh kvm-build.sh config-template build-dir more-configs
+# Usage: kvm-build.sh config-template build-dir more-configs
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
index 7f1ff1a8fc4b..43f764098e50 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
@@ -2,7 +2,7 @@
 #
 # Analyze a given results directory for locktorture progress.
 #
-# Usage: sh kvm-recheck-lock.sh resdir
+# Usage: kvm-recheck-lock.sh resdir
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index 307c4b95f325..d6cc07fc137f 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -2,7 +2,7 @@
 #
 # Analyze a given results directory for rcutorture progress.
 #
-# Usage: sh kvm-recheck-rcu.sh resdir
+# Usage: kvm-recheck-rcu.sh resdir
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index 3f6c9b78d177..4f5b20f367a9 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -4,7 +4,7 @@
 # check the build and console output for errors.  Given a directory
 # containing results directories, this recursively checks them all.
 #
-# Usage: sh kvm-recheck.sh resdir ...
+# Usage: kvm-recheck.sh resdir ...
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 0f69dcbf9def..f6b2b4771b78 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -6,7 +6,7 @@
 # Execute this in the source tree.  Do not run it as a background task
 # because qemu does not seem to like that much.
 #
-# Usage: sh kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args
+# Usage: kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args
 #
 # qemu-args defaults to "-nographic", along with arguments specifying the
 #                       number of CPUs and other options generated from
@@ -140,6 +140,7 @@ fi
 # Generate -smp qemu argument.
 qemu_args="-nographic $qemu_args"
 cpu_count=`configNR_CPUS.sh $config_template`
+cpu_count=`configfrag_boot_cpus "$boot_args" "$config_template" "$cpu_count"`
 vcpus=`identify_qemu_vcpus`
 if test $cpu_count -gt $vcpus
 then
@@ -214,7 +215,7 @@ then
                 fi
                 if test $kruntime -ge $((seconds + grace))
                 then
-                        echo "!!! Hang at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1
+                        echo "!!! PID $qemu_pid hung at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1
                         kill -KILL $qemu_pid
                         break
                 fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 589e9c38413b..e527dc952eb0 100644..100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -7,7 +7,7 @@
 # Edit the definitions below to set the locations of the various directories,
 # as well as the test duration.
 #
-# Usage: sh kvm.sh [ options ]
+# Usage: kvm.sh [ options ]
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -188,7 +188,9 @@ for CF in $configs
 do
         if test -f "$CONFIGFRAG/$kversion/$CF"
         then
-                echo $CF `configNR_CPUS.sh $CONFIGFRAG/$kversion/$CF` >> $T/cfgcpu
+                cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$kversion/$CF`
+                cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$kversion/$CF" "$cpu_count"`
+                echo $CF $cpu_count >> $T/cfgcpu
         else
                 echo "The --configs file $CF does not exist, terminating."
                 exit 1
diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh
index 543230951c38..499d1e598e42 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 #
 # Check the build output from an rcutorture run for goodness.
 # The "file" is a pathname on the local system, and "title" is
@@ -6,8 +6,7 @@
 #
 # The file must contain kernel build output.
 #
-# Usage:
-#       sh parse-build.sh file title
+# Usage: parse-build.sh file title
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 4185d4cab32e..f962ba4cf68b 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -1,11 +1,10 @@
-#!/bin/sh
+#!/bin/bash
 #
 # Check the console output from an rcutorture run for oopses.
 # The "file" is a pathname on the local system, and "title" is
 # a text string for error-message purposes.
 #
-# Usage:
-#       sh parse-console.sh file title
+# Usage: parse-console.sh file title
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -33,6 +32,10 @@ title="$2"
 
 . functions.sh
 
+if grep -Pq '\x00' < $file
+then
+        print_warning Console output contains nul bytes, old qemu still running?
+fi
 egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T
 if test -s $T
 then
diff --git a/tools/testing/selftests/rcutorture/bin/parse-torture.sh b/tools/testing/selftests/rcutorture/bin/parse-torture.sh
index 3455560ab4e4..e3c5f0705696 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-torture.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-torture.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 #
 # Check the console output from a torture run for goodness.
 # The "file" is a pathname on the local system, and "title" is
@@ -7,8 +7,7 @@
 # The file must contain torture output, but can be interspersed
 # with other dmesg text, as in console-log output.
 #
-# Usage:
-#       sh parse-torture.sh file title
+# Usage: parse-torture.sh file title
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFLIST b/tools/testing/selftests/rcutorture/configs/lock/CFLIST
index a061b22d1892..6910b7370761 100644
--- a/tools/testing/selftests/rcutorture/configs/lock/CFLIST
+++ b/tools/testing/selftests/rcutorture/configs/lock/CFLIST
@@ -1 +1,4 @@
 LOCK01
+LOCK02
+LOCK03
+LOCK04
\ No newline at end of file
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK02 b/tools/testing/selftests/rcutorture/configs/lock/LOCK02
new file mode 100644
index 000000000000..1d1da1477fc3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK02
@@ -0,0 +1,6 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK02.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK02.boot
new file mode 100644
index 000000000000..5aa44b4f1b51
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK02.boot
@@ -0,0 +1 @@
+locktorture.torture_type=mutex_lock
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK03 b/tools/testing/selftests/rcutorture/configs/lock/LOCK03
new file mode 100644
index 000000000000..1d1da1477fc3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK03
@@ -0,0 +1,6 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK03.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK03.boot
new file mode 100644
index 000000000000..a67bbe0245c9
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK03.boot
@@ -0,0 +1 @@
+locktorture.torture_type=rwsem_lock
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK04 b/tools/testing/selftests/rcutorture/configs/lock/LOCK04
new file mode 100644
index 000000000000..1d1da1477fc3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK04
@@ -0,0 +1,6 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK04.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK04.boot
new file mode 100644
index 000000000000..48c04fe47fb4
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK04.boot
@@ -0,0 +1 @@
+locktorture.torture_type=rw_lock
diff --git a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh
index 9746ea1cd6c7..252aae618984 100644
--- a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh
@@ -38,6 +38,6 @@ per_version_boot_params () {
         echo $1 `locktorture_param_onoff "$1" "$2"` \
                 locktorture.stat_interval=15 \
                 locktorture.shutdown_secs=$3 \
-                locktorture.locktorture_runnable=1 \
+                locktorture.torture_runnable=1 \
                 locktorture.verbose=1
 }
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
index cd3d29cb0a47..a3a1a05a2b5c 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
+++ b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
@@ -11,3 +11,6 @@ SRCU-N
 SRCU-P
 TINY01
 TINY02
+TASKS01
+TASKS02
+TASKS03
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01
new file mode 100644
index 000000000000..97f0a0b27ef7
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01
@@ -0,0 +1,9 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=2
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_RCU=y
+CONFIG_TASKS_RCU=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot
new file mode 100644
index 000000000000..cd2a188eeb6d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=tasks
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
new file mode 100644
index 000000000000..696d2ea74d13
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
@@ -0,0 +1,5 @@
+CONFIG_SMP=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_TASKS_RCU=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot
new file mode 100644
index 000000000000..cd2a188eeb6d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=tasks
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
new file mode 100644
index 000000000000..9c60da5b5d1d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
@@ -0,0 +1,13 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=2
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_TASKS_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=n
+CONFIG_NO_HZ_FULL=y
+CONFIG_NO_HZ_FULL_ALL=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot
new file mode 100644
index 000000000000..cd2a188eeb6d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=tasks
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
index 063b7079c621..38e3895759dd 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
@@ -1,5 +1,4 @@
 CONFIG_SMP=y
-CONFIG_NR_CPUS=8
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
@@ -10,8 +9,7 @@ CONFIG_NO_HZ_FULL=n
 CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_RCU_TRACE=y
 CONFIG_HOTPLUG_CPU=y
-CONFIG_RCU_FANOUT=8
-CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_MAXSMP=y
 CONFIG_RCU_NOCB_CPU=y
 CONFIG_RCU_NOCB_CPU_ZERO=y
 CONFIG_DEBUG_LOCK_ALLOC=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
index 0fc8a3428938..adc3abc82fb8 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
@@ -1 +1 @@
-rcutorture.torture_type=rcu_bh
+rcutorture.torture_type=rcu_bh maxcpus=8
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
index ab6225506909..8f1017666aa7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
@@ -1,5 +1,6 @@
 CONFIG_SMP=y
 CONFIG_NR_CPUS=16
+CONFIG_CPUMASK_OFFSTACK=y
 CONFIG_PREEMPT_NONE=y
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
@@ -7,7 +8,7 @@ CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=y
-CONFIG_NO_HZ_FULL_ALL=y
+CONFIG_NO_HZ_FULL_ALL=n
 CONFIG_NO_HZ_FULL_SYSIDLE=y
 CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_TRACE=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot
new file mode 100644
index 000000000000..d44609937503
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot
@@ -0,0 +1 @@
+nohz_full=2-9
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
index 8977d8d31b19..ffb85ed786fa 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
@@ -51,7 +51,7 @@ per_version_boot_params () {
                 `rcutorture_param_n_barrier_cbs "$1"` \
                 rcutorture.stat_interval=15 \
                 rcutorture.shutdown_secs=$3 \
-                rcutorture.rcutorture_runnable=1 \
+                rcutorture.torture_runnable=1 \
                 rcutorture.test_no_idle_hz=1 \
                 rcutorture.verbose=1
 }
diff --git a/tools/testing/selftests/rcutorture/doc/initrd.txt b/tools/testing/selftests/rcutorture/doc/initrd.txt
index 49d134c25c04..4170e714f044 100644
--- a/tools/testing/selftests/rcutorture/doc/initrd.txt
+++ b/tools/testing/selftests/rcutorture/doc/initrd.txt
@@ -6,6 +6,7 @@ this case.  There are probably much better ways of doing this.
 That said, here are the commands:
 
 ------------------------------------------------------------------------
+cd tools/testing/selftests/rcutorture
 zcat /initrd.img > /tmp/initrd.img.zcat
 mkdir initrd
 cd initrd
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 3f94e1afd6cf..4c4b1f631ecf 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -3,6 +3,7 @@
 CC = $(CROSS_COMPILE)gcc
 CFLAGS = -Wall
 BINARIES = hugepage-mmap hugepage-shm map_hugetlb thuge-gen hugetlbfstest
+BINARIES += transhuge-stress
 
 all: $(BINARIES)
 %: %.c
diff --git a/tools/testing/selftests/vm/transhuge-stress.c b/tools/testing/selftests/vm/transhuge-stress.c
new file mode 100644
index 000000000000..fd7f1b4a96f9
--- /dev/null
+++ b/tools/testing/selftests/vm/transhuge-stress.c
@@ -0,0 +1,144 @@
+/*
+ * Stress test for transparent huge pages, memory compaction and migration.
+ *
+ * Authors: Konstantin Khlebnikov <koct9i@gmail.com>
+ *
+ * This is free and unencumbered software released into the public domain.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <err.h>
+#include <time.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <string.h>
+#include <sys/mman.h>
+
+#define PAGE_SHIFT 12
+#define HPAGE_SHIFT 21
+
+#define PAGE_SIZE (1 << PAGE_SHIFT)
+#define HPAGE_SIZE (1 << HPAGE_SHIFT)
+
+#define PAGEMAP_PRESENT(ent)    (((ent) & (1ull << 63)) != 0)
+#define PAGEMAP_PFN(ent)        ((ent) & ((1ull << 55) - 1))
+
+int pagemap_fd;
+
+int64_t allocate_transhuge(void *ptr)
+{
+        uint64_t ent[2];
+
+        /* drop pmd */
+        if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE,
+                                MAP_FIXED | MAP_ANONYMOUS |
+                                MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr)
+                errx(2, "mmap transhuge");
+
+        if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE))
+                err(2, "MADV_HUGEPAGE");
+
+        /* allocate transparent huge page */
+        *(volatile void **)ptr = ptr;
+
+        if (pread(pagemap_fd, ent, sizeof(ent),
+                        (uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent))
+                err(2, "read pagemap");
+
+        if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) &&
+            PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) &&
+            !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1)))
+                return PAGEMAP_PFN(ent[0]);
+
+        return -1;
+}
+
+int main(int argc, char **argv)
+{
+        size_t ram, len;
+        void *ptr, *p;
+        struct timespec a, b;
+        double s;
+        uint8_t *map;
+        size_t map_len;
+
+        ram = sysconf(_SC_PHYS_PAGES);
+        if (ram > SIZE_MAX / sysconf(_SC_PAGESIZE) / 4)
+                ram = SIZE_MAX / 4;
+        else
+                ram *= sysconf(_SC_PAGESIZE);
+
+        if (argc == 1)
+                len = ram;
+        else if (!strcmp(argv[1], "-h"))
+                errx(1, "usage: %s [size in MiB]", argv[0]);
+        else
+                len = atoll(argv[1]) << 20;
+
+        warnx("allocate %zd transhuge pages, using %zd MiB virtual memory"
+              " and %zd MiB of ram", len >> HPAGE_SHIFT, len >> 20,
+              len >> (20 + HPAGE_SHIFT - PAGE_SHIFT - 1));
+
+        pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+        if (pagemap_fd < 0)
+                err(2, "open pagemap");
+
+        len -= len % HPAGE_SIZE;
+        ptr = mmap(NULL, len + HPAGE_SIZE, PROT_READ | PROT_WRITE,
+                        MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE, -1, 0);
+        if (ptr == MAP_FAILED)
+                err(2, "initial mmap");
+        ptr += HPAGE_SIZE - (uintptr_t)ptr % HPAGE_SIZE;
+
+        if (madvise(ptr, len, MADV_HUGEPAGE))
+                err(2, "MADV_HUGEPAGE");
+
+        map_len = ram >> (HPAGE_SHIFT - 1);
+        map = malloc(map_len);
+        if (!map)
+                errx(2, "map malloc");
+
+        while (1) {
+                int nr_succeed = 0, nr_failed = 0, nr_pages = 0;
+
+                memset(map, 0, map_len);
+
+                clock_gettime(CLOCK_MONOTONIC, &a);
+                for (p = ptr; p < ptr + len; p += HPAGE_SIZE) {
+                        int64_t pfn;
+
+                        pfn = allocate_transhuge(p);
+
+                        if (pfn < 0) {
+                                nr_failed++;
+                        } else {
+                                size_t idx = pfn >> (HPAGE_SHIFT - PAGE_SHIFT);
+
+                                nr_succeed++;
+                                if (idx >= map_len) {
+                                        map = realloc(map, idx + 1);
+                                        if (!map)
+                                                errx(2, "map realloc");
+                                        memset(map + map_len, 0, idx + 1 - map_len);
+                                        map_len = idx + 1;
+                                }
+                                if (!map[idx])
+                                        nr_pages++;
+                                map[idx] = 1;
+                        }
+
+                        /* split transhuge page, keep last page */
+                        if (madvise(p, HPAGE_SIZE - PAGE_SIZE, MADV_DONTNEED))
+                                err(2, "MADV_DONTNEED");
+                }
+                clock_gettime(CLOCK_MONOTONIC, &b);
+                s = b.tv_sec - a.tv_sec + (b.tv_nsec - a.tv_nsec) / 1000000000.;
+
+                warnx("%.3f s/loop, %.3f ms/page, %10.3f MiB/s\t"
+                      "%4d succeed, %4d failed, %4d different pages",
+                      s, s * 1000 / (len >> HPAGE_SHIFT), len / s / (1 << 20),
+                      nr_succeed, nr_failed, nr_pages);
+        }
+}
diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c
index a87e99f37c52..88d5e71be044 100644
--- a/tools/usb/ffs-test.c
+++ b/tools/usb/ffs-test.c
@@ -1,5 +1,5 @@
 /*
- * ffs-test.c.c -- user mode filesystem api for usb composite function
+ * ffs-test.c -- user mode filesystem api for usb composite function
  *
  * Copyright (C) 2010 Samsung Electronics
  *                    Author: Michal Nazarewicz <mina86@mina86.com>
@@ -29,6 +29,7 @@
 #include <fcntl.h>
 #include <pthread.h>
 #include <stdarg.h>
+#include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -106,7 +107,9 @@ static void _msg(unsigned level, const char *fmt, ...)
 /******************** Descriptors and Strings *******************************/
 
 static const struct {
-        struct usb_functionfs_descs_head header;
+        struct usb_functionfs_descs_head_v2 header;
+        __le32 fs_count;
+        __le32 hs_count;
         struct {
                 struct usb_interface_descriptor intf;
                 struct usb_endpoint_descriptor_no_audio sink;
@@ -114,11 +117,12 @@ static const struct {
         } __attribute__((packed)) fs_descs, hs_descs;
 } __attribute__((packed)) descriptors = {
         .header = {
-                .magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC),
+                .magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC_V2),
+                .flags = cpu_to_le32(FUNCTIONFS_HAS_FS_DESC |
+                                     FUNCTIONFS_HAS_HS_DESC),
                 .length = cpu_to_le32(sizeof descriptors),
-                .fs_count = cpu_to_le32(3),
-                .hs_count = cpu_to_le32(3),
         },
+        .fs_count = cpu_to_le32(3),
         .fs_descs = {
                 .intf = {
                         .bLength = sizeof descriptors.fs_descs.intf,
@@ -142,6 +146,7 @@ static const struct {
                         /* .wMaxPacketSize = autoconfiguration (kernel) */
                 },
         },
+        .hs_count = cpu_to_le32(3),
         .hs_descs = {
                 .intf = {
                         .bLength = sizeof descriptors.fs_descs.intf,
@@ -168,6 +173,89 @@ static const struct {
         },
 };
 
+static size_t descs_to_legacy(void **legacy, const void *descriptors_v2)
+{
+        const unsigned char *descs_end, *descs_start;
+        __u32 length, fs_count = 0, hs_count = 0, count;
+
+        /* Read v2 header */
+        {
+                const struct {
+                        const struct usb_functionfs_descs_head_v2 header;
+                        const __le32 counts[];
+                } __attribute__((packed)) *const in = descriptors_v2;
+                const __le32 *counts = in->counts;
+                __u32 flags;
+
+                if (le32_to_cpu(in->header.magic) !=
+                    FUNCTIONFS_DESCRIPTORS_MAGIC_V2)
+                        return 0;
+                length = le32_to_cpu(in->header.length);
+                if (length <= sizeof in->header)
+                        return 0;
+                length -= sizeof in->header;
+                flags = le32_to_cpu(in->header.flags);
+                if (flags & ~(FUNCTIONFS_HAS_FS_DESC | FUNCTIONFS_HAS_HS_DESC |
+                              FUNCTIONFS_HAS_SS_DESC))
+                        return 0;
+
+#define GET_NEXT_COUNT_IF_FLAG(ret, flg) do {           \
+                        if (!(flags & (flg)))           \
+                                break;                  \
+                        if (length < 4)                 \
+                                return 0;               \
+                        ret = le32_to_cpu(*counts);     \
+                        length -= 4;                    \
+                        ++counts;                       \
+                } while (0)
+
+                GET_NEXT_COUNT_IF_FLAG(fs_count, FUNCTIONFS_HAS_FS_DESC);
+                GET_NEXT_COUNT_IF_FLAG(hs_count, FUNCTIONFS_HAS_HS_DESC);
+                GET_NEXT_COUNT_IF_FLAG(count, FUNCTIONFS_HAS_SS_DESC);
+
+                count = fs_count + hs_count;
+                if (!count)
+                        return 0;
+                descs_start = (const void *)counts;
+
+#undef GET_NEXT_COUNT_IF_FLAG
+        }
+
+        /*
+         * Find the end of FS and HS USB descriptors.  SS descriptors
+         * are ignored since legacy format does not support them.
+         */
+        descs_end = descs_start;
+        do {
+                if (length < *descs_end)
+                        return 0;
+                length -= *descs_end;
+                descs_end += *descs_end;
+        } while (--count);
+
+        /* Allocate legacy descriptors and copy the data. */
+        {
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
+                struct {
+                        struct usb_functionfs_descs_head header;
+                        __u8 descriptors[];
+                } __attribute__((packed)) *out;
+#pragma GCC diagnostic pop
+
+                length = sizeof out->header + (descs_end - descs_start);
+                out = malloc(length);
+                out->header.magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC);
+                out->header.length = cpu_to_le32(length);
+                out->header.fs_count = cpu_to_le32(fs_count);
+                out->header.hs_count = cpu_to_le32(hs_count);
+                memcpy(out->descriptors, descs_start, descs_end - descs_start);
+                *legacy = out;
+        }
+
+        return length;
+}
+
 
 #define STR_INTERFACE_ "Source/Sink"
 
@@ -487,12 +575,29 @@ ep0_consume(struct thread *ignore, const void *buf, size_t nbytes)
         return nbytes;
 }
 
-static void ep0_init(struct thread *t)
+static void ep0_init(struct thread *t, bool legacy_descriptors)
 {
+        void *legacy;
         ssize_t ret;
+        size_t len;
+
+        if (legacy_descriptors) {
+                info("%s: writing descriptors\n", t->filename);
+                goto legacy;
+        }
 
-        info("%s: writing descriptors\n", t->filename);
+        info("%s: writing descriptors (in v2 format)\n", t->filename);
         ret = write(t->fd, &descriptors, sizeof descriptors);
+
+        if (ret < 0 && errno == EINVAL) {
+                warn("%s: new format rejected, trying legacy\n", t->filename);
+legacy:
+                len = descs_to_legacy(&legacy, &descriptors);
+                if (len) {
+                        ret = write(t->fd, legacy, len);
+                        free(legacy);
+                }
+        }
         die_on(ret < 0, "%s: write: descriptors", t->filename);
 
         info("%s: writing strings\n", t->filename);
@@ -503,14 +608,15 @@ static void ep0_init(struct thread *t)
 
 /******************** Main **************************************************/
 
-int main(void)
+int main(int argc, char **argv)
 {
+        bool legacy_descriptors;
         unsigned i;
 
-        /* XXX TODO: Argument parsing missing */
+        legacy_descriptors = argc > 2 && !strcmp(argv[1], "-l");
 
         init_thread(threads);
-        ep0_init(threads);
+        ep0_init(threads, legacy_descriptors);
 
         for (i = 1; i < sizeof threads / sizeof *threads; ++i)
                 init_thread(threads + i);
diff --git a/tools/usb/usbip/.gitignore b/tools/usb/usbip/.gitignore
new file mode 100644
index 000000000000..9aad9e30a8ba
--- /dev/null
+++ b/tools/usb/usbip/.gitignore
@@ -0,0 +1,28 @@
+Makefile
+Makefile.in
+aclocal.m4
+autom4te.cache/
+config.guess
+config.h
+config.h.in
+config.log
+config.status
+config.sub
+configure
+depcomp
+install-sh
+libsrc/Makefile
+libsrc/Makefile.in
+libtool
+ltmain.sh
+missing
+src/Makefile
+src/Makefile.in
+stamp-h1
+libsrc/libusbip.la
+libsrc/libusbip_la-names.lo
+libsrc/libusbip_la-usbip_common.lo
+libsrc/libusbip_la-usbip_host_driver.lo
+libsrc/libusbip_la-vhci_driver.lo
+src/usbip
+src/usbipd
diff --git a/tools/usb/usbip/AUTHORS b/tools/usb/usbip/AUTHORS
new file mode 100644
index 000000000000..a27ea8d03aec
--- /dev/null
+++ b/tools/usb/usbip/AUTHORS
@@ -0,0 +1,3 @@
+Takahiro Hirofuchi
+Robert Leibl
+matt mooney <mfm@muteddisk.com>
diff --git a/tools/usb/usbip/COPYING b/tools/usb/usbip/COPYING
new file mode 100644
index 000000000000..c5611e48a8e1
--- /dev/null
+++ b/tools/usb/usbip/COPYING
@@ -0,0 +1,340 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.
+     51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Library General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+                            NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that 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.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) year  name of author
+    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+  `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+  <signature of Ty Coon>, 1 April 1989
+  Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs.  If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library.  If this is what you want to do, use the GNU Library General
+Public License instead of this License.
diff --git a/tools/usb/usbip/INSTALL b/tools/usb/usbip/INSTALL
new file mode 100644
index 000000000000..d3c5b40a9409
--- /dev/null
+++ b/tools/usb/usbip/INSTALL
@@ -0,0 +1,237 @@
+Installation Instructions
+*************************
+
+Copyright (C) 1994, 1995, 1996, 1999, 2000, 2001, 2002, 2004, 2005,
+2006, 2007 Free Software Foundation, Inc.
+
+This file is free documentation; the Free Software Foundation gives
+unlimited permission to copy, distribute and modify it.
+
+Basic Installation
+==================
+
+Briefly, the shell commands `./configure; make; make install' should
+configure, build, and install this package.  The following
+more-detailed instructions are generic; see the `README' file for
+instructions specific to this package.
+
+   The `configure' shell script attempts to guess correct values for
+various system-dependent variables used during compilation.  It uses
+those values to create a `Makefile' in each directory of the package.
+It may also create one or more `.h' files containing system-dependent
+definitions.  Finally, it creates a shell script `config.status' that
+you can run in the future to recreate the current configuration, and a
+file `config.log' containing compiler output (useful mainly for
+debugging `configure').
+
+   It can also use an optional file (typically called `config.cache'
+and enabled with `--cache-file=config.cache' or simply `-C') that saves
+the results of its tests to speed up reconfiguring.  Caching is
+disabled by default to prevent problems with accidental use of stale
+cache files.
+
+   If you need to do unusual things to compile the package, please try
+to figure out how `configure' could check whether to do them, and mail
+diffs or instructions to the address given in the `README' so they can
+be considered for the next release.  If you are using the cache, and at
+some point `config.cache' contains results you don't want to keep, you
+may remove or edit it.
+
+   The file `configure.ac' (or `configure.in') is used to create
+`configure' by a program called `autoconf'.  You need `configure.ac' if
+you want to change it or regenerate `configure' using a newer version
+of `autoconf'.
+
+The simplest way to compile this package is:
+
+  1. `cd' to the directory containing the package's source code and type
+     `./configure' to configure the package for your system.
+
+     Running `configure' might take a while.  While running, it prints
+     some messages telling which features it is checking for.
+
+  2. Type `make' to compile the package.
+
+  3. Optionally, type `make check' to run any self-tests that come with
+     the package.
+
+  4. Type `make install' to install the programs and any data files and
+     documentation.
+
+  5. You can remove the program binaries and object files from the
+     source code directory by typing `make clean'.  To also remove the
+     files that `configure' created (so you can compile the package for
+     a different kind of computer), type `make distclean'.  There is
+     also a `make maintainer-clean' target, but that is intended mainly
+     for the package's developers.  If you use it, you may have to get
+     all sorts of other programs in order to regenerate files that came
+     with the distribution.
+
+  6. Often, you can also type `make uninstall' to remove the installed
+     files again.
+
+Compilers and Options
+=====================
+
+Some systems require unusual options for compilation or linking that the
+`configure' script does not know about.  Run `./configure --help' for
+details on some of the pertinent environment variables.
+
+   You can give `configure' initial values for configuration parameters
+by setting variables in the command line or in the environment.  Here
+is an example:
+
+     ./configure CC=c99 CFLAGS=-g LIBS=-lposix
+
+   *Note Defining Variables::, for more details.
+
+Compiling For Multiple Architectures
+====================================
+
+You can compile the package for more than one kind of computer at the
+same time, by placing the object files for each architecture in their
+own directory.  To do this, you can use GNU `make'.  `cd' to the
+directory where you want the object files and executables to go and run
+the `configure' script.  `configure' automatically checks for the
+source code in the directory that `configure' is in and in `..'.
+
+   With a non-GNU `make', it is safer to compile the package for one
+architecture at a time in the source code directory.  After you have
+installed the package for one architecture, use `make distclean' before
+reconfiguring for another architecture.
+
+Installation Names
+==================
+
+By default, `make install' installs the package's commands under
+`/usr/local/bin', include files under `/usr/local/include', etc.  You
+can specify an installation prefix other than `/usr/local' by giving
+`configure' the option `--prefix=PREFIX'.
+
+   You can specify separate installation prefixes for
+architecture-specific files and architecture-independent files.  If you
+pass the option `--exec-prefix=PREFIX' to `configure', the package uses
+PREFIX as the prefix for installing programs and libraries.
+Documentation and other data files still use the regular prefix.
+
+   In addition, if you use an unusual directory layout you can give
+options like `--bindir=DIR' to specify different values for particular
+kinds of files.  Run `configure --help' for a list of the directories
+you can set and what kinds of files go in them.
+
+   If the package supports it, you can cause programs to be installed
+with an extra prefix or suffix on their names by giving `configure' the
+option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'.
+
+Optional Features
+=================
+
+Some packages pay attention to `--enable-FEATURE' options to
+`configure', where FEATURE indicates an optional part of the package.
+They may also pay attention to `--with-PACKAGE' options, where PACKAGE
+is something like `gnu-as' or `x' (for the X Window System).  The
+`README' should mention any `--enable-' and `--with-' options that the
+package recognizes.
+
+   For packages that use the X Window System, `configure' can usually
+find the X include and library files automatically, but if it doesn't,
+you can use the `configure' options `--x-includes=DIR' and
+`--x-libraries=DIR' to specify their locations.
+
+Specifying the System Type
+==========================
+
+There may be some features `configure' cannot figure out automatically,
+but needs to determine by the type of machine the package will run on.
+Usually, assuming the package is built to be run on the _same_
+architectures, `configure' can figure that out, but if it prints a
+message saying it cannot guess the machine type, give it the
+`--build=TYPE' option.  TYPE can either be a short name for the system
+type, such as `sun4', or a canonical name which has the form:
+
+     CPU-COMPANY-SYSTEM
+
+where SYSTEM can have one of these forms:
+
+     OS KERNEL-OS
+
+   See the file `config.sub' for the possible values of each field.  If
+`config.sub' isn't included in this package, then this package doesn't
+need to know the machine type.
+
+   If you are _building_ compiler tools for cross-compiling, you should
+use the option `--target=TYPE' to select the type of system they will
+produce code for.
+
+   If you want to _use_ a cross compiler, that generates code for a
+platform different from the build platform, you should specify the
+"host" platform (i.e., that on which the generated programs will
+eventually be run) with `--host=TYPE'.
+
+Sharing Defaults
+================
+
+If you want to set default values for `configure' scripts to share, you
+can create a site shell script called `config.site' that gives default
+values for variables like `CC', `cache_file', and `prefix'.
+`configure' looks for `PREFIX/share/config.site' if it exists, then
+`PREFIX/etc/config.site' if it exists.  Or, you can set the
+`CONFIG_SITE' environment variable to the location of the site script.
+A warning: not all `configure' scripts look for a site script.
+
+Defining Variables
+==================
+
+Variables not defined in a site shell script can be set in the
+environment passed to `configure'.  However, some packages may run
+configure again during the build, and the customized values of these
+variables may be lost.  In order to avoid this problem, you should set
+them in the `configure' command line, using `VAR=value'.  For example:
+
+     ./configure CC=/usr/local2/bin/gcc
+
+causes the specified `gcc' to be used as the C compiler (unless it is
+overridden in the site shell script).
+
+Unfortunately, this technique does not work for `CONFIG_SHELL' due to
+an Autoconf bug.  Until the bug is fixed you can use this workaround:
+
+     CONFIG_SHELL=/bin/bash /bin/bash ./configure CONFIG_SHELL=/bin/bash
+
+`configure' Invocation
+======================
+
+`configure' recognizes the following options to control how it operates.
+
+`--help'
+`-h'
+     Print a summary of the options to `configure', and exit.
+
+`--version'
+`-V'
+     Print the version of Autoconf used to generate the `configure'
+     script, and exit.
+
+`--cache-file=FILE'
+     Enable the cache: use and save the results of the tests in FILE,
+     traditionally `config.cache'.  FILE defaults to `/dev/null' to
+     disable caching.
+
+`--config-cache'
+`-C'
+     Alias for `--cache-file=config.cache'.
+
+`--quiet'
+`--silent'
+`-q'
+     Do not print messages saying which checks are being made.  To
+     suppress all normal output, redirect it to `/dev/null' (any error
+     messages will still be shown).
+
+`--srcdir=DIR'
+     Look for the package's source code in directory DIR.  Usually
+     `configure' can determine that directory automatically.
+
+`configure' also accepts some other, not widely useful, options.  Run
+`configure --help' for more details.
+
diff --git a/tools/usb/usbip/Makefile.am b/tools/usb/usbip/Makefile.am
new file mode 100644
index 000000000000..66f8bf038c9f
--- /dev/null
+++ b/tools/usb/usbip/Makefile.am
@@ -0,0 +1,6 @@
+SUBDIRS := libsrc src
+includedir = @includedir@/usbip
+include_HEADERS := $(addprefix libsrc/, \
+                     usbip_common.h vhci_driver.h usbip_host_driver.h)
+
+dist_man_MANS := $(addprefix doc/, usbip.8 usbipd.8)
diff --git a/tools/usb/usbip/README b/tools/usb/usbip/README
new file mode 100644
index 000000000000..831f49fea3ce
--- /dev/null
+++ b/tools/usb/usbip/README
@@ -0,0 +1,202 @@
+#
+# README for usbip-utils
+#
+# Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
+#               2005-2008 Takahiro Hirofuchi
+
+
+[Requirements]
+    - USB/IP device drivers
+        Found in the staging directory of the Linux kernel.
+
+    - libudev >= 2.0
+        libudev library
+
+    - libwrap0-dev
+        tcp wrapper library
+
+    - gcc >= 4.0
+
+    - libtool, automake >= 1.9, autoconf >= 2.5.0, pkg-config
+
+[Optional]
+    - hwdata
+        Contains USB device identification data.
+
+
+[Install]
+    0. Generate configuration scripts.
+        $ ./autogen.sh
+
+    1. Compile & install the userspace utilities.
+        $ ./configure [--with-tcp-wrappers=no] [--with-usbids-dir=<dir>]
+        $ make install
+
+    2. Compile & install USB/IP drivers.
+
+
+[Usage]
+    server:# (Physically attach your USB device.)
+
+    server:# insmod usbip-core.ko
+    server:# insmod usbip-host.ko
+
+    server:# usbipd -D
+        - Start usbip daemon.
+
+    server:# usbip list -l
+        - List driver assignments for USB devices.
+
+    server:# usbip bind --busid 1-2
+        - Bind usbip-host.ko to the device with busid 1-2.
+        - The USB device 1-2 is now exportable to other hosts!
+        - Use `usbip unbind --busid 1-2' to stop exporting the device.
+
+    client:# insmod usbip-core.ko
+    client:# insmod vhci-hcd.ko
+
+    client:# usbip list --remote <host>
+        - List exported USB devices on the <host>.
+
+    client:# usbip attach --remote <host> --busid 1-2
+        - Connect the remote USB device.
+
+    client:# usbip port
+        - Show virtual port status.
+
+    client:# usbip detach --port <port>
+        - Detach the USB device.
+
+
+[Example]
+---------------------------
+        SERVER SIDE
+---------------------------
+Physically attach your USB devices to this host.
+
+    trois:# insmod path/to/usbip-core.ko
+    trois:# insmod path/to/usbip-host.ko
+    trois:# usbipd -D
+
+In another terminal, let's look up what USB devices are physically
+attached to this host.
+
+    trois:# usbip list -l
+    Local USB devices
+    =================
+     - busid 1-1 (05a9:a511)
+             1-1:1.0 -> ov511
+
+     - busid 3-2 (0711:0902)
+             3-2:1.0 -> none
+
+     - busid 3-3.1 (08bb:2702)
+             3-3.1:1.0 -> snd-usb-audio
+             3-3.1:1.1 -> snd-usb-audio
+
+     - busid 3-3.2 (04bb:0206)
+             3-3.2:1.0 -> usb-storage
+
+     - busid 3-3 (0409:0058)
+             3-3:1.0 -> hub
+
+     - busid 4-1 (046d:08b2)
+             4-1:1.0 -> none
+             4-1:1.1 -> none
+             4-1:1.2 -> none
+
+     - busid 5-2 (058f:9254)
+             5-2:1.0 -> hub
+
+A USB storage device of busid 3-3.2 is now bound to the usb-storage
+driver. To export this device, we first mark the device as
+"exportable"; the device is bound to the usbip-host driver. Please
+remember you can not export a USB hub.
+
+Mark the device of busid 3-3.2 as exportable:
+
+    trois:# usbip --debug bind --busid 3-3.2
+    ...
+    usbip debug: usbip_bind.c:162:[unbind_other] 3-3.2:1.0 -> usb-storage
+    ...
+    bind device on busid 3-3.2: complete
+
+    trois:# usbip list -l
+    Local USB devices
+    =================
+    ...
+
+     - busid 3-3.2 (04bb:0206)
+             3-3.2:1.0 -> usbip-host
+    ...
+
+---------------------------
+        CLIENT SIDE
+---------------------------
+First, let's list available remote devices that are marked as
+exportable on the host.
+
+    deux:# insmod path/to/usbip-core.ko
+    deux:# insmod path/to/vhci-hcd.ko
+
+    deux:# usbip list --remote 10.0.0.3
+    Exportable USB devices
+    ======================
+     - 10.0.0.3
+            1-1: Prolific Technology, Inc. : unknown product (067b:3507)
+               : /sys/devices/pci0000:00/0000:00:1f.2/usb1/1-1
+               : (Defined at Interface level) / unknown subclass / unknown protocol (00/00/00)
+               :  0 - Mass Storage / SCSI / Bulk (Zip) (08/06/50)
+
+        1-2.2.1: Apple Computer, Inc. : unknown product (05ac:0203)
+               : /sys/devices/pci0000:00/0000:00:1f.2/usb1/1-2/1-2.2/1-2.2.1
+               : (Defined at Interface level) / unknown subclass / unknown protocol (00/00/00)
+               :  0 - Human Interface Devices / Boot Interface Subclass / Keyboard (03/01/01)
+
+        1-2.2.3: OmniVision Technologies, Inc. : OV511+ WebCam (05a9:a511)
+               : /sys/devices/pci0000:00/0000:00:1f.2/usb1/1-2/1-2.2/1-2.2.3
+               : (Defined at Interface level) / unknown subclass / unknown protocol (00/00/00)
+               :  0 - Vendor Specific Class / unknown subclass / unknown protocol (ff/00/00)
+
+            3-1: Logitech, Inc. : QuickCam Pro 4000 (046d:08b2)
+               : /sys/devices/pci0000:00/0000:00:1e.0/0000:02:0a.0/usb3/3-1
+               : (Defined at Interface level) / unknown subclass / unknown protocol (00/00/00)
+               :  0 - Data / unknown subclass / unknown protocol (0a/ff/00)
+               :  1 - Audio / Control Device / unknown protocol (01/01/00)
+               :  2 - Audio / Streaming / unknown protocol (01/02/00)
+
+Attach a remote USB device:
+
+    deux:# usbip attach --remote 10.0.0.3 --busid 1-1
+    port 0 attached
+
+Show the devices attached to this client:
+
+    deux:# usbip port
+    Port 00: <Port in Use> at Full Speed(12Mbps)
+           Prolific Technology, Inc. : unknown product (067b:3507)
+           6-1 -> usbip://10.0.0.3:3240/1-1  (remote bus/dev 001/004)
+           6-1:1.0 used by usb-storage
+                          /sys/class/scsi_device/0:0:0:0/device
+                          /sys/class/scsi_host/host0/device
+                          /sys/block/sda/device
+
+Detach the imported device:
+
+    deux:# usbip detach --port 0
+    port 0 detached
+
+
+[Checklist]
+    - See 'Debug Tips' on the project wiki.
+        - http://usbip.wiki.sourceforge.net/how-to-debug-usbip
+    - usbip-host.ko must be bound to the target device.
+        - See /proc/bus/usb/devices and find "Driver=..." lines of the device.
+    - Shutdown firewall.
+        - usbip now uses TCP port 3240.
+    - Disable SELinux.
+    - Check the kernel and daemon messages.
+
+
+[Contact]
+    Mailing List: linux-usb@vger.kernel.org
diff --git a/tools/usb/usbip/autogen.sh b/tools/usb/usbip/autogen.sh
new file mode 100755
index 000000000000..e1112d3fcbf6
--- /dev/null
+++ b/tools/usb/usbip/autogen.sh
@@ -0,0 +1,9 @@
+#!/bin/sh -x
+
+#aclocal
+#autoheader
+#libtoolize --copy --force
+#automake-1.9 -acf
+#autoconf
+
+autoreconf -i -f -v
diff --git a/tools/usb/usbip/cleanup.sh b/tools/usb/usbip/cleanup.sh
new file mode 100755
index 000000000000..955c3ccb729a
--- /dev/null
+++ b/tools/usb/usbip/cleanup.sh
@@ -0,0 +1,12 @@
+#!/bin/sh
+
+if [ -r Makefile ]; then
+        make distclean
+fi
+
+FILES="aclocal.m4 autom4te.cache compile config.guess config.h.in config.log \
+       config.status config.sub configure cscope.out depcomp install-sh      \
+       libsrc/Makefile libsrc/Makefile.in libtool ltmain.sh Makefile         \
+       Makefile.in missing src/Makefile src/Makefile.in"
+
+rm -vRf $FILES
diff --git a/tools/usb/usbip/configure.ac b/tools/usb/usbip/configure.ac
new file mode 100644
index 000000000000..607d05c5ccfd
--- /dev/null
+++ b/tools/usb/usbip/configure.ac
@@ -0,0 +1,111 @@
+dnl Process this file with autoconf to produce a configure script.
+
+AC_PREREQ(2.59)
+AC_INIT([usbip-utils], [2.0], [linux-usb@vger.kernel.org])
+AC_DEFINE([USBIP_VERSION], [0x00000111], [binary-coded decimal version number])
+
+CURRENT=0
+REVISION=1
+AGE=0
+AC_SUBST([LIBUSBIP_VERSION], [$CURRENT:$REVISION:$AGE], [library version])
+
+AC_CONFIG_SRCDIR([src/usbipd.c])
+AC_CONFIG_HEADERS([config.h])
+
+AM_INIT_AUTOMAKE([foreign])
+LT_INIT
+
+# Silent build for automake >= 1.11
+m4_ifdef([AM_SILENT_RULES], [AM_SILENT_RULES([yes])])
+
+AC_SUBST([EXTRA_CFLAGS], ["-Wall -Werror -Wextra -std=gnu99"])
+
+# Checks for programs.
+AC_PROG_CC
+AC_PROG_INSTALL
+AC_PROG_MAKE_SET
+
+# Checks for header files.
+AC_HEADER_DIRENT
+AC_HEADER_STDC
+AC_CHECK_HEADERS([arpa/inet.h fcntl.h netdb.h netinet/in.h stdint.h stdlib.h dnl
+                  string.h sys/socket.h syslog.h unistd.h])
+
+# Checks for typedefs, structures, and compiler characteristics.
+AC_TYPE_INT32_T
+AC_TYPE_SIZE_T
+AC_TYPE_SSIZE_T
+AC_TYPE_UINT16_T
+AC_TYPE_UINT32_T
+AC_TYPE_UINT8_T
+
+# Checks for library functions.
+AC_FUNC_REALLOC
+AC_CHECK_FUNCS([memset mkdir regcomp socket strchr strerror strstr dnl
+                strtoul])
+
+AC_CHECK_HEADER([libudev.h],
+                [AC_CHECK_LIB([udev], [udev_new],
+                              [LIBS="$LIBS -ludev"],
+                              [AC_MSG_ERROR([Missing udev library!])])],
+                [AC_MSG_ERROR([Missing /usr/include/libudev.h])])
+
+# Checks for libwrap library.
+AC_MSG_CHECKING([whether to use the libwrap (TCP wrappers) library])
+AC_ARG_WITH([tcp-wrappers],
+            [AS_HELP_STRING([--with-tcp-wrappers],
+                            [use the libwrap (TCP wrappers) library])],
+            dnl [ACTION-IF-GIVEN]
+            [if test "$withval" = "yes"; then
+                     AC_MSG_RESULT([yes])
+                     AC_MSG_CHECKING([for hosts_access in -lwrap])
+                     saved_LIBS="$LIBS"
+                     LIBS="-lwrap $saved_LIBS"
+                     AC_TRY_LINK(
+                       [int hosts_access(); int allow_severity, deny_severity;],
+                       [hosts_access()],
+                       [AC_MSG_RESULT([yes]);
+                        AC_DEFINE([HAVE_LIBWRAP], [1],
+                                  [use tcp wrapper]) wrap_LIB="-lwrap"],
+                       [AC_MSG_RESULT([not found]); exit 1])
+             else
+                     AC_MSG_RESULT([no]);
+             fi],
+            dnl [ACTION-IF-NOT-GIVEN]
+            [AC_MSG_RESULT([(default)])
+             AC_MSG_CHECKING([for hosts_access in -lwrap])
+             saved_LIBS="$LIBS"
+             LIBS="-lwrap $saved_LIBS"
+             AC_TRY_LINK(
+               [int hosts_access(); int allow_severity, deny_severity;],
+               [hosts_access()],
+               [AC_MSG_RESULT([yes]);
+                AC_DEFINE([HAVE_LIBWRAP], [1], [use tcp wrapper])],
+               [AC_MSG_RESULT([no]); LIBS="$saved_LIBS"])])
+
+# Sets directory containing usb.ids.
+AC_ARG_WITH([usbids-dir],
+            [AS_HELP_STRING([--with-usbids-dir=DIR],
+               [where usb.ids is found (default /usr/share/hwdata/)])],
+            [USBIDS_DIR=$withval], [USBIDS_DIR="/usr/share/hwdata/"])
+AC_SUBST([USBIDS_DIR])
+
+# use _FORTIFY_SOURCE
+AC_MSG_CHECKING([whether to use fortify])
+AC_ARG_WITH([fortify],
+            [AS_HELP_STRING([--with-fortify],
+                            [use _FORTIFY_SROUCE option when compiling)])],
+                            dnl [ACTION-IF-GIVEN]
+                            [if test "$withval" = "yes"; then
+                                AC_MSG_RESULT([yes])
+                                CFLAGS="$CFLAGS -D_FORTIFY_SOURCE -O"
+                             else
+                                AC_MSG_RESULT([no])
+                                CFLAGS="$CFLAGS -U_FORTIFY_SOURCE"
+                             fi
+                            ],
+                            dnl [ACTION-IF-NOT-GIVEN]
+                            [AC_MSG_RESULT([default])])
+
+AC_CONFIG_FILES([Makefile libsrc/Makefile src/Makefile])
+AC_OUTPUT
diff --git a/tools/usb/usbip/doc/usbip.8 b/tools/usb/usbip/doc/usbip.8
new file mode 100644
index 000000000000..a6097be25d28
--- /dev/null
+++ b/tools/usb/usbip/doc/usbip.8
@@ -0,0 +1,95 @@
+.TH USBIP "8" "February 2009" "usbip" "System Administration Utilities"
+.SH NAME
+usbip \- manage USB/IP devices
+.SH SYNOPSIS
+.B usbip
+[\fIoptions\fR] <\fIcommand\fR> <\fIargs\fR>
+
+.SH DESCRIPTION
+On a USB/IP server, devices can be listed, bound, and unbound using
+this program.  On a USB/IP client, devices exported by USB/IP servers
+can be listed, attached and detached.
+
+.SH OPTIONS
+.HP
+\fB\-\-debug\fR
+.IP
+Print debugging information.
+.PP
+
+.HP
+\fB\-\-log\fR
+.IP
+Log to syslog.
+.PP
+
+.HP
+\fB\-\-tcp-port PORT\fR
+.IP
+Connect to PORT on remote host (used for attach and list --remote).
+.PP
+
+.SH COMMANDS
+.HP
+\fBversion\fR
+.IP
+Show version and exit.
+.PP
+
+.HP
+\fBhelp\fR [\fIcommand\fR]
+.IP
+Print the program help message, or help on a specific command, and
+then exit.
+.PP
+
+.HP
+\fBattach\fR \-\-remote=<\fIhost\fR> \-\-busid=<\fIbus_id\fR>
+.IP
+Attach a remote USB device.
+.PP
+
+.HP
+\fBdetach\fR \-\-port=<\fIport\fR>
+.IP
+Detach an imported USB device.
+.PP
+
+.HP
+\fBbind\fR \-\-busid=<\fIbusid\fR>
+.IP
+Make a device exportable.
+.PP
+
+.HP
+\fBunbind\fR \-\-busid=<\fIbusid\fR>
+.IP
+Stop exporting a device so it can be used by a local driver.
+.PP
+
+.HP
+\fBlist\fR \-\-remote=<\fIhost\fR>
+.IP
+List USB devices exported by a remote host.
+.PP
+
+.HP
+\fBlist\fR \-\-local
+.IP
+List local USB devices.
+.PP
+
+
+.SH EXAMPLES
+
+    client:# usbip list --remote=server
+        - List exportable usb devices on the server.
+
+    client:# usbip attach --remote=server --busid=1-2
+        - Connect the remote USB device.
+
+    client:# usbip detach --port=0
+        - Detach the usb device.
+
+.SH "SEE ALSO"
+\fBusbipd\fP\fB(8)\fB\fP
diff --git a/tools/usb/usbip/doc/usbipd.8 b/tools/usb/usbip/doc/usbipd.8
new file mode 100644
index 000000000000..ac4635db3f03
--- /dev/null
+++ b/tools/usb/usbip/doc/usbipd.8
@@ -0,0 +1,91 @@
+.TH USBIP "8" "February 2009" "usbip" "System Administration Utilities"
+.SH NAME
+usbipd \- USB/IP server daemon
+.SH SYNOPSIS
+.B usbipd
+[\fIoptions\fR]
+
+.SH DESCRIPTION
+.B usbipd
+provides USB/IP clients access to exported USB devices.
+
+Devices have to explicitly be exported using
+.B usbip bind
+before usbipd makes them available to other hosts.
+
+The daemon accepts connections from USB/IP clients
+on TCP port 3240 by default.
+
+.SH OPTIONS
+.HP
+\fB\-4\fR, \fB\-\-ipv4\fR
+.IP
+Bind to IPv4. Default is both.
+.PP
+
+.HP
+\fB\-6\fR, \fB\-\-ipv6\fR
+.IP
+Bind to IPv6. Default is both.
+.PP
+
+.HP
+\fB\-D\fR, \fB\-\-daemon\fR
+.IP
+Run as a daemon process.
+.PP
+
+.HP
+\fB\-d\fR, \fB\-\-debug\fR
+.IP
+Print debugging information.
+.PP
+
+.HP
+\fB\-PFILE\fR, \fB\-\-pid FILE\fR
+.IP
+Write process id to FILE.
+.br
+If no FILE specified, use /var/run/usbipd.pid
+.PP
+
+\fB\-tPORT\fR, \fB\-\-tcp\-port PORT\fR
+.IP
+Listen on TCP/IP port PORT.
+.PP
+
+\fB\-h\fR, \fB\-\-help\fR
+.IP
+Print the program help message and exit.
+.PP
+
+.HP
+\fB\-v\fR, \fB\-\-version\fR
+.IP
+Show version.
+.PP
+
+.SH LIMITATIONS
+
+.B usbipd
+offers no authentication or authorization for USB/IP. Any
+USB/IP client can connect and use exported devices.
+
+.SH EXAMPLES
+
+    server:# modprobe usbip
+
+    server:# usbipd -D
+        - Start usbip daemon.
+
+    server:# usbip list --local
+        - List driver assignments for usb devices.
+
+    server:# usbip bind --busid=1-2
+        - Bind usbip-host.ko to the device of busid 1-2.
+        - A usb device 1-2 is now exportable to other hosts!
+        - Use 'usbip unbind --busid=1-2' when you want to shutdown exporting and use the device locally.
+
+.SH "SEE ALSO"
+\fBusbip\fP\fB(8)\fB\fP
+
diff --git a/tools/usb/usbip/libsrc/Makefile.am b/tools/usb/usbip/libsrc/Makefile.am
new file mode 100644
index 000000000000..7c8f8a4d54e4
--- /dev/null
+++ b/tools/usb/usbip/libsrc/Makefile.am
@@ -0,0 +1,8 @@
+libusbip_la_CPPFLAGS = -DUSBIDS_FILE='"@USBIDS_DIR@/usb.ids"'
+libusbip_la_CFLAGS   = @EXTRA_CFLAGS@
+libusbip_la_LDFLAGS  = -version-info @LIBUSBIP_VERSION@
+
+lib_LTLIBRARIES := libusbip.la
+libusbip_la_SOURCES := names.c names.h usbip_host_driver.c usbip_host_driver.h \
+                       usbip_common.c usbip_common.h vhci_driver.c vhci_driver.h \
+                       sysfs_utils.c sysfs_utils.h
diff --git a/tools/usb/usbip/libsrc/list.h b/tools/usb/usbip/libsrc/list.h
new file mode 100644
index 000000000000..8d0c936e184f
--- /dev/null
+++ b/tools/usb/usbip/libsrc/list.h
@@ -0,0 +1,136 @@
+#ifndef _LIST_H
+#define _LIST_H
+
+/* Stripped down implementation of linked list taken
+ * from the Linux Kernel.
+ */
+
+/*
+ * Simple doubly linked list implementation.
+ *
+ * Some of the internal functions ("__xxx") are useful when
+ * manipulating whole lists rather than single entries, as
+ * sometimes we already know the next/prev entries and we can
+ * generate better code by using them directly rather than
+ * using the generic single-entry routines.
+ */
+
+struct list_head {
+        struct list_head *next, *prev;
+};
+
+#define LIST_HEAD_INIT(name) { &(name), &(name) }
+
+#define LIST_HEAD(name) \
+        struct list_head name = LIST_HEAD_INIT(name)
+
+static inline void INIT_LIST_HEAD(struct list_head *list)
+{
+        list->next = list;
+        list->prev = list;
+}
+
+/*
+ * Insert a new entry between two known consecutive entries.
+ *
+ * This is only for internal list manipulation where we know
+ * the prev/next entries already!
+ */
+static inline void __list_add(struct list_head *new,
+                              struct list_head *prev,
+                              struct list_head *next)
+{
+        next->prev = new;
+        new->next = next;
+        new->prev = prev;
+        prev->next = new;
+}
+
+/**
+ * list_add - add a new entry
+ * @new: new entry to be added
+ * @head: list head to add it after
+ *
+ * Insert a new entry after the specified head.
+ * This is good for implementing stacks.
+ */
+static inline void list_add(struct list_head *new, struct list_head *head)
+{
+        __list_add(new, head, head->next);
+}
+
+/*
+ * Delete a list entry by making the prev/next entries
+ * point to each other.
+ *
+ * This is only for internal list manipulation where we know
+ * the prev/next entries already!
+ */
+static inline void __list_del(struct list_head * prev, struct list_head * next)
+{
+        next->prev = prev;
+        prev->next = next;
+}
+
+#define POISON_POINTER_DELTA 0
+#define LIST_POISON1  ((void *) 0x00100100 + POISON_POINTER_DELTA)
+#define LIST_POISON2  ((void *) 0x00200200 + POISON_POINTER_DELTA)
+
+/**
+ * list_del - deletes entry from list.
+ * @entry: the element to delete from the list.
+ * Note: list_empty() on entry does not return true after this, the entry is
+ * in an undefined state.
+ */
+static inline void __list_del_entry(struct list_head *entry)
+{
+        __list_del(entry->prev, entry->next);
+}
+
+static inline void list_del(struct list_head *entry)
+{
+        __list_del(entry->prev, entry->next);
+        entry->next = LIST_POISON1;
+        entry->prev = LIST_POISON2;
+}
+
+/**
+ * list_entry - get the struct for this entry
+ * @ptr:        the &struct list_head pointer.
+ * @type:       the type of the struct this is embedded in.
+ * @member:     the name of the list_struct within the struct.
+ */
+#define list_entry(ptr, type, member) \
+        container_of(ptr, type, member)
+/**
+ * list_for_each        -       iterate over a list
+ * @pos:        the &struct list_head to use as a loop cursor.
+ * @head:       the head for your list.
+ */
+#define list_for_each(pos, head) \
+        for (pos = (head)->next; pos != (head); pos = pos->next)
+
+/**
+ * list_for_each_safe - iterate over a list safe against removal of list entry
+ * @pos:        the &struct list_head to use as a loop cursor.
+ * @n:          another &struct list_head to use as temporary storage
+ * @head:       the head for your list.
+ */
+#define list_for_each_safe(pos, n, head) \
+        for (pos = (head)->next, n = pos->next; pos != (head); \
+                pos = n, n = pos->next)
+
+#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
+
+/**
+ * container_of - cast a member of a structure out to the containing structure
+ * @ptr:        the pointer to the member.
+ * @type:       the type of the container struct this is embedded in.
+ * @member:     the name of the member within the struct.
+ *
+ */
+#define container_of(ptr, type, member) ({                      \
+        const typeof( ((type *)0)->member ) *__mptr = (ptr);    \
+        (type *)( (char *)__mptr - offsetof(type,member) );})
+
+#endif
diff --git a/tools/usb/usbip/libsrc/names.c b/tools/usb/usbip/libsrc/names.c
new file mode 100644
index 000000000000..81ff8522405c
--- /dev/null
+++ b/tools/usb/usbip/libsrc/names.c
@@ -0,0 +1,504 @@
+/*
+ *      names.c  --  USB name database manipulation routines
+ *
+ *      Copyright (C) 1999, 2000  Thomas Sailer (sailer@ife.ee.ethz.ch)
+ *
+ *      This program is free software; you can redistribute it and/or modify
+ *      it under the terms of the GNU General Public License as published by
+ *      the Free Software Foundation; either version 2 of the License, or
+ *      (at your option) any later version.
+ *
+ *      This program is distributed in the hope that 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.
+ *
+ *      You should have received a copy of the GNU General Public License
+ *      along with this program; if not, write to the Free Software
+ *      Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ *
+ *
+ *
+ *
+ *      Copyright (C) 2005 Takahiro Hirofuchi
+ *              - names_deinit() is added.
+ *
+ */
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <dirent.h>
+#include <string.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <ctype.h>
+
+#include "names.h"
+#include "usbip_common.h"
+
+struct vendor {
+        struct vendor *next;
+        u_int16_t vendorid;
+        char name[1];
+};
+
+struct product {
+        struct product *next;
+        u_int16_t vendorid, productid;
+        char name[1];
+};
+
+struct class {
+        struct class *next;
+        u_int8_t classid;
+        char name[1];
+};
+
+struct subclass {
+        struct subclass *next;
+        u_int8_t classid, subclassid;
+        char name[1];
+};
+
+struct protocol {
+        struct protocol *next;
+        u_int8_t classid, subclassid, protocolid;
+        char name[1];
+};
+
+struct genericstrtable {
+        struct genericstrtable *next;
+        unsigned int num;
+        char name[1];
+};
+
+
+#define HASH1  0x10
+#define HASH2  0x02
+#define HASHSZ 16
+
+static unsigned int hashnum(unsigned int num)
+{
+        unsigned int mask1 = HASH1 << 27, mask2 = HASH2 << 27;
+
+        for (; mask1 >= HASH1; mask1 >>= 1, mask2 >>= 1)
+                if (num & mask1)
+                        num ^= mask2;
+        return num & (HASHSZ-1);
+}
+
+
+static struct vendor *vendors[HASHSZ] = { NULL, };
+static struct product *products[HASHSZ] = { NULL, };
+static struct class *classes[HASHSZ] = { NULL, };
+static struct subclass *subclasses[HASHSZ] = { NULL, };
+static struct protocol *protocols[HASHSZ] = { NULL, };
+
+const char *names_vendor(u_int16_t vendorid)
+{
+        struct vendor *v;
+
+        v = vendors[hashnum(vendorid)];
+        for (; v; v = v->next)
+                if (v->vendorid == vendorid)
+                        return v->name;
+        return NULL;
+}
+
+const char *names_product(u_int16_t vendorid, u_int16_t productid)
+{
+        struct product *p;
+
+        p = products[hashnum((vendorid << 16) | productid)];
+        for (; p; p = p->next)
+                if (p->vendorid == vendorid && p->productid == productid)
+                        return p->name;
+        return NULL;
+}
+
+const char *names_class(u_int8_t classid)
+{
+        struct class *c;
+
+        c = classes[hashnum(classid)];
+        for (; c; c = c->next)
+                if (c->classid == classid)
+                        return c->name;
+        return NULL;
+}
+
+const char *names_subclass(u_int8_t classid, u_int8_t subclassid)
+{
+        struct subclass *s;
+
+        s = subclasses[hashnum((classid << 8) | subclassid)];
+        for (; s; s = s->next)
+                if (s->classid == classid && s->subclassid == subclassid)
+                        return s->name;
+        return NULL;
+}
+
+const char *names_protocol(u_int8_t classid, u_int8_t subclassid,
+                           u_int8_t protocolid)
+{
+        struct protocol *p;
+
+        p = protocols[hashnum((classid << 16) | (subclassid << 8)
+                              | protocolid)];
+        for (; p; p = p->next)
+                if (p->classid == classid && p->subclassid == subclassid &&
+                    p->protocolid == protocolid)
+                        return p->name;
+        return NULL;
+}
+
+/* add a cleanup function by takahiro */
+struct pool {
+        struct pool *next;
+        void *mem;
+};
+
+static struct pool *pool_head;
+
+static void *my_malloc(size_t size)
+{
+        struct pool *p;
+
+        p = calloc(1, sizeof(struct pool));
+        if (!p)
+                return NULL;
+
+        p->mem = calloc(1, size);
+        if (!p->mem) {
+                free(p);
+                return NULL;
+        }
+
+        p->next = pool_head;
+        pool_head = p;
+
+        return p->mem;
+}
+
+void names_free(void)
+{
+        struct pool *pool;
+
+        if (!pool_head)
+                return;
+
+        for (pool = pool_head; pool != NULL; ) {
+                struct pool *tmp;
+
+                if (pool->mem)
+                        free(pool->mem);
+
+                tmp = pool;
+                pool = pool->next;
+                free(tmp);
+        }
+}
+
+static int new_vendor(const char *name, u_int16_t vendorid)
+{
+        struct vendor *v;
+        unsigned int h = hashnum(vendorid);
+
+        v = vendors[h];
+        for (; v; v = v->next)
+                if (v->vendorid == vendorid)
+                        return -1;
+        v = my_malloc(sizeof(struct vendor) + strlen(name));
+        if (!v)
+                return -1;
+        strcpy(v->name, name);
+        v->vendorid = vendorid;
+        v->next = vendors[h];
+        vendors[h] = v;
+        return 0;
+}
+
+static int new_product(const char *name, u_int16_t vendorid,
+                       u_int16_t productid)
+{
+        struct product *p;
+        unsigned int h = hashnum((vendorid << 16) | productid);
+
+        p = products[h];
+        for (; p; p = p->next)
+                if (p->vendorid == vendorid && p->productid == productid)
+                        return -1;
+        p = my_malloc(sizeof(struct product) + strlen(name));
+        if (!p)
+                return -1;
+        strcpy(p->name, name);
+        p->vendorid = vendorid;
+        p->productid = productid;
+        p->next = products[h];
+        products[h] = p;
+        return 0;
+}
+
+static int new_class(const char *name, u_int8_t classid)
+{
+        struct class *c;
+        unsigned int h = hashnum(classid);
+
+        c = classes[h];
+        for (; c; c = c->next)
+                if (c->classid == classid)
+                        return -1;
+        c = my_malloc(sizeof(struct class) + strlen(name));
+        if (!c)
+                return -1;
+        strcpy(c->name, name);
+        c->classid = classid;
+        c->next = classes[h];
+        classes[h] = c;
+        return 0;
+}
+
+static int new_subclass(const char *name, u_int8_t classid, u_int8_t subclassid)
+{
+        struct subclass *s;
+        unsigned int h = hashnum((classid << 8) | subclassid);
+
+        s = subclasses[h];
+        for (; s; s = s->next)
+                if (s->classid == classid && s->subclassid == subclassid)
+                        return -1;
+        s = my_malloc(sizeof(struct subclass) + strlen(name));
+        if (!s)
+                return -1;
+        strcpy(s->name, name);
+        s->classid = classid;
+        s->subclassid = subclassid;
+        s->next = subclasses[h];
+        subclasses[h] = s;
+        return 0;
+}
+
+static int new_protocol(const char *name, u_int8_t classid, u_int8_t subclassid,
+                        u_int8_t protocolid)
+{
+        struct protocol *p;
+        unsigned int h = hashnum((classid << 16) | (subclassid << 8)
+                                 | protocolid);
+
+        p = protocols[h];
+        for (; p; p = p->next)
+                if (p->classid == classid && p->subclassid == subclassid
+                    && p->protocolid == protocolid)
+                        return -1;
+        p = my_malloc(sizeof(struct protocol) + strlen(name));
+        if (!p)
+                return -1;
+        strcpy(p->name, name);
+        p->classid = classid;
+        p->subclassid = subclassid;
+        p->protocolid = protocolid;
+        p->next = protocols[h];
+        protocols[h] = p;
+        return 0;
+}
+
+static void parse(FILE *f)
+{
+        char buf[512], *cp;
+        unsigned int linectr = 0;
+        int lastvendor = -1;
+        int lastclass = -1;
+        int lastsubclass = -1;
+        int lasthut = -1;
+        int lastlang = -1;
+        unsigned int u;
+
+        while (fgets(buf, sizeof(buf), f)) {
+                linectr++;
+                /* remove line ends */
+                cp = strchr(buf, '\r');
+                if (cp)
+                        *cp = 0;
+                cp = strchr(buf, '\n');
+                if (cp)
+                        *cp = 0;
+                if (buf[0] == '#' || !buf[0])
+                        continue;
+                cp = buf;
+                if (buf[0] == 'P' && buf[1] == 'H' && buf[2] == 'Y' &&
+                    buf[3] == 'S' && buf[4] == 'D' &&
+                    buf[5] == 'E' && buf[6] == 'S' && /*isspace(buf[7])*/
+                    buf[7] == ' ') {
+                        continue;
+                }
+                if (buf[0] == 'P' && buf[1] == 'H' &&
+                    buf[2] == 'Y' && /*isspace(buf[3])*/ buf[3] == ' ') {
+                        continue;
+                }
+                if (buf[0] == 'B' && buf[1] == 'I' && buf[2] == 'A' &&
+                    buf[3] == 'S' && /*isspace(buf[4])*/ buf[4] == ' ') {
+                        continue;
+                }
+                if (buf[0] == 'L' && /*isspace(buf[1])*/ buf[1] == ' ') {
+                        lasthut = lastclass = lastvendor = lastsubclass = -1;
+                        /*
+                         * set 1 as pseudo-id to indicate that the parser is
+                         * in a `L' section.
+                         */
+                        lastlang = 1;
+                        continue;
+                }
+                if (buf[0] == 'C' && /*isspace(buf[1])*/ buf[1] == ' ') {
+                        /* class spec */
+                        cp = buf+2;
+                        while (isspace(*cp))
+                                cp++;
+                        if (!isxdigit(*cp)) {
+                                err("Invalid class spec at line %u", linectr);
+                                continue;
+                        }
+                        u = strtoul(cp, &cp, 16);
+                        while (isspace(*cp))
+                                cp++;
+                        if (!*cp) {
+                                err("Invalid class spec at line %u", linectr);
+                                continue;
+                        }
+                        if (new_class(cp, u))
+                                err("Duplicate class spec at line %u class %04x %s",
+                                    linectr, u, cp);
+                        dbg("line %5u class %02x %s", linectr, u, cp);
+                        lasthut = lastlang = lastvendor = lastsubclass = -1;
+                        lastclass = u;
+                        continue;
+                }
+                if (buf[0] == 'A' && buf[1] == 'T' && isspace(buf[2])) {
+                        /* audio terminal type spec */
+                        continue;
+                }
+                if (buf[0] == 'H' && buf[1] == 'C' && buf[2] == 'C'
+                    && isspace(buf[3])) {
+                        /* HID Descriptor bCountryCode */
+                        continue;
+                }
+                if (isxdigit(*cp)) {
+                        /* vendor */
+                        u = strtoul(cp, &cp, 16);
+                        while (isspace(*cp))
+                                cp++;
+                        if (!*cp) {
+                                err("Invalid vendor spec at line %u", linectr);
+                                continue;
+                        }
+                        if (new_vendor(cp, u))
+                                err("Duplicate vendor spec at line %u vendor %04x %s",
+                                    linectr, u, cp);
+                        dbg("line %5u vendor %04x %s", linectr, u, cp);
+                        lastvendor = u;
+                        lasthut = lastlang = lastclass = lastsubclass = -1;
+                        continue;
+                }
+                if (buf[0] == '\t' && isxdigit(buf[1])) {
+                        /* product or subclass spec */
+                        u = strtoul(buf+1, &cp, 16);
+                        while (isspace(*cp))
+                                cp++;
+                        if (!*cp) {
+                                err("Invalid product/subclass spec at line %u",
+                                    linectr);
+                                continue;
+                        }
+                        if (lastvendor != -1) {
+                                if (new_product(cp, lastvendor, u))
+                                        err("Duplicate product spec at line %u product %04x:%04x %s",
+                                            linectr, lastvendor, u, cp);
+                                dbg("line %5u product %04x:%04x %s", linectr,
+                                    lastvendor, u, cp);
+                                continue;
+                        }
+                        if (lastclass != -1) {
+                                if (new_subclass(cp, lastclass, u))
+                                        err("Duplicate subclass spec at line %u class %02x:%02x %s",
+                                            linectr, lastclass, u, cp);
+                                dbg("line %5u subclass %02x:%02x %s", linectr,
+                                    lastclass, u, cp);
+                                lastsubclass = u;
+                                continue;
+                        }
+                        if (lasthut != -1) {
+                                /* do not store hut */
+                                continue;
+                        }
+                        if (lastlang != -1) {
+                                /* do not store langid */
+                                continue;
+                        }
+                        err("Product/Subclass spec without prior Vendor/Class spec at line %u",
+                            linectr);
+                        continue;
+                }
+                if (buf[0] == '\t' && buf[1] == '\t' && isxdigit(buf[2])) {
+                        /* protocol spec */
+                        u = strtoul(buf+2, &cp, 16);
+                        while (isspace(*cp))
+                                cp++;
+                        if (!*cp) {
+                                err("Invalid protocol spec at line %u",
+                                    linectr);
+                                continue;
+                        }
+                        if (lastclass != -1 && lastsubclass != -1) {
+                                if (new_protocol(cp, lastclass, lastsubclass,
+                                                 u))
+                                        err("Duplicate protocol spec at line %u class %02x:%02x:%02x %s",
+                                            linectr, lastclass, lastsubclass,
+                                            u, cp);
+                                dbg("line %5u protocol %02x:%02x:%02x %s",
+                                    linectr, lastclass, lastsubclass, u, cp);
+                                continue;
+                        }
+                        err("Protocol spec without prior Class and Subclass spec at line %u",
+                            linectr);
+                        continue;
+                }
+                if (buf[0] == 'H' && buf[1] == 'I' &&
+                    buf[2] == 'D' && /*isspace(buf[3])*/ buf[3] == ' ') {
+                        continue;
+                }
+                if (buf[0] == 'H' && buf[1] == 'U' &&
+                    buf[2] == 'T' && /*isspace(buf[3])*/ buf[3] == ' ') {
+                        lastlang = lastclass = lastvendor = lastsubclass = -1;
+                        /*
+                         * set 1 as pseudo-id to indicate that the parser is
+                         * in a `HUT' section.
+                         */
+                        lasthut = 1;
+                        continue;
+                }
+                if (buf[0] == 'R' && buf[1] == ' ')
+                        continue;
+
+                if (buf[0] == 'V' && buf[1] == 'T')
+                        continue;
+
+                err("Unknown line at line %u", linectr);
+        }
+}
+
+
+int names_init(char *n)
+{
+        FILE *f;
+
+        f = fopen(n, "r");
+        if (!f)
+                return errno;
+
+        parse(f);
+        fclose(f);
+        return 0;
+}
diff --git a/tools/usb/usbip/libsrc/names.h b/tools/usb/usbip/libsrc/names.h
new file mode 100644
index 000000000000..680926512de2
--- /dev/null
+++ b/tools/usb/usbip/libsrc/names.h
@@ -0,0 +1,41 @@
+/*
+ *      names.h  --  USB name database manipulation routines
+ *
+ *      Copyright (C) 1999, 2000  Thomas Sailer (sailer@ife.ee.ethz.ch)
+ *
+ *      This program is free software; you can redistribute it and/or modify
+ *      it under the terms of the GNU General Public License as published by
+ *      the Free Software Foundation; either version 2 of the License, or
+ *      (at your option) any later version.
+ *
+ *      This program is distributed in the hope that 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.
+ *
+ *      You should have received a copy of the GNU General Public License
+ *      along with this program; if not, write to the Free Software
+ *      Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ *
+ *
+ *      Copyright (C) 2005 Takahiro Hirofuchi
+ *             - names_free() is added.
+ */
+
+#ifndef _NAMES_H
+#define _NAMES_H
+
+#include <sys/types.h>
+
+/* used by usbip_common.c */
+extern const char *names_vendor(u_int16_t vendorid);
+extern const char *names_product(u_int16_t vendorid, u_int16_t productid);
+extern const char *names_class(u_int8_t classid);
+extern const char *names_subclass(u_int8_t classid, u_int8_t subclassid);
+extern const char *names_protocol(u_int8_t classid, u_int8_t subclassid,
+                                  u_int8_t protocolid);
+extern int  names_init(char *n);
+extern void names_free(void);
+
+#endif /* _NAMES_H */
diff --git a/tools/usb/usbip/libsrc/sysfs_utils.c b/tools/usb/usbip/libsrc/sysfs_utils.c
new file mode 100644
index 000000000000..36ac88ece0b8
--- /dev/null
+++ b/tools/usb/usbip/libsrc/sysfs_utils.c
@@ -0,0 +1,31 @@
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <errno.h>
+
+#include "sysfs_utils.h"
+#include "usbip_common.h"
+
+int write_sysfs_attribute(const char *attr_path, const char *new_value,
+                          size_t len)
+{
+        int fd;
+        int length;
+
+        fd = open(attr_path, O_WRONLY);
+        if (fd < 0) {
+                dbg("error opening attribute %s", attr_path);
+                return -1;
+        }
+
+        length = write(fd, new_value, len);
+        if (length < 0) {
+                dbg("error writing to attribute %s", attr_path);
+                close(fd);
+                return -1;
+        }
+
+        close(fd);
+
+        return 0;
+}
diff --git a/tools/usb/usbip/libsrc/sysfs_utils.h b/tools/usb/usbip/libsrc/sysfs_utils.h
new file mode 100644
index 000000000000..32ac1d105d18
--- /dev/null
+++ b/tools/usb/usbip/libsrc/sysfs_utils.h
@@ -0,0 +1,8 @@
+
+#ifndef __SYSFS_UTILS_H
+#define __SYSFS_UTILS_H
+
+int write_sysfs_attribute(const char *attr_path, const char *new_value,
+                          size_t len);
+
+#endif
diff --git a/tools/usb/usbip/libsrc/usbip_common.c b/tools/usb/usbip/libsrc/usbip_common.c
new file mode 100644
index 000000000000..ac73710473de
--- /dev/null
+++ b/tools/usb/usbip/libsrc/usbip_common.c
@@ -0,0 +1,285 @@
+/*
+ * Copyright (C) 2005-2007 Takahiro Hirofuchi
+ */
+
+#include <libudev.h>
+#include "usbip_common.h"
+#include "names.h"
+
+#undef  PROGNAME
+#define PROGNAME "libusbip"
+
+int usbip_use_syslog;
+int usbip_use_stderr;
+int usbip_use_debug;
+
+extern struct udev *udev_context;
+
+struct speed_string {
+        int num;
+        char *speed;
+        char *desc;
+};
+
+static const struct speed_string speed_strings[] = {
+        { USB_SPEED_UNKNOWN, "unknown", "Unknown Speed"},
+        { USB_SPEED_LOW,  "1.5", "Low Speed(1.5Mbps)"  },
+        { USB_SPEED_FULL, "12",  "Full Speed(12Mbps)" },
+        { USB_SPEED_HIGH, "480", "High Speed(480Mbps)" },
+        { USB_SPEED_WIRELESS, "53.3-480", "Wireless"},
+        { USB_SPEED_SUPER, "5000", "Super Speed(5000Mbps)" },
+        { 0, NULL, NULL }
+};
+
+struct portst_string {
+        int num;
+        char *desc;
+};
+
+static struct portst_string portst_strings[] = {
+        { SDEV_ST_AVAILABLE,    "Device Available" },
+        { SDEV_ST_USED,         "Device in Use" },
+        { SDEV_ST_ERROR,        "Device Error"},
+        { VDEV_ST_NULL,         "Port Available"},
+        { VDEV_ST_NOTASSIGNED,  "Port Initializing"},
+        { VDEV_ST_USED,         "Port in Use"},
+        { VDEV_ST_ERROR,        "Port Error"},
+        { 0, NULL}
+};
+
+const char *usbip_status_string(int32_t status)
+{
+        for (int i = 0; portst_strings[i].desc != NULL; i++)
+                if (portst_strings[i].num == status)
+                        return portst_strings[i].desc;
+
+        return "Unknown Status";
+}
+
+const char *usbip_speed_string(int num)
+{
+        for (int i = 0; speed_strings[i].speed != NULL; i++)
+                if (speed_strings[i].num == num)
+                        return speed_strings[i].desc;
+
+        return "Unknown Speed";
+}
+
+
+#define DBG_UDEV_INTEGER(name)\
+        dbg("%-20s = %x", to_string(name), (int) udev->name)
+
+#define DBG_UINF_INTEGER(name)\
+        dbg("%-20s = %x", to_string(name), (int) uinf->name)
+
+void dump_usb_interface(struct usbip_usb_interface *uinf)
+{
+        char buff[100];
+
+        usbip_names_get_class(buff, sizeof(buff),
+                        uinf->bInterfaceClass,
+                        uinf->bInterfaceSubClass,
+                        uinf->bInterfaceProtocol);
+        dbg("%-20s = %s", "Interface(C/SC/P)", buff);
+}
+
+void dump_usb_device(struct usbip_usb_device *udev)
+{
+        char buff[100];
+
+        dbg("%-20s = %s", "path",  udev->path);
+        dbg("%-20s = %s", "busid", udev->busid);
+
+        usbip_names_get_class(buff, sizeof(buff),
+                        udev->bDeviceClass,
+                        udev->bDeviceSubClass,
+                        udev->bDeviceProtocol);
+        dbg("%-20s = %s", "Device(C/SC/P)", buff);
+
+        DBG_UDEV_INTEGER(bcdDevice);
+
+        usbip_names_get_product(buff, sizeof(buff),
+                        udev->idVendor,
+                        udev->idProduct);
+        dbg("%-20s = %s", "Vendor/Product", buff);
+
+        DBG_UDEV_INTEGER(bNumConfigurations);
+        DBG_UDEV_INTEGER(bNumInterfaces);
+
+        dbg("%-20s = %s", "speed",
+                        usbip_speed_string(udev->speed));
+
+        DBG_UDEV_INTEGER(busnum);
+        DBG_UDEV_INTEGER(devnum);
+}
+
+
+int read_attr_value(struct udev_device *dev, const char *name,
+                    const char *format)
+{
+        const char *attr;
+        int num = 0;
+        int ret;
+
+        attr = udev_device_get_sysattr_value(dev, name);
+        if (!attr) {
+                err("udev_device_get_sysattr_value failed");
+                goto err;
+        }
+
+        /* The client chooses the device configuration
+         * when attaching it so right after being bound
+         * to usbip-host on the server the device will
+         * have no configuration.
+         * Therefore, attributes such as bConfigurationValue
+         * and bNumInterfaces will not exist and sscanf will
+         * fail. Check for these cases and don't treat them
+         * as errors.
+         */
+
+        ret = sscanf(attr, format, &num);
+        if (ret < 1) {
+                if (strcmp(name, "bConfigurationValue") &&
+                                strcmp(name, "bNumInterfaces")) {
+                        err("sscanf failed for attribute %s", name);
+                        goto err;
+                }
+        }
+
+err:
+
+        return num;
+}
+
+
+int read_attr_speed(struct udev_device *dev)
+{
+        const char *speed;
+
+        speed = udev_device_get_sysattr_value(dev, "speed");
+        if (!speed) {
+                err("udev_device_get_sysattr_value failed");
+                goto err;
+        }
+
+        for (int i = 0; speed_strings[i].speed != NULL; i++) {
+                if (!strcmp(speed, speed_strings[i].speed))
+                        return speed_strings[i].num;
+        }
+
+err:
+
+        return USB_SPEED_UNKNOWN;
+}
+
+#define READ_ATTR(object, type, dev, name, format)                            \
+        do {                                                                  \
+                (object)->name = (type) read_attr_value(dev, to_string(name), \
+                                                        format);              \
+        } while (0)
+
+
+int read_usb_device(struct udev_device *sdev, struct usbip_usb_device *udev)
+{
+        uint32_t busnum, devnum;
+        const char *path, *name;
+
+        READ_ATTR(udev, uint8_t,  sdev, bDeviceClass,           "%02x\n");
+        READ_ATTR(udev, uint8_t,  sdev, bDeviceSubClass,        "%02x\n");
+        READ_ATTR(udev, uint8_t,  sdev, bDeviceProtocol,        "%02x\n");
+
+        READ_ATTR(udev, uint16_t, sdev, idVendor,               "%04x\n");
+        READ_ATTR(udev, uint16_t, sdev, idProduct,              "%04x\n");
+        READ_ATTR(udev, uint16_t, sdev, bcdDevice,              "%04x\n");
+
+        READ_ATTR(udev, uint8_t,  sdev, bConfigurationValue,    "%02x\n");
+        READ_ATTR(udev, uint8_t,  sdev, bNumConfigurations,     "%02x\n");
+        READ_ATTR(udev, uint8_t,  sdev, bNumInterfaces,         "%02x\n");
+
+        READ_ATTR(udev, uint8_t,  sdev, devnum,                 "%d\n");
+        udev->speed = read_attr_speed(sdev);
+
+        path = udev_device_get_syspath(sdev);
+        name = udev_device_get_sysname(sdev);
+
+        strncpy(udev->path,  path,  SYSFS_PATH_MAX);
+        strncpy(udev->busid, name, SYSFS_BUS_ID_SIZE);
+
+        sscanf(name, "%u-%u", &busnum, &devnum);
+        udev->busnum = busnum;
+
+        return 0;
+}
+
+int read_usb_interface(struct usbip_usb_device *udev, int i,
+                       struct usbip_usb_interface *uinf)
+{
+        char busid[SYSFS_BUS_ID_SIZE];
+        struct udev_device *sif;
+
+        sprintf(busid, "%s:%d.%d", udev->busid, udev->bConfigurationValue, i);
+
+        sif = udev_device_new_from_subsystem_sysname(udev_context, "usb", busid);
+        if (!sif) {
+                err("udev_device_new_from_subsystem_sysname %s failed", busid);
+                return -1;
+        }
+
+        READ_ATTR(uinf, uint8_t,  sif, bInterfaceClass,         "%02x\n");
+        READ_ATTR(uinf, uint8_t,  sif, bInterfaceSubClass,      "%02x\n");
+        READ_ATTR(uinf, uint8_t,  sif, bInterfaceProtocol,      "%02x\n");
+
+        return 0;
+}
+
+int usbip_names_init(char *f)
+{
+        return names_init(f);
+}
+
+void usbip_names_free(void)
+{
+        names_free();
+}
+
+void usbip_names_get_product(char *buff, size_t size, uint16_t vendor,
+                             uint16_t product)
+{
+        const char *prod, *vend;
+
+        prod = names_product(vendor, product);
+        if (!prod)
+                prod = "unknown product";
+
+
+        vend = names_vendor(vendor);
+        if (!vend)
+                vend = "unknown vendor";
+
+        snprintf(buff, size, "%s : %s (%04x:%04x)", vend, prod, vendor, product);
+}
+
+void usbip_names_get_class(char *buff, size_t size, uint8_t class,
+                           uint8_t subclass, uint8_t protocol)
+{
+        const char *c, *s, *p;
+
+        if (class == 0 && subclass == 0 && protocol == 0) {
+                snprintf(buff, size, "(Defined at Interface level) (%02x/%02x/%02x)", class, subclass, protocol);
+                return;
+        }
+
+        p = names_protocol(class, subclass, protocol);
+        if (!p)
+                p = "unknown protocol";
+
+        s = names_subclass(class, subclass);
+        if (!s)
+                s = "unknown subclass";
+
+        c = names_class(class);
+        if (!c)
+                c = "unknown class";
+
+        snprintf(buff, size, "%s / %s / %s (%02x/%02x/%02x)", c, s, p, class, subclass, protocol);
+}
diff --git a/tools/usb/usbip/libsrc/usbip_common.h b/tools/usb/usbip/libsrc/usbip_common.h
new file mode 100644
index 000000000000..15fe792e1e96
--- /dev/null
+++ b/tools/usb/usbip/libsrc/usbip_common.h
@@ -0,0 +1,137 @@
+/*
+ * Copyright (C) 2005-2007 Takahiro Hirofuchi
+ */
+
+#ifndef __USBIP_COMMON_H
+#define __USBIP_COMMON_H
+
+#include <libudev.h>
+
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <syslog.h>
+#include <unistd.h>
+#include <linux/usb/ch9.h>
+#include <linux/usbip.h>
+
+#ifndef USBIDS_FILE
+#define USBIDS_FILE "/usr/share/hwdata/usb.ids"
+#endif
+
+#ifndef VHCI_STATE_PATH
+#define VHCI_STATE_PATH "/var/run/vhci_hcd"
+#endif
+
+/* kernel module names */
+#define USBIP_CORE_MOD_NAME     "usbip-core"
+#define USBIP_HOST_DRV_NAME     "usbip-host"
+#define USBIP_VHCI_DRV_NAME     "vhci_hcd"
+
+/* sysfs constants */
+#define SYSFS_MNT_PATH         "/sys"
+#define SYSFS_BUS_NAME         "bus"
+#define SYSFS_BUS_TYPE         "usb"
+#define SYSFS_DRIVERS_NAME     "drivers"
+
+#define SYSFS_PATH_MAX          256
+#define SYSFS_BUS_ID_SIZE       32
+
+extern int usbip_use_syslog;
+extern int usbip_use_stderr;
+extern int usbip_use_debug ;
+
+#define PROGNAME "usbip"
+
+#define pr_fmt(fmt)     "%s: %s: " fmt "\n", PROGNAME
+#define dbg_fmt(fmt)    pr_fmt("%s:%d:[%s] " fmt), "debug",     \
+                        __FILE__, __LINE__, __func__
+
+#define err(fmt, args...)                                               \
+        do {                                                            \
+                if (usbip_use_syslog) {                                 \
+                        syslog(LOG_ERR, pr_fmt(fmt), "error", ##args);  \
+                }                                                       \
+                if (usbip_use_stderr) {                                 \
+                        fprintf(stderr, pr_fmt(fmt), "error", ##args);  \
+                }                                                       \
+        } while (0)
+
+#define info(fmt, args...)                                              \
+        do {                                                            \
+                if (usbip_use_syslog) {                                 \
+                        syslog(LOG_INFO, pr_fmt(fmt), "info", ##args);  \
+                }                                                       \
+                if (usbip_use_stderr) {                                 \
+                        fprintf(stderr, pr_fmt(fmt), "info", ##args);   \
+                }                                                       \
+        } while (0)
+
+#define dbg(fmt, args...)                                               \
+        do {                                                            \
+        if (usbip_use_debug) {                                          \
+                if (usbip_use_syslog) {                                 \
+                        syslog(LOG_DEBUG, dbg_fmt(fmt), ##args);        \
+                }                                                       \
+                if (usbip_use_stderr) {                                 \
+                        fprintf(stderr, dbg_fmt(fmt), ##args);          \
+                }                                                       \
+        }                                                               \
+        } while (0)
+
+#define BUG()                                           \
+        do {                                            \
+                err("sorry, it's a bug!");              \
+                abort();                                \
+        } while (0)
+
+struct usbip_usb_interface {
+        uint8_t bInterfaceClass;
+        uint8_t bInterfaceSubClass;
+        uint8_t bInterfaceProtocol;
+        uint8_t padding;        /* alignment */
+} __attribute__((packed));
+
+struct usbip_usb_device {
+        char path[SYSFS_PATH_MAX];
+        char busid[SYSFS_BUS_ID_SIZE];
+
+        uint32_t busnum;
+        uint32_t devnum;
+        uint32_t speed;
+
+        uint16_t idVendor;
+        uint16_t idProduct;
+        uint16_t bcdDevice;
+
+        uint8_t bDeviceClass;
+        uint8_t bDeviceSubClass;
+        uint8_t bDeviceProtocol;
+        uint8_t bConfigurationValue;
+        uint8_t bNumConfigurations;
+        uint8_t bNumInterfaces;
+} __attribute__((packed));
+
+#define to_string(s)    #s
+
+void dump_usb_interface(struct usbip_usb_interface *);
+void dump_usb_device(struct usbip_usb_device *);
+int read_usb_device(struct udev_device *sdev, struct usbip_usb_device *udev);
+int read_attr_value(struct udev_device *dev, const char *name,
+                    const char *format);
+int read_usb_interface(struct usbip_usb_device *udev, int i,
+                       struct usbip_usb_interface *uinf);
+
+const char *usbip_speed_string(int num);
+const char *usbip_status_string(int32_t status);
+
+int usbip_names_init(char *);
+void usbip_names_free(void);
+void usbip_names_get_product(char *buff, size_t size, uint16_t vendor,
+                             uint16_t product);
+void usbip_names_get_class(char *buff, size_t size, uint8_t class,
+                           uint8_t subclass, uint8_t protocol);
+
+#endif /* __USBIP_COMMON_H */
diff --git a/tools/usb/usbip/libsrc/usbip_host_driver.c b/tools/usb/usbip/libsrc/usbip_host_driver.c
new file mode 100644
index 000000000000..bef08d5c44e8
--- /dev/null
+++ b/tools/usb/usbip/libsrc/usbip_host_driver.c
@@ -0,0 +1,280 @@
+/*
+ * Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
+ *               2005-2007 Takahiro Hirofuchi
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+
+#include <errno.h>
+#include <unistd.h>
+
+#include <libudev.h>
+
+#include "usbip_common.h"
+#include "usbip_host_driver.h"
+#include "list.h"
+#include "sysfs_utils.h"
+
+#undef  PROGNAME
+#define PROGNAME "libusbip"
+
+struct usbip_host_driver *host_driver;
+struct udev *udev_context;
+
+static int32_t read_attr_usbip_status(struct usbip_usb_device *udev)
+{
+        char status_attr_path[SYSFS_PATH_MAX];
+        int fd;
+        int length;
+        char status;
+        int value = 0;
+
+        snprintf(status_attr_path, SYSFS_PATH_MAX, "%s/usbip_status",
+                 udev->path);
+
+        fd = open(status_attr_path, O_RDONLY);
+        if (fd < 0) {
+                err("error opening attribute %s", status_attr_path);
+                return -1;
+        }
+
+        length = read(fd, &status, 1);
+        if (length < 0) {
+                err("error reading attribute %s", status_attr_path);
+                close(fd);
+                return -1;
+        }
+
+        value = atoi(&status);
+
+        return value;
+}
+
+static
+struct usbip_exported_device *usbip_exported_device_new(const char *sdevpath)
+{
+        struct usbip_exported_device *edev = NULL;
+        struct usbip_exported_device *edev_old;
+        size_t size;
+        int i;
+
+        edev = calloc(1, sizeof(struct usbip_exported_device));
+
+        edev->sudev = udev_device_new_from_syspath(udev_context, sdevpath);
+        if (!edev->sudev) {
+                err("udev_device_new_from_syspath: %s", sdevpath);
+                goto err;
+        }
+
+        read_usb_device(edev->sudev, &edev->udev);
+
+        edev->status = read_attr_usbip_status(&edev->udev);
+        if (edev->status < 0)
+                goto err;
+
+        /* reallocate buffer to include usb interface data */
+        size = sizeof(struct usbip_exported_device) +
+                edev->udev.bNumInterfaces * sizeof(struct usbip_usb_interface);
+
+        edev_old = edev;
+        edev = realloc(edev, size);
+        if (!edev) {
+                edev = edev_old;
+                dbg("realloc failed");
+                goto err;
+        }
+
+        for (i = 0; i < edev->udev.bNumInterfaces; i++)
+                read_usb_interface(&edev->udev, i, &edev->uinf[i]);
+
+        return edev;
+err:
+        if (edev->sudev)
+                udev_device_unref(edev->sudev);
+        if (edev)
+                free(edev);
+
+        return NULL;
+}
+
+static int refresh_exported_devices(void)
+{
+        struct usbip_exported_device *edev;
+        struct udev_enumerate *enumerate;
+        struct udev_list_entry *devices, *dev_list_entry;
+        struct udev_device *dev;
+        const char *path;
+        const char *driver;
+
+        enumerate = udev_enumerate_new(udev_context);
+        udev_enumerate_add_match_subsystem(enumerate, "usb");
+        udev_enumerate_scan_devices(enumerate);
+
+        devices = udev_enumerate_get_list_entry(enumerate);
+
+        udev_list_entry_foreach(dev_list_entry, devices) {
+                path = udev_list_entry_get_name(dev_list_entry);
+                dev = udev_device_new_from_syspath(udev_context, path);
+                if (dev == NULL)
+                        continue;
+
+                /* Check whether device uses usbip-host driver. */
+                driver = udev_device_get_driver(dev);
+                if (driver != NULL && !strcmp(driver, USBIP_HOST_DRV_NAME)) {
+                        edev = usbip_exported_device_new(path);
+                        if (!edev) {
+                                dbg("usbip_exported_device_new failed");
+                                continue;
+                        }
+
+                        list_add(&edev->node, &host_driver->edev_list);
+                        host_driver->ndevs++;
+                }
+        }
+
+        return 0;
+}
+
+static void usbip_exported_device_destroy(void)
+{
+        struct list_head *i, *tmp;
+        struct usbip_exported_device *edev;
+
+        list_for_each_safe(i, tmp, &host_driver->edev_list) {
+                edev = list_entry(i, struct usbip_exported_device, node);
+                list_del(i);
+                free(edev);
+        }
+}
+
+int usbip_host_driver_open(void)
+{
+        int rc;
+
+        udev_context = udev_new();
+        if (!udev_context) {
+                err("udev_new failed");
+                return -1;
+        }
+
+        host_driver = calloc(1, sizeof(*host_driver));
+
+        host_driver->ndevs = 0;
+        INIT_LIST_HEAD(&host_driver->edev_list);
+
+        rc = refresh_exported_devices();
+        if (rc < 0)
+                goto err_free_host_driver;
+
+        return 0;
+
+err_free_host_driver:
+        free(host_driver);
+        host_driver = NULL;
+
+        udev_unref(udev_context);
+
+        return -1;
+}
+
+void usbip_host_driver_close(void)
+{
+        if (!host_driver)
+                return;
+
+        usbip_exported_device_destroy();
+
+        free(host_driver);
+        host_driver = NULL;
+
+        udev_unref(udev_context);
+}
+
+int usbip_host_refresh_device_list(void)
+{
+        int rc;
+
+        usbip_exported_device_destroy();
+
+        host_driver->ndevs = 0;
+        INIT_LIST_HEAD(&host_driver->edev_list);
+
+        rc = refresh_exported_devices();
+        if (rc < 0)
+                return -1;
+
+        return 0;
+}
+
+int usbip_host_export_device(struct usbip_exported_device *edev, int sockfd)
+{
+        char attr_name[] = "usbip_sockfd";
+        char sockfd_attr_path[SYSFS_PATH_MAX];
+        char sockfd_buff[30];
+        int ret;
+
+        if (edev->status != SDEV_ST_AVAILABLE) {
+                dbg("device not available: %s", edev->udev.busid);
+                switch (edev->status) {
+                case SDEV_ST_ERROR:
+                        dbg("status SDEV_ST_ERROR");
+                        break;
+                case SDEV_ST_USED:
+                        dbg("status SDEV_ST_USED");
+                        break;
+                default:
+                        dbg("status unknown: 0x%x", edev->status);
+                }
+                return -1;
+        }
+
+        /* only the first interface is true */
+        snprintf(sockfd_attr_path, sizeof(sockfd_attr_path), "%s/%s",
+                 edev->udev.path, attr_name);
+
+        snprintf(sockfd_buff, sizeof(sockfd_buff), "%d\n", sockfd);
+
+        ret = write_sysfs_attribute(sockfd_attr_path, sockfd_buff,
+                                    strlen(sockfd_buff));
+        if (ret < 0) {
+                err("write_sysfs_attribute failed: sockfd %s to %s",
+                    sockfd_buff, sockfd_attr_path);
+                return ret;
+        }
+
+        info("connect: %s", edev->udev.busid);
+
+        return ret;
+}
+
+struct usbip_exported_device *usbip_host_get_device(int num)
+{
+        struct list_head *i;
+        struct usbip_exported_device *edev;
+        int cnt = 0;
+
+        list_for_each(i, &host_driver->edev_list) {
+                edev = list_entry(i, struct usbip_exported_device, node);
+                if (num == cnt)
+                        return edev;
+                else
+                        cnt++;
+        }
+
+        return NULL;
+}
diff --git a/tools/usb/usbip/libsrc/usbip_host_driver.h b/tools/usb/usbip/libsrc/usbip_host_driver.h
new file mode 100644
index 000000000000..2a31f855c616
--- /dev/null
+++ b/tools/usb/usbip/libsrc/usbip_host_driver.h
@@ -0,0 +1,49 @@
+/*
+ * Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
+ *               2005-2007 Takahiro Hirofuchi
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __USBIP_HOST_DRIVER_H
+#define __USBIP_HOST_DRIVER_H
+
+#include <stdint.h>
+#include "usbip_common.h"
+#include "list.h"
+
+struct usbip_host_driver {
+        int ndevs;
+        /* list of exported device */
+        struct list_head edev_list;
+};
+
+struct usbip_exported_device {
+        struct udev_device *sudev;
+        int32_t status;
+        struct usbip_usb_device udev;
+        struct list_head node;
+        struct usbip_usb_interface uinf[];
+};
+
+extern struct usbip_host_driver *host_driver;
+
+int usbip_host_driver_open(void);
+void usbip_host_driver_close(void);
+
+int usbip_host_refresh_device_list(void);
+int usbip_host_export_device(struct usbip_exported_device *edev, int sockfd);
+struct usbip_exported_device *usbip_host_get_device(int num);
+
+#endif /* __USBIP_HOST_DRIVER_H */
diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c
new file mode 100644
index 000000000000..ad9204773533
--- /dev/null
+++ b/tools/usb/usbip/libsrc/vhci_driver.c
@@ -0,0 +1,411 @@
+/*
+ * Copyright (C) 2005-2007 Takahiro Hirofuchi
+ */
+
+#include "usbip_common.h"
+#include "vhci_driver.h"
+#include <limits.h>
+#include <netdb.h>
+#include <libudev.h>
+#include "sysfs_utils.h"
+
+#undef  PROGNAME
+#define PROGNAME "libusbip"
+
+struct usbip_vhci_driver *vhci_driver;
+struct udev *udev_context;
+
+static struct usbip_imported_device *
+imported_device_init(struct usbip_imported_device *idev, char *busid)
+{
+        struct udev_device *sudev;
+
+        sudev = udev_device_new_from_subsystem_sysname(udev_context,
+                                                       "usb", busid);
+        if (!sudev) {
+                dbg("udev_device_new_from_subsystem_sysname failed: %s", busid);
+                goto err;
+        }
+        read_usb_device(sudev, &idev->udev);
+        udev_device_unref(sudev);
+
+        return idev;
+
+err:
+        return NULL;
+}
+
+
+
+static int parse_status(const char *value)
+{
+        int ret = 0;
+        char *c;
+
+
+        for (int i = 0; i < vhci_driver->nports; i++)
+                memset(&vhci_driver->idev[i], 0, sizeof(vhci_driver->idev[i]));
+
+
+        /* skip a header line */
+        c = strchr(value, '\n');
+        if (!c)
+                return -1;
+        c++;
+
+        while (*c != '\0') {
+                int port, status, speed, devid;
+                unsigned long socket;
+                char lbusid[SYSFS_BUS_ID_SIZE];
+
+                ret = sscanf(c, "%d %d %d %x %lx %31s\n",
+                                &port, &status, &speed,
+                                &devid, &socket, lbusid);
+
+                if (ret < 5) {
+                        dbg("sscanf failed: %d", ret);
+                        BUG();
+                }
+
+                dbg("port %d status %d speed %d devid %x",
+                                port, status, speed, devid);
+                dbg("socket %lx lbusid %s", socket, lbusid);
+
+
+                /* if a device is connected, look at it */
+                {
+                        struct usbip_imported_device *idev = &vhci_driver->idev[port];
+
+                        idev->port      = port;
+                        idev->status    = status;
+
+                        idev->devid     = devid;
+
+                        idev->busnum    = (devid >> 16);
+                        idev->devnum    = (devid & 0x0000ffff);
+
+                        if (idev->status != VDEV_ST_NULL
+                            && idev->status != VDEV_ST_NOTASSIGNED) {
+                                idev = imported_device_init(idev, lbusid);
+                                if (!idev) {
+                                        dbg("imported_device_init failed");
+                                        return -1;
+                                }
+                        }
+                }
+
+
+                /* go to the next line */
+                c = strchr(c, '\n');
+                if (!c)
+                        break;
+                c++;
+        }
+
+        dbg("exit");
+
+        return 0;
+}
+
+static int refresh_imported_device_list(void)
+{
+        const char *attr_status;
+
+        attr_status = udev_device_get_sysattr_value(vhci_driver->hc_device,
+                                               "status");
+        if (!attr_status) {
+                err("udev_device_get_sysattr_value failed");
+                return -1;
+        }
+
+        return parse_status(attr_status);
+}
+
+static int get_nports(void)
+{
+        char *c;
+        int nports = 0;
+        const char *attr_status;
+
+        attr_status = udev_device_get_sysattr_value(vhci_driver->hc_device,
+                                               "status");
+        if (!attr_status) {
+                err("udev_device_get_sysattr_value failed");
+                return -1;
+        }
+
+        /* skip a header line */
+        c = strchr(attr_status, '\n');
+        if (!c)
+                return 0;
+        c++;
+
+        while (*c != '\0') {
+                /* go to the next line */
+                c = strchr(c, '\n');
+                if (!c)
+                        return nports;
+                c++;
+                nports += 1;
+        }
+
+        return nports;
+}
+
+/*
+ * Read the given port's record.
+ *
+ * To avoid buffer overflow we will read the entire line and
+ * validate each part's size. The initial buffer is padded by 4 to
+ * accommodate the 2 spaces, 1 newline and an additional character
+ * which is needed to properly validate the 3rd part without it being
+ * truncated to an acceptable length.
+ */
+static int read_record(int rhport, char *host, unsigned long host_len,
+                char *port, unsigned long port_len, char *busid)
+{
+        int part;
+        FILE *file;
+        char path[PATH_MAX+1];
+        char *buffer, *start, *end;
+        char delim[] = {' ', ' ', '\n'};
+        int max_len[] = {(int)host_len, (int)port_len, SYSFS_BUS_ID_SIZE};
+        size_t buffer_len = host_len + port_len + SYSFS_BUS_ID_SIZE + 4;
+
+        buffer = malloc(buffer_len);
+        if (!buffer)
+                return -1;
+
+        snprintf(path, PATH_MAX, VHCI_STATE_PATH"/port%d", rhport);
+
+        file = fopen(path, "r");
+        if (!file) {
+                err("fopen");
+                free(buffer);
+                return -1;
+        }
+
+        if (fgets(buffer, buffer_len, file) == NULL) {
+                err("fgets");
+                free(buffer);
+                fclose(file);
+                return -1;
+        }
+        fclose(file);
+
+        /* validate the length of each of the 3 parts */
+        start = buffer;
+        for (part = 0; part < 3; part++) {
+                end = strchr(start, delim[part]);
+                if (end == NULL || (end - start) > max_len[part]) {
+                        free(buffer);
+                        return -1;
+                }
+                start = end + 1;
+        }
+
+        if (sscanf(buffer, "%s %s %s\n", host, port, busid) != 3) {
+                err("sscanf");
+                free(buffer);
+                return -1;
+        }
+
+        free(buffer);
+
+        return 0;
+}
+
+/* ---------------------------------------------------------------------- */
+
+int usbip_vhci_driver_open(void)
+{
+        udev_context = udev_new();
+        if (!udev_context) {
+                err("udev_new failed");
+                return -1;
+        }
+
+        vhci_driver = calloc(1, sizeof(struct usbip_vhci_driver));
+
+        /* will be freed in usbip_driver_close() */
+        vhci_driver->hc_device =
+                udev_device_new_from_subsystem_sysname(udev_context,
+                                                       USBIP_VHCI_BUS_TYPE,
+                                                       USBIP_VHCI_DRV_NAME);
+        if (!vhci_driver->hc_device) {
+                err("udev_device_new_from_subsystem_sysname failed");
+                goto err;
+        }
+
+        vhci_driver->nports = get_nports();
+
+        dbg("available ports: %d", vhci_driver->nports);
+
+        if (refresh_imported_device_list())
+                goto err;
+
+        return 0;
+
+err:
+        udev_device_unref(vhci_driver->hc_device);
+
+        if (vhci_driver)
+                free(vhci_driver);
+
+        vhci_driver = NULL;
+
+        udev_unref(udev_context);
+
+        return -1;
+}
+
+
+void usbip_vhci_driver_close(void)
+{
+        if (!vhci_driver)
+                return;
+
+        udev_device_unref(vhci_driver->hc_device);
+
+        free(vhci_driver);
+
+        vhci_driver = NULL;
+
+        udev_unref(udev_context);
+}
+
+
+int usbip_vhci_refresh_device_list(void)
+{
+
+        if (refresh_imported_device_list())
+                goto err;
+
+        return 0;
+err:
+        dbg("failed to refresh device list");
+        return -1;
+}
+
+
+int usbip_vhci_get_free_port(void)
+{
+        for (int i = 0; i < vhci_driver->nports; i++) {
+                if (vhci_driver->idev[i].status == VDEV_ST_NULL)
+                        return i;
+        }
+
+        return -1;
+}
+
+int usbip_vhci_attach_device2(uint8_t port, int sockfd, uint32_t devid,
+                uint32_t speed) {
+        char buff[200]; /* what size should be ? */
+        char attach_attr_path[SYSFS_PATH_MAX];
+        char attr_attach[] = "attach";
+        const char *path;
+        int ret;
+
+        snprintf(buff, sizeof(buff), "%u %d %u %u",
+                        port, sockfd, devid, speed);
+        dbg("writing: %s", buff);
+
+        path = udev_device_get_syspath(vhci_driver->hc_device);
+        snprintf(attach_attr_path, sizeof(attach_attr_path), "%s/%s",
+                 path, attr_attach);
+        dbg("attach attribute path: %s", attach_attr_path);
+
+        ret = write_sysfs_attribute(attach_attr_path, buff, strlen(buff));
+        if (ret < 0) {
+                dbg("write_sysfs_attribute failed");
+                return -1;
+        }
+
+        dbg("attached port: %d", port);
+
+        return 0;
+}
+
+static unsigned long get_devid(uint8_t busnum, uint8_t devnum)
+{
+        return (busnum << 16) | devnum;
+}
+
+/* will be removed */
+int usbip_vhci_attach_device(uint8_t port, int sockfd, uint8_t busnum,
+                uint8_t devnum, uint32_t speed)
+{
+        int devid = get_devid(busnum, devnum);
+
+        return usbip_vhci_attach_device2(port, sockfd, devid, speed);
+}
+
+int usbip_vhci_detach_device(uint8_t port)
+{
+        char detach_attr_path[SYSFS_PATH_MAX];
+        char attr_detach[] = "detach";
+        char buff[200]; /* what size should be ? */
+        const char *path;
+        int ret;
+
+        snprintf(buff, sizeof(buff), "%u", port);
+        dbg("writing: %s", buff);
+
+        path = udev_device_get_syspath(vhci_driver->hc_device);
+        snprintf(detach_attr_path, sizeof(detach_attr_path), "%s/%s",
+                 path, attr_detach);
+        dbg("detach attribute path: %s", detach_attr_path);
+
+        ret = write_sysfs_attribute(detach_attr_path, buff, strlen(buff));
+        if (ret < 0) {
+                dbg("write_sysfs_attribute failed");
+                return -1;
+        }
+
+        dbg("detached port: %d", port);
+
+        return 0;
+}
+
+int usbip_vhci_imported_device_dump(struct usbip_imported_device *idev)
+{
+        char product_name[100];
+        char host[NI_MAXHOST] = "unknown host";
+        char serv[NI_MAXSERV] = "unknown port";
+        char remote_busid[SYSFS_BUS_ID_SIZE];
+        int ret;
+        int read_record_error = 0;
+
+        if (idev->status == VDEV_ST_NULL || idev->status == VDEV_ST_NOTASSIGNED)
+                return 0;
+
+        ret = read_record(idev->port, host, sizeof(host), serv, sizeof(serv),
+                          remote_busid);
+        if (ret) {
+                err("read_record");
+                read_record_error = 1;
+        }
+
+        printf("Port %02d: <%s> at %s\n", idev->port,
+               usbip_status_string(idev->status),
+               usbip_speed_string(idev->udev.speed));
+
+        usbip_names_get_product(product_name, sizeof(product_name),
+                                idev->udev.idVendor, idev->udev.idProduct);
+
+        printf("       %s\n",  product_name);
+
+        if (!read_record_error) {
+                printf("%10s -> usbip://%s:%s/%s\n", idev->udev.busid,
+                       host, serv, remote_busid);
+                printf("%10s -> remote bus/dev %03d/%03d\n", " ",
+                       idev->busnum, idev->devnum);
+        } else {
+                printf("%10s -> unknown host, remote port and remote busid\n",
+                       idev->udev.busid);
+                printf("%10s -> remote bus/dev %03d/%03d\n", " ",
+                       idev->busnum, idev->devnum);
+        }
+
+        return 0;
+}
diff --git a/tools/usb/usbip/libsrc/vhci_driver.h b/tools/usb/usbip/libsrc/vhci_driver.h
new file mode 100644
index 000000000000..fa2316cf2cac
--- /dev/null
+++ b/tools/usb/usbip/libsrc/vhci_driver.h
@@ -0,0 +1,59 @@
+/*
+ * Copyright (C) 2005-2007 Takahiro Hirofuchi
+ */
+
+#ifndef __VHCI_DRIVER_H
+#define __VHCI_DRIVER_H
+
+#include <libudev.h>
+#include <stdint.h>
+
+#include "usbip_common.h"
+
+#define USBIP_VHCI_BUS_TYPE "platform"
+#define MAXNPORT 128
+
+struct usbip_imported_device {
+        uint8_t port;
+        uint32_t status;
+
+        uint32_t devid;
+
+        uint8_t busnum;
+        uint8_t devnum;
+
+        /* usbip_class_device list */
+        struct usbip_usb_device udev;
+};
+
+struct usbip_vhci_driver {
+
+        /* /sys/devices/platform/vhci_hcd */
+        struct udev_device *hc_device;
+
+        int nports;
+        struct usbip_imported_device idev[MAXNPORT];
+};
+
+
+extern struct usbip_vhci_driver *vhci_driver;
+
+int usbip_vhci_driver_open(void);
+void usbip_vhci_driver_close(void);
+
+int  usbip_vhci_refresh_device_list(void);
+
+
+int usbip_vhci_get_free_port(void);
+int usbip_vhci_attach_device2(uint8_t port, int sockfd, uint32_t devid,
+                uint32_t speed);
+
+/* will be removed */
+int usbip_vhci_attach_device(uint8_t port, int sockfd, uint8_t busnum,
+                uint8_t devnum, uint32_t speed);
+
+int usbip_vhci_detach_device(uint8_t port);
+
+int usbip_vhci_imported_device_dump(struct usbip_imported_device *idev);
+
+#endif /* __VHCI_DRIVER_H */
diff --git a/tools/usb/usbip/src/Makefile.am b/tools/usb/usbip/src/Makefile.am
new file mode 100644
index 000000000000..e81a4ebadeff
--- /dev/null
+++ b/tools/usb/usbip/src/Makefile.am
@@ -0,0 +1,11 @@
+AM_CPPFLAGS = -I$(top_srcdir)/libsrc -DUSBIDS_FILE='"@USBIDS_DIR@/usb.ids"'
+AM_CFLAGS   = @EXTRA_CFLAGS@
+LDADD       = $(top_builddir)/libsrc/libusbip.la
+
+sbin_PROGRAMS := usbip usbipd
+
+usbip_SOURCES := usbip.h utils.h usbip.c utils.c usbip_network.c \
+                 usbip_attach.c usbip_detach.c usbip_list.c \
+                 usbip_bind.c usbip_unbind.c usbip_port.c
+
+usbipd_SOURCES := usbip_network.h usbipd.c usbip_network.c
diff --git a/tools/usb/usbip/src/usbip.c b/tools/usb/usbip/src/usbip.c
new file mode 100644
index 000000000000..d7599d943529
--- /dev/null
+++ b/tools/usb/usbip/src/usbip.c
@@ -0,0 +1,201 @@
+/*
+ * command structure borrowed from udev
+ * (git://git.kernel.org/pub/scm/linux/hotplug/udev.git)
+ *
+ * Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
+ *               2005-2007 Takahiro Hirofuchi
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+#include <getopt.h>
+#include <syslog.h>
+
+#include "usbip_common.h"
+#include "usbip_network.h"
+#include "usbip.h"
+
+static int usbip_help(int argc, char *argv[]);
+static int usbip_version(int argc, char *argv[]);
+
+static const char usbip_version_string[] = PACKAGE_STRING;
+
+static const char usbip_usage_string[] =
+        "usbip [--debug] [--log] [--tcp-port PORT] [version]\n"
+        "             [help] <command> <args>\n";
+
+static void usbip_usage(void)
+{
+        printf("usage: %s", usbip_usage_string);
+}
+
+struct command {
+        const char *name;
+        int (*fn)(int argc, char *argv[]);
+        const char *help;
+        void (*usage)(void);
+};
+
+static const struct command cmds[] = {
+        {
+                .name  = "help",
+                .fn    = usbip_help,
+                .help  = NULL,
+                .usage = NULL
+        },
+        {
+                .name  = "version",
+                .fn    = usbip_version,
+                .help  = NULL,
+                .usage = NULL
+        },
+        {
+                .name  = "attach",
+                .fn    = usbip_attach,
+                .help  = "Attach a remote USB device",
+                .usage = usbip_attach_usage
+        },
+        {
+                .name  = "detach",
+                .fn    = usbip_detach,
+                .help  = "Detach a remote USB device",
+                .usage = usbip_detach_usage
+        },
+        {
+                .name  = "list",
+                .fn    = usbip_list,
+                .help  = "List exportable or local USB devices",
+                .usage = usbip_list_usage
+        },
+        {
+                .name  = "bind",
+                .fn    = usbip_bind,
+                .help  = "Bind device to " USBIP_HOST_DRV_NAME ".ko",
+                .usage = usbip_bind_usage
+        },
+        {
+                .name  = "unbind",
+                .fn    = usbip_unbind,
+                .help  = "Unbind device from " USBIP_HOST_DRV_NAME ".ko",
+                .usage = usbip_unbind_usage
+        },
+        {
+                .name  = "port",
+                .fn    = usbip_port_show,
+                .help  = "Show imported USB devices",
+                .usage = NULL
+        },
+        { NULL, NULL, NULL, NULL }
+};
+
+static int usbip_help(int argc, char *argv[])
+{
+        const struct command *cmd;
+        int i;
+        int ret = 0;
+
+        if (argc > 1 && argv++) {
+                for (i = 0; cmds[i].name != NULL; i++)
+                        if (!strcmp(cmds[i].name, argv[0]) && cmds[i].usage) {
+                                cmds[i].usage();
+                                goto done;
+                        }
+                ret = -1;
+        }
+
+        usbip_usage();
+        printf("\n");
+        for (cmd = cmds; cmd->name != NULL; cmd++)
+                if (cmd->help != NULL)
+                        printf("  %-10s %s\n", cmd->name, cmd->help);
+        printf("\n");
+done:
+        return ret;
+}
+
+static int usbip_version(int argc, char *argv[])
+{
+        (void) argc;
+        (void) argv;
+
+        printf(PROGNAME " (%s)\n", usbip_version_string);
+        return 0;
+}
+
+static int run_command(const struct command *cmd, int argc, char *argv[])
+{
+        dbg("running command: `%s'", cmd->name);
+        return cmd->fn(argc, argv);
+}
+
+int main(int argc, char *argv[])
+{
+        static const struct option opts[] = {
+                { "debug",    no_argument,       NULL, 'd' },
+                { "log",      no_argument,       NULL, 'l' },
+                { "tcp-port", required_argument, NULL, 't' },
+                { NULL,       0,                 NULL,  0  }
+        };
+
+        char *cmd;
+        int opt;
+        int i, rc = -1;
+
+        usbip_use_stderr = 1;
+        opterr = 0;
+        for (;;) {
+                opt = getopt_long(argc, argv, "+dlt:", opts, NULL);
+
+                if (opt == -1)
+                        break;
+
+                switch (opt) {
+                case 'd':
+                        usbip_use_debug = 1;
+                        break;
+                case 'l':
+                        usbip_use_syslog = 1;
+                        openlog("", LOG_PID, LOG_USER);
+                        break;
+                case 't':
+                        usbip_setup_port_number(optarg);
+                        break;
+                case '?':
+                        printf("usbip: invalid option\n");
+                default:
+                        usbip_usage();
+                        goto out;
+                }
+        }
+
+        cmd = argv[optind];
+        if (cmd) {
+                for (i = 0; cmds[i].name != NULL; i++)
+                        if (!strcmp(cmds[i].name, cmd)) {
+                                argc -= optind;
+                                argv += optind;
+                                optind = 0;
+                                rc = run_command(&cmds[i], argc, argv);
+                                goto out;
+                        }
+        }
+
+        /* invalid command */
+        usbip_help(0, NULL);
+out:
+        return (rc > -1 ? EXIT_SUCCESS : EXIT_FAILURE);
+}
diff --git a/tools/usb/usbip/src/usbip.h b/tools/usb/usbip/src/usbip.h
new file mode 100644
index 000000000000..84fe66a9d8ad
--- /dev/null
+++ b/tools/usb/usbip/src/usbip.h
@@ -0,0 +1,40 @@
+/*
+ * Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
+ *               2005-2007 Takahiro Hirofuchi
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __USBIP_H
+#define __USBIP_H
+
+#ifdef HAVE_CONFIG_H
+#include "../config.h"
+#endif
+
+/* usbip commands */
+int usbip_attach(int argc, char *argv[]);
+int usbip_detach(int argc, char *argv[]);
+int usbip_list(int argc, char *argv[]);
+int usbip_bind(int argc, char *argv[]);
+int usbip_unbind(int argc, char *argv[]);
+int usbip_port_show(int argc, char *argv[]);
+
+void usbip_attach_usage(void);
+void usbip_detach_usage(void);
+void usbip_list_usage(void);
+void usbip_bind_usage(void);
+void usbip_unbind_usage(void);
+
+#endif /* __USBIP_H */
diff --git a/tools/usb/usbip/src/usbip_attach.c b/tools/usb/usbip/src/usbip_attach.c
new file mode 100644
index 000000000000..d58a14dfc094
--- /dev/null
+++ b/tools/usb/usbip/src/usbip_attach.c
@@ -0,0 +1,241 @@
+/*
+ * Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
+ *               2005-2007 Takahiro Hirofuchi
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <sys/stat.h>
+
+#include <limits.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <string.h>
+
+#include <fcntl.h>
+#include <getopt.h>
+#include <unistd.h>
+#include <errno.h>
+
+#include "vhci_driver.h"
+#include "usbip_common.h"
+#include "usbip_network.h"
+#include "usbip.h"
+
+static const char usbip_attach_usage_string[] =
+        "usbip attach <args>\n"
+        "    -r, --remote=<host>      The machine with exported USB devices\n"
+        "    -b, --busid=<busid>    Busid of the device on <host>\n";
+
+void usbip_attach_usage(void)
+{
+        printf("usage: %s", usbip_attach_usage_string);
+}
+
+#define MAX_BUFF 100
+static int record_connection(char *host, char *port, char *busid, int rhport)
+{
+        int fd;
+        char path[PATH_MAX+1];
+        char buff[MAX_BUFF+1];
+        int ret;
+
+        ret = mkdir(VHCI_STATE_PATH, 0700);
+        if (ret < 0) {
+                /* if VHCI_STATE_PATH exists, then it better be a directory */
+                if (errno == EEXIST) {
+                        struct stat s;
+
+                        ret = stat(VHCI_STATE_PATH, &s);
+                        if (ret < 0)
+                                return -1;
+                        if (!(s.st_mode & S_IFDIR))
+                                return -1;
+                } else
+                        return -1;
+        }
+
+        snprintf(path, PATH_MAX, VHCI_STATE_PATH"/port%d", rhport);
+
+        fd = open(path, O_WRONLY|O_CREAT|O_TRUNC, S_IRWXU);
+        if (fd < 0)
+                return -1;
+
+        snprintf(buff, MAX_BUFF, "%s %s %s\n",
+                        host, port, busid);
+
+        ret = write(fd, buff, strlen(buff));
+        if (ret != (ssize_t) strlen(buff)) {
+                close(fd);
+                return -1;
+        }
+
+        close(fd);
+
+        return 0;
+}
+
+static int import_device(int sockfd, struct usbip_usb_device *udev)
+{
+        int rc;
+        int port;
+
+        rc = usbip_vhci_driver_open();
+        if (rc < 0) {
+                err("open vhci_driver");
+                return -1;
+        }
+
+        port = usbip_vhci_get_free_port();
+        if (port < 0) {
+                err("no free port");
+                usbip_vhci_driver_close();
+                return -1;
+        }
+
+        rc = usbip_vhci_attach_device(port, sockfd, udev->busnum,
+                                      udev->devnum, udev->speed);
+        if (rc < 0) {
+                err("import device");
+                usbip_vhci_driver_close();
+                return -1;
+        }
+
+        usbip_vhci_driver_close();
+
+        return port;
+}
+
+static int query_import_device(int sockfd, char *busid)
+{
+        int rc;
+        struct op_import_request request;
+        struct op_import_reply   reply;
+        uint16_t code = OP_REP_IMPORT;
+
+        memset(&request, 0, sizeof(request));
+        memset(&reply, 0, sizeof(reply));
+
+        /* send a request */
+        rc = usbip_net_send_op_common(sockfd, OP_REQ_IMPORT, 0);
+        if (rc < 0) {
+                err("send op_common");
+                return -1;
+        }
+
+        strncpy(request.busid, busid, SYSFS_BUS_ID_SIZE-1);
+
+        PACK_OP_IMPORT_REQUEST(0, &request);
+
+        rc = usbip_net_send(sockfd, (void *) &request, sizeof(request));
+        if (rc < 0) {
+                err("send op_import_request");
+                return -1;
+        }
+
+        /* receive a reply */
+        rc = usbip_net_recv_op_common(sockfd, &code);
+        if (rc < 0) {
+                err("recv op_common");
+                return -1;
+        }
+
+        rc = usbip_net_recv(sockfd, (void *) &reply, sizeof(reply));
+        if (rc < 0) {
+                err("recv op_import_reply");
+                return -1;
+        }
+
+        PACK_OP_IMPORT_REPLY(0, &reply);
+
+        /* check the reply */
+        if (strncmp(reply.udev.busid, busid, SYSFS_BUS_ID_SIZE)) {
+                err("recv different busid %s", reply.udev.busid);
+                return -1;
+        }
+
+        /* import a device */
+        return import_device(sockfd, &reply.udev);
+}
+
+static int attach_device(char *host, char *busid)
+{
+        int sockfd;
+        int rc;
+        int rhport;
+
+        sockfd = usbip_net_tcp_connect(host, usbip_port_string);
+        if (sockfd < 0) {
+                err("tcp connect");
+                return -1;
+        }
+
+        rhport = query_import_device(sockfd, busid);
+        if (rhport < 0) {
+                err("query");
+                return -1;
+        }
+
+        close(sockfd);
+
+        rc = record_connection(host, usbip_port_string, busid, rhport);
+        if (rc < 0) {
+                err("record connection");
+                return -1;
+        }
+
+        return 0;
+}
+
+int usbip_attach(int argc, char *argv[])
+{
+        static const struct option opts[] = {
+                { "remote", required_argument, NULL, 'r' },
+                { "busid",  required_argument, NULL, 'b' },
+                { NULL, 0,  NULL, 0 }
+        };
+        char *host = NULL;
+        char *busid = NULL;
+        int opt;
+        int ret = -1;
+
+        for (;;) {
+                opt = getopt_long(argc, argv, "r:b:", opts, NULL);
+
+                if (opt == -1)
+                        break;
+
+                switch (opt) {
+                case 'r':
+                        host = optarg;
+                        break;
+                case 'b':
+                        busid = optarg;
+                        break;
+                default:
+                        goto err_out;
+                }
+        }
+
+        if (!host || !busid)
+                goto err_out;
+
+        ret = attach_device(host, busid);
+        goto out;
+
+err_out:
+        usbip_attach_usage();
+out:
+        return ret;
+}
diff --git a/tools/usb/usbip/src/usbip_bind.c b/tools/usb/usbip/src/usbip_bind.c
new file mode 100644
index 000000000000..fa46141ae68b
--- /dev/null
+++ b/tools/usb/usbip/src/usbip_bind.c
@@ -0,0 +1,214 @@
+/*
+ * Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
+ *               2005-2007 Takahiro Hirofuchi
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <libudev.h>
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <getopt.h>
+
+#include "usbip_common.h"
+#include "utils.h"
+#include "usbip.h"
+#include "sysfs_utils.h"
+
+enum unbind_status {
+        UNBIND_ST_OK,
+        UNBIND_ST_USBIP_HOST,
+        UNBIND_ST_FAILED
+};
+
+static const char usbip_bind_usage_string[] =
+        "usbip bind <args>\n"
+        "    -b, --busid=<busid>    Bind " USBIP_HOST_DRV_NAME ".ko to device "
+        "on <busid>\n";
+
+void usbip_bind_usage(void)
+{
+        printf("usage: %s", usbip_bind_usage_string);
+}
+
+/* call at unbound state */
+static int bind_usbip(char *busid)
+{
+        char attr_name[] = "bind";
+        char bind_attr_path[SYSFS_PATH_MAX];
+        int rc = -1;
+
+        snprintf(bind_attr_path, sizeof(bind_attr_path), "%s/%s/%s/%s/%s/%s",
+                 SYSFS_MNT_PATH, SYSFS_BUS_NAME, SYSFS_BUS_TYPE,
+                 SYSFS_DRIVERS_NAME, USBIP_HOST_DRV_NAME, attr_name);
+
+        rc = write_sysfs_attribute(bind_attr_path, busid, strlen(busid));
+        if (rc < 0) {
+                err("error binding device %s to driver: %s", busid,
+                    strerror(errno));
+                return -1;
+        }
+
+        return 0;
+}
+
+/* buggy driver may cause dead lock */
+static int unbind_other(char *busid)
+{
+        enum unbind_status status = UNBIND_ST_OK;
+
+        char attr_name[] = "unbind";
+        char unbind_attr_path[SYSFS_PATH_MAX];
+        int rc = -1;
+
+        struct udev *udev;
+        struct udev_device *dev;
+        const char *driver;
+        const char *bDevClass;
+
+        /* Create libudev context. */
+        udev = udev_new();
+
+        /* Get the device. */
+        dev = udev_device_new_from_subsystem_sysname(udev, "usb", busid);
+        if (!dev) {
+                dbg("unable to find device with bus ID %s", busid);
+                goto err_close_busid_dev;
+        }
+
+        /* Check what kind of device it is. */
+        bDevClass  = udev_device_get_sysattr_value(dev, "bDeviceClass");
+        if (!bDevClass) {
+                dbg("unable to get bDevClass device attribute");
+                goto err_close_busid_dev;
+        }
+
+        if (!strncmp(bDevClass, "09", strlen(bDevClass))) {
+                dbg("skip unbinding of hub");
+                goto err_close_busid_dev;
+        }
+
+        /* Get the device driver. */
+        driver = udev_device_get_driver(dev);
+        if (!driver) {
+                /* No driver bound to this device. */
+                goto out;
+        }
+
+        if (!strncmp(USBIP_HOST_DRV_NAME, driver,
+                                strlen(USBIP_HOST_DRV_NAME))) {
+                /* Already bound to usbip-host. */
+                status = UNBIND_ST_USBIP_HOST;
+                goto out;
+        }
+
+        /* Unbind device from driver. */
+        snprintf(unbind_attr_path, sizeof(unbind_attr_path), "%s/%s/%s/%s/%s/%s",
+                 SYSFS_MNT_PATH, SYSFS_BUS_NAME, SYSFS_BUS_TYPE,
+                 SYSFS_DRIVERS_NAME, driver, attr_name);
+
+        rc = write_sysfs_attribute(unbind_attr_path, busid, strlen(busid));
+        if (rc < 0) {
+                err("error unbinding device %s from driver", busid);
+                goto err_close_busid_dev;
+        }
+
+        goto out;
+
+err_close_busid_dev:
+        status = UNBIND_ST_FAILED;
+out:
+        udev_device_unref(dev);
+        udev_unref(udev);
+
+        return status;
+}
+
+static int bind_device(char *busid)
+{
+        int rc;
+        struct udev *udev;
+        struct udev_device *dev;
+
+        /* Check whether the device with this bus ID exists. */
+        udev = udev_new();
+        dev = udev_device_new_from_subsystem_sysname(udev, "usb", busid);
+        if (!dev) {
+                err("device with the specified bus ID does not exist");
+                return -1;
+        }
+        udev_unref(udev);
+
+        rc = unbind_other(busid);
+        if (rc == UNBIND_ST_FAILED) {
+                err("could not unbind driver from device on busid %s", busid);
+                return -1;
+        } else if (rc == UNBIND_ST_USBIP_HOST) {
+                err("device on busid %s is already bound to %s", busid,
+                    USBIP_HOST_DRV_NAME);
+                return -1;
+        }
+
+        rc = modify_match_busid(busid, 1);
+        if (rc < 0) {
+                err("unable to bind device on %s", busid);
+                return -1;
+        }
+
+        rc = bind_usbip(busid);
+        if (rc < 0) {
+                err("could not bind device to %s", USBIP_HOST_DRV_NAME);
+                modify_match_busid(busid, 0);
+                return -1;
+        }
+
+        info("bind device on busid %s: complete", busid);
+
+        return 0;
+}
+
+int usbip_bind(int argc, char *argv[])
+{
+        static const struct option opts[] = {
+                { "busid", required_argument, NULL, 'b' },
+                { NULL,    0,                 NULL,  0  }
+        };
+
+        int opt;
+        int ret = -1;
+
+        for (;;) {
+                opt = getopt_long(argc, argv, "b:", opts, NULL);
+
+                if (opt == -1)
+                        break;
+
+                switch (opt) {
+                case 'b':
+                        ret = bind_device(optarg);
+                        goto out;
+                default:
+                        goto err_out;
+                }
+        }
+
+err_out:
+        usbip_bind_usage();
+out:
+        return ret;
+}
diff --git a/tools/usb/usbip/src/usbip_detach.c b/tools/usb/usbip/src/usbip_detach.c
new file mode 100644
index 000000000000..05c6d15856eb
--- /dev/null
+++ b/tools/usb/usbip/src/usbip_detach.c
@@ -0,0 +1,110 @@
+/*
+ * Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
+ *               2005-2007 Takahiro Hirofuchi
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <ctype.h>
+#include <limits.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <getopt.h>
+#include <unistd.h>
+
+#include "vhci_driver.h"
+#include "usbip_common.h"
+#include "usbip_network.h"
+#include "usbip.h"
+
+static const char usbip_detach_usage_string[] =
+        "usbip detach <args>\n"
+        "    -p, --port=<port>    " USBIP_VHCI_DRV_NAME
+        " port the device is on\n";
+
+void usbip_detach_usage(void)
+{
+        printf("usage: %s", usbip_detach_usage_string);
+}
+
+static int detach_port(char *port)
+{
+        int ret;
+        uint8_t portnum;
+        char path[PATH_MAX+1];
+
+        for (unsigned int i = 0; i < strlen(port); i++)
+                if (!isdigit(port[i])) {
+                        err("invalid port %s", port);
+                        return -1;
+                }
+
+        /* check max port */
+
+        portnum = atoi(port);
+
+        /* remove the port state file */
+
+        snprintf(path, PATH_MAX, VHCI_STATE_PATH"/port%d", portnum);
+
+        remove(path);
+        rmdir(VHCI_STATE_PATH);
+
+        ret = usbip_vhci_driver_open();
+        if (ret < 0) {
+                err("open vhci_driver");
+                return -1;
+        }
+
+        ret = usbip_vhci_detach_device(portnum);
+        if (ret < 0)
+                return -1;
+
+        usbip_vhci_driver_close();
+
+        return ret;
+}
+
+int usbip_detach(int argc, char *argv[])
+{
+        static const struct option opts[] = {
+                { "port", required_argument, NULL, 'p' },
+                { NULL, 0, NULL, 0 }
+        };
+        int opt;
+        int ret = -1;
+
+        for (;;) {
+                opt = getopt_long(argc, argv, "p:", opts, NULL);
+
+                if (opt == -1)
+                        break;
+
+                switch (opt) {
+                case 'p':
+                        ret = detach_port(optarg);
+                        goto out;
+                default:
+                        goto err_out;
+                }
+        }
+
+err_out:
+        usbip_detach_usage();
+out:
+        return ret;
+}
diff --git a/tools/usb/usbip/src/usbip_list.c b/tools/usb/usbip/src/usbip_list.c
new file mode 100644
index 000000000000..d5ce34a410e7
--- /dev/null
+++ b/tools/usb/usbip/src/usbip_list.c
@@ -0,0 +1,283 @@
+/*
+ * Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
+ *               2005-2007 Takahiro Hirofuchi
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <sys/types.h>
+#include <libudev.h>
+
+#include <errno.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <getopt.h>
+#include <netdb.h>
+#include <unistd.h>
+
+#include "usbip_common.h"
+#include "usbip_network.h"
+#include "usbip.h"
+
+static const char usbip_list_usage_string[] =
+        "usbip list [-p|--parsable] <args>\n"
+        "    -p, --parsable         Parsable list format\n"
+        "    -r, --remote=<host>    List the exportable USB devices on <host>\n"
+        "    -l, --local            List the local USB devices\n";
+
+void usbip_list_usage(void)
+{
+        printf("usage: %s", usbip_list_usage_string);
+}
+
+static int get_exported_devices(char *host, int sockfd)
+{
+        char product_name[100];
+        char class_name[100];
+        struct op_devlist_reply reply;
+        uint16_t code = OP_REP_DEVLIST;
+        struct usbip_usb_device udev;
+        struct usbip_usb_interface uintf;
+        unsigned int i;
+        int rc, j;
+
+        rc = usbip_net_send_op_common(sockfd, OP_REQ_DEVLIST, 0);
+        if (rc < 0) {
+                dbg("usbip_net_send_op_common failed");
+                return -1;
+        }
+
+        rc = usbip_net_recv_op_common(sockfd, &code);
+        if (rc < 0) {
+                dbg("usbip_net_recv_op_common failed");
+                return -1;
+        }
+
+        memset(&reply, 0, sizeof(reply));
+        rc = usbip_net_recv(sockfd, &reply, sizeof(reply));
+        if (rc < 0) {
+                dbg("usbip_net_recv_op_devlist failed");
+                return -1;
+        }
+        PACK_OP_DEVLIST_REPLY(0, &reply);
+        dbg("exportable devices: %d\n", reply.ndev);
+
+        if (reply.ndev == 0) {
+                info("no exportable devices found on %s", host);
+                return 0;
+        }
+
+        printf("Exportable USB devices\n");
+        printf("======================\n");
+        printf(" - %s\n", host);
+
+        for (i = 0; i < reply.ndev; i++) {
+                memset(&udev, 0, sizeof(udev));
+                rc = usbip_net_recv(sockfd, &udev, sizeof(udev));
+                if (rc < 0) {
+                        dbg("usbip_net_recv failed: usbip_usb_device[%d]", i);
+                        return -1;
+                }
+                usbip_net_pack_usb_device(0, &udev);
+
+                usbip_names_get_product(product_name, sizeof(product_name),
+                                        udev.idVendor, udev.idProduct);
+                usbip_names_get_class(class_name, sizeof(class_name),
+                                      udev.bDeviceClass, udev.bDeviceSubClass,
+                                      udev.bDeviceProtocol);
+                printf("%11s: %s\n", udev.busid, product_name);
+                printf("%11s: %s\n", "", udev.path);
+                printf("%11s: %s\n", "", class_name);
+
+                for (j = 0; j < udev.bNumInterfaces; j++) {
+                        rc = usbip_net_recv(sockfd, &uintf, sizeof(uintf));
+                        if (rc < 0) {
+                                err("usbip_net_recv failed: usbip_usb_intf[%d]",
+                                                j);
+
+                                return -1;
+                        }
+                        usbip_net_pack_usb_interface(0, &uintf);
+
+                        usbip_names_get_class(class_name, sizeof(class_name),
+                                        uintf.bInterfaceClass,
+                                        uintf.bInterfaceSubClass,
+                                        uintf.bInterfaceProtocol);
+                        printf("%11s: %2d - %s\n", "", j, class_name);
+                }
+
+                printf("\n");
+        }
+
+        return 0;
+}
+
+static int list_exported_devices(char *host)
+{
+        int rc;
+        int sockfd;
+
+        sockfd = usbip_net_tcp_connect(host, usbip_port_string);
+        if (sockfd < 0) {
+                err("could not connect to %s:%s: %s", host,
+                    usbip_port_string, gai_strerror(sockfd));
+                return -1;
+        }
+        dbg("connected to %s:%s", host, usbip_port_string);
+
+        rc = get_exported_devices(host, sockfd);
+        if (rc < 0) {
+                err("failed to get device list from %s", host);
+                return -1;
+        }
+
+        close(sockfd);
+
+        return 0;
+}
+
+static void print_device(const char *busid, const char *vendor,
+                         const char *product, bool parsable)
+{
+        if (parsable)
+                printf("busid=%s#usbid=%.4s:%.4s#", busid, vendor, product);
+        else
+                printf(" - busid %s (%.4s:%.4s)\n", busid, vendor, product);
+}
+
+static void print_product_name(char *product_name, bool parsable)
+{
+        if (!parsable)
+                printf("   %s\n", product_name);
+}
+
+static int list_devices(bool parsable)
+{
+        struct udev *udev;
+        struct udev_enumerate *enumerate;
+        struct udev_list_entry *devices, *dev_list_entry;
+        struct udev_device *dev;
+        const char *path;
+        const char *idVendor;
+        const char *idProduct;
+        const char *bConfValue;
+        const char *bNumIntfs;
+        const char *busid;
+        char product_name[128];
+        int ret = -1;
+
+        /* Create libudev context. */
+        udev = udev_new();
+
+        /* Create libudev device enumeration. */
+        enumerate = udev_enumerate_new(udev);
+
+        /* Take only USB devices that are not hubs and do not have
+         * the bInterfaceNumber attribute, i.e. are not interfaces.
+         */
+        udev_enumerate_add_match_subsystem(enumerate, "usb");
+        udev_enumerate_add_nomatch_sysattr(enumerate, "bDeviceClass", "09");
+        udev_enumerate_add_nomatch_sysattr(enumerate, "bInterfaceNumber", NULL);
+        udev_enumerate_scan_devices(enumerate);
+
+        devices = udev_enumerate_get_list_entry(enumerate);
+
+        /* Show information about each device. */
+        udev_list_entry_foreach(dev_list_entry, devices) {
+                path = udev_list_entry_get_name(dev_list_entry);
+                dev = udev_device_new_from_syspath(udev, path);
+
+                /* Get device information. */
+                idVendor = udev_device_get_sysattr_value(dev, "idVendor");
+                idProduct = udev_device_get_sysattr_value(dev, "idProduct");
+                bConfValue = udev_device_get_sysattr_value(dev, "bConfigurationValue");
+                bNumIntfs = udev_device_get_sysattr_value(dev, "bNumInterfaces");
+                busid = udev_device_get_sysname(dev);
+                if (!idVendor || !idProduct || !bConfValue || !bNumIntfs) {
+                        err("problem getting device attributes: %s",
+                            strerror(errno));
+                        goto err_out;
+                }
+
+                /* Get product name. */
+                usbip_names_get_product(product_name, sizeof(product_name),
+                                        strtol(idVendor, NULL, 16),
+                                        strtol(idProduct, NULL, 16));
+
+                /* Print information. */
+                print_device(busid, idVendor, idProduct, parsable);
+                print_product_name(product_name, parsable);
+
+                printf("\n");
+
+                udev_device_unref(dev);
+        }
+
+        ret = 0;
+
+err_out:
+        udev_enumerate_unref(enumerate);
+        udev_unref(udev);
+
+        return ret;
+}
+
+int usbip_list(int argc, char *argv[])
+{
+        static const struct option opts[] = {
+                { "parsable", no_argument,       NULL, 'p' },
+                { "remote",   required_argument, NULL, 'r' },
+                { "local",    no_argument,       NULL, 'l' },
+                { NULL,       0,                 NULL,  0  }
+        };
+
+        bool parsable = false;
+        int opt;
+        int ret = -1;
+
+        if (usbip_names_init(USBIDS_FILE))
+                err("failed to open %s", USBIDS_FILE);
+
+        for (;;) {
+                opt = getopt_long(argc, argv, "pr:l", opts, NULL);
+
+                if (opt == -1)
+                        break;
+
+                switch (opt) {
+                case 'p':
+                        parsable = true;
+                        break;
+                case 'r':
+                        ret = list_exported_devices(optarg);
+                        goto out;
+                case 'l':
+                        ret = list_devices(parsable);
+                        goto out;
+                default:
+                        goto err_out;
+                }
+        }
+
+err_out:
+        usbip_list_usage();
+out:
+        usbip_names_free();
+
+        return ret;
+}
diff --git a/tools/usb/usbip/src/usbip_network.c b/tools/usb/usbip/src/usbip_network.c
new file mode 100644
index 000000000000..b4c37e76a6e0
--- /dev/null
+++ b/tools/usb/usbip/src/usbip_network.c
@@ -0,0 +1,303 @@
+/*
+ * Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
+ *               2005-2007 Takahiro Hirofuchi
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <sys/socket.h>
+
+#include <string.h>
+
+#include <arpa/inet.h>
+#include <netdb.h>
+#include <netinet/tcp.h>
+#include <unistd.h>
+
+#ifdef HAVE_LIBWRAP
+#include <tcpd.h>
+#endif
+
+#include "usbip_common.h"
+#include "usbip_network.h"
+
+int usbip_port = 3240;
+char *usbip_port_string = "3240";
+
+void usbip_setup_port_number(char *arg)
+{
+        dbg("parsing port arg '%s'", arg);
+        char *end;
+        unsigned long int port = strtoul(arg, &end, 10);
+
+        if (end == arg) {
+                err("port: could not parse '%s' as a decimal integer", arg);
+                return;
+        }
+
+        if (*end != '\0') {
+                err("port: garbage at end of '%s'", arg);
+                return;
+        }
+
+        if (port > UINT16_MAX) {
+                err("port: %s too high (max=%d)",
+                    arg, UINT16_MAX);
+                return;
+        }
+
+        usbip_port = port;
+        usbip_port_string = arg;
+        info("using port %d (\"%s\")", usbip_port, usbip_port_string);
+}
+
+void usbip_net_pack_uint32_t(int pack, uint32_t *num)
+{
+        uint32_t i;
+
+        if (pack)
+                i = htonl(*num);
+        else
+                i = ntohl(*num);
+
+        *num = i;
+}
+
+void usbip_net_pack_uint16_t(int pack, uint16_t *num)
+{
+        uint16_t i;
+
+        if (pack)
+                i = htons(*num);
+        else
+                i = ntohs(*num);
+
+        *num = i;
+}
+
+void usbip_net_pack_usb_device(int pack, struct usbip_usb_device *udev)
+{
+        usbip_net_pack_uint32_t(pack, &udev->busnum);
+        usbip_net_pack_uint32_t(pack, &udev->devnum);
+        usbip_net_pack_uint32_t(pack, &udev->speed);
+
+        usbip_net_pack_uint16_t(pack, &udev->idVendor);
+        usbip_net_pack_uint16_t(pack, &udev->idProduct);
+        usbip_net_pack_uint16_t(pack, &udev->bcdDevice);
+}
+
+void usbip_net_pack_usb_interface(int pack __attribute__((unused)),
+                                  struct usbip_usb_interface *udev
+                                  __attribute__((unused)))
+{
+        /* uint8_t members need nothing */
+}
+
+static ssize_t usbip_net_xmit(int sockfd, void *buff, size_t bufflen,
+                              int sending)
+{
+        ssize_t nbytes;
+        ssize_t total = 0;
+
+        if (!bufflen)
+                return 0;
+
+        do {
+                if (sending)
+                        nbytes = send(sockfd, buff, bufflen, 0);
+                else
+                        nbytes = recv(sockfd, buff, bufflen, MSG_WAITALL);
+
+                if (nbytes <= 0)
+                        return -1;
+
+                buff     = (void *)((intptr_t) buff + nbytes);
+                bufflen -= nbytes;
+                total   += nbytes;
+
+        } while (bufflen > 0);
+
+        return total;
+}
+
+ssize_t usbip_net_recv(int sockfd, void *buff, size_t bufflen)
+{
+        return usbip_net_xmit(sockfd, buff, bufflen, 0);
+}
+
+ssize_t usbip_net_send(int sockfd, void *buff, size_t bufflen)
+{
+        return usbip_net_xmit(sockfd, buff, bufflen, 1);
+}
+
+int usbip_net_send_op_common(int sockfd, uint32_t code, uint32_t status)
+{
+        struct op_common op_common;
+        int rc;
+
+        memset(&op_common, 0, sizeof(op_common));
+
+        op_common.version = USBIP_VERSION;
+        op_common.code    = code;
+        op_common.status  = status;
+
+        PACK_OP_COMMON(1, &op_common);
+
+        rc = usbip_net_send(sockfd, &op_common, sizeof(op_common));
+        if (rc < 0) {
+                dbg("usbip_net_send failed: %d", rc);
+                return -1;
+        }
+
+        return 0;
+}
+
+int usbip_net_recv_op_common(int sockfd, uint16_t *code)
+{
+        struct op_common op_common;
+        int rc;
+
+        memset(&op_common, 0, sizeof(op_common));
+
+        rc = usbip_net_recv(sockfd, &op_common, sizeof(op_common));
+        if (rc < 0) {
+                dbg("usbip_net_recv failed: %d", rc);
+                goto err;
+        }
+
+        PACK_OP_COMMON(0, &op_common);
+
+        if (op_common.version != USBIP_VERSION) {
+                dbg("version mismatch: %d %d", op_common.version,
+                    USBIP_VERSION);
+                goto err;
+        }
+
+        switch (*code) {
+        case OP_UNSPEC:
+                break;
+        default:
+                if (op_common.code != *code) {
+                        dbg("unexpected pdu %#0x for %#0x", op_common.code,
+                            *code);
+                        goto err;
+                }
+        }
+
+        if (op_common.status != ST_OK) {
+                dbg("request failed at peer: %d", op_common.status);
+                goto err;
+        }
+
+        *code = op_common.code;
+
+        return 0;
+err:
+        return -1;
+}
+
+int usbip_net_set_reuseaddr(int sockfd)
+{
+        const int val = 1;
+        int ret;
+
+        ret = setsockopt(sockfd, SOL_SOCKET, SO_REUSEADDR, &val, sizeof(val));
+        if (ret < 0)
+                dbg("setsockopt: SO_REUSEADDR");
+
+        return ret;
+}
+
+int usbip_net_set_nodelay(int sockfd)
+{
+        const int val = 1;
+        int ret;
+
+        ret = setsockopt(sockfd, IPPROTO_TCP, TCP_NODELAY, &val, sizeof(val));
+        if (ret < 0)
+                dbg("setsockopt: TCP_NODELAY");
+
+        return ret;
+}
+
+int usbip_net_set_keepalive(int sockfd)
+{
+        const int val = 1;
+        int ret;
+
+        ret = setsockopt(sockfd, SOL_SOCKET, SO_KEEPALIVE, &val, sizeof(val));
+        if (ret < 0)
+                dbg("setsockopt: SO_KEEPALIVE");
+
+        return ret;
+}
+
+int usbip_net_set_v6only(int sockfd)
+{
+        const int val = 1;
+        int ret;
+
+        ret = setsockopt(sockfd, IPPROTO_IPV6, IPV6_V6ONLY, &val, sizeof(val));
+        if (ret < 0)
+                dbg("setsockopt: IPV6_V6ONLY");
+
+        return ret;
+}
+
+/*
+ * IPv6 Ready
+ */
+int usbip_net_tcp_connect(char *hostname, char *service)
+{
+        struct addrinfo hints, *res, *rp;
+        int sockfd;
+        int ret;
+
+        memset(&hints, 0, sizeof(hints));
+        hints.ai_family = AF_UNSPEC;
+        hints.ai_socktype = SOCK_STREAM;
+
+        /* get all possible addresses */
+        ret = getaddrinfo(hostname, service, &hints, &res);
+        if (ret < 0) {
+                dbg("getaddrinfo: %s service %s: %s", hostname, service,
+                    gai_strerror(ret));
+                return ret;
+        }
+
+        /* try the addresses */
+        for (rp = res; rp; rp = rp->ai_next) {
+                sockfd = socket(rp->ai_family, rp->ai_socktype,
+                                rp->ai_protocol);
+                if (sockfd < 0)
+                        continue;
+
+                /* should set TCP_NODELAY for usbip */
+                usbip_net_set_nodelay(sockfd);
+                /* TODO: write code for heartbeat */
+                usbip_net_set_keepalive(sockfd);
+
+                if (connect(sockfd, rp->ai_addr, rp->ai_addrlen) == 0)
+                        break;
+
+                close(sockfd);
+        }
+
+        freeaddrinfo(res);
+
+        if (!rp)
+                return EAI_SYSTEM;
+
+        return sockfd;
+}
diff --git a/tools/usb/usbip/src/usbip_network.h b/tools/usb/usbip/src/usbip_network.h
new file mode 100644
index 000000000000..c1e875cf1078
--- /dev/null
+++ b/tools/usb/usbip/src/usbip_network.h
@@ -0,0 +1,185 @@
+/*
+ * Copyright (C) 2005-2007 Takahiro Hirofuchi
+ */
+
+#ifndef __USBIP_NETWORK_H
+#define __USBIP_NETWORK_H
+
+#ifdef HAVE_CONFIG_H
+#include "../config.h"
+#endif
+
+#include <sys/types.h>
+
+#include <stdint.h>
+
+extern int usbip_port;
+extern char *usbip_port_string;
+void usbip_setup_port_number(char *arg);
+
+/* ---------------------------------------------------------------------- */
+/* Common header for all the kinds of PDUs. */
+struct op_common {
+        uint16_t version;
+
+#define OP_REQUEST      (0x80 << 8)
+#define OP_REPLY        (0x00 << 8)
+        uint16_t code;
+
+        /* add more error code */
+#define ST_OK   0x00
+#define ST_NA   0x01
+        uint32_t status; /* op_code status (for reply) */
+
+} __attribute__((packed));
+
+#define PACK_OP_COMMON(pack, op_common)  do {\
+        usbip_net_pack_uint16_t(pack, &(op_common)->version);\
+        usbip_net_pack_uint16_t(pack, &(op_common)->code);\
+        usbip_net_pack_uint32_t(pack, &(op_common)->status);\
+} while (0)
+
+/* ---------------------------------------------------------------------- */
+/* Dummy Code */
+#define OP_UNSPEC       0x00
+#define OP_REQ_UNSPEC   OP_UNSPEC
+#define OP_REP_UNSPEC   OP_UNSPEC
+
+/* ---------------------------------------------------------------------- */
+/* Retrieve USB device information. (still not used) */
+#define OP_DEVINFO      0x02
+#define OP_REQ_DEVINFO  (OP_REQUEST | OP_DEVINFO)
+#define OP_REP_DEVINFO  (OP_REPLY   | OP_DEVINFO)
+
+struct op_devinfo_request {
+        char busid[SYSFS_BUS_ID_SIZE];
+} __attribute__((packed));
+
+struct op_devinfo_reply {
+        struct usbip_usb_device udev;
+        struct usbip_usb_interface uinf[];
+} __attribute__((packed));
+
+/* ---------------------------------------------------------------------- */
+/* Import a remote USB device. */
+#define OP_IMPORT       0x03
+#define OP_REQ_IMPORT   (OP_REQUEST | OP_IMPORT)
+#define OP_REP_IMPORT   (OP_REPLY   | OP_IMPORT)
+
+struct op_import_request {
+        char busid[SYSFS_BUS_ID_SIZE];
+} __attribute__((packed));
+
+struct op_import_reply {
+        struct usbip_usb_device udev;
+//      struct usbip_usb_interface uinf[];
+} __attribute__((packed));
+
+#define PACK_OP_IMPORT_REQUEST(pack, request)  do {\
+} while (0)
+
+#define PACK_OP_IMPORT_REPLY(pack, reply)  do {\
+        usbip_net_pack_usb_device(pack, &(reply)->udev);\
+} while (0)
+
+/* ---------------------------------------------------------------------- */
+/* Export a USB device to a remote host. */
+#define OP_EXPORT       0x06
+#define OP_REQ_EXPORT   (OP_REQUEST | OP_EXPORT)
+#define OP_REP_EXPORT   (OP_REPLY   | OP_EXPORT)
+
+struct op_export_request {
+        struct usbip_usb_device udev;
+} __attribute__((packed));
+
+struct op_export_reply {
+        int returncode;
+} __attribute__((packed));
+
+
+#define PACK_OP_EXPORT_REQUEST(pack, request)  do {\
+        usbip_net_pack_usb_device(pack, &(request)->udev);\
+} while (0)
+
+#define PACK_OP_EXPORT_REPLY(pack, reply)  do {\
+} while (0)
+
+/* ---------------------------------------------------------------------- */
+/* un-Export a USB device from a remote host. */
+#define OP_UNEXPORT     0x07
+#define OP_REQ_UNEXPORT (OP_REQUEST | OP_UNEXPORT)
+#define OP_REP_UNEXPORT (OP_REPLY   | OP_UNEXPORT)
+
+struct op_unexport_request {
+        struct usbip_usb_device udev;
+} __attribute__((packed));
+
+struct op_unexport_reply {
+        int returncode;
+} __attribute__((packed));
+
+#define PACK_OP_UNEXPORT_REQUEST(pack, request)  do {\
+        usbip_net_pack_usb_device(pack, &(request)->udev);\
+} while (0)
+
+#define PACK_OP_UNEXPORT_REPLY(pack, reply)  do {\
+} while (0)
+
+/* ---------------------------------------------------------------------- */
+/* Negotiate IPSec encryption key. (still not used) */
+#define OP_CRYPKEY      0x04
+#define OP_REQ_CRYPKEY  (OP_REQUEST | OP_CRYPKEY)
+#define OP_REP_CRYPKEY  (OP_REPLY   | OP_CRYPKEY)
+
+struct op_crypkey_request {
+        /* 128bit key */
+        uint32_t key[4];
+} __attribute__((packed));
+
+struct op_crypkey_reply {
+        uint32_t __reserved;
+} __attribute__((packed));
+
+
+/* ---------------------------------------------------------------------- */
+/* Retrieve the list of exported USB devices. */
+#define OP_DEVLIST      0x05
+#define OP_REQ_DEVLIST  (OP_REQUEST | OP_DEVLIST)
+#define OP_REP_DEVLIST  (OP_REPLY   | OP_DEVLIST)
+
+struct op_devlist_request {
+} __attribute__((packed));
+
+struct op_devlist_reply {
+        uint32_t ndev;
+        /* followed by reply_extra[] */
+} __attribute__((packed));
+
+struct op_devlist_reply_extra {
+        struct usbip_usb_device    udev;
+        struct usbip_usb_interface uinf[];
+} __attribute__((packed));
+
+#define PACK_OP_DEVLIST_REQUEST(pack, request)  do {\
+} while (0)
+
+#define PACK_OP_DEVLIST_REPLY(pack, reply)  do {\
+        usbip_net_pack_uint32_t(pack, &(reply)->ndev);\
+} while (0)
+
+void usbip_net_pack_uint32_t(int pack, uint32_t *num);
+void usbip_net_pack_uint16_t(int pack, uint16_t *num);
+void usbip_net_pack_usb_device(int pack, struct usbip_usb_device *udev);
+void usbip_net_pack_usb_interface(int pack, struct usbip_usb_interface *uinf);
+
+ssize_t usbip_net_recv(int sockfd, void *buff, size_t bufflen);
+ssize_t usbip_net_send(int sockfd, void *buff, size_t bufflen);
+int usbip_net_send_op_common(int sockfd, uint32_t code, uint32_t status);
+int usbip_net_recv_op_common(int sockfd, uint16_t *code);
+int usbip_net_set_reuseaddr(int sockfd);
+int usbip_net_set_nodelay(int sockfd);
+int usbip_net_set_keepalive(int sockfd);
+int usbip_net_set_v6only(int sockfd);
+int usbip_net_tcp_connect(char *hostname, char *port);
+
+#endif /* __USBIP_NETWORK_H */
diff --git a/tools/usb/usbip/src/usbip_port.c b/tools/usb/usbip/src/usbip_port.c
new file mode 100644
index 000000000000..a2e884fd9226
--- /dev/null
+++ b/tools/usb/usbip/src/usbip_port.c
@@ -0,0 +1,57 @@
+/*
+ * Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
+ *               2005-2007 Takahiro Hirofuchi
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ */
+
+#include "vhci_driver.h"
+#include "usbip_common.h"
+
+static int list_imported_devices(void)
+{
+        int i;
+        struct usbip_imported_device *idev;
+        int ret;
+
+        ret = usbip_vhci_driver_open();
+        if (ret < 0) {
+                err("open vhci_driver");
+                return -1;
+        }
+
+        printf("Imported USB devices\n");
+        printf("====================\n");
+
+        for (i = 0; i < vhci_driver->nports; i++) {
+                idev = &vhci_driver->idev[i];
+
+                if (usbip_vhci_imported_device_dump(idev) < 0)
+                        ret = -1;
+        }
+
+        usbip_vhci_driver_close();
+
+        return ret;
+
+}
+
+int usbip_port_show(__attribute__((unused)) int argc,
+                    __attribute__((unused)) char *argv[])
+{
+        int ret;
+
+        ret = list_imported_devices();
+        if (ret < 0)
+                err("list imported devices");
+
+        return ret;
+}
diff --git a/tools/usb/usbip/src/usbip_unbind.c b/tools/usb/usbip/src/usbip_unbind.c
new file mode 100644
index 000000000000..a4a496c9cbaf
--- /dev/null
+++ b/tools/usb/usbip/src/usbip_unbind.c
@@ -0,0 +1,141 @@
+/*
+ * Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
+ *               2005-2007 Takahiro Hirofuchi
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <libudev.h>
+
+#include <errno.h>
+#include <stdio.h>
+#include <string.h>
+
+#include <getopt.h>
+
+#include "usbip_common.h"
+#include "utils.h"
+#include "usbip.h"
+#include "sysfs_utils.h"
+
+static const char usbip_unbind_usage_string[] =
+        "usbip unbind <args>\n"
+        "    -b, --busid=<busid>    Unbind " USBIP_HOST_DRV_NAME ".ko from "
+        "device on <busid>\n";
+
+void usbip_unbind_usage(void)
+{
+        printf("usage: %s", usbip_unbind_usage_string);
+}
+
+static int unbind_device(char *busid)
+{
+        char bus_type[] = "usb";
+        int rc, ret = -1;
+
+        char unbind_attr_name[] = "unbind";
+        char unbind_attr_path[SYSFS_PATH_MAX];
+        char rebind_attr_name[] = "rebind";
+        char rebind_attr_path[SYSFS_PATH_MAX];
+
+        struct udev *udev;
+        struct udev_device *dev;
+        const char *driver;
+
+        /* Create libudev context. */
+        udev = udev_new();
+
+        /* Check whether the device with this bus ID exists. */
+        dev = udev_device_new_from_subsystem_sysname(udev, "usb", busid);
+        if (!dev) {
+                err("device with the specified bus ID does not exist");
+                goto err_close_udev;
+        }
+
+        /* Check whether the device is using usbip-host driver. */
+        driver = udev_device_get_driver(dev);
+        if (!driver || strcmp(driver, "usbip-host")) {
+                err("device is not bound to usbip-host driver");
+                goto err_close_udev;
+        }
+
+        /* Unbind device from driver. */
+        snprintf(unbind_attr_path, sizeof(unbind_attr_path), "%s/%s/%s/%s/%s/%s",
+                 SYSFS_MNT_PATH, SYSFS_BUS_NAME, bus_type, SYSFS_DRIVERS_NAME,
+                 USBIP_HOST_DRV_NAME, unbind_attr_name);
+
+        rc = write_sysfs_attribute(unbind_attr_path, busid, strlen(busid));
+        if (rc < 0) {
+                err("error unbinding device %s from driver", busid);
+                goto err_close_udev;
+        }
+
+        /* Notify driver of unbind. */
+        rc = modify_match_busid(busid, 0);
+        if (rc < 0) {
+                err("unable to unbind device on %s", busid);
+                goto err_close_udev;
+        }
+
+        /* Trigger new probing. */
+        snprintf(rebind_attr_path, sizeof(unbind_attr_path), "%s/%s/%s/%s/%s/%s",
+                        SYSFS_MNT_PATH, SYSFS_BUS_NAME, bus_type, SYSFS_DRIVERS_NAME,
+                        USBIP_HOST_DRV_NAME, rebind_attr_name);
+
+        rc = write_sysfs_attribute(rebind_attr_path, busid, strlen(busid));
+        if (rc < 0) {
+                err("error rebinding");
+                goto err_close_udev;
+        }
+
+        ret = 0;
+        info("unbind device on busid %s: complete", busid);
+
+err_close_udev:
+        udev_device_unref(dev);
+        udev_unref(udev);
+
+        return ret;
+}
+
+int usbip_unbind(int argc, char *argv[])
+{
+        static const struct option opts[] = {
+                { "busid", required_argument, NULL, 'b' },
+                { NULL,    0,                 NULL,  0  }
+        };
+
+        int opt;
+        int ret = -1;
+
+        for (;;) {
+                opt = getopt_long(argc, argv, "b:", opts, NULL);
+
+                if (opt == -1)
+                        break;
+
+                switch (opt) {
+                case 'b':
+                        ret = unbind_device(optarg);
+                        goto out;
+                default:
+                        goto err_out;
+                }
+        }
+
+err_out:
+        usbip_unbind_usage();
+out:
+        return ret;
+}
diff --git a/tools/usb/usbip/src/usbipd.c b/tools/usb/usbip/src/usbipd.c
new file mode 100644
index 000000000000..2f87f2d348ba
--- /dev/null
+++ b/tools/usb/usbip/src/usbipd.c
@@ -0,0 +1,679 @@
+/*
+ * Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
+ *               2005-2007 Takahiro Hirofuchi
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifdef HAVE_CONFIG_H
+#include "../config.h"
+#endif
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <unistd.h>
+#include <netdb.h>
+#include <string.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <arpa/inet.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#ifdef HAVE_LIBWRAP
+#include <tcpd.h>
+#endif
+
+#include <getopt.h>
+#include <signal.h>
+#include <poll.h>
+
+#include "usbip_host_driver.h"
+#include "usbip_common.h"
+#include "usbip_network.h"
+#include "list.h"
+
+#undef  PROGNAME
+#define PROGNAME "usbipd"
+#define MAXSOCKFD 20
+
+#define MAIN_LOOP_TIMEOUT 10
+
+#define DEFAULT_PID_FILE "/var/run/" PROGNAME ".pid"
+
+static const char usbip_version_string[] = PACKAGE_STRING;
+
+static const char usbipd_help_string[] =
+        "usage: usbipd [options]\n"
+        "\n"
+        "       -4, --ipv4\n"
+        "               Bind to IPv4. Default is both.\n"
+        "\n"
+        "       -6, --ipv6\n"
+        "               Bind to IPv6. Default is both.\n"
+        "\n"
+        "       -D, --daemon\n"
+        "               Run as a daemon process.\n"
+        "\n"
+        "       -d, --debug\n"
+        "               Print debugging information.\n"
+        "\n"
+        "       -PFILE, --pid FILE\n"
+        "               Write process id to FILE.\n"
+        "               If no FILE specified, use " DEFAULT_PID_FILE "\n"
+        "\n"
+        "       -tPORT, --tcp-port PORT\n"
+        "               Listen on TCP/IP port PORT.\n"
+        "\n"
+        "       -h, --help\n"
+        "               Print this help.\n"
+        "\n"
+        "       -v, --version\n"
+        "               Show version.\n";
+
+static void usbipd_help(void)
+{
+        printf("%s\n", usbipd_help_string);
+}
+
+static int recv_request_import(int sockfd)
+{
+        struct op_import_request req;
+        struct op_common reply;
+        struct usbip_exported_device *edev;
+        struct usbip_usb_device pdu_udev;
+        struct list_head *i;
+        int found = 0;
+        int error = 0;
+        int rc;
+
+        memset(&req, 0, sizeof(req));
+        memset(&reply, 0, sizeof(reply));
+
+        rc = usbip_net_recv(sockfd, &req, sizeof(req));
+        if (rc < 0) {
+                dbg("usbip_net_recv failed: import request");
+                return -1;
+        }
+        PACK_OP_IMPORT_REQUEST(0, &req);
+
+        list_for_each(i, &host_driver->edev_list) {
+                edev = list_entry(i, struct usbip_exported_device, node);
+                if (!strncmp(req.busid, edev->udev.busid, SYSFS_BUS_ID_SIZE)) {
+                        info("found requested device: %s", req.busid);
+                        found = 1;
+                        break;
+                }
+        }
+
+        if (found) {
+                /* should set TCP_NODELAY for usbip */
+                usbip_net_set_nodelay(sockfd);
+
+                /* export device needs a TCP/IP socket descriptor */
+                rc = usbip_host_export_device(edev, sockfd);
+                if (rc < 0)
+                        error = 1;
+        } else {
+                info("requested device not found: %s", req.busid);
+                error = 1;
+        }
+
+        rc = usbip_net_send_op_common(sockfd, OP_REP_IMPORT,
+                                      (!error ? ST_OK : ST_NA));
+        if (rc < 0) {
+                dbg("usbip_net_send_op_common failed: %#0x", OP_REP_IMPORT);
+                return -1;
+        }
+
+        if (error) {
+                dbg("import request busid %s: failed", req.busid);
+                return -1;
+        }
+
+        memcpy(&pdu_udev, &edev->udev, sizeof(pdu_udev));
+        usbip_net_pack_usb_device(1, &pdu_udev);
+
+        rc = usbip_net_send(sockfd, &pdu_udev, sizeof(pdu_udev));
+        if (rc < 0) {
+                dbg("usbip_net_send failed: devinfo");
+                return -1;
+        }
+
+        dbg("import request busid %s: complete", req.busid);
+
+        return 0;
+}
+
+static int send_reply_devlist(int connfd)
+{
+        struct usbip_exported_device *edev;
+        struct usbip_usb_device pdu_udev;
+        struct usbip_usb_interface pdu_uinf;
+        struct op_devlist_reply reply;
+        struct list_head *j;
+        int rc, i;
+
+        reply.ndev = 0;
+        /* number of exported devices */
+        list_for_each(j, &host_driver->edev_list) {
+                reply.ndev += 1;
+        }
+        info("exportable devices: %d", reply.ndev);
+
+        rc = usbip_net_send_op_common(connfd, OP_REP_DEVLIST, ST_OK);
+        if (rc < 0) {
+                dbg("usbip_net_send_op_common failed: %#0x", OP_REP_DEVLIST);
+                return -1;
+        }
+        PACK_OP_DEVLIST_REPLY(1, &reply);
+
+        rc = usbip_net_send(connfd, &reply, sizeof(reply));
+        if (rc < 0) {
+                dbg("usbip_net_send failed: %#0x", OP_REP_DEVLIST);
+                return -1;
+        }
+
+        list_for_each(j, &host_driver->edev_list) {
+                edev = list_entry(j, struct usbip_exported_device, node);
+                dump_usb_device(&edev->udev);
+                memcpy(&pdu_udev, &edev->udev, sizeof(pdu_udev));
+                usbip_net_pack_usb_device(1, &pdu_udev);
+
+                rc = usbip_net_send(connfd, &pdu_udev, sizeof(pdu_udev));
+                if (rc < 0) {
+                        dbg("usbip_net_send failed: pdu_udev");
+                        return -1;
+                }
+
+                for (i = 0; i < edev->udev.bNumInterfaces; i++) {
+                        dump_usb_interface(&edev->uinf[i]);
+                        memcpy(&pdu_uinf, &edev->uinf[i], sizeof(pdu_uinf));
+                        usbip_net_pack_usb_interface(1, &pdu_uinf);
+
+                        rc = usbip_net_send(connfd, &pdu_uinf,
+                                        sizeof(pdu_uinf));
+                        if (rc < 0) {
+                                err("usbip_net_send failed: pdu_uinf");
+                                return -1;
+                        }
+                }
+        }
+
+        return 0;
+}
+
+static int recv_request_devlist(int connfd)
+{
+        struct op_devlist_request req;
+        int rc;
+
+        memset(&req, 0, sizeof(req));
+
+        rc = usbip_net_recv(connfd, &req, sizeof(req));
+        if (rc < 0) {
+                dbg("usbip_net_recv failed: devlist request");
+                return -1;
+        }
+
+        rc = send_reply_devlist(connfd);
+        if (rc < 0) {
+                dbg("send_reply_devlist failed");
+                return -1;
+        }
+
+        return 0;
+}
+
+static int recv_pdu(int connfd)
+{
+        uint16_t code = OP_UNSPEC;
+        int ret;
+
+        ret = usbip_net_recv_op_common(connfd, &code);
+        if (ret < 0) {
+                dbg("could not receive opcode: %#0x", code);
+                return -1;
+        }
+
+        ret = usbip_host_refresh_device_list();
+        if (ret < 0) {
+                dbg("could not refresh device list: %d", ret);
+                return -1;
+        }
+
+        info("received request: %#0x(%d)", code, connfd);
+        switch (code) {
+        case OP_REQ_DEVLIST:
+                ret = recv_request_devlist(connfd);
+                break;
+        case OP_REQ_IMPORT:
+                ret = recv_request_import(connfd);
+                break;
+        case OP_REQ_DEVINFO:
+        case OP_REQ_CRYPKEY:
+        default:
+                err("received an unknown opcode: %#0x", code);
+                ret = -1;
+        }
+
+        if (ret == 0)
+                info("request %#0x(%d): complete", code, connfd);
+        else
+                info("request %#0x(%d): failed", code, connfd);
+
+        return ret;
+}
+
+#ifdef HAVE_LIBWRAP
+static int tcpd_auth(int connfd)
+{
+        struct request_info request;
+        int rc;
+
+        request_init(&request, RQ_DAEMON, PROGNAME, RQ_FILE, connfd, 0);
+        fromhost(&request);
+        rc = hosts_access(&request);
+        if (rc == 0)
+                return -1;
+
+        return 0;
+}
+#endif
+
+static int do_accept(int listenfd)
+{
+        int connfd;
+        struct sockaddr_storage ss;
+        socklen_t len = sizeof(ss);
+        char host[NI_MAXHOST], port[NI_MAXSERV];
+        int rc;
+
+        memset(&ss, 0, sizeof(ss));
+
+        connfd = accept(listenfd, (struct sockaddr *)&ss, &len);
+        if (connfd < 0) {
+                err("failed to accept connection");
+                return -1;
+        }
+
+        rc = getnameinfo((struct sockaddr *)&ss, len, host, sizeof(host),
+                         port, sizeof(port), NI_NUMERICHOST | NI_NUMERICSERV);
+        if (rc)
+                err("getnameinfo: %s", gai_strerror(rc));
+
+#ifdef HAVE_LIBWRAP
+        rc = tcpd_auth(connfd);
+        if (rc < 0) {
+                info("denied access from %s", host);
+                close(connfd);
+                return -1;
+        }
+#endif
+        info("connection from %s:%s", host, port);
+
+        return connfd;
+}
+
+int process_request(int listenfd)
+{
+        pid_t childpid;
+        int connfd;
+
+        connfd = do_accept(listenfd);
+        if (connfd < 0)
+                return -1;
+        childpid = fork();
+        if (childpid == 0) {
+                close(listenfd);
+                recv_pdu(connfd);
+                exit(0);
+        }
+        close(connfd);
+        return 0;
+}
+
+static void addrinfo_to_text(struct addrinfo *ai, char buf[],
+                             const size_t buf_size)
+{
+        char hbuf[NI_MAXHOST];
+        char sbuf[NI_MAXSERV];
+        int rc;
+
+        buf[0] = '\0';
+
+        rc = getnameinfo(ai->ai_addr, ai->ai_addrlen, hbuf, sizeof(hbuf),
+                         sbuf, sizeof(sbuf), NI_NUMERICHOST | NI_NUMERICSERV);
+        if (rc)
+                err("getnameinfo: %s", gai_strerror(rc));
+
+        snprintf(buf, buf_size, "%s:%s", hbuf, sbuf);
+}
+
+static int listen_all_addrinfo(struct addrinfo *ai_head, int sockfdlist[],
+                             int maxsockfd)
+{
+        struct addrinfo *ai;
+        int ret, nsockfd = 0;
+        const size_t ai_buf_size = NI_MAXHOST + NI_MAXSERV + 2;
+        char ai_buf[ai_buf_size];
+
+        for (ai = ai_head; ai && nsockfd < maxsockfd; ai = ai->ai_next) {
+                int sock;
+
+                addrinfo_to_text(ai, ai_buf, ai_buf_size);
+                dbg("opening %s", ai_buf);
+                sock = socket(ai->ai_family, ai->ai_socktype, ai->ai_protocol);
+                if (sock < 0) {
+                        err("socket: %s: %d (%s)",
+                            ai_buf, errno, strerror(errno));
+                        continue;
+                }
+
+                usbip_net_set_reuseaddr(sock);
+                usbip_net_set_nodelay(sock);
+                /* We use seperate sockets for IPv4 and IPv6
+                 * (see do_standalone_mode()) */
+                usbip_net_set_v6only(sock);
+
+                if (sock >= FD_SETSIZE) {
+                        err("FD_SETSIZE: %s: sock=%d, max=%d",
+                            ai_buf, sock, FD_SETSIZE);
+                        close(sock);
+                        continue;
+                }
+
+                ret = bind(sock, ai->ai_addr, ai->ai_addrlen);
+                if (ret < 0) {
+                        err("bind: %s: %d (%s)",
+                            ai_buf, errno, strerror(errno));
+                        close(sock);
+                        continue;
+                }
+
+                ret = listen(sock, SOMAXCONN);
+                if (ret < 0) {
+                        err("listen: %s: %d (%s)",
+                            ai_buf, errno, strerror(errno));
+                        close(sock);
+                        continue;
+                }
+
+                info("listening on %s", ai_buf);
+                sockfdlist[nsockfd++] = sock;
+        }
+
+        return nsockfd;
+}
+
+static struct addrinfo *do_getaddrinfo(char *host, int ai_family)
+{
+        struct addrinfo hints, *ai_head;
+        int rc;
+
+        memset(&hints, 0, sizeof(hints));
+        hints.ai_family   = ai_family;
+        hints.ai_socktype = SOCK_STREAM;
+        hints.ai_flags    = AI_PASSIVE;
+
+        rc = getaddrinfo(host, usbip_port_string, &hints, &ai_head);
+        if (rc) {
+                err("failed to get a network address %s: %s", usbip_port_string,
+                    gai_strerror(rc));
+                return NULL;
+        }
+
+        return ai_head;
+}
+
+static void signal_handler(int i)
+{
+        dbg("received '%s' signal", strsignal(i));
+}
+
+static void set_signal(void)
+{
+        struct sigaction act;
+
+        memset(&act, 0, sizeof(act));
+        act.sa_handler = signal_handler;
+        sigemptyset(&act.sa_mask);
+        sigaction(SIGTERM, &act, NULL);
+        sigaction(SIGINT, &act, NULL);
+        act.sa_handler = SIG_IGN;
+        sigaction(SIGCLD, &act, NULL);
+}
+
+static const char *pid_file;
+
+static void write_pid_file(void)
+{
+        if (pid_file) {
+                dbg("creating pid file %s", pid_file);
+                FILE *fp;
+
+                fp = fopen(pid_file, "w");
+                if (!fp) {
+                        err("pid_file: %s: %d (%s)",
+                            pid_file, errno, strerror(errno));
+                        return;
+                }
+                fprintf(fp, "%d\n", getpid());
+                fclose(fp);
+        }
+}
+
+static void remove_pid_file(void)
+{
+        if (pid_file) {
+                dbg("removing pid file %s", pid_file);
+                unlink(pid_file);
+        }
+}
+
+static int do_standalone_mode(int daemonize, int ipv4, int ipv6)
+{
+        struct addrinfo *ai_head;
+        int sockfdlist[MAXSOCKFD];
+        int nsockfd, family;
+        int i, terminate;
+        struct pollfd *fds;
+        struct timespec timeout;
+        sigset_t sigmask;
+
+        if (usbip_host_driver_open()) {
+                err("please load " USBIP_CORE_MOD_NAME ".ko and "
+                    USBIP_HOST_DRV_NAME ".ko!");
+                return -1;
+        }
+
+        if (daemonize) {
+                if (daemon(0, 0) < 0) {
+                        err("daemonizing failed: %s", strerror(errno));
+                        usbip_host_driver_close();
+                        return -1;
+                }
+                umask(0);
+                usbip_use_syslog = 1;
+        }
+        set_signal();
+        write_pid_file();
+
+        info("starting " PROGNAME " (%s)", usbip_version_string);
+
+        /*
+         * To suppress warnings on systems with bindv6only disabled
+         * (default), we use seperate sockets for IPv6 and IPv4 and set
+         * IPV6_V6ONLY on the IPv6 sockets.
+         */
+        if (ipv4 && ipv6)
+                family = AF_UNSPEC;
+        else if (ipv4)
+                family = AF_INET;
+        else
+                family = AF_INET6;
+
+        ai_head = do_getaddrinfo(NULL, family);
+        if (!ai_head) {
+                usbip_host_driver_close();
+                return -1;
+        }
+        nsockfd = listen_all_addrinfo(ai_head, sockfdlist,
+                sizeof(sockfdlist) / sizeof(*sockfdlist));
+        freeaddrinfo(ai_head);
+        if (nsockfd <= 0) {
+                err("failed to open a listening socket");
+                usbip_host_driver_close();
+                return -1;
+        }
+
+        dbg("listening on %d address%s", nsockfd, (nsockfd == 1) ? "" : "es");
+
+        fds = calloc(nsockfd, sizeof(struct pollfd));
+        for (i = 0; i < nsockfd; i++) {
+                fds[i].fd = sockfdlist[i];
+                fds[i].events = POLLIN;
+        }
+        timeout.tv_sec = MAIN_LOOP_TIMEOUT;
+        timeout.tv_nsec = 0;
+
+        sigfillset(&sigmask);
+        sigdelset(&sigmask, SIGTERM);
+        sigdelset(&sigmask, SIGINT);
+
+        terminate = 0;
+        while (!terminate) {
+                int r;
+
+                r = ppoll(fds, nsockfd, &timeout, &sigmask);
+                if (r < 0) {
+                        dbg("%s", strerror(errno));
+                        terminate = 1;
+                } else if (r) {
+                        for (i = 0; i < nsockfd; i++) {
+                                if (fds[i].revents & POLLIN) {
+                                        dbg("read event on fd[%d]=%d",
+                                            i, sockfdlist[i]);
+                                        process_request(sockfdlist[i]);
+                                }
+                        }
+                } else {
+                        dbg("heartbeat timeout on ppoll()");
+                }
+        }
+
+        info("shutting down " PROGNAME);
+        free(fds);
+        usbip_host_driver_close();
+
+        return 0;
+}
+
+int main(int argc, char *argv[])
+{
+        static const struct option longopts[] = {
+                { "ipv4",     no_argument,       NULL, '4' },
+                { "ipv6",     no_argument,       NULL, '6' },
+                { "daemon",   no_argument,       NULL, 'D' },
+                { "daemon",   no_argument,       NULL, 'D' },
+                { "debug",    no_argument,       NULL, 'd' },
+                { "pid",      optional_argument, NULL, 'P' },
+                { "tcp-port", required_argument, NULL, 't' },
+                { "help",     no_argument,       NULL, 'h' },
+                { "version",  no_argument,       NULL, 'v' },
+                { NULL,       0,                 NULL,  0  }
+        };
+
+        enum {
+                cmd_standalone_mode = 1,
+                cmd_help,
+                cmd_version
+        } cmd;
+
+        int daemonize = 0;
+        int ipv4 = 0, ipv6 = 0;
+        int opt, rc = -1;
+
+        pid_file = NULL;
+
+        usbip_use_stderr = 1;
+        usbip_use_syslog = 0;
+
+        if (geteuid() != 0)
+                err("not running as root?");
+
+        cmd = cmd_standalone_mode;
+        for (;;) {
+                opt = getopt_long(argc, argv, "46DdP::t:hv", longopts, NULL);
+
+                if (opt == -1)
+                        break;
+
+                switch (opt) {
+                case '4':
+                        ipv4 = 1;
+                        break;
+                case '6':
+                        ipv6 = 1;
+                        break;
+                case 'D':
+                        daemonize = 1;
+                        break;
+                case 'd':
+                        usbip_use_debug = 1;
+                        break;
+                case 'h':
+                        cmd = cmd_help;
+                        break;
+                case 'P':
+                        pid_file = optarg ? optarg : DEFAULT_PID_FILE;
+                        break;
+                case 't':
+                        usbip_setup_port_number(optarg);
+                        break;
+                case 'v':
+                        cmd = cmd_version;
+                        break;
+                case '?':
+                        usbipd_help();
+                default:
+                        goto err_out;
+                }
+        }
+
+        if (!ipv4 && !ipv6)
+                ipv4 = ipv6 = 1;
+
+        switch (cmd) {
+        case cmd_standalone_mode:
+                rc = do_standalone_mode(daemonize, ipv4, ipv6);
+                remove_pid_file();
+                break;
+        case cmd_version:
+                printf(PROGNAME " (%s)\n", usbip_version_string);
+                rc = 0;
+                break;
+        case cmd_help:
+                usbipd_help();
+                rc = 0;
+                break;
+        default:
+                usbipd_help();
+                goto err_out;
+        }
+
+err_out:
+        return (rc > -1 ? EXIT_SUCCESS : EXIT_FAILURE);
+}
diff --git a/tools/usb/usbip/src/utils.c b/tools/usb/usbip/src/utils.c
new file mode 100644
index 000000000000..2b3d6d235015
--- /dev/null
+++ b/tools/usb/usbip/src/utils.c
@@ -0,0 +1,52 @@
+/*
+ * Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
+ *               2005-2007 Takahiro Hirofuchi
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <errno.h>
+#include <stdio.h>
+#include <string.h>
+
+#include "usbip_common.h"
+#include "utils.h"
+#include "sysfs_utils.h"
+
+int modify_match_busid(char *busid, int add)
+{
+        char attr_name[] = "match_busid";
+        char command[SYSFS_BUS_ID_SIZE + 4];
+        char match_busid_attr_path[SYSFS_PATH_MAX];
+        int rc;
+
+        snprintf(match_busid_attr_path, sizeof(match_busid_attr_path),
+                 "%s/%s/%s/%s/%s/%s", SYSFS_MNT_PATH, SYSFS_BUS_NAME,
+                 SYSFS_BUS_TYPE, SYSFS_DRIVERS_NAME, USBIP_HOST_DRV_NAME,
+                 attr_name);
+
+        if (add)
+                snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s", busid);
+        else
+                snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s", busid);
+
+        rc = write_sysfs_attribute(match_busid_attr_path, command,
+                                   sizeof(command));
+        if (rc < 0) {
+                dbg("failed to write match_busid: %s", strerror(errno));
+                return -1;
+        }
+
+        return 0;
+}
diff --git a/tools/usb/usbip/src/utils.h b/tools/usb/usbip/src/utils.h
new file mode 100644
index 000000000000..5916fd3e02a6
--- /dev/null
+++ b/tools/usb/usbip/src/utils.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2011 matt mooney <mfm@muteddisk.com>
+ *               2005-2007 Takahiro Hirofuchi
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __UTILS_H
+#define __UTILS_H
+
+int modify_match_busid(char *busid, int add);
+
+#endif /* __UTILS_H */
+
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index c4d6d2e20e0d..264fbc297e0b 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -132,6 +132,7 @@ static const char * const page_flag_names[] = {
         [KPF_NOPAGE]            = "n:nopage",
         [KPF_KSM]               = "x:ksm",
         [KPF_THP]               = "t:thp",
+        [KPF_BALLOON]           = "o:balloon",
 
         [KPF_RESERVED]          = "r:reserved",
         [KPF_MLOCKED]           = "m:mlocked",