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

Pull perf fixes from Ingo Molnar:
 "Tooling fixes, the biggest patch is one that decouples the kernel's
  list.h from tooling list.h"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  perf tools: Fallback to srcdir/Documentation/tips.txt
  perf ui/tui: Print helpline message as is
  perf tools: Set and pass DOCDIR to builtin-report.c
  perf tools: Add file_only config option to strlist
  perf tools: Add more usage tips
  perf record: Add --buildid-all option
  tools subcmd: Add missing NORETURN define for parse-options.h
  tools: Fix formatting of the "make -C tools" help message
  tools: Make list.h self-sufficient
  perf tools: Fix mmap2 event allocation in synthesize code
  perf stat: Fix recort_usage typo
  perf test: Reset err after using it hold errcode in hist testcases
  perf test: Fix false TEST_OK result for 'perf test hist'
  tools build: Add BPF feature check to test-all
  perf bpf: Fix build breakage due to libbpf
  tools: Move Makefile.arch from perf/config to tools/scripts
  perf tools: Fix PowerPC native building
  perf tools: Fix phony build target for build-test
  perf tools: Add -lutil in python lib list for broken python-config
  perf tools: Add missing sources to perf's MANIFEST
  ...

28 files changed, 918 insertions, 66 deletions

diff --git a/tools/Makefile b/tools/Makefile
index 1dc6900468ed..6339f6ac3ccb 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -8,24 +8,24 @@ include scripts/Makefile.include
 help:
         @echo 'Possible targets:'
         @echo ''
-        @echo '  acpi       - ACPI tools'
-        @echo '  cgroup     - cgroup tools'
-        @echo '  cpupower   - a tool for all things x86 CPU power'
-        @echo '  firewire   - the userspace part of nosy, an IEEE-1394 traffic sniffer'
-        @echo '  hv         - tools used when in Hyper-V clients'
-        @echo '  iio        - IIO tools'
-        @echo '  lguest     - a minimal 32-bit x86 hypervisor'
-        @echo '  perf       - Linux performance measurement and analysis tool'
-        @echo '  selftests  - various kernel selftests'
-        @echo '  spi        - spi tools'
-        @echo '  turbostat  - Intel CPU idle stats and freq reporting tool'
-        @echo '  usb        - USB testing tools'
-        @echo '  virtio     - vhost test module'
-        @echo '  net        - misc networking tools'
-        @echo '  vm         - misc vm tools'
+        @echo '  acpi                   - ACPI tools'
+        @echo '  cgroup                 - cgroup tools'
+        @echo '  cpupower               - a tool for all things x86 CPU power'
+        @echo '  firewire               - the userspace part of nosy, an IEEE-1394 traffic sniffer'
+        @echo '  freefall               - laptop accelerometer program for disk protection'
+        @echo '  hv                     - tools used when in Hyper-V clients'
+        @echo '  iio                    - IIO tools'
+        @echo '  lguest                 - a minimal 32-bit x86 hypervisor'
+        @echo '  net                    - misc networking tools'
+        @echo '  perf                   - Linux performance measurement and analysis tool'
+        @echo '  selftests              - various kernel selftests'
+        @echo '  spi                    - spi tools'
+        @echo '  tmon                   - thermal monitoring and tuning tool'
+        @echo '  turbostat              - Intel CPU idle stats and freq reporting tool'
+        @echo '  usb                    - USB testing tools'
+        @echo '  virtio                 - vhost test module'
+        @echo '  vm                     - misc vm tools'
         @echo '  x86_energy_perf_policy - Intel energy policy tool'
-        @echo '  tmon       - thermal monitoring and tuning tool'
-        @echo '  freefall   - laptop accelerometer program for disk protection'
         @echo ''
         @echo 'You can do:'
         @echo ' $$ make -C tools/ <tool>_install'
@@ -128,6 +128,12 @@ liblockdep_clean:
 libapi_clean:
         $(call descend,lib/api,clean)
 
+libbpf_clean:
+        $(call descend,lib/bpf,clean)
+
+libsubcmd_clean:
+        $(call descend,lib/subcmd,clean)
+
 perf_clean:
         $(call descend,$(@:_clean=),clean)
 
@@ -143,9 +149,12 @@ tmon_clean:
 freefall_clean:
         $(call descend,laptop/freefall,clean)
 
+build_clean:
+        $(call descend,build,clean)
+
 clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean lguest_clean \
                 perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \
                 vm_clean net_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
-                freefall_clean
+                freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean
 
 .PHONY: FORCE
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 33cf6f20bd4e..81025cade45f 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -125,6 +125,10 @@
 # include "test-get_cpuid.c"
 #undef main
 
+#define main main_test_bpf
+# include "test-bpf.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
         main_test_libpython();
@@ -153,6 +157,7 @@ int main(int argc, char *argv[])
         main_test_pthread_attr_setaffinity_np();
         main_test_lzma();
         main_test_get_cpuid();
+        main_test_bpf();
 
         return 0;
 }
diff --git a/tools/build/feature/test-bpf.c b/tools/build/feature/test-bpf.c
index 062bac811af9..b389026839b9 100644
--- a/tools/build/feature/test-bpf.c
+++ b/tools/build/feature/test-bpf.c
@@ -1,9 +1,23 @@
+#include <asm/unistd.h>
 #include <linux/bpf.h>
+#include <unistd.h>
+
+#ifndef __NR_bpf
+# if defined(__i386__)
+#  define __NR_bpf 357
+# elif defined(__x86_64__)
+#  define __NR_bpf 321
+# elif defined(__aarch64__)
+#  define __NR_bpf 280
+#  error __NR_bpf not defined. libbpf does not support your arch.
+# endif
+#endif
 
 int main(void)
 {
         union bpf_attr attr;
 
+        /* Check fields in attr */
         attr.prog_type = BPF_PROG_TYPE_KPROBE;
         attr.insn_cnt = 0;
         attr.insns = 0;
@@ -14,5 +28,9 @@ int main(void)
         attr.kern_version = 0;
 
         attr = attr;
-        return 0;
+        /*
+         * Test existence of __NR_bpf and BPF_PROG_LOAD.
+         * This call should fail if we run the testcase.
+         */
+        return syscall(__NR_bpf, BPF_PROG_LOAD, attr, sizeof(attr));
 }
diff --git a/tools/include/linux/list.h b/tools/include/linux/list.h
index a017f1595676..1da423820ad4 100644
--- a/tools/include/linux/list.h
+++ b/tools/include/linux/list.h
@@ -1,11 +1,751 @@
-#include <linux/compiler.h>
-#include <linux/kernel.h>
+#ifndef __TOOLS_LINUX_LIST_H
+#define __TOOLS_LINUX_LIST_H
+
 #include <linux/types.h>
+#include <linux/poison.h>
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+
+/*
+ * 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.
+ */
+
+#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!
+ */
+#ifndef CONFIG_DEBUG_LIST
+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;
+}
+#else
+extern void __list_add(struct list_head *new,
+                              struct list_head *prev,
+                              struct list_head *next);
+#endif
+
+/**
+ * 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);
+}
+
+
+/**
+ * list_add_tail - add a new entry
+ * @new: new entry to be added
+ * @head: list head to add it before
+ *
+ * Insert a new entry before the specified head.
+ * This is useful for implementing queues.
+ */
+static inline void list_add_tail(struct list_head *new, struct list_head *head)
+{
+        __list_add(new, head->prev, head);
+}
+
+/*
+ * 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;
+        WRITE_ONCE(prev->next, next);
+}
+
+/**
+ * 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.
+ */
+#ifndef CONFIG_DEBUG_LIST
+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;
+}
+#else
+extern void __list_del_entry(struct list_head *entry);
+extern void list_del(struct list_head *entry);
+#endif
+
+/**
+ * list_replace - replace old entry by new one
+ * @old : the element to be replaced
+ * @new : the new element to insert
+ *
+ * If @old was empty, it will be overwritten.
+ */
+static inline void list_replace(struct list_head *old,
+                                struct list_head *new)
+{
+        new->next = old->next;
+        new->next->prev = new;
+        new->prev = old->prev;
+        new->prev->next = new;
+}
+
+static inline void list_replace_init(struct list_head *old,
+                                        struct list_head *new)
+{
+        list_replace(old, new);
+        INIT_LIST_HEAD(old);
+}
+
+/**
+ * list_del_init - deletes entry from list and reinitialize it.
+ * @entry: the element to delete from the list.
+ */
+static inline void list_del_init(struct list_head *entry)
+{
+        __list_del_entry(entry);
+        INIT_LIST_HEAD(entry);
+}
+
+/**
+ * list_move - delete from one list and add as another's head
+ * @list: the entry to move
+ * @head: the head that will precede our entry
+ */
+static inline void list_move(struct list_head *list, struct list_head *head)
+{
+        __list_del_entry(list);
+        list_add(list, head);
+}
+
+/**
+ * list_move_tail - delete from one list and add as another's tail
+ * @list: the entry to move
+ * @head: the head that will follow our entry
+ */
+static inline void list_move_tail(struct list_head *list,
+                                  struct list_head *head)
+{
+        __list_del_entry(list);
+        list_add_tail(list, head);
+}
+
+/**
+ * list_is_last - tests whether @list is the last entry in list @head
+ * @list: the entry to test
+ * @head: the head of the list
+ */
+static inline int list_is_last(const struct list_head *list,
+                                const struct list_head *head)
+{
+        return list->next == head;
+}
+
+/**
+ * list_empty - tests whether a list is empty
+ * @head: the list to test.
+ */
+static inline int list_empty(const struct list_head *head)
+{
+        return head->next == head;
+}
+
+/**
+ * list_empty_careful - tests whether a list is empty and not being modified
+ * @head: the list to test
+ *
+ * Description:
+ * tests whether a list is empty _and_ checks that no other CPU might be
+ * in the process of modifying either member (next or prev)
+ *
+ * NOTE: using list_empty_careful() without synchronization
+ * can only be safe if the only activity that can happen
+ * to the list entry is list_del_init(). Eg. it cannot be used
+ * if another CPU could re-list_add() it.
+ */
+static inline int list_empty_careful(const struct list_head *head)
+{
+        struct list_head *next = head->next;
+        return (next == head) && (next == head->prev);
+}
+
+/**
+ * list_rotate_left - rotate the list to the left
+ * @head: the head of the list
+ */
+static inline void list_rotate_left(struct list_head *head)
+{
+        struct list_head *first;
+
+        if (!list_empty(head)) {
+                first = head->next;
+                list_move_tail(first, head);
+        }
+}
+
+/**
+ * list_is_singular - tests whether a list has just one entry.
+ * @head: the list to test.
+ */
+static inline int list_is_singular(const struct list_head *head)
+{
+        return !list_empty(head) && (head->next == head->prev);
+}
+
+static inline void __list_cut_position(struct list_head *list,
+                struct list_head *head, struct list_head *entry)
+{
+        struct list_head *new_first = entry->next;
+        list->next = head->next;
+        list->next->prev = list;
+        list->prev = entry;
+        entry->next = list;
+        head->next = new_first;
+        new_first->prev = head;
+}
+
+/**
+ * list_cut_position - cut a list into two
+ * @list: a new list to add all removed entries
+ * @head: a list with entries
+ * @entry: an entry within head, could be the head itself
+ *      and if so we won't cut the list
+ *
+ * This helper moves the initial part of @head, up to and
+ * including @entry, from @head to @list. You should
+ * pass on @entry an element you know is on @head. @list
+ * should be an empty list or a list you do not care about
+ * losing its data.
+ *
+ */
+static inline void list_cut_position(struct list_head *list,
+                struct list_head *head, struct list_head *entry)
+{
+        if (list_empty(head))
+                return;
+        if (list_is_singular(head) &&
+                (head->next != entry && head != entry))
+                return;
+        if (entry == head)
+                INIT_LIST_HEAD(list);
+        else
+                __list_cut_position(list, head, entry);
+}
+
+static inline void __list_splice(const struct list_head *list,
+                                 struct list_head *prev,
+                                 struct list_head *next)
+{
+        struct list_head *first = list->next;
+        struct list_head *last = list->prev;
+
+        first->prev = prev;
+        prev->next = first;
+
+        last->next = next;
+        next->prev = last;
+}
+
+/**
+ * list_splice - join two lists, this is designed for stacks
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ */
+static inline void list_splice(const struct list_head *list,
+                                struct list_head *head)
+{
+        if (!list_empty(list))
+                __list_splice(list, head, head->next);
+}
+
+/**
+ * list_splice_tail - join two lists, each list being a queue
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ */
+static inline void list_splice_tail(struct list_head *list,
+                                struct list_head *head)
+{
+        if (!list_empty(list))
+                __list_splice(list, head->prev, head);
+}
+
+/**
+ * list_splice_init - join two lists and reinitialise the emptied list.
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ *
+ * The list at @list is reinitialised
+ */
+static inline void list_splice_init(struct list_head *list,
+                                    struct list_head *head)
+{
+        if (!list_empty(list)) {
+                __list_splice(list, head, head->next);
+                INIT_LIST_HEAD(list);
+        }
+}
+
+/**
+ * list_splice_tail_init - join two lists and reinitialise the emptied list
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ *
+ * Each of the lists is a queue.
+ * The list at @list is reinitialised
+ */
+static inline void list_splice_tail_init(struct list_head *list,
+                                         struct list_head *head)
+{
+        if (!list_empty(list)) {
+                __list_splice(list, head->prev, head);
+                INIT_LIST_HEAD(list);
+        }
+}
+
+/**
+ * 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_head within the struct.
+ */
+#define list_entry(ptr, type, member) \
+        container_of(ptr, type, member)
+
+/**
+ * list_first_entry - get the first element from a list
+ * @ptr:        the list head to take the element from.
+ * @type:       the type of the struct this is embedded in.
+ * @member:     the name of the list_head within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ */
+#define list_first_entry(ptr, type, member) \
+        list_entry((ptr)->next, type, member)
+
+/**
+ * list_last_entry - get the last element from a list
+ * @ptr:        the list head to take the element from.
+ * @type:       the type of the struct this is embedded in.
+ * @member:     the name of the list_head within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ */
+#define list_last_entry(ptr, type, member) \
+        list_entry((ptr)->prev, type, member)
+
+/**
+ * list_first_entry_or_null - get the first element from a list
+ * @ptr:        the list head to take the element from.
+ * @type:       the type of the struct this is embedded in.
+ * @member:     the name of the list_head within the struct.
+ *
+ * Note that if the list is empty, it returns NULL.
+ */
+#define list_first_entry_or_null(ptr, type, member) \
+        (!list_empty(ptr) ? list_first_entry(ptr, type, member) : NULL)
+
+/**
+ * list_next_entry - get the next element in list
+ * @pos:        the type * to cursor
+ * @member:     the name of the list_head within the struct.
+ */
+#define list_next_entry(pos, member) \
+        list_entry((pos)->member.next, typeof(*(pos)), member)
+
+/**
+ * list_prev_entry - get the prev element in list
+ * @pos:        the type * to cursor
+ * @member:     the name of the list_head within the struct.
+ */
+#define list_prev_entry(pos, member) \
+        list_entry((pos)->member.prev, typeof(*(pos)), 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_prev   -       iterate over a list backwards
+ * @pos:        the &struct list_head to use as a loop cursor.
+ * @head:       the head for your list.
+ */
+#define list_for_each_prev(pos, head) \
+        for (pos = (head)->prev; pos != (head); pos = pos->prev)
+
+/**
+ * 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)
+
+/**
+ * list_for_each_prev_safe - iterate over a list backwards 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_prev_safe(pos, n, head) \
+        for (pos = (head)->prev, n = pos->prev; \
+             pos != (head); \
+             pos = n, n = pos->prev)
+
+/**
+ * list_for_each_entry  -       iterate over list of given type
+ * @pos:        the type * to use as a loop cursor.
+ * @head:       the head for your list.
+ * @member:     the name of the list_head within the struct.
+ */
+#define list_for_each_entry(pos, head, member)                          \
+        for (pos = list_first_entry(head, typeof(*pos), member);        \
+             &pos->member != (head);                                    \
+             pos = list_next_entry(pos, member))
+
+/**
+ * list_for_each_entry_reverse - iterate backwards over list of given type.
+ * @pos:        the type * to use as a loop cursor.
+ * @head:       the head for your list.
+ * @member:     the name of the list_head within the struct.
+ */
+#define list_for_each_entry_reverse(pos, head, member)                  \
+        for (pos = list_last_entry(head, typeof(*pos), member);         \
+             &pos->member != (head);                                    \
+             pos = list_prev_entry(pos, member))
+
+/**
+ * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue()
+ * @pos:        the type * to use as a start point
+ * @head:       the head of the list
+ * @member:     the name of the list_head within the struct.
+ *
+ * Prepares a pos entry for use as a start point in list_for_each_entry_continue().
+ */
+#define list_prepare_entry(pos, head, member) \
+        ((pos) ? : list_entry(head, typeof(*pos), member))
+
+/**
+ * list_for_each_entry_continue - continue iteration over list of given type
+ * @pos:        the type * to use as a loop cursor.
+ * @head:       the head for your list.
+ * @member:     the name of the list_head within the struct.
+ *
+ * Continue to iterate over list of given type, continuing after
+ * the current position.
+ */
+#define list_for_each_entry_continue(pos, head, member)                 \
+        for (pos = list_next_entry(pos, member);                        \
+             &pos->member != (head);                                    \
+             pos = list_next_entry(pos, member))
+
+/**
+ * list_for_each_entry_continue_reverse - iterate backwards from the given point
+ * @pos:        the type * to use as a loop cursor.
+ * @head:       the head for your list.
+ * @member:     the name of the list_head within the struct.
+ *
+ * Start to iterate over list of given type backwards, continuing after
+ * the current position.
+ */
+#define list_for_each_entry_continue_reverse(pos, head, member)         \
+        for (pos = list_prev_entry(pos, member);                        \
+             &pos->member != (head);                                    \
+             pos = list_prev_entry(pos, member))
+
+/**
+ * list_for_each_entry_from - iterate over list of given type from the current point
+ * @pos:        the type * to use as a loop cursor.
+ * @head:       the head for your list.
+ * @member:     the name of the list_head within the struct.
+ *
+ * Iterate over list of given type, continuing from current position.
+ */
+#define list_for_each_entry_from(pos, head, member)                     \
+        for (; &pos->member != (head);                                  \
+             pos = list_next_entry(pos, member))
+
+/**
+ * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry
+ * @pos:        the type * to use as a loop cursor.
+ * @n:          another type * to use as temporary storage
+ * @head:       the head for your list.
+ * @member:     the name of the list_head within the struct.
+ */
+#define list_for_each_entry_safe(pos, n, head, member)                  \
+        for (pos = list_first_entry(head, typeof(*pos), member),        \
+                n = list_next_entry(pos, member);                       \
+             &pos->member != (head);                                    \
+             pos = n, n = list_next_entry(n, member))
+
+/**
+ * list_for_each_entry_safe_continue - continue list iteration safe against removal
+ * @pos:        the type * to use as a loop cursor.
+ * @n:          another type * to use as temporary storage
+ * @head:       the head for your list.
+ * @member:     the name of the list_head within the struct.
+ *
+ * Iterate over list of given type, continuing after current point,
+ * safe against removal of list entry.
+ */
+#define list_for_each_entry_safe_continue(pos, n, head, member)                 \
+        for (pos = list_next_entry(pos, member),                                \
+                n = list_next_entry(pos, member);                               \
+             &pos->member != (head);                                            \
+             pos = n, n = list_next_entry(n, member))
+
+/**
+ * list_for_each_entry_safe_from - iterate over list from current point safe against removal
+ * @pos:        the type * to use as a loop cursor.
+ * @n:          another type * to use as temporary storage
+ * @head:       the head for your list.
+ * @member:     the name of the list_head within the struct.
+ *
+ * Iterate over list of given type from current point, safe against
+ * removal of list entry.
+ */
+#define list_for_each_entry_safe_from(pos, n, head, member)                     \
+        for (n = list_next_entry(pos, member);                                  \
+             &pos->member != (head);                                            \
+             pos = n, n = list_next_entry(n, member))
+
+/**
+ * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal
+ * @pos:        the type * to use as a loop cursor.
+ * @n:          another type * to use as temporary storage
+ * @head:       the head for your list.
+ * @member:     the name of the list_head within the struct.
+ *
+ * Iterate backwards over list of given type, safe against removal
+ * of list entry.
+ */
+#define list_for_each_entry_safe_reverse(pos, n, head, member)          \
+        for (pos = list_last_entry(head, typeof(*pos), member),         \
+                n = list_prev_entry(pos, member);                       \
+             &pos->member != (head);                                    \
+             pos = n, n = list_prev_entry(n, member))
 
-#include "../../../include/linux/list.h"
+/**
+ * list_safe_reset_next - reset a stale list_for_each_entry_safe loop
+ * @pos:        the loop cursor used in the list_for_each_entry_safe loop
+ * @n:          temporary storage used in list_for_each_entry_safe
+ * @member:     the name of the list_head within the struct.
+ *
+ * list_safe_reset_next is not safe to use in general if the list may be
+ * modified concurrently (eg. the lock is dropped in the loop body). An
+ * exception to this is if the cursor element (pos) is pinned in the list,
+ * and list_safe_reset_next is called after re-taking the lock and before
+ * completing the current iteration of the loop body.
+ */
+#define list_safe_reset_next(pos, n, member)                            \
+        n = list_next_entry(pos, member)
+
+/*
+ * Double linked lists with a single pointer list head.
+ * Mostly useful for hash tables where the two pointer list head is
+ * too wasteful.
+ * You lose the ability to access the tail in O(1).
+ */
+
+#define HLIST_HEAD_INIT { .first = NULL }
+#define HLIST_HEAD(name) struct hlist_head name = {  .first = NULL }
+#define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL)
+static inline void INIT_HLIST_NODE(struct hlist_node *h)
+{
+        h->next = NULL;
+        h->pprev = NULL;
+}
+
+static inline int hlist_unhashed(const struct hlist_node *h)
+{
+        return !h->pprev;
+}
+
+static inline int hlist_empty(const struct hlist_head *h)
+{
+        return !h->first;
+}
+
+static inline void __hlist_del(struct hlist_node *n)
+{
+        struct hlist_node *next = n->next;
+        struct hlist_node **pprev = n->pprev;
+
+        WRITE_ONCE(*pprev, next);
+        if (next)
+                next->pprev = pprev;
+}
+
+static inline void hlist_del(struct hlist_node *n)
+{
+        __hlist_del(n);
+        n->next = LIST_POISON1;
+        n->pprev = LIST_POISON2;
+}
+
+static inline void hlist_del_init(struct hlist_node *n)
+{
+        if (!hlist_unhashed(n)) {
+                __hlist_del(n);
+                INIT_HLIST_NODE(n);
+        }
+}
+
+static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h)
+{
+        struct hlist_node *first = h->first;
+        n->next = first;
+        if (first)
+                first->pprev = &n->next;
+        h->first = n;
+        n->pprev = &h->first;
+}
+
+/* next must be != NULL */
+static inline void hlist_add_before(struct hlist_node *n,
+                                        struct hlist_node *next)
+{
+        n->pprev = next->pprev;
+        n->next = next;
+        next->pprev = &n->next;
+        *(n->pprev) = n;
+}
+
+static inline void hlist_add_behind(struct hlist_node *n,
+                                    struct hlist_node *prev)
+{
+        n->next = prev->next;
+        prev->next = n;
+        n->pprev = &prev->next;
+
+        if (n->next)
+                n->next->pprev  = &n->next;
+}
+
+/* after that we'll appear to be on some hlist and hlist_del will work */
+static inline void hlist_add_fake(struct hlist_node *n)
+{
+        n->pprev = &n->next;
+}
+
+static inline bool hlist_fake(struct hlist_node *h)
+{
+        return h->pprev == &h->next;
+}
+
+/*
+ * Move a list from one list head to another. Fixup the pprev
+ * reference of the first entry if it exists.
+ */
+static inline void hlist_move_list(struct hlist_head *old,
+                                   struct hlist_head *new)
+{
+        new->first = old->first;
+        if (new->first)
+                new->first->pprev = &new->first;
+        old->first = NULL;
+}
+
+#define hlist_entry(ptr, type, member) container_of(ptr,type,member)
+
+#define hlist_for_each(pos, head) \
+        for (pos = (head)->first; pos ; pos = pos->next)
+
+#define hlist_for_each_safe(pos, n, head) \
+        for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \
+             pos = n)
+
+#define hlist_entry_safe(ptr, type, member) \
+        ({ typeof(ptr) ____ptr = (ptr); \
+           ____ptr ? hlist_entry(____ptr, type, member) : NULL; \
+        })
+
+/**
+ * hlist_for_each_entry - iterate over list of given type
+ * @pos:        the type * to use as a loop cursor.
+ * @head:       the head for your list.
+ * @member:     the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry(pos, head, member)                         \
+        for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\
+             pos;                                                       \
+             pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
+
+/**
+ * hlist_for_each_entry_continue - iterate over a hlist continuing after current point
+ * @pos:        the type * to use as a loop cursor.
+ * @member:     the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_continue(pos, member)                      \
+        for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\
+             pos;                                                       \
+             pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
+
+/**
+ * hlist_for_each_entry_from - iterate over a hlist continuing from current point
+ * @pos:        the type * to use as a loop cursor.
+ * @member:     the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_from(pos, member)                          \
+        for (; pos;                                                     \
+             pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
+
+/**
+ * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry
+ * @pos:        the type * to use as a loop cursor.
+ * @n:          another &struct hlist_node to use as temporary storage
+ * @head:       the head for your list.
+ * @member:     the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_safe(pos, n, head, member)                 \
+        for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\
+             pos && ({ n = pos->member.next; 1; });                     \
+             pos = hlist_entry_safe(n, typeof(*pos), member))
 
-#ifndef TOOLS_LIST_H
-#define TOOLS_LIST_H
 /**
  * list_del_range - deletes range of entries from list.
  * @begin: first element in the range to delete from the list.
@@ -27,4 +767,5 @@ static inline void list_del_range(struct list_head *begin,
  */
 #define list_for_each_from(pos, head) \
         for (; pos != (head); pos = pos->next)
-#endif
+
+#endif /* __TOOLS_LINUX_LIST_H */
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 919b71780710..fc1bc75ae56d 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -6,6 +6,12 @@ BPF_EXTRAVERSION = 1
 
 MAKEFLAGS += --no-print-directory
 
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
 
 # Makefiles suck: This macro sets a default value of $(2) for the
 # variable named by $(1), unless the variable has been set by
@@ -31,7 +37,8 @@ INSTALL = install
 DESTDIR ?=
 DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
 
-LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+include $(srctree)/tools/scripts/Makefile.arch
+
 ifeq ($(LP64), 1)
   libdir_relative = lib64
 else
@@ -57,13 +64,6 @@ ifndef VERBOSE
   VERBOSE = 0
 endif
 
-ifeq ($(srctree),)
-srctree := $(patsubst %/,%,$(dir $(shell pwd)))
-srctree := $(patsubst %/,%,$(dir $(srctree)))
-srctree := $(patsubst %/,%,$(dir $(srctree)))
-#$(info Determined 'srctree' to be $(srctree))
-endif
-
 FEATURE_USER = .libbpf
 FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf
 FEATURE_DISPLAY = libelf bpf
@@ -192,7 +192,7 @@ config-clean:
         $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
 
 clean:
-        $(call QUIET_CLEAN, libbpf) $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d \
+        $(call QUIET_CLEAN, libbpf) $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd \
                 $(RM) LIBBPF-CFLAGS
         $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
 
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 5bdc6eab6852..1f91cc941b7c 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -14,8 +14,8 @@
 #include "bpf.h"
 
 /*
- * When building perf, unistd.h is override. Define __NR_bpf is
- * required to be defined.
+ * When building perf, unistd.h is overrided. __NR_bpf is
+ * required to be defined explicitly.
  */
 #ifndef __NR_bpf
 # if defined(__i386__)
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index 7e319afac78a..90d2baeb621a 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -149,7 +149,7 @@ install_lib: all_cmd
 install: install_lib
 
 clean:
-        $(RM) *.o *~ $(TARGETS) *.a *liblockdep*.so* $(VERSION_FILES) .*.d
+        $(RM) *.o *~ $(TARGETS) *.a *liblockdep*.so* $(VERSION_FILES) .*.d .*.cmd
         $(RM) tags TAGS
 
 PHONY += force
diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h
index 13a2cc1d6140..d60cab2726da 100644
--- a/tools/lib/subcmd/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -4,6 +4,10 @@
 #include <stdbool.h>
 #include <stdint.h>
 
+#ifndef NORETURN
+#define NORETURN __attribute__((__noreturn__))
+#endif
+
 enum parse_opt_type {
         /* special types */
         OPTION_END,
diff --git a/tools/perf/Build b/tools/perf/Build
index 6b67e6f4179f..a43fae7f439a 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -42,6 +42,7 @@ CFLAGS_perf.o              += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))"	\
                               -include $(OUTPUT)PERF-VERSION-FILE
 CFLAGS_builtin-trace.o     += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))"
 CFLAGS_builtin-report.o    += -DTIPDIR="BUILD_STR($(tipdir_SQ))"
+CFLAGS_builtin-report.o    += -DDOCDIR="BUILD_STR($(srcdir_SQ)/Documentation)"
 
 libperf-y += util/
 libperf-y += arch/
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 3a1a32f5479f..fbceb631387c 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -338,6 +338,9 @@ Options passed to clang when compiling BPF scriptlets.
 Specify vmlinux path which has debuginfo.
 (enabled when BPF prologue is on)
 
+--buildid-all::
+Record build-id of all DSOs regardless whether it's actually hit or not.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index a1c10e360db5..e0ce9573b79b 100644
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -12,3 +12,18 @@ List events using substring match: perf list <keyword>
 To see list of saved events and attributes: perf evlist -v
 Use --symfs <dir> if your symbol files are in non-standard locations
 To see callchains in a more compact form: perf report -g folded
+Show individual samples with: perf script
+Limit to show entries above 5% only: perf report --percent-limit 5
+Profiling branch (mis)predictions with: perf record -b / perf report
+Treat branches as callchains: perf report --branch-history
+To count events in every 1000 msec: perf stat -I 1000
+Print event counts in CSV format with: perf stat -x,
+If you have debuginfo enabled, try: perf report -s sym,srcline
+For memory address profiling, try: perf mem record / perf mem report
+For tracepoint events, try: perf report -s trace_fields
+To record callchains for each sample: perf record -g
+To record every process run by an user: perf record -u <user>
+Skip collecing build-id when recording: perf record -B
+To change sampling frequency to 100 Hz: perf record -F 100
+See assembly instructions with percentage: perf annotate <symbol>
+If you prefer Intel style assembly, try: perf annotate -M intel
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index ddf922f93aa1..2e1fa2357528 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -28,6 +28,7 @@ tools/lib/string.c
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/lib/find_bit.c
+tools/lib/bitmap.c
 tools/include/asm/atomic.h
 tools/include/asm/barrier.h
 tools/include/asm/bug.h
@@ -57,6 +58,7 @@ tools/include/linux/rbtree_augmented.h
 tools/include/linux/string.h
 tools/include/linux/types.h
 tools/include/linux/err.h
+tools/include/linux/bitmap.h
 include/asm-generic/bitops/arch_hweight.h
 include/asm-generic/bitops/const_hweight.h
 include/asm-generic/bitops/fls64.h
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index dc4e0adf5c5b..319712a4e02b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -50,6 +50,7 @@ struct record {
         int                     realtime_prio;
         bool                    no_buildid;
         bool                    no_buildid_cache;
+        bool                    buildid_all;
         unsigned long long      samples;
 };
 
@@ -362,6 +363,13 @@ static int process_buildids(struct record *rec)
          */
         symbol_conf.ignore_vmlinux_buildid = true;
 
+        /*
+         * If --buildid-all is given, it marks all DSO regardless of hits,
+         * so no need to process samples.
+         */
+        if (rec->buildid_all)
+                rec->tool.sample = NULL;
+
         return perf_session__process_events(session);
 }
 
@@ -756,12 +764,8 @@ out_child:
 
                 if (!rec->no_buildid) {
                         process_buildids(rec);
-                        /*
-                         * We take all buildids when the file contains
-                         * AUX area tracing data because we do not decode the
-                         * trace because it would take too long.
-                         */
-                        if (rec->opts.full_auxtrace)
+
+                        if (rec->buildid_all)
                                 dsos__hit_all(rec->session);
                 }
                 perf_session__write_header(rec->session, rec->evlist, fd, true);
@@ -1138,6 +1142,8 @@ struct option __record_options[] = {
                    "options passed to clang when compiling BPF scriptlets"),
         OPT_STRING(0, "vmlinux", &symbol_conf.vmlinux_name,
                    "file", "vmlinux pathname"),
+        OPT_BOOLEAN(0, "buildid-all", &record.buildid_all,
+                    "Record build-id of all DSOs regardless of hits"),
         OPT_END()
 };
 
@@ -1255,6 +1261,14 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
         if (err)
                 goto out_symbol_exit;
 
+        /*
+         * We take all buildids when the file contains
+         * AUX area tracing data because we do not decode the
+         * trace because it would take too long.
+         */
+        if (rec->opts.full_auxtrace)
+                rec->buildid_all = true;
+
         if (record_opts__config(&rec->opts)) {
                 err = -EINVAL;
                 goto out_symbol_exit;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index d5a42ee12529..2bf537f190a0 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -28,6 +28,7 @@
 #include "util/tool.h"
 
 #include <subcmd/parse-options.h>
+#include <subcmd/exec-cmd.h>
 #include "util/parse-events.h"
 
 #include "util/thread.h"
@@ -433,7 +434,14 @@ static int report__browse_hists(struct report *rep)
         int ret;
         struct perf_session *session = rep->session;
         struct perf_evlist *evlist = session->evlist;
-        const char *help = perf_tip(TIPDIR);
+        const char *help = perf_tip(system_path(TIPDIR));
+
+        if (help == NULL) {
+                /* fallback for people who don't install perf ;-) */
+                help = perf_tip(DOCDIR);
+                if (help == NULL)
+                        help = "Cannot load tips.txt file, please install perf!";
+        }
 
         switch (use_browser) {
         case 1:
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7f568244662b..038e877081b6 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1588,7 +1588,7 @@ static int add_default_attributes(void)
         return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
 }
 
-static const char * const recort_usage[] = {
+static const char * const stat_record_usage[] = {
         "perf stat record [<options>]",
         NULL,
 };
@@ -1611,7 +1611,7 @@ static int __cmd_record(int argc, const char **argv)
         struct perf_session *session;
         struct perf_data_file *file = &perf_stat.file;
 
-        argc = parse_options(argc, argv, stat_options, record_usage,
+        argc = parse_options(argc, argv, stat_options, stat_record_usage,
                              PARSE_OPT_STOP_AT_NON_OPTION);
 
         if (output_name)
@@ -1745,7 +1745,7 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
         return set_maps(st);
 }
 
-static const char * const report_usage[] = {
+static const char * const stat_report_usage[] = {
         "perf stat report [<options>]",
         NULL,
 };
@@ -1779,7 +1779,7 @@ static int __cmd_report(int argc, const char **argv)
         struct stat st;
         int ret;
 
-        argc = parse_options(argc, argv, options, report_usage, 0);
+        argc = parse_options(argc, argv, options, stat_report_usage, 0);
 
         if (!input_name || !strlen(input_name)) {
                 if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 254d06e39bea..e5959c136a19 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -17,7 +17,7 @@ detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected)
 
 CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
 
-include $(src-perf)/config/Makefile.arch
+include $(srctree)/tools/scripts/Makefile.arch
 
 $(call detected_var,ARCH)
 
@@ -493,7 +493,7 @@ else
 
       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_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
       PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
       FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 
@@ -692,6 +692,7 @@ template_dir = share/perf-core/templates
 STRACE_GROUPS_DIR = share/perf-core/strace/groups
 htmldir = share/doc/perf-doc
 tipdir = share/doc/perf-tip
+srcdir = $(srctree)/tools/perf
 ifeq ($(prefix),/usr)
 sysconfdir = /etc
 ETC_PERFCONFIG = $(sysconfdir)/perfconfig
@@ -722,6 +723,7 @@ tipdir_SQ = $(subst ','\'',$(tipdir))
 prefix_SQ = $(subst ','\'',$(prefix))
 sysconfdir_SQ = $(subst ','\'',$(sysconfdir))
 libdir_SQ = $(subst ','\'',$(libdir))
+srcdir_SQ = $(subst ','\'',$(srcdir))
 
 ifneq ($(filter /%,$(firstword $(perfexecdir))),)
 perfexec_instdir = $(perfexecdir)
@@ -776,6 +778,7 @@ $(call detected_var,STRACE_GROUPS_DIR_SQ)
 $(call detected_var,prefix_SQ)
 $(call detected_var,perfexecdir_SQ)
 $(call detected_var,tipdir_SQ)
+$(call detected_var,srcdir_SQ)
 $(call detected_var,LIBDIR)
 $(call detected_var,GTK_CFLAGS)
 $(call detected_var,PERL_EMBED_CCOPTS)
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index bcfd081ee1d2..071a8b5f5232 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -87,11 +87,6 @@ struct machine *setup_fake_machine(struct machines *machines)
                 return NULL;
         }
 
-        if (machine__create_kernel_maps(machine)) {
-                pr_debug("Cannot create kernel maps\n");
-                return NULL;
-        }
-
         for (i = 0; i < ARRAY_SIZE(fake_threads); i++) {
                 struct thread *thread;
 
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index e36089212061..5e6a86e50fb9 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -706,6 +706,7 @@ int test__hists_cumulate(int subtest __maybe_unused)
         err = parse_events(evlist, "cpu-clock", NULL);
         if (err)
                 goto out;
+        err = TEST_FAIL;
 
         machines__init(&machines);
 
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 2a784befd9ce..351a42463444 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -120,6 +120,7 @@ int test__hists_filter(int subtest __maybe_unused)
         err = parse_events(evlist, "task-clock", NULL);
         if (err)
                 goto out;
+        err = TEST_FAIL;
 
         /* default sort order (comm,dso,sym) will be used */
         if (setup_sorting(NULL) < 0)
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index c764d69ac6ef..64b257d8d557 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -293,6 +293,7 @@ int test__hists_link(int subtest __maybe_unused)
         if (err)
                 goto out;
 
+        err = TEST_FAIL;
         /* default sort order (comm,dso,sym) will be used */
         if (setup_sorting(NULL) < 0)
                 goto out;
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index ebe6cd485b5d..b231265148d8 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -597,6 +597,7 @@ int test__hists_output(int subtest __maybe_unused)
         err = parse_events(evlist, "cpu-clock", NULL);
         if (err)
                 goto out;
+        err = TEST_FAIL;
 
         machines__init(&machines);
 
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index c1fbb8e884c0..df38decc48c3 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -1,3 +1,5 @@
+include ../scripts/Makefile.include
+
 ifndef MK
 ifeq ($(MAKECMDGOALS),)
 # no target specified, trigger the whole suite
@@ -12,7 +14,19 @@ endif
 else
 PERF := .
 
-include config/Makefile.arch
+# As per kernel Makefile, avoid funny character set dependencies
+unexport LC_ALL
+LC_COLLATE=C
+LC_NUMERIC=C
+export LC_COLLATE LC_NUMERIC
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
+include $(srctree)/tools/scripts/Makefile.arch
 
 # FIXME looks like x86 is the only arch running tests ;-)
 # we need some IS_(32/64) flag to make this generic
@@ -280,5 +294,5 @@ all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools
 out: $(run_O)
         @echo OK
 
-.PHONY: all $(run) $(run_O) tarpkg clean
+.PHONY: all $(run) $(run_O) tarpkg clean make_kernelsrc make_kernelsrc_tools
 endif # ifndef MK
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 901d481e6cea..08c09ad755d2 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -480,7 +480,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *help)
 
         hists__browser_title(browser->hists, hbt, title, sizeof(title));
 
-        if (ui_browser__show(&browser->b, title, help) < 0)
+        if (ui_browser__show(&browser->b, title, "%s", help) < 0)
                 return -1;
 
         while (1) {
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index cd61bb1f3917..85155e91b61b 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -503,7 +503,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
         if (comm_event == NULL)
                 goto out;
 
-        mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size);
+        mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size);
         if (mmap_event == NULL)
                 goto out_free_comm;
 
@@ -577,7 +577,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
         if (comm_event == NULL)
                 goto out;
 
-        mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size);
+        mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size);
         if (mmap_event == NULL)
                 goto out_free_comm;
 
diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c
index bdf98f6f27bb..0d3dfcb919b4 100644
--- a/tools/perf/util/strlist.c
+++ b/tools/perf/util/strlist.c
@@ -126,6 +126,11 @@ static int strlist__parse_list_entry(struct strlist *slist, const char *s,
                         err = strlist__load(slist, subst);
                         goto out;
                 }
+
+                if (slist->file_only) {
+                        err = -ENOENT;
+                        goto out;
+                }
         }
 
         err = strlist__add(slist, s);
@@ -157,11 +162,13 @@ struct strlist *strlist__new(const char *list, const struct strlist_config *conf
 
         if (slist != NULL) {
                 bool dupstr = true;
+                bool file_only = false;
                 const char *dirname = NULL;
 
                 if (config) {
                         dupstr = !config->dont_dupstr;
                         dirname = config->dirname;
+                        file_only = config->file_only;
                 }
 
                 rblist__init(&slist->rblist);
@@ -170,6 +177,7 @@ struct strlist *strlist__new(const char *list, const struct strlist_config *conf
                 slist->rblist.node_delete = strlist__node_delete;
 
                 slist->dupstr    = dupstr;
+                slist->file_only = file_only;
 
                 if (list && strlist__parse_list(slist, list, dirname) != 0)
                         goto out_error;
diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h
index 297565aa7535..ca990029e243 100644
--- a/tools/perf/util/strlist.h
+++ b/tools/perf/util/strlist.h
@@ -13,11 +13,18 @@ struct str_node {
 
 struct strlist {
         struct rblist rblist;
-        bool           dupstr;
+        bool          dupstr;
+        bool          file_only;
 };
 
+/*
+ * @file_only: When dirname is present, only consider entries as filenames,
+ *             that should not be added to the list if dirname/entry is not
+ *             found
+ */
 struct strlist_config {
         bool dont_dupstr;
+        bool file_only;
         const char *dirname;
 };
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 88b8f8d21f58..ead9509835d2 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -17,7 +17,6 @@
 #include <unistd.h>
 #include "callchain.h"
 #include "strlist.h"
-#include <subcmd/exec-cmd.h>
 
 struct callchain_param  callchain_param = {
         .mode   = CHAIN_GRAPH_ABS,
@@ -672,14 +671,16 @@ const char *perf_tip(const char *dirpath)
         struct str_node *node;
         char *tip = NULL;
         struct strlist_config conf = {
-                .dirname = system_path(dirpath) ,
+                .dirname = dirpath,
+                .file_only = true,
         };
 
         tips = strlist__new("tips.txt", &conf);
-        if (tips == NULL || strlist__nr_entries(tips) == 1) {
-                tip = (char *)"Cannot find tips.txt file";
+        if (tips == NULL)
+                return errno == ENOENT ? NULL : "Tip: get more memory! ;-p";
+
+        if (strlist__nr_entries(tips) == 0)
                 goto out;
-        }
 
         node = strlist__entry(tips, random() % strlist__nr_entries(tips));
         if (asprintf(&tip, "Tip: %s", node->s) < 0)
diff --git a/tools/perf/config/Makefile.arch b/tools/scripts/Makefile.arch
index e11fbd6fae78..e11fbd6fae78 100644
--- a/tools/perf/config/Makefile.arch
+++ b/tools/scripts/Makefile.arch