73 files changed, 2921 insertions, 230 deletions

diff --git a/tools/Makefile b/tools/Makefile
index 0ba0df3b516f..6339f6ac3ccb 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -8,23 +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 '  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'
@@ -52,7 +53,7 @@ acpi: FORCE
 cpupower: FORCE
         $(call descend,power/$@)
 
-cgroup firewire hv guest usb virtio vm net iio: FORCE
+cgroup firewire hv guest spi usb virtio vm net iio: FORCE
         $(call descend,$@)
 
 liblockdep: FORCE
@@ -118,7 +119,7 @@ acpi_clean:
 cpupower_clean:
         $(call descend,power/cpupower,clean)
 
-cgroup_clean hv_clean firewire_clean lguest_clean usb_clean virtio_clean vm_clean net_clean iio_clean:
+cgroup_clean hv_clean firewire_clean lguest_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean:
         $(call descend,$(@:_clean=),clean)
 
 liblockdep_clean:
@@ -127,6 +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)
 
@@ -142,9 +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 usb_clean virtio_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/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c
index 5480e4e424eb..fdc9ca4c0356 100644
--- a/tools/hv/hv_fcopy_daemon.c
+++ b/tools/hv/hv_fcopy_daemon.c
@@ -37,12 +37,14 @@
 
 static int target_fd;
 static char target_fname[W_MAX_PATH];
+static unsigned long long filesize;
 
 static int hv_start_fcopy(struct hv_start_fcopy *smsg)
 {
         int error = HV_E_FAIL;
         char *q, *p;
 
+        filesize = 0;
         p = (char *)smsg->path_name;
         snprintf(target_fname, sizeof(target_fname), "%s/%s",
                  (char *)smsg->path_name, (char *)smsg->file_name);
@@ -98,14 +100,26 @@ done:
 static int hv_copy_data(struct hv_do_fcopy *cpmsg)
 {
         ssize_t bytes_written;
+        int ret = 0;
 
         bytes_written = pwrite(target_fd, cpmsg->data, cpmsg->size,
                                 cpmsg->offset);
 
-        if (bytes_written != cpmsg->size)
-                return HV_E_FAIL;
+        filesize += cpmsg->size;
+        if (bytes_written != cpmsg->size) {
+                switch (errno) {
+                case ENOSPC:
+                        ret = HV_ERROR_DISK_FULL;
+                        break;
+                default:
+                        ret = HV_E_FAIL;
+                        break;
+                }
+                syslog(LOG_ERR, "pwrite failed to write %llu bytes: %ld (%s)",
+                       filesize, (long)bytes_written, strerror(errno));
+        }
 
-        return 0;
+        return ret;
 }
 
 static int hv_copy_finished(void)
@@ -165,7 +179,7 @@ int main(int argc, char *argv[])
         }
 
         openlog("HV_FCOPY", 0, LOG_USER);
-        syslog(LOG_INFO, "HV_FCOPY starting; pid is:%d", getpid());
+        syslog(LOG_INFO, "starting; pid is:%d", getpid());
 
         fcopy_fd = open("/dev/vmbus/hv_fcopy", O_RDWR);
 
@@ -201,7 +215,7 @@ int main(int argc, char *argv[])
                         }
                         kernel_modver = *(__u32 *)buffer;
                         in_handshake = 0;
-                        syslog(LOG_INFO, "HV_FCOPY: kernel module version: %d",
+                        syslog(LOG_INFO, "kernel module version: %d",
                                kernel_modver);
                         continue;
                 }
diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c
index 96234b638249..5d51d6ff08e6 100644
--- a/tools/hv/hv_vss_daemon.c
+++ b/tools/hv/hv_vss_daemon.c
@@ -254,7 +254,7 @@ int main(int argc, char *argv[])
                         syslog(LOG_ERR, "Illegal op:%d\n", op);
                 }
                 vss_msg->error = error;
-                len = write(vss_fd, &error, sizeof(struct hv_vss_msg));
+                len = write(vss_fd, vss_msg, sizeof(struct hv_vss_msg));
                 if (len != sizeof(struct hv_vss_msg)) {
                         syslog(LOG_ERR, "write failed; error: %d %s", errno,
                                strerror(errno));
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
diff --git a/tools/spi/.gitignore b/tools/spi/.gitignore
new file mode 100644
index 000000000000..4280576397e8
--- /dev/null
+++ b/tools/spi/.gitignore
@@ -0,0 +1,2 @@
+spidev_fdx
+spidev_test
diff --git a/tools/spi/Makefile b/tools/spi/Makefile
new file mode 100644
index 000000000000..cd0db62e4d9d
--- /dev/null
+++ b/tools/spi/Makefile
@@ -0,0 +1,4 @@
+all: spidev_test spidev_fdx
+
+clean:
+        $(RM) spidev_test spidev_fdx
diff --git a/tools/spi/spidev_fdx.c b/tools/spi/spidev_fdx.c
new file mode 100644
index 000000000000..0ea3e51292fc
--- /dev/null
+++ b/tools/spi/spidev_fdx.c
@@ -0,0 +1,158 @@
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <string.h>
+
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include <linux/types.h>
+#include <linux/spi/spidev.h>
+
+
+static int verbose;
+
+static void do_read(int fd, int len)
+{
+        unsigned char   buf[32], *bp;
+        int             status;
+
+        /* read at least 2 bytes, no more than 32 */
+        if (len < 2)
+                len = 2;
+        else if (len > sizeof(buf))
+                len = sizeof(buf);
+        memset(buf, 0, sizeof buf);
+
+        status = read(fd, buf, len);
+        if (status < 0) {
+                perror("read");
+                return;
+        }
+        if (status != len) {
+                fprintf(stderr, "short read\n");
+                return;
+        }
+
+        printf("read(%2d, %2d): %02x %02x,", len, status,
+                buf[0], buf[1]);
+        status -= 2;
+        bp = buf + 2;
+        while (status-- > 0)
+                printf(" %02x", *bp++);
+        printf("\n");
+}
+
+static void do_msg(int fd, int len)
+{
+        struct spi_ioc_transfer xfer[2];
+        unsigned char           buf[32], *bp;
+        int                     status;
+
+        memset(xfer, 0, sizeof xfer);
+        memset(buf, 0, sizeof buf);
+
+        if (len > sizeof buf)
+                len = sizeof buf;
+
+        buf[0] = 0xaa;
+        xfer[0].tx_buf = (unsigned long)buf;
+        xfer[0].len = 1;
+
+        xfer[1].rx_buf = (unsigned long) buf;
+        xfer[1].len = len;
+
+        status = ioctl(fd, SPI_IOC_MESSAGE(2), xfer);
+        if (status < 0) {
+                perror("SPI_IOC_MESSAGE");
+                return;
+        }
+
+        printf("response(%2d, %2d): ", len, status);
+        for (bp = buf; len; len--)
+                printf(" %02x", *bp++);
+        printf("\n");
+}
+
+static void dumpstat(const char *name, int fd)
+{
+        __u8    lsb, bits;
+        __u32   mode, speed;
+
+        if (ioctl(fd, SPI_IOC_RD_MODE32, &mode) < 0) {
+                perror("SPI rd_mode");
+                return;
+        }
+        if (ioctl(fd, SPI_IOC_RD_LSB_FIRST, &lsb) < 0) {
+                perror("SPI rd_lsb_fist");
+                return;
+        }
+        if (ioctl(fd, SPI_IOC_RD_BITS_PER_WORD, &bits) < 0) {
+                perror("SPI bits_per_word");
+                return;
+        }
+        if (ioctl(fd, SPI_IOC_RD_MAX_SPEED_HZ, &speed) < 0) {
+                perror("SPI max_speed_hz");
+                return;
+        }
+
+        printf("%s: spi mode 0x%x, %d bits %sper word, %d Hz max\n",
+                name, mode, bits, lsb ? "(lsb first) " : "", speed);
+}
+
+int main(int argc, char **argv)
+{
+        int             c;
+        int             readcount = 0;
+        int             msglen = 0;
+        int             fd;
+        const char      *name;
+
+        while ((c = getopt(argc, argv, "hm:r:v")) != EOF) {
+                switch (c) {
+                case 'm':
+                        msglen = atoi(optarg);
+                        if (msglen < 0)
+                                goto usage;
+                        continue;
+                case 'r':
+                        readcount = atoi(optarg);
+                        if (readcount < 0)
+                                goto usage;
+                        continue;
+                case 'v':
+                        verbose++;
+                        continue;
+                case 'h':
+                case '?':
+usage:
+                        fprintf(stderr,
+                                "usage: %s [-h] [-m N] [-r N] /dev/spidevB.D\n",
+                                argv[0]);
+                        return 1;
+                }
+        }
+
+        if ((optind + 1) != argc)
+                goto usage;
+        name = argv[optind];
+
+        fd = open(name, O_RDWR);
+        if (fd < 0) {
+                perror("open");
+                return 1;
+        }
+
+        dumpstat(name, fd);
+
+        if (msglen)
+                do_msg(fd, msglen);
+
+        if (readcount)
+                do_read(fd, readcount);
+
+        close(fd);
+        return 0;
+}
diff --git a/tools/spi/spidev_test.c b/tools/spi/spidev_test.c
new file mode 100644
index 000000000000..8a73d8185316
--- /dev/null
+++ b/tools/spi/spidev_test.c
@@ -0,0 +1,399 @@
+/*
+ * SPI testing utility (using spidev driver)
+ *
+ * Copyright (c) 2007  MontaVista Software, Inc.
+ * Copyright (c) 2007  Anton Vorontsov <avorontsov@ru.mvista.com>
+ *
+ * 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.
+ *
+ * Cross-compile with cross-gcc -I/path/to/cross-kernel/include
+ */
+
+#include <stdint.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <getopt.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <linux/types.h>
+#include <linux/spi/spidev.h>
+
+#define ARRAY_SIZE(a) (sizeof(a) / sizeof((a)[0]))
+
+static void pabort(const char *s)
+{
+        perror(s);
+        abort();
+}
+
+static const char *device = "/dev/spidev1.1";
+static uint32_t mode;
+static uint8_t bits = 8;
+static char *input_file;
+static char *output_file;
+static uint32_t speed = 500000;
+static uint16_t delay;
+static int verbose;
+
+uint8_t default_tx[] = {
+        0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+        0x40, 0x00, 0x00, 0x00, 0x00, 0x95,
+        0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+        0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+        0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+        0xF0, 0x0D,
+};
+
+uint8_t default_rx[ARRAY_SIZE(default_tx)] = {0, };
+char *input_tx;
+
+static void hex_dump(const void *src, size_t length, size_t line_size,
+                     char *prefix)
+{
+        int i = 0;
+        const unsigned char *address = src;
+        const unsigned char *line = address;
+        unsigned char c;
+
+        printf("%s | ", prefix);
+        while (length-- > 0) {
+                printf("%02X ", *address++);
+                if (!(++i % line_size) || (length == 0 && i % line_size)) {
+                        if (length == 0) {
+                                while (i++ % line_size)
+                                        printf("__ ");
+                        }
+                        printf(" | ");  /* right close */
+                        while (line < address) {
+                                c = *line++;
+                                printf("%c", (c < 33 || c == 255) ? 0x2E : c);
+                        }
+                        printf("\n");
+                        if (length > 0)
+                                printf("%s | ", prefix);
+                }
+        }
+}
+
+/*
+ *  Unescape - process hexadecimal escape character
+ *      converts shell input "\x23" -> 0x23
+ */
+static int unescape(char *_dst, char *_src, size_t len)
+{
+        int ret = 0;
+        int match;
+        char *src = _src;
+        char *dst = _dst;
+        unsigned int ch;
+
+        while (*src) {
+                if (*src == '\\' && *(src+1) == 'x') {
+                        match = sscanf(src + 2, "%2x", &ch);
+                        if (!match)
+                                pabort("malformed input string");
+
+                        src += 4;
+                        *dst++ = (unsigned char)ch;
+                } else {
+                        *dst++ = *src++;
+                }
+                ret++;
+        }
+        return ret;
+}
+
+static void transfer(int fd, uint8_t const *tx, uint8_t const *rx, size_t len)
+{
+        int ret;
+        int out_fd;
+        struct spi_ioc_transfer tr = {
+                .tx_buf = (unsigned long)tx,
+                .rx_buf = (unsigned long)rx,
+                .len = len,
+                .delay_usecs = delay,
+                .speed_hz = speed,
+                .bits_per_word = bits,
+        };
+
+        if (mode & SPI_TX_QUAD)
+                tr.tx_nbits = 4;
+        else if (mode & SPI_TX_DUAL)
+                tr.tx_nbits = 2;
+        if (mode & SPI_RX_QUAD)
+                tr.rx_nbits = 4;
+        else if (mode & SPI_RX_DUAL)
+                tr.rx_nbits = 2;
+        if (!(mode & SPI_LOOP)) {
+                if (mode & (SPI_TX_QUAD | SPI_TX_DUAL))
+                        tr.rx_buf = 0;
+                else if (mode & (SPI_RX_QUAD | SPI_RX_DUAL))
+                        tr.tx_buf = 0;
+        }
+
+        ret = ioctl(fd, SPI_IOC_MESSAGE(1), &tr);
+        if (ret < 1)
+                pabort("can't send spi message");
+
+        if (verbose)
+                hex_dump(tx, len, 32, "TX");
+
+        if (output_file) {
+                out_fd = open(output_file, O_WRONLY | O_CREAT | O_TRUNC, 0666);
+                if (out_fd < 0)
+                        pabort("could not open output file");
+
+                ret = write(out_fd, rx, len);
+                if (ret != len)
+                        pabort("not all bytes written to output file");
+
+                close(out_fd);
+        }
+
+        if (verbose || !output_file)
+                hex_dump(rx, len, 32, "RX");
+}
+
+static void print_usage(const char *prog)
+{
+        printf("Usage: %s [-DsbdlHOLC3]\n", prog);
+        puts("  -D --device   device to use (default /dev/spidev1.1)\n"
+             "  -s --speed    max speed (Hz)\n"
+             "  -d --delay    delay (usec)\n"
+             "  -b --bpw      bits per word\n"
+             "  -i --input    input data from a file (e.g. \"test.bin\")\n"
+             "  -o --output   output data to a file (e.g. \"results.bin\")\n"
+             "  -l --loop     loopback\n"
+             "  -H --cpha     clock phase\n"
+             "  -O --cpol     clock polarity\n"
+             "  -L --lsb      least significant bit first\n"
+             "  -C --cs-high  chip select active high\n"
+             "  -3 --3wire    SI/SO signals shared\n"
+             "  -v --verbose  Verbose (show tx buffer)\n"
+             "  -p            Send data (e.g. \"1234\\xde\\xad\")\n"
+             "  -N --no-cs    no chip select\n"
+             "  -R --ready    slave pulls low to pause\n"
+             "  -2 --dual     dual transfer\n"
+             "  -4 --quad     quad transfer\n");
+        exit(1);
+}
+
+static void parse_opts(int argc, char *argv[])
+{
+        while (1) {
+                static const struct option lopts[] = {
+                        { "device",  1, 0, 'D' },
+                        { "speed",   1, 0, 's' },
+                        { "delay",   1, 0, 'd' },
+                        { "bpw",     1, 0, 'b' },
+                        { "input",   1, 0, 'i' },
+                        { "output",  1, 0, 'o' },
+                        { "loop",    0, 0, 'l' },
+                        { "cpha",    0, 0, 'H' },
+                        { "cpol",    0, 0, 'O' },
+                        { "lsb",     0, 0, 'L' },
+                        { "cs-high", 0, 0, 'C' },
+                        { "3wire",   0, 0, '3' },
+                        { "no-cs",   0, 0, 'N' },
+                        { "ready",   0, 0, 'R' },
+                        { "dual",    0, 0, '2' },
+                        { "verbose", 0, 0, 'v' },
+                        { "quad",    0, 0, '4' },
+                        { NULL, 0, 0, 0 },
+                };
+                int c;
+
+                c = getopt_long(argc, argv, "D:s:d:b:i:o:lHOLC3NR24p:v",
+                                lopts, NULL);
+
+                if (c == -1)
+                        break;
+
+                switch (c) {
+                case 'D':
+                        device = optarg;
+                        break;
+                case 's':
+                        speed = atoi(optarg);
+                        break;
+                case 'd':
+                        delay = atoi(optarg);
+                        break;
+                case 'b':
+                        bits = atoi(optarg);
+                        break;
+                case 'i':
+                        input_file = optarg;
+                        break;
+                case 'o':
+                        output_file = optarg;
+                        break;
+                case 'l':
+                        mode |= SPI_LOOP;
+                        break;
+                case 'H':
+                        mode |= SPI_CPHA;
+                        break;
+                case 'O':
+                        mode |= SPI_CPOL;
+                        break;
+                case 'L':
+                        mode |= SPI_LSB_FIRST;
+                        break;
+                case 'C':
+                        mode |= SPI_CS_HIGH;
+                        break;
+                case '3':
+                        mode |= SPI_3WIRE;
+                        break;
+                case 'N':
+                        mode |= SPI_NO_CS;
+                        break;
+                case 'v':
+                        verbose = 1;
+                        break;
+                case 'R':
+                        mode |= SPI_READY;
+                        break;
+                case 'p':
+                        input_tx = optarg;
+                        break;
+                case '2':
+                        mode |= SPI_TX_DUAL;
+                        break;
+                case '4':
+                        mode |= SPI_TX_QUAD;
+                        break;
+                default:
+                        print_usage(argv[0]);
+                        break;
+                }
+        }
+        if (mode & SPI_LOOP) {
+                if (mode & SPI_TX_DUAL)
+                        mode |= SPI_RX_DUAL;
+                if (mode & SPI_TX_QUAD)
+                        mode |= SPI_RX_QUAD;
+        }
+}
+
+static void transfer_escaped_string(int fd, char *str)
+{
+        size_t size = strlen(str + 1);
+        uint8_t *tx;
+        uint8_t *rx;
+
+        tx = malloc(size);
+        if (!tx)
+                pabort("can't allocate tx buffer");
+
+        rx = malloc(size);
+        if (!rx)
+                pabort("can't allocate rx buffer");
+
+        size = unescape((char *)tx, str, size);
+        transfer(fd, tx, rx, size);
+        free(rx);
+        free(tx);
+}
+
+static void transfer_file(int fd, char *filename)
+{
+        ssize_t bytes;
+        struct stat sb;
+        int tx_fd;
+        uint8_t *tx;
+        uint8_t *rx;
+
+        if (stat(filename, &sb) == -1)
+                pabort("can't stat input file");
+
+        tx_fd = open(filename, O_RDONLY);
+        if (fd < 0)
+                pabort("can't open input file");
+
+        tx = malloc(sb.st_size);
+        if (!tx)
+                pabort("can't allocate tx buffer");
+
+        rx = malloc(sb.st_size);
+        if (!rx)
+                pabort("can't allocate rx buffer");
+
+        bytes = read(tx_fd, tx, sb.st_size);
+        if (bytes != sb.st_size)
+                pabort("failed to read input file");
+
+        transfer(fd, tx, rx, sb.st_size);
+        free(rx);
+        free(tx);
+        close(tx_fd);
+}
+
+int main(int argc, char *argv[])
+{
+        int ret = 0;
+        int fd;
+
+        parse_opts(argc, argv);
+
+        fd = open(device, O_RDWR);
+        if (fd < 0)
+                pabort("can't open device");
+
+        /*
+         * spi mode
+         */
+        ret = ioctl(fd, SPI_IOC_WR_MODE32, &mode);
+        if (ret == -1)
+                pabort("can't set spi mode");
+
+        ret = ioctl(fd, SPI_IOC_RD_MODE32, &mode);
+        if (ret == -1)
+                pabort("can't get spi mode");
+
+        /*
+         * bits per word
+         */
+        ret = ioctl(fd, SPI_IOC_WR_BITS_PER_WORD, &bits);
+        if (ret == -1)
+                pabort("can't set bits per word");
+
+        ret = ioctl(fd, SPI_IOC_RD_BITS_PER_WORD, &bits);
+        if (ret == -1)
+                pabort("can't get bits per word");
+
+        /*
+         * max speed hz
+         */
+        ret = ioctl(fd, SPI_IOC_WR_MAX_SPEED_HZ, &speed);
+        if (ret == -1)
+                pabort("can't set max speed hz");
+
+        ret = ioctl(fd, SPI_IOC_RD_MAX_SPEED_HZ, &speed);
+        if (ret == -1)
+                pabort("can't get max speed hz");
+
+        printf("spi mode: 0x%x\n", mode);
+        printf("bits per word: %d\n", bits);
+        printf("max speed: %d Hz (%d KHz)\n", speed, speed/1000);
+
+        if (input_tx && input_file)
+                pabort("only one of -p and --input may be selected");
+
+        if (input_tx)
+                transfer_escaped_string(fd, input_tx);
+        else if (input_file)
+                transfer_file(fd, input_file);
+        else
+                transfer(fd, default_tx, default_rx, sizeof(default_tx));
+
+        close(fd);
+
+        return ret;
+}
diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild
index 38b00ecb2ed5..a34bfd0c8928 100644
--- a/tools/testing/nvdimm/Kbuild
+++ b/tools/testing/nvdimm/Kbuild
@@ -9,6 +9,8 @@ ldflags-y += --wrap=memunmap
 ldflags-y += --wrap=__devm_request_region
 ldflags-y += --wrap=__request_region
 ldflags-y += --wrap=__release_region
+ldflags-y += --wrap=devm_memremap_pages
+ldflags-y += --wrap=phys_to_pfn_t
 
 DRIVERS := ../../../drivers
 NVDIMM_SRC := $(DRIVERS)/nvdimm
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index b7251314bbc0..7ec7df9e7fc7 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/io.h>
+#include <linux/mm.h>
 #include "nfit_test.h"
 
 static LIST_HEAD(iomap_head);
@@ -41,7 +42,7 @@ void nfit_test_teardown(void)
 }
 EXPORT_SYMBOL(nfit_test_teardown);
 
-static struct nfit_test_resource *get_nfit_res(resource_size_t resource)
+static struct nfit_test_resource *__get_nfit_res(resource_size_t resource)
 {
         struct iomap_ops *ops;
 
@@ -51,14 +52,22 @@ static struct nfit_test_resource *get_nfit_res(resource_size_t resource)
         return NULL;
 }
 
-void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size,
-                void __iomem *(*fallback_fn)(resource_size_t, unsigned long))
+static struct nfit_test_resource *get_nfit_res(resource_size_t resource)
 {
-        struct nfit_test_resource *nfit_res;
+        struct nfit_test_resource *res;
 
         rcu_read_lock();
-        nfit_res = get_nfit_res(offset);
+        res = __get_nfit_res(resource);
         rcu_read_unlock();
+
+        return res;
+}
+
+void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size,
+                void __iomem *(*fallback_fn)(resource_size_t, unsigned long))
+{
+        struct nfit_test_resource *nfit_res = get_nfit_res(offset);
+
         if (nfit_res)
                 return (void __iomem *) nfit_res->buf + offset
                         - nfit_res->res->start;
@@ -68,11 +77,8 @@ void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size,
 void __iomem *__wrap_devm_ioremap_nocache(struct device *dev,
                 resource_size_t offset, unsigned long size)
 {
-        struct nfit_test_resource *nfit_res;
+        struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
-        rcu_read_lock();
-        nfit_res = get_nfit_res(offset);
-        rcu_read_unlock();
         if (nfit_res)
                 return (void __iomem *) nfit_res->buf + offset
                         - nfit_res->res->start;
@@ -83,25 +89,58 @@ EXPORT_SYMBOL(__wrap_devm_ioremap_nocache);
 void *__wrap_devm_memremap(struct device *dev, resource_size_t offset,
                 size_t size, unsigned long flags)
 {
-        struct nfit_test_resource *nfit_res;
+        struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
-        rcu_read_lock();
-        nfit_res = get_nfit_res(offset);
-        rcu_read_unlock();
         if (nfit_res)
                 return nfit_res->buf + offset - nfit_res->res->start;
         return devm_memremap(dev, offset, size, flags);
 }
 EXPORT_SYMBOL(__wrap_devm_memremap);
 
+#ifdef __HAVE_ARCH_PTE_DEVMAP
+#include <linux/memremap.h>
+#include <linux/pfn_t.h>
+
+void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res,
+                struct percpu_ref *ref, struct vmem_altmap *altmap)
+{
+        resource_size_t offset = res->start;
+        struct nfit_test_resource *nfit_res = get_nfit_res(offset);
+
+        if (nfit_res)
+                return nfit_res->buf + offset - nfit_res->res->start;
+        return devm_memremap_pages(dev, res, ref, altmap);
+}
+EXPORT_SYMBOL(__wrap_devm_memremap_pages);
+
+pfn_t __wrap_phys_to_pfn_t(dma_addr_t addr, unsigned long flags)
+{
+        struct nfit_test_resource *nfit_res = get_nfit_res(addr);
+
+        if (nfit_res)
+                flags &= ~PFN_MAP;
+        return phys_to_pfn_t(addr, flags);
+}
+EXPORT_SYMBOL(__wrap_phys_to_pfn_t);
+#else
+/* to be removed post 4.5-rc1 */
+void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res)
+{
+        resource_size_t offset = res->start;
+        struct nfit_test_resource *nfit_res = get_nfit_res(offset);
+
+        if (nfit_res)
+                return nfit_res->buf + offset - nfit_res->res->start;
+        return devm_memremap_pages(dev, res);
+}
+EXPORT_SYMBOL(__wrap_devm_memremap_pages);
+#endif
+
 void *__wrap_memremap(resource_size_t offset, size_t size,
                 unsigned long flags)
 {
-        struct nfit_test_resource *nfit_res;
+        struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
-        rcu_read_lock();
-        nfit_res = get_nfit_res(offset);
-        rcu_read_unlock();
         if (nfit_res)
                 return nfit_res->buf + offset - nfit_res->res->start;
         return memremap(offset, size, flags);
@@ -110,11 +149,8 @@ EXPORT_SYMBOL(__wrap_memremap);
 
 void __wrap_devm_memunmap(struct device *dev, void *addr)
 {
-        struct nfit_test_resource *nfit_res;
+        struct nfit_test_resource *nfit_res = get_nfit_res((long) addr);
 
-        rcu_read_lock();
-        nfit_res = get_nfit_res((unsigned long) addr);
-        rcu_read_unlock();
         if (nfit_res)
                 return;
         return devm_memunmap(dev, addr);
@@ -135,11 +171,7 @@ EXPORT_SYMBOL(__wrap_ioremap_wc);
 
 void __wrap_iounmap(volatile void __iomem *addr)
 {
-        struct nfit_test_resource *nfit_res;
-
-        rcu_read_lock();
-        nfit_res = get_nfit_res((unsigned long) addr);
-        rcu_read_unlock();
+        struct nfit_test_resource *nfit_res = get_nfit_res((long) addr);
         if (nfit_res)
                 return;
         return iounmap(addr);
@@ -148,11 +180,8 @@ EXPORT_SYMBOL(__wrap_iounmap);
 
 void __wrap_memunmap(void *addr)
 {
-        struct nfit_test_resource *nfit_res;
+        struct nfit_test_resource *nfit_res = get_nfit_res((long) addr);
 
-        rcu_read_lock();
-        nfit_res = get_nfit_res((unsigned long) addr);
-        rcu_read_unlock();
         if (nfit_res)
                 return;
         return memunmap(addr);
@@ -166,9 +195,7 @@ static struct resource *nfit_test_request_region(struct device *dev,
         struct nfit_test_resource *nfit_res;
 
         if (parent == &iomem_resource) {
-                rcu_read_lock();
                 nfit_res = get_nfit_res(start);
-                rcu_read_unlock();
                 if (nfit_res) {
                         struct resource *res = nfit_res->res + 1;
 
@@ -218,9 +245,7 @@ void __wrap___release_region(struct resource *parent, resource_size_t start,
         struct nfit_test_resource *nfit_res;
 
         if (parent == &iomem_resource) {
-                rcu_read_lock();
                 nfit_res = get_nfit_res(start);
-                rcu_read_unlock();
                 if (nfit_res) {
                         struct resource *res = nfit_res->res + 1;
 
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 51cf8256c6cd..90bd2ea41032 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -248,6 +248,8 @@ static int nfit_test_cmd_ars_status(struct nd_cmd_ars_status *nd_cmd,
 
         nd_cmd->out_length = 256;
         nd_cmd->num_records = 0;
+        nd_cmd->address = 0;
+        nd_cmd->length = -1ULL;
         nd_cmd->status = 0;
 
         return 0;
@@ -1088,6 +1090,8 @@ static void nfit_test1_setup(struct nfit_test *t)
         struct acpi_nfit_memory_map *memdev;
         struct acpi_nfit_control_region *dcr;
         struct acpi_nfit_system_address *spa;
+        struct nvdimm_bus_descriptor *nd_desc;
+        struct acpi_nfit_desc *acpi_desc;
 
         offset = 0;
         /* spa0 (flat range with no bdw aliasing) */
@@ -1135,6 +1139,13 @@ static void nfit_test1_setup(struct nfit_test *t)
         dcr->command_size = 0;
         dcr->status_offset = 0;
         dcr->status_size = 0;
+
+        acpi_desc = &t->acpi_desc;
+        set_bit(ND_CMD_ARS_CAP, &acpi_desc->bus_dsm_force_en);
+        set_bit(ND_CMD_ARS_START, &acpi_desc->bus_dsm_force_en);
+        set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_dsm_force_en);
+        nd_desc = &acpi_desc->nd_desc;
+        nd_desc->ndctl = nfit_test_ctl;
 }
 
 static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index c8edff6803d1..b04afc3295df 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,10 +1,12 @@
 TARGETS = breakpoints
+TARGETS += capabilities
 TARGETS += cpu-hotplug
 TARGETS += efivarfs
 TARGETS += exec
 TARGETS += firmware
 TARGETS += ftrace
 TARGETS += futex
+TARGETS += ipc
 TARGETS += kcmp
 TARGETS += lib
 TARGETS += membarrier
diff --git a/tools/testing/selftests/breakpoints/.gitignore b/tools/testing/selftests/breakpoints/.gitignore
new file mode 100644
index 000000000000..9b3193d06608
--- /dev/null
+++ b/tools/testing/selftests/breakpoints/.gitignore
@@ -0,0 +1 @@
+breakpoint_test
diff --git a/tools/testing/selftests/capabilities/Makefile b/tools/testing/selftests/capabilities/Makefile
index 8c8f0c1f0889..008602aed920 100644
--- a/tools/testing/selftests/capabilities/Makefile
+++ b/tools/testing/selftests/capabilities/Makefile
@@ -1,18 +1,15 @@
-all:
-
-include ../lib.mk
-
-.PHONY: all clean
-
-TARGETS := validate_cap test_execve
+TEST_FILES := validate_cap
 TEST_PROGS := test_execve
 
-CFLAGS := -O2 -g -std=gnu99 -Wall -lcap-ng
+BINARIES := $(TEST_FILES) $(TEST_PROGS)
 
-all: $(TARGETS)
+CFLAGS += -O2 -g -std=gnu99 -Wall
+LDLIBS += -lcap-ng -lrt -ldl
+
+all: $(BINARIES)
 
 clean:
-        $(RM) $(TARGETS)
+        $(RM) $(BINARIES)
+
+include ../lib.mk
 
-$(TARGETS): %: %.c
-        $(CC) -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl
diff --git a/tools/testing/selftests/firmware/fw_filesystem.sh b/tools/testing/selftests/firmware/fw_filesystem.sh
index c4366dc74e01..5c495ad7958a 100755
--- a/tools/testing/selftests/firmware/fw_filesystem.sh
+++ b/tools/testing/selftests/firmware/fw_filesystem.sh
@@ -48,8 +48,21 @@ echo "ABCD0123" >"$FW"
 
 NAME=$(basename "$FW")
 
+if printf '\000' >"$DIR"/trigger_request; then
+        echo "$0: empty filename should not succeed" >&2
+        exit 1
+fi
+
+if printf '\000' >"$DIR"/trigger_async_request; then
+        echo "$0: empty filename should not succeed (async)" >&2
+        exit 1
+fi
+
 # Request a firmware that doesn't exist, it should fail.
-echo -n "nope-$NAME" >"$DIR"/trigger_request
+if echo -n "nope-$NAME" >"$DIR"/trigger_request; then
+        echo "$0: firmware shouldn't have loaded" >&2
+        exit 1
+fi
 if diff -q "$FW" /dev/test_firmware >/dev/null ; then
         echo "$0: firmware was not expected to match" >&2
         exit 1
@@ -74,4 +87,18 @@ else
         echo "$0: filesystem loading works"
 fi
 
+# Try the asynchronous version too
+if ! echo -n "$NAME" >"$DIR"/trigger_async_request ; then
+        echo "$0: could not trigger async request" >&2
+        exit 1
+fi
+
+# Verify the contents are what we expect.
+if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then
+        echo "$0: firmware was not loaded (async)" >&2
+        exit 1
+else
+        echo "$0: async filesystem loading works"
+fi
+
 exit 0
diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile
new file mode 100644
index 000000000000..f5f1a28715ff
--- /dev/null
+++ b/tools/testing/selftests/intel_pstate/Makefile
@@ -0,0 +1,15 @@
+CC := $(CROSS_COMPILE)gcc
+CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE
+LDFLAGS := $(LDFLAGS) -lm
+
+TARGETS := msr aperf
+
+TEST_PROGS := $(TARGETS) run.sh
+
+.PHONY: all clean
+all: $(TARGETS)
+
+$(TARGETS): $(HEADERS)
+
+clean:
+        rm -f $(TARGETS)
diff --git a/tools/testing/selftests/intel_pstate/aperf.c b/tools/testing/selftests/intel_pstate/aperf.c
new file mode 100644
index 000000000000..6046e183f4ad
--- /dev/null
+++ b/tools/testing/selftests/intel_pstate/aperf.c
@@ -0,0 +1,80 @@
+#include <math.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <sys/timeb.h>
+#include <sched.h>
+#include <errno.h>
+
+void usage(char *name) {
+        printf ("Usage: %s cpunum\n", name);
+}
+
+int main(int argc, char **argv) {
+        int i, cpu, fd;
+        char msr_file_name[64];
+        long long tsc, old_tsc, new_tsc;
+        long long aperf, old_aperf, new_aperf;
+        long long mperf, old_mperf, new_mperf;
+        struct timeb before, after;
+        long long int start, finish, total;
+        cpu_set_t cpuset;
+
+        if (argc != 2) {
+                usage(argv[0]);
+                return 1;
+        }
+
+        errno = 0;
+        cpu = strtol(argv[1], (char **) NULL, 10);
+
+        if (errno) {
+                usage(argv[0]);
+                return 1;
+        }
+
+        sprintf(msr_file_name, "/dev/cpu/%d/msr", cpu);
+        fd = open(msr_file_name, O_RDONLY);
+
+        if (fd == -1) {
+                perror("Failed to open");
+                return 1;
+        }
+
+        CPU_ZERO(&cpuset);
+        CPU_SET(cpu, &cpuset);
+
+        if (sched_setaffinity(0, sizeof(cpu_set_t), &cpuset)) {
+                perror("Failed to set cpu affinity");
+                return 1;
+        }
+
+        ftime(&before);
+        pread(fd, &old_tsc,  sizeof(old_tsc), 0x10);
+        pread(fd, &old_aperf,  sizeof(old_mperf), 0xe7);
+        pread(fd, &old_mperf,  sizeof(old_aperf), 0xe8);
+
+        for (i=0; i<0x8fffffff; i++) {
+                sqrt(i);
+        }
+
+        ftime(&after);
+        pread(fd, &new_tsc,  sizeof(new_tsc), 0x10);
+        pread(fd, &new_aperf,  sizeof(new_mperf), 0xe7);
+        pread(fd, &new_mperf,  sizeof(new_aperf), 0xe8);
+
+        tsc = new_tsc-old_tsc;
+        aperf = new_aperf-old_aperf;
+        mperf = new_mperf-old_mperf;
+
+        start = before.time*1000 + before.millitm;
+        finish = after.time*1000 + after.millitm;
+        total = finish - start;
+
+        printf("runTime: %4.2f\n", 1.0*total/1000);
+        printf("freq: %7.0f\n", tsc / (1.0*aperf / (1.0 * mperf)) / total);
+        return 0;
+}
diff --git a/tools/testing/selftests/intel_pstate/msr.c b/tools/testing/selftests/intel_pstate/msr.c
new file mode 100644
index 000000000000..abbbfc84d359
--- /dev/null
+++ b/tools/testing/selftests/intel_pstate/msr.c
@@ -0,0 +1,39 @@
+#include <math.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <sys/timeb.h>
+#include <sched.h>
+#include <errno.h>
+
+
+int main(int argc, char **argv) {
+        int cpu, fd;
+        long long msr;
+        char msr_file_name[64];
+
+        if (argc != 2)
+                return 1;
+
+        errno = 0;
+        cpu = strtol(argv[1], (char **) NULL, 10);
+
+        if (errno)
+                return 1;
+
+        sprintf(msr_file_name, "/dev/cpu/%d/msr", cpu);
+        fd = open(msr_file_name, O_RDONLY);
+
+        if (fd == -1) {
+                perror("Failed to open");
+                return 1;
+        }
+
+        pread(fd, &msr,  sizeof(msr), 0x199);
+
+        printf("msr 0x199: 0x%llx\n", msr);
+        return 0;
+}
diff --git a/tools/testing/selftests/intel_pstate/run.sh b/tools/testing/selftests/intel_pstate/run.sh
new file mode 100755
index 000000000000..bdaf37e92684
--- /dev/null
+++ b/tools/testing/selftests/intel_pstate/run.sh
@@ -0,0 +1,113 @@
+#!/bin/bash
+#
+# This test runs on Intel x86 based hardware which support the intel_pstate
+# driver.  The test checks the frequency settings from the maximum turbo
+# state to the minimum supported frequency, in decrements of 100MHz.  The
+# test runs the aperf.c program to put load on each processor.
+#
+# The results are displayed in a table which indicate the "Target" state,
+# or the requested frequency in MHz, the Actual frequency, as read from
+# /proc/cpuinfo, the difference between the Target and Actual frequencies,
+# and the value of MSR 0x199 (MSR_IA32_PERF_CTL) which indicates what
+# pstate the cpu is in, and the value of
+# /sys/devices/system/cpu/intel_pstate/max_perf_pct X maximum turbo state
+#
+# Notes: In some cases several frequency values may be placed in the
+# /tmp/result.X files.  This is done on purpose in order to catch cases
+# where the pstate driver may not be working at all.  There is the case
+# where, for example, several "similar" frequencies are in the file:
+#
+#
+#/tmp/result.3100:1:cpu MHz              : 2899.980
+#/tmp/result.3100:2:cpu MHz              : 2900.000
+#/tmp/result.3100:3:msr 0x199: 0x1e00
+#/tmp/result.3100:4:max_perf_pct 94
+#
+# and the test will error out in those cases.  The result.X file can be checked
+# for consistency and modified to remove the extra MHz values.  The result.X
+# files can be re-evaluated by setting EVALUATE_ONLY to 1 below.
+
+EVALUATE_ONLY=0
+
+max_cpus=$(($(nproc)-1))
+
+# compile programs
+gcc -o aperf aperf.c -lm
+[ $? -ne 0 ] && echo "Problem compiling aperf.c." && exit 1
+gcc -o msr msr.c -lm
+[ $? -ne 0 ] && echo "Problem compiling msr.c." && exit 1
+
+function run_test () {
+
+        file_ext=$1
+        for cpu in `seq 0 $max_cpus`
+        do
+                echo "launching aperf load on $cpu"
+                ./aperf $cpu &
+        done
+
+        echo "sleeping for 5 seconds"
+        sleep 5
+        num_freqs=$(cat /proc/cpuinfo | grep MHz | sort -u | wc -l)
+        if [ $num_freqs -le 2 ]; then
+                cat /proc/cpuinfo | grep MHz | sort -u | tail -1 > /tmp/result.$1
+        else
+                cat /proc/cpuinfo | grep MHz | sort -u > /tmp/result.$1
+        fi
+        ./msr 0 >> /tmp/result.$1
+
+        max_perf_pct=$(cat /sys/devices/system/cpu/intel_pstate/max_perf_pct)
+        echo "max_perf_pct $max_perf_pct" >> /tmp/result.$1
+
+        for job in `jobs -p`
+        do
+                echo "waiting for job id $job"
+                wait $job
+        done
+}
+
+#
+# MAIN (ALL UNITS IN MHZ)
+#
+
+# Get the marketing frequency
+_mkt_freq=$(cat /proc/cpuinfo | grep -m 1 "model name" | awk '{print $NF}')
+_mkt_freq=$(echo $_mkt_freq | tr -d [:alpha:][:punct:])
+mkt_freq=${_mkt_freq}0
+
+# Get the ranges from cpupower
+_min_freq=$(cpupower frequency-info -l | tail -1 | awk ' { print $1 } ')
+min_freq=$(($_min_freq / 1000))
+_max_freq=$(cpupower frequency-info -l | tail -1 | awk ' { print $2 } ')
+max_freq=$(($_max_freq / 1000))
+
+
+for freq in `seq $max_freq -100 $min_freq`
+do
+        echo "Setting maximum frequency to $freq"
+        cpupower frequency-set -g powersave --max=${freq}MHz >& /dev/null
+        [ $EVALUATE_ONLY -eq 0 ] && run_test $freq
+done
+
+echo "=============================================================================="
+
+echo "The marketing frequency of the cpu is $mkt_freq MHz"
+echo "The maximum frequency of the cpu is $max_freq MHz"
+echo "The minimum frequency of the cpu is $min_freq MHz"
+
+cpupower frequency-set -g powersave --max=${max_freq}MHz >& /dev/null
+
+# make a pretty table
+echo "Target      Actual      Difference     MSR(0x199)     max_perf_pct"
+for freq in `seq $max_freq -100 $min_freq`
+do
+        result_freq=$(cat /tmp/result.${freq} | grep "cpu MHz" | awk ' { print $4 } ' | awk -F "." ' { print $1 } ')
+        msr=$(cat /tmp/result.${freq} | grep "msr" | awk ' { print $3 } ')
+        max_perf_pct=$(cat /tmp/result.${freq} | grep "max_perf_pct" | awk ' { print $2 } ' )
+        if [ $result_freq -eq $freq ]; then
+                echo " $freq        $result_freq             0          $msr         $(($max_perf_pct*3300))"
+        else
+                echo " $freq        $result_freq          $(($result_freq-$freq))          $msr          $(($max_perf_pct*$max_freq))"
+        fi
+done
+exit 0
diff --git a/tools/testing/selftests/powerpc/benchmarks/.gitignore b/tools/testing/selftests/powerpc/benchmarks/.gitignore
index b4709ea588c1..6fa673316ac2 100644
--- a/tools/testing/selftests/powerpc/benchmarks/.gitignore
+++ b/tools/testing/selftests/powerpc/benchmarks/.gitignore
@@ -1 +1,2 @@
 gettimeofday
+context_switch
diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile
index 5fa48702070d..912445ff7ce7 100644
--- a/tools/testing/selftests/powerpc/benchmarks/Makefile
+++ b/tools/testing/selftests/powerpc/benchmarks/Makefile
@@ -1,4 +1,4 @@
-TEST_PROGS := gettimeofday
+TEST_PROGS := gettimeofday context_switch
 
 CFLAGS += -O2
 
@@ -6,6 +6,9 @@ all: $(TEST_PROGS)
 
 $(TEST_PROGS): ../harness.c
 
+context_switch: ../utils.c
+context_switch: LDLIBS += -lpthread
+
 include ../../lib.mk
 
 clean:
diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
new file mode 100644
index 000000000000..7b785941adec
--- /dev/null
+++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
@@ -0,0 +1,466 @@
+/*
+ * Context switch microbenchmark.
+ *
+ * Copyright (C) 2015 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.
+ */
+
+#define _GNU_SOURCE
+#include <sched.h>
+#include <string.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <getopt.h>
+#include <signal.h>
+#include <assert.h>
+#include <pthread.h>
+#include <limits.h>
+#include <sys/time.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/shm.h>
+#include <linux/futex.h>
+
+#include "../utils.h"
+
+static unsigned int timeout = 30;
+
+static int touch_vdso;
+struct timeval tv;
+
+static int touch_fp = 1;
+double fp;
+
+static int touch_vector = 1;
+typedef int v4si __attribute__ ((vector_size (16)));
+v4si a, b, c;
+
+#ifdef __powerpc__
+static int touch_altivec = 1;
+
+static void __attribute__((__target__("no-vsx"))) altivec_touch_fn(void)
+{
+        c = a + b;
+}
+#endif
+
+static void touch(void)
+{
+        if (touch_vdso)
+                gettimeofday(&tv, NULL);
+
+        if (touch_fp)
+                fp += 0.1;
+
+#ifdef __powerpc__
+        if (touch_altivec)
+                altivec_touch_fn();
+#endif
+
+        if (touch_vector)
+                c = a + b;
+
+        asm volatile("# %0 %1 %2": : "r"(&tv), "r"(&fp), "r"(&c));
+}
+
+static void start_thread_on(void *(*fn)(void *), void *arg, unsigned long cpu)
+{
+        pthread_t tid;
+        cpu_set_t cpuset;
+        pthread_attr_t attr;
+
+        CPU_ZERO(&cpuset);
+        CPU_SET(cpu, &cpuset);
+
+        pthread_attr_init(&attr);
+
+        if (pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset)) {
+                perror("pthread_attr_setaffinity_np");
+                exit(1);
+        }
+
+        if (pthread_create(&tid, &attr, fn, arg)) {
+                perror("pthread_create");
+                exit(1);
+        }
+}
+
+static void start_process_on(void *(*fn)(void *), void *arg, unsigned long cpu)
+{
+        int pid;
+        cpu_set_t cpuset;
+
+        pid = fork();
+        if (pid == -1) {
+                perror("fork");
+                exit(1);
+        }
+
+        if (pid)
+                return;
+
+        CPU_ZERO(&cpuset);
+        CPU_SET(cpu, &cpuset);
+
+        if (sched_setaffinity(0, sizeof(cpuset), &cpuset)) {
+                perror("sched_setaffinity");
+                exit(1);
+        }
+
+        fn(arg);
+
+        exit(0);
+}
+
+static unsigned long iterations;
+static unsigned long iterations_prev;
+
+static void sigalrm_handler(int junk)
+{
+        unsigned long i = iterations;
+
+        printf("%ld\n", i - iterations_prev);
+        iterations_prev = i;
+
+        if (--timeout == 0)
+                kill(0, SIGUSR1);
+
+        alarm(1);
+}
+
+static void sigusr1_handler(int junk)
+{
+        exit(0);
+}
+
+struct actions {
+        void (*setup)(int, int);
+        void *(*thread1)(void *);
+        void *(*thread2)(void *);
+};
+
+#define READ 0
+#define WRITE 1
+
+static int pipe_fd1[2];
+static int pipe_fd2[2];
+
+static void pipe_setup(int cpu1, int cpu2)
+{
+        if (pipe(pipe_fd1) || pipe(pipe_fd2))
+                exit(1);
+}
+
+static void *pipe_thread1(void *arg)
+{
+        signal(SIGALRM, sigalrm_handler);
+        alarm(1);
+
+        while (1) {
+                assert(read(pipe_fd1[READ], &c, 1) == 1);
+                touch();
+
+                assert(write(pipe_fd2[WRITE], &c, 1) == 1);
+                touch();
+
+                iterations += 2;
+        }
+
+        return NULL;
+}
+
+static void *pipe_thread2(void *arg)
+{
+        while (1) {
+                assert(write(pipe_fd1[WRITE], &c, 1) == 1);
+                touch();
+
+                assert(read(pipe_fd2[READ], &c, 1) == 1);
+                touch();
+        }
+
+        return NULL;
+}
+
+static struct actions pipe_actions = {
+        .setup = pipe_setup,
+        .thread1 = pipe_thread1,
+        .thread2 = pipe_thread2,
+};
+
+static void yield_setup(int cpu1, int cpu2)
+{
+        if (cpu1 != cpu2) {
+                fprintf(stderr, "Both threads must be on the same CPU for yield test\n");
+                exit(1);
+        }
+}
+
+static void *yield_thread1(void *arg)
+{
+        signal(SIGALRM, sigalrm_handler);
+        alarm(1);
+
+        while (1) {
+                sched_yield();
+                touch();
+
+                iterations += 2;
+        }
+
+        return NULL;
+}
+
+static void *yield_thread2(void *arg)
+{
+        while (1) {
+                sched_yield();
+                touch();
+        }
+
+        return NULL;
+}
+
+static struct actions yield_actions = {
+        .setup = yield_setup,
+        .thread1 = yield_thread1,
+        .thread2 = yield_thread2,
+};
+
+static long sys_futex(void *addr1, int op, int val1, struct timespec *timeout,
+                      void *addr2, int val3)
+{
+        return syscall(SYS_futex, addr1, op, val1, timeout, addr2, val3);
+}
+
+static unsigned long cmpxchg(unsigned long *p, unsigned long expected,
+                             unsigned long desired)
+{
+        unsigned long exp = expected;
+
+        __atomic_compare_exchange_n(p, &exp, desired, 0,
+                                    __ATOMIC_SEQ_CST, __ATOMIC_SEQ_CST);
+        return exp;
+}
+
+static unsigned long xchg(unsigned long *p, unsigned long val)
+{
+        return __atomic_exchange_n(p, val, __ATOMIC_SEQ_CST);
+}
+
+static int mutex_lock(unsigned long *m)
+{
+        int c;
+
+        c = cmpxchg(m, 0, 1);
+        if (!c)
+                return 0;
+
+        if (c == 1)
+                c = xchg(m, 2);
+
+        while (c) {
+                sys_futex(m, FUTEX_WAIT, 2, NULL, NULL, 0);
+                c = xchg(m, 2);
+        }
+
+        return 0;
+}
+
+static int mutex_unlock(unsigned long *m)
+{
+        if (*m == 2)
+                *m = 0;
+        else if (xchg(m, 0) == 1)
+                return 0;
+
+        sys_futex(m, FUTEX_WAKE, 1, NULL, NULL, 0);
+
+        return 0;
+}
+
+static unsigned long *m1, *m2;
+
+static void futex_setup(int cpu1, int cpu2)
+{
+        int shmid;
+        void *shmaddr;
+
+        shmid = shmget(IPC_PRIVATE, getpagesize(), SHM_R | SHM_W);
+        if (shmid < 0) {
+                perror("shmget");
+                exit(1);
+        }
+
+        shmaddr = shmat(shmid, NULL, 0);
+        if (shmaddr == (char *)-1) {
+                perror("shmat");
+                shmctl(shmid, IPC_RMID, NULL);
+                exit(1);
+        }
+
+        shmctl(shmid, IPC_RMID, NULL);
+
+        m1 = shmaddr;
+        m2 = shmaddr + sizeof(*m1);
+
+        *m1 = 0;
+        *m2 = 0;
+
+        mutex_lock(m1);
+        mutex_lock(m2);
+}
+
+static void *futex_thread1(void *arg)
+{
+        signal(SIGALRM, sigalrm_handler);
+        alarm(1);
+
+        while (1) {
+                mutex_lock(m2);
+                mutex_unlock(m1);
+
+                iterations += 2;
+        }
+
+        return NULL;
+}
+
+static void *futex_thread2(void *arg)
+{
+        while (1) {
+                mutex_unlock(m2);
+                mutex_lock(m1);
+        }
+
+        return NULL;
+}
+
+static struct actions futex_actions = {
+        .setup = futex_setup,
+        .thread1 = futex_thread1,
+        .thread2 = futex_thread2,
+};
+
+static int processes;
+
+static struct option options[] = {
+        { "test", required_argument, 0, 't' },
+        { "process", no_argument, &processes, 1 },
+        { "timeout", required_argument, 0, 's' },
+        { "vdso", no_argument, &touch_vdso, 1 },
+        { "no-fp", no_argument, &touch_fp, 0 },
+#ifdef __powerpc__
+        { "no-altivec", no_argument, &touch_altivec, 0 },
+#endif
+        { "no-vector", no_argument, &touch_vector, 0 },
+        { 0, },
+};
+
+static void usage(void)
+{
+        fprintf(stderr, "Usage: context_switch2 <options> CPU1 CPU2\n\n");
+        fprintf(stderr, "\t\t--test=X\tpipe, futex or yield (default)\n");
+        fprintf(stderr, "\t\t--process\tUse processes (default threads)\n");
+        fprintf(stderr, "\t\t--timeout=X\tDuration in seconds to run (default 30)\n");
+        fprintf(stderr, "\t\t--vdso\t\ttouch VDSO\n");
+        fprintf(stderr, "\t\t--fp\t\ttouch FP\n");
+#ifdef __powerpc__
+        fprintf(stderr, "\t\t--altivec\ttouch altivec\n");
+#endif
+        fprintf(stderr, "\t\t--vector\ttouch vector\n");
+}
+
+int main(int argc, char *argv[])
+{
+        signed char c;
+        struct actions *actions = &yield_actions;
+        int cpu1;
+        int cpu2;
+        static void (*start_fn)(void *(*fn)(void *), void *arg, unsigned long cpu);
+
+        while (1) {
+                int option_index = 0;
+
+                c = getopt_long(argc, argv, "", options, &option_index);
+
+                if (c == -1)
+                        break;
+
+                switch (c) {
+                case 0:
+                        if (options[option_index].flag != 0)
+                                break;
+
+                        usage();
+                        exit(1);
+                        break;
+
+                case 't':
+                        if (!strcmp(optarg, "pipe")) {
+                                actions = &pipe_actions;
+                        } else if (!strcmp(optarg, "yield")) {
+                                actions = &yield_actions;
+                        } else if (!strcmp(optarg, "futex")) {
+                                actions = &futex_actions;
+                        } else {
+                                usage();
+                                exit(1);
+                        }
+                        break;
+
+                case 's':
+                        timeout = atoi(optarg);
+                        break;
+
+                default:
+                        usage();
+                        exit(1);
+                }
+        }
+
+        if (processes)
+                start_fn = start_process_on;
+        else
+                start_fn = start_thread_on;
+
+        if (((argc - optind) != 2)) {
+                cpu1 = cpu2 = pick_online_cpu();
+        } else {
+                cpu1 = atoi(argv[optind++]);
+                cpu2 = atoi(argv[optind++]);
+        }
+
+        printf("Using %s with ", processes ? "processes" : "threads");
+
+        if (actions == &pipe_actions)
+                printf("pipe");
+        else if (actions == &yield_actions)
+                printf("yield");
+        else
+                printf("futex");
+
+        printf(" on cpus %d/%d touching FP:%s altivec:%s vector:%s vdso:%s\n",
+               cpu1, cpu2, touch_fp ?  "yes" : "no", touch_altivec ? "yes" : "no",
+               touch_vector ? "yes" : "no", touch_vdso ? "yes" : "no");
+
+        /* Create a new process group so we can signal everyone for exit */
+        setpgid(getpid(), getpid());
+
+        signal(SIGUSR1, sigusr1_handler);
+
+        actions->setup(cpu1, cpu2);
+
+        start_fn(actions->thread1, NULL, cpu1);
+        start_fn(actions->thread2, NULL, cpu2);
+
+        while (1)
+                sleep(3600);
+
+        return 0;
+}
diff --git a/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c b/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c
index 8265504de571..08a8b95e3bc1 100644
--- a/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c
+++ b/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c
@@ -60,14 +60,6 @@ int dscr_inherit_exec(void)
                 else
                         set_dscr(dscr);
 
-                /*
-                 * XXX: Force a context switch out so that DSCR
-                 * current value is copied into the thread struct
-                 * which is required for the child to inherit the
-                 * changed value.
-                 */
-                sleep(1);
-
                 pid = fork();
                 if (pid == -1) {
                         perror("fork() failed");
diff --git a/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c b/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c
index 4e414caf7f40..3e5a6d195e9a 100644
--- a/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c
+++ b/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c
@@ -40,14 +40,6 @@ int dscr_inherit(void)
                 else
                         set_dscr(dscr);
 
-                /*
-                 * XXX: Force a context switch out so that DSCR
-                 * current value is copied into the thread struct
-                 * which is required for the child to inherit the
-                 * changed value.
-                 */
-                sleep(1);
-
                 pid = fork();
                 if (pid == -1) {
                         perror("fork() failed");
diff --git a/tools/testing/selftests/powerpc/harness.c b/tools/testing/selftests/powerpc/harness.c
index f7997affd143..52f9be7f61f0 100644
--- a/tools/testing/selftests/powerpc/harness.c
+++ b/tools/testing/selftests/powerpc/harness.c
@@ -116,46 +116,3 @@ int test_harness(int (test_function)(void), char *name)
 
         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/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile
index a9099d9f8f39..ac41a7177f2e 100644
--- a/tools/testing/selftests/powerpc/pmu/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/Makefile
@@ -2,7 +2,7 @@ noarg:
         $(MAKE) -C ../
 
 TEST_PROGS := count_instructions l3_bank_test per_event_excludes
-EXTRA_SOURCES := ../harness.c event.c lib.c
+EXTRA_SOURCES := ../harness.c event.c lib.c ../utils.c
 
 all: $(TEST_PROGS) ebb
 
@@ -12,6 +12,8 @@ $(TEST_PROGS): $(EXTRA_SOURCES)
 count_instructions: loop.S count_instructions.c $(EXTRA_SOURCES)
         $(CC) $(CFLAGS) -m64 -o $@ $^
 
+per_event_excludes: ../utils.c
+
 include ../../lib.mk
 
 DEFAULT_RUN_TESTS := $(RUN_TESTS)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
index 5cdc9dbf2b27..8d2279c4bb4b 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
@@ -18,7 +18,8 @@ TEST_PROGS := reg_access_test event_attributes_test cycles_test	\
 
 all: $(TEST_PROGS)
 
-$(TEST_PROGS): ../../harness.c ../event.c ../lib.c ebb.c ebb_handler.S trace.c busy_loop.S
+$(TEST_PROGS): ../../harness.c ../../utils.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/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
index 9729d9f90218..e67452f1bcff 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -13,7 +13,6 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/ioctl.h>
-#include <linux/auxvec.h>
 
 #include "trace.h"
 #include "reg.h"
@@ -324,7 +323,7 @@ bool ebb_is_supported(void)
 {
 #ifdef PPC_FEATURE2_EBB
         /* EBB requires at least POWER8 */
-        return ((long)get_auxv_entry(AT_HWCAP2) & PPC_FEATURE2_EBB);
+        return have_hwcap2(PPC_FEATURE2_EBB);
 #else
         return false;
 #endif
diff --git a/tools/testing/selftests/powerpc/pmu/lib.c b/tools/testing/selftests/powerpc/pmu/lib.c
index a07104c2afe6..a361ad3334ce 100644
--- a/tools/testing/selftests/powerpc/pmu/lib.c
+++ b/tools/testing/selftests/powerpc/pmu/lib.c
@@ -15,32 +15,6 @@
 #include "lib.h"
 
 
-int pick_online_cpu(void)
-{
-        cpu_set_t mask;
-        int cpu;
-
-        CPU_ZERO(&mask);
-
-        if (sched_getaffinity(0, sizeof(mask), &mask)) {
-                perror("sched_getaffinity");
-                return -1;
-        }
-
-        /* We prefer a primary thread, but skip 0 */
-        for (cpu = 8; cpu < CPU_SETSIZE; cpu += 8)
-                if (CPU_ISSET(cpu, &mask))
-                        return cpu;
-
-        /* Search for anything, but in reverse */
-        for (cpu = CPU_SETSIZE - 1; cpu >= 0; cpu--)
-                if (CPU_ISSET(cpu, &mask))
-                        return cpu;
-
-        printf("No cpus in affinity mask?!\n");
-        return -1;
-}
-
 int bind_to_cpu(int cpu)
 {
         cpu_set_t mask;
diff --git a/tools/testing/selftests/powerpc/pmu/lib.h b/tools/testing/selftests/powerpc/pmu/lib.h
index ca5d72ae3be6..0213af4ff332 100644
--- a/tools/testing/selftests/powerpc/pmu/lib.h
+++ b/tools/testing/selftests/powerpc/pmu/lib.h
@@ -19,7 +19,6 @@ union pipe {
         int fds[2];
 };
 
-extern int pick_online_cpu(void);
 extern int bind_to_cpu(int cpu);
 extern int kill_child_and_wait(pid_t child_pid);
 extern int wait_for_child(pid_t child_pid);
diff --git a/tools/testing/selftests/powerpc/scripts/hmi.sh b/tools/testing/selftests/powerpc/scripts/hmi.sh
new file mode 100755
index 000000000000..83fb253ae3bd
--- /dev/null
+++ b/tools/testing/selftests/powerpc/scripts/hmi.sh
@@ -0,0 +1,89 @@
+#!/bin/sh
+#
+# Copyright 2015, Daniel Axtens, IBM Corporation
+#
+# 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; version 2 of the License.
+#
+# 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.
+
+
+# do we have ./getscom, ./putscom?
+if [ -x ./getscom ] && [ -x ./putscom ]; then
+        GETSCOM=./getscom
+        PUTSCOM=./putscom
+elif which getscom > /dev/null; then
+        GETSCOM=$(which getscom)
+        PUTSCOM=$(which putscom)
+else
+        cat <<EOF
+Can't find getscom/putscom in . or \$PATH.
+See https://github.com/open-power/skiboot.
+The tool is in external/xscom-utils
+EOF
+        exit 1
+fi
+
+# We will get 8 HMI events per injection
+# todo: deal with things being offline
+expected_hmis=8
+COUNT_HMIS() {
+    dmesg | grep -c 'Harmless Hypervisor Maintenance interrupt'
+}
+
+# massively expand snooze delay, allowing injection on all cores
+ppc64_cpu --smt-snooze-delay=1000000000
+
+# when we exit, restore it
+trap "ppc64_cpu --smt-snooze-delay=100" 0 1
+
+# for each chip+core combination
+# todo - less fragile parsing
+egrep -o 'OCC: Chip [0-9a-f]+ Core [0-9a-f]' < /sys/firmware/opal/msglog |
+while read chipcore; do
+        chip=$(echo "$chipcore"|awk '{print $3}')
+        core=$(echo "$chipcore"|awk '{print $5}')
+        fir="0x1${core}013100"
+
+        # verify that Core FIR is zero as expected
+        if [ "$($GETSCOM -c 0x${chip} $fir)" != 0 ]; then
+                echo "FIR was not zero before injection for chip $chip, core $core. Aborting!"
+                echo "Result of $GETSCOM -c 0x${chip} $fir:"
+                $GETSCOM -c 0x${chip} $fir
+                echo "If you get a -5 error, the core may be in idle state. Try stress-ng."
+                echo "Otherwise, try $PUTSCOM -c 0x${chip} $fir 0"
+                exit 1
+        fi
+
+        # keep track of the number of HMIs handled
+        old_hmis=$(COUNT_HMIS)
+
+        # do injection, adding a marker to dmesg for clarity
+        echo "Injecting HMI on core $core, chip $chip" | tee /dev/kmsg
+        # inject a RegFile recoverable error
+        if ! $PUTSCOM -c 0x${chip} $fir 2000000000000000 > /dev/null; then
+                echo "Error injecting. Aborting!"
+                exit 1
+        fi
+
+        # now we want to wait for all the HMIs to be processed
+        # we expect one per thread on the core
+        i=0;
+        new_hmis=$(COUNT_HMIS)
+        while [ $new_hmis -lt $((old_hmis + expected_hmis)) ] && [ $i -lt 12 ]; do
+            echo "Seen $((new_hmis - old_hmis)) HMI(s) out of $expected_hmis expected, sleeping"
+            sleep 5;
+            i=$((i + 1))
+            new_hmis=$(COUNT_HMIS)
+        done
+        if [ $i = 12 ]; then
+            echo "Haven't seen expected $expected_hmis recoveries after 1 min. Aborting."
+            exit 1
+        fi
+        echo "Processed $expected_hmis events; presumed success. Check dmesg."
+        echo ""
+done
diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore
index 2699635d2cd9..7d0f14b8cb2e 100644
--- a/tools/testing/selftests/powerpc/tm/.gitignore
+++ b/tools/testing/selftests/powerpc/tm/.gitignore
@@ -1,2 +1,5 @@
 tm-resched-dscr
 tm-syscall
+tm-signal-msr-resv
+tm-signal-stack
+tm-vmxcopy
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index 4bea62a319dc..737f72c964e6 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -1,8 +1,8 @@
-TEST_PROGS := tm-resched-dscr tm-syscall
+TEST_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack tm-vmxcopy
 
 all: $(TEST_PROGS)
 
-$(TEST_PROGS): ../harness.c
+$(TEST_PROGS): ../harness.c ../utils.c
 
 tm-syscall: tm-syscall-asm.S
 tm-syscall: CFLAGS += -mhtm -I../../../../../usr/include
diff --git a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
index 42d4c8caad81..8fde93d6021f 100644
--- a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
+++ b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
@@ -29,6 +29,7 @@
 #include <asm/tm.h>
 
 #include "utils.h"
+#include "tm.h"
 
 #define TBEGIN          ".long 0x7C00051D ;"
 #define TEND            ".long 0x7C00055D ;"
@@ -42,6 +43,8 @@ int test_body(void)
 {
         uint64_t rv, dscr1 = 1, dscr2, texasr;
 
+        SKIP_IF(!have_htm());
+
         printf("Check DSCR TM context switch: ");
         fflush(stdout);
         for (;;) {
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-msr-resv.c b/tools/testing/selftests/powerpc/tm/tm-signal-msr-resv.c
new file mode 100644
index 000000000000..d86653f282b1
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-msr-resv.c
@@ -0,0 +1,74 @@
+/*
+ * Copyright 2015, Michael Neuling, IBM Corp.
+ * Licensed under GPLv2.
+ *
+ * Test the kernel's signal return code to ensure that it doesn't
+ * crash when both the transactional and suspend MSR bits are set in
+ * the signal context.
+ *
+ * For this test, we send ourselves a SIGUSR1.  In the SIGUSR1 handler
+ * we modify the signal context to set both MSR TM S and T bits (which
+ * is "reserved" by the PowerISA). When we return from the signal
+ * handler (implicit sigreturn), the kernel should detect reserved MSR
+ * value and send us with a SIGSEGV.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <signal.h>
+#include <unistd.h>
+
+#include "utils.h"
+#include "tm.h"
+
+int segv_expected = 0;
+
+void signal_segv(int signum)
+{
+        if (segv_expected && (signum == SIGSEGV))
+                _exit(0);
+        _exit(1);
+}
+
+void signal_usr1(int signum, siginfo_t *info, void *uc)
+{
+        ucontext_t *ucp = uc;
+
+        /* Link tm checkpointed context to normal context */
+        ucp->uc_link = ucp;
+        /* Set all TM bits so that the context is now invalid */
+#ifdef __powerpc64__
+        ucp->uc_mcontext.gp_regs[PT_MSR] |= (7ULL << 32);
+#else
+        ucp->uc_mcontext.regs->gpr[PT_MSR] |= (7ULL);
+#endif
+        /* Should segv on return becuase of invalid context */
+        segv_expected = 1;
+}
+
+int tm_signal_msr_resv()
+{
+        struct sigaction act;
+
+        SKIP_IF(!have_htm());
+
+        act.sa_sigaction = signal_usr1;
+        sigemptyset(&act.sa_mask);
+        act.sa_flags = SA_SIGINFO;
+        if (sigaction(SIGUSR1, &act, NULL) < 0) {
+                perror("sigaction sigusr1");
+                exit(1);
+        }
+        if (signal(SIGSEGV, signal_segv) == SIG_ERR)
+                exit(1);
+
+        raise(SIGUSR1);
+
+        /* We shouldn't get here as we exit in the segv handler */
+        return 1;
+}
+
+int main(void)
+{
+        return test_harness(tm_signal_msr_resv, "tm_signal_msr_resv");
+}
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-stack.c b/tools/testing/selftests/powerpc/tm/tm-signal-stack.c
new file mode 100644
index 000000000000..e44a238c1d77
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-stack.c
@@ -0,0 +1,76 @@
+/*
+ * Copyright 2015, Michael Neuling, IBM Corp.
+ * Licensed under GPLv2.
+ *
+ * Test the kernel's signal delievery code to ensure that we don't
+ * trelaim twice in the kernel signal delivery code.  This can happen
+ * if we trigger a signal when in a transaction and the stack pointer
+ * is bogus.
+ *
+ * This test case registers a SEGV handler, sets the stack pointer
+ * (r1) to NULL, starts a transaction and then generates a SEGV.  The
+ * SEGV should be handled but we exit here as the stack pointer is
+ * invalid and hance we can't sigreturn.  We only need to check that
+ * this flow doesn't crash the kernel.
+ */
+
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <signal.h>
+
+#include "utils.h"
+#include "tm.h"
+
+void signal_segv(int signum)
+{
+        /* This should never actually run since stack is foobar */
+        exit(1);
+}
+
+int tm_signal_stack()
+{
+        int pid;
+
+        SKIP_IF(!have_htm());
+
+        pid = fork();
+        if (pid < 0)
+                exit(1);
+
+        if (pid) { /* Parent */
+                /*
+                 * It's likely the whole machine will crash here so if
+                 * the child ever exits, we are good.
+                 */
+                wait(NULL);
+                return 0;
+        }
+
+        /*
+         * The flow here is:
+         * 1) register a signal handler (so signal delievery occurs)
+         * 2) make stack pointer (r1) = NULL
+         * 3) start transaction
+         * 4) cause segv
+         */
+        if (signal(SIGSEGV, signal_segv) == SIG_ERR)
+                exit(1);
+        asm volatile("li 1, 0 ;"                /* stack ptr == NULL */
+                     "1:"
+                     ".long 0x7C00051D ;"       /* tbegin */
+                     "beq 1b ;"                 /* retry forever */
+                     ".long 0x7C0005DD ; ;"     /* tsuspend */
+                     "ld 2, 0(1) ;"             /* trigger segv" */
+                     : : : "memory");
+
+        /* This should never get here due to above segv */
+        return 1;
+}
+
+int main(void)
+{
+        return test_harness(tm_signal_stack, "tm_signal_stack");
+}
diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall.c b/tools/testing/selftests/powerpc/tm/tm-syscall.c
index e835bf7ec7ae..60560cb20e38 100644
--- a/tools/testing/selftests/powerpc/tm/tm-syscall.c
+++ b/tools/testing/selftests/powerpc/tm/tm-syscall.c
@@ -13,12 +13,11 @@
 #include <unistd.h>
 #include <sys/syscall.h>
 #include <asm/tm.h>
-#include <asm/cputable.h>
-#include <linux/auxvec.h>
 #include <sys/time.h>
 #include <stdlib.h>
 
 #include "utils.h"
+#include "tm.h"
 
 extern int getppid_tm_active(void);
 extern int getppid_tm_suspended(void);
@@ -77,16 +76,6 @@ pid_t getppid_tm(bool suspend)
         exit(-1);
 }
 
-static inline bool have_htm_nosc(void)
-{
-#ifdef PPC_FEATURE2_HTM_NOSC
-        return ((long)get_auxv_entry(AT_HWCAP2) & PPC_FEATURE2_HTM_NOSC);
-#else
-        printf("PPC_FEATURE2_HTM_NOSC not defined, can't check AT_HWCAP2\n");
-        return false;
-#endif
-}
-
 int tm_syscall(void)
 {
         unsigned count = 0;
diff --git a/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c b/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c
new file mode 100644
index 000000000000..0274de7b11f3
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c
@@ -0,0 +1,103 @@
+/*
+ * Copyright 2015, Michael Neuling, IBM Corp.
+ * Licensed under GPLv2.
+ *
+ * Original: Michael Neuling 4/12/2013
+ * Edited: Rashmica Gupta 4/12/2015
+ *
+ * See if the altivec state is leaked out of an aborted transaction due to
+ * kernel vmx copy loops.
+ *
+ * When the transaction aborts, VSR values should rollback to the values
+ * they held before the transaction commenced. Using VSRs while transaction
+ * is suspended should not affect the checkpointed values.
+ *
+ * (1) write A to a VSR
+ * (2) start transaction
+ * (3) suspend transaction
+ * (4) change the VSR to B
+ * (5) trigger kernel vmx copy loop
+ * (6) abort transaction
+ * (7) check that the VSR value is A
+ */
+
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <string.h>
+#include <assert.h>
+
+#include "tm.h"
+#include "utils.h"
+
+int test_vmxcopy()
+{
+        long double vecin = 1.3;
+        long double vecout;
+        unsigned long pgsize = getpagesize();
+        int i;
+        int fd;
+        int size = pgsize*16;
+        char tmpfile[] = "/tmp/page_faultXXXXXX";
+        char buf[pgsize];
+        char *a;
+        uint64_t aborted = 0;
+
+        SKIP_IF(!have_htm());
+
+        fd = mkstemp(tmpfile);
+        assert(fd >= 0);
+
+        memset(buf, 0, pgsize);
+        for (i = 0; i < size; i += pgsize)
+                assert(write(fd, buf, pgsize) == pgsize);
+
+        unlink(tmpfile);
+
+        a = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_PRIVATE, fd, 0);
+        assert(a != MAP_FAILED);
+
+        asm __volatile__(
+                "lxvd2x 40,0,%[vecinptr];"      /* set 40 to initial value*/
+                "tbegin.;"
+                "beq    3f;"
+                "tsuspend.;"
+                "xxlxor 40,40,40;"              /* set 40 to 0 */
+                "std    5, 0(%[map]);"          /* cause kernel vmx copy page */
+                "tabort. 0;"
+                "tresume.;"
+                "tend.;"
+                "li     %[res], 0;"
+                "b      5f;"
+
+                /* Abort handler */
+                "3:;"
+                "li     %[res], 1;"
+
+                "5:;"
+                "stxvd2x 40,0,%[vecoutptr];"
+                : [res]"=r"(aborted)
+                : [vecinptr]"r"(&vecin),
+                  [vecoutptr]"r"(&vecout),
+                  [map]"r"(a)
+                : "memory", "r0", "r3", "r4", "r5", "r6", "r7");
+
+        if (aborted && (vecin != vecout)){
+                printf("FAILED: vector state leaked on abort %f != %f\n",
+                       (double)vecin, (double)vecout);
+                return 1;
+        }
+
+        munmap(a, size);
+
+        close(fd);
+
+        return 0;
+}
+
+int main(void)
+{
+        return test_harness(test_vmxcopy, "tm_vmxcopy");
+}
diff --git a/tools/testing/selftests/powerpc/tm/tm.h b/tools/testing/selftests/powerpc/tm/tm.h
new file mode 100644
index 000000000000..24144b25772c
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright 2015, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#ifndef _SELFTESTS_POWERPC_TM_TM_H
+#define _SELFTESTS_POWERPC_TM_TM_H
+
+#include <stdbool.h>
+#include <asm/cputable.h>
+
+#include "../utils.h"
+
+static inline bool have_htm(void)
+{
+#ifdef PPC_FEATURE2_HTM
+        return have_hwcap2(PPC_FEATURE2_HTM);
+#else
+        printf("PPC_FEATURE2_HTM not defined, can't check AT_HWCAP2\n");
+        return false;
+#endif
+}
+
+static inline bool have_htm_nosc(void)
+{
+#ifdef PPC_FEATURE2_HTM_NOSC
+        return have_hwcap2(PPC_FEATURE2_HTM_NOSC);
+#else
+        printf("PPC_FEATURE2_HTM_NOSC not defined, can't check AT_HWCAP2\n");
+        return false;
+#endif
+}
+
+#endif /* _SELFTESTS_POWERPC_TM_TM_H */
diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c
new file mode 100644
index 000000000000..dcf74184bfd0
--- /dev/null
+++ b/tools/testing/selftests/powerpc/utils.c
@@ -0,0 +1,87 @@
+/*
+ * Copyright 2013-2015, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#define _GNU_SOURCE     /* For CPU_ZERO etc. */
+
+#include <elf.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <link.h>
+#include <sched.h>
+#include <stdio.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "utils.h"
+
+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;
+}
+
+int pick_online_cpu(void)
+{
+        cpu_set_t mask;
+        int cpu;
+
+        CPU_ZERO(&mask);
+
+        if (sched_getaffinity(0, sizeof(mask), &mask)) {
+                perror("sched_getaffinity");
+                return -1;
+        }
+
+        /* We prefer a primary thread, but skip 0 */
+        for (cpu = 8; cpu < CPU_SETSIZE; cpu += 8)
+                if (CPU_ISSET(cpu, &mask))
+                        return cpu;
+
+        /* Search for anything, but in reverse */
+        for (cpu = CPU_SETSIZE - 1; cpu >= 0; cpu--)
+                if (CPU_ISSET(cpu, &mask))
+                        return cpu;
+
+        printf("No cpus in affinity mask?!\n");
+        return -1;
+}
diff --git a/tools/testing/selftests/powerpc/utils.h b/tools/testing/selftests/powerpc/utils.h
index b7d41086bb0a..175ac6ad10dd 100644
--- a/tools/testing/selftests/powerpc/utils.h
+++ b/tools/testing/selftests/powerpc/utils.h
@@ -8,6 +8,7 @@
 
 #include <stdint.h>
 #include <stdbool.h>
+#include <linux/auxvec.h>
 
 /* Avoid headaches with PRI?64 - just use %ll? always */
 typedef unsigned long long u64;
@@ -21,6 +22,12 @@ typedef uint8_t u8;
 
 int test_harness(int (test_function)(void), char *name);
 extern void *get_auxv_entry(int type);
+int pick_online_cpu(void);
+
+static inline bool have_hwcap2(unsigned long ftr2)
+{
+        return ((unsigned long)get_auxv_entry(AT_HWCAP2) & ftr2) == ftr2;
+}
 
 /* Yes, this is evil */
 #define FAIL_IF(x)                                              \
diff --git a/tools/testing/selftests/ptrace/.gitignore b/tools/testing/selftests/ptrace/.gitignore
new file mode 100644
index 000000000000..b3e59d41fd82
--- /dev/null
+++ b/tools/testing/selftests/ptrace/.gitignore
@@ -0,0 +1 @@
+peeksiginfo
diff --git a/tools/testing/selftests/seccomp/test_harness.h b/tools/testing/selftests/seccomp/test_harness.h
index fb2841601f2f..a786c69c7584 100644
--- a/tools/testing/selftests/seccomp/test_harness.h
+++ b/tools/testing/selftests/seccomp/test_harness.h
@@ -42,6 +42,7 @@
 #define TEST_HARNESS_H_
 
 #define _GNU_SOURCE
+#include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -370,8 +371,8 @@
         __typeof__(_expected) __exp = (_expected); \
         __typeof__(_seen) __seen = (_seen); \
         if (!(__exp _t __seen)) { \
-                unsigned long long __exp_print = (unsigned long long)__exp; \
-                unsigned long long __seen_print = (unsigned long long)__seen; \
+                unsigned long long __exp_print = (uintptr_t)__exp; \
+                unsigned long long __seen_print = (uintptr_t)__seen; \
                 __TH_LOG("Expected %s (%llu) %s %s (%llu)", \
                          #_expected, __exp_print, #_t, \
                          #_seen, __seen_print); \
diff --git a/tools/testing/selftests/timers/.gitignore b/tools/testing/selftests/timers/.gitignore
index ced998151bc4..68f3fc71ac44 100644
--- a/tools/testing/selftests/timers/.gitignore
+++ b/tools/testing/selftests/timers/.gitignore
@@ -16,3 +16,4 @@ set-timer-lat
 skew_consistency
 threadtest
 valid-adjtimex
+adjtick
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index ff1bb16cec4f..a937a9d26b60 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -2,3 +2,8 @@ hugepage-mmap
 hugepage-shm
 map_hugetlb
 thuge-gen
+compaction_test
+mlock2-tests
+on-fault-limit
+transhuge-stress
+userfaultfd
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index eabcff411984..d0c473f65850 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -4,9 +4,11 @@ include ../lib.mk
 
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
-TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs ldt_gdt syscall_nt ptrace_syscall
+TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault sigreturn test_syscall_vdso unwind_vdso \
-                        test_FCMOV test_FCOMI test_FISTTP
+                        test_FCMOV test_FCOMI test_FISTTP \
+                        ldt_gdt \
+                        vdso_restorer
 
 TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
 BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32)
diff --git a/tools/testing/selftests/x86/vdso_restorer.c b/tools/testing/selftests/x86/vdso_restorer.c
new file mode 100644
index 000000000000..cb038424a403
--- /dev/null
+++ b/tools/testing/selftests/x86/vdso_restorer.c
@@ -0,0 +1,88 @@
+/*
+ * vdso_restorer.c - tests vDSO-based signal restore
+ * Copyright (c) 2015 Andrew Lutomirski
+ *
+ * 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.
+ *
+ * This makes sure that sa_restorer == NULL keeps working on 32-bit
+ * configurations.  Modern glibc doesn't use it under any circumstances,
+ * so it's easy to overlook breakage.
+ *
+ * 64-bit userspace has never supported sa_restorer == NULL, so this is
+ * 32-bit only.
+ */
+
+#define _GNU_SOURCE
+
+#include <err.h>
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#include <syscall.h>
+#include <sys/syscall.h>
+
+/* Open-code this -- the headers are too messy to easily use them. */
+struct real_sigaction {
+        void *handler;
+        unsigned long flags;
+        void *restorer;
+        unsigned int mask[2];
+};
+
+static volatile sig_atomic_t handler_called;
+
+static void handler_with_siginfo(int sig, siginfo_t *info, void *ctx_void)
+{
+        handler_called = 1;
+}
+
+static void handler_without_siginfo(int sig)
+{
+        handler_called = 1;
+}
+
+int main()
+{
+        int nerrs = 0;
+        struct real_sigaction sa;
+
+        memset(&sa, 0, sizeof(sa));
+        sa.handler = handler_with_siginfo;
+        sa.flags = SA_SIGINFO;
+        sa.restorer = NULL;     /* request kernel-provided restorer */
+
+        if (syscall(SYS_rt_sigaction, SIGUSR1, &sa, NULL, 8) != 0)
+                err(1, "raw rt_sigaction syscall");
+
+        raise(SIGUSR1);
+
+        if (handler_called) {
+                printf("[OK]\tSA_SIGINFO handler returned successfully\n");
+        } else {
+                printf("[FAIL]\tSA_SIGINFO handler was not called\n");
+                nerrs++;
+        }
+
+        sa.flags = 0;
+        sa.handler = handler_without_siginfo;
+        if (syscall(SYS_sigaction, SIGUSR1, &sa, 0) != 0)
+                err(1, "raw sigaction syscall");
+        handler_called = 0;
+
+        raise(SIGUSR1);
+
+        if (handler_called) {
+                printf("[OK]\t!SA_SIGINFO handler returned successfully\n");
+        } else {
+                printf("[FAIL]\t!SA_SIGINFO handler was not called\n");
+                nerrs++;
+        }
+}