282 files changed, 7583 insertions, 3670 deletions

diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c
index 8f96b3ee0724..f437d739f37d 100644
--- a/tools/hv/hv_fcopy_daemon.c
+++ b/tools/hv/hv_fcopy_daemon.c
@@ -33,6 +33,7 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <dirent.h>
+#include <getopt.h>
 
 static int target_fd;
 static char target_fname[W_MAX_PATH];
@@ -126,15 +127,43 @@ static int hv_copy_cancel(void)
 
 }
 
-int main(void)
+void print_usage(char *argv[])
+{
+        fprintf(stderr, "Usage: %s [options]\n"
+                "Options are:\n"
+                "  -n, --no-daemon        stay in foreground, don't daemonize\n"
+                "  -h, --help             print this help\n", argv[0]);
+}
+
+int main(int argc, char *argv[])
 {
         int fd, fcopy_fd, len;
         int error;
+        int daemonize = 1, long_index = 0, opt;
         int version = FCOPY_CURRENT_VERSION;
         char *buffer[4096 * 2];
         struct hv_fcopy_hdr *in_msg;
 
-        if (daemon(1, 0)) {
+        static struct option long_options[] = {
+                {"help",        no_argument,       0,  'h' },
+                {"no-daemon",   no_argument,       0,  'n' },
+                {0,             0,                 0,  0   }
+        };
+
+        while ((opt = getopt_long(argc, argv, "hn", long_options,
+                                  &long_index)) != -1) {
+                switch (opt) {
+                case 'n':
+                        daemonize = 0;
+                        break;
+                case 'h':
+                default:
+                        print_usage(argv);
+                        exit(EXIT_FAILURE);
+                }
+        }
+
+        if (daemonize && daemon(1, 0)) {
                 syslog(LOG_ERR, "daemon() failed; error: %s", strerror(errno));
                 exit(EXIT_FAILURE);
         }
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 4088b816a3ee..6a6432a20a1d 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -43,6 +43,7 @@
 #include <fcntl.h>
 #include <dirent.h>
 #include <net/if.h>
+#include <getopt.h>
 
 /*
  * KVP protocol: The user mode component first registers with the
@@ -1417,7 +1418,15 @@ netlink_send(int fd, struct cn_msg *msg)
         return sendmsg(fd, &message, 0);
 }
 
-int main(void)
+void print_usage(char *argv[])
+{
+        fprintf(stderr, "Usage: %s [options]\n"
+                "Options are:\n"
+                "  -n, --no-daemon        stay in foreground, don't daemonize\n"
+                "  -h, --help             print this help\n", argv[0]);
+}
+
+int main(int argc, char *argv[])
 {
         int fd, len, nl_group;
         int error;
@@ -1435,9 +1444,30 @@ int main(void)
         struct hv_kvp_ipaddr_value *kvp_ip_val;
         char *kvp_recv_buffer;
         size_t kvp_recv_buffer_len;
+        int daemonize = 1, long_index = 0, opt;
+
+        static struct option long_options[] = {
+                {"help",        no_argument,       0,  'h' },
+                {"no-daemon",   no_argument,       0,  'n' },
+                {0,             0,                 0,  0   }
+        };
+
+        while ((opt = getopt_long(argc, argv, "hn", long_options,
+                                  &long_index)) != -1) {
+                switch (opt) {
+                case 'n':
+                        daemonize = 0;
+                        break;
+                case 'h':
+                default:
+                        print_usage(argv);
+                        exit(EXIT_FAILURE);
+                }
+        }
 
-        if (daemon(1, 0))
+        if (daemonize && daemon(1, 0))
                 return 1;
+
         openlog("KVP", 0, LOG_USER);
         syslog(LOG_INFO, "KVP starting; pid is:%d", getpid());
 
@@ -1529,8 +1559,15 @@ int main(void)
                                 addr_p, &addr_l);
 
                 if (len < 0) {
+                        int saved_errno = errno;
                         syslog(LOG_ERR, "recvfrom failed; pid:%u error:%d %s",
                                         addr.nl_pid, errno, strerror(errno));
+
+                        if (saved_errno == ENOBUFS) {
+                                syslog(LOG_ERR, "receive error: ignored");
+                                continue;
+                        }
+
                         close(fd);
                         return -1;
                 }
@@ -1733,8 +1770,15 @@ kvp_done:
 
                 len = netlink_send(fd, incoming_cn_msg);
                 if (len < 0) {
+                        int saved_errno = errno;
                         syslog(LOG_ERR, "net_link send failed; error: %d %s", errno,
                                         strerror(errno));
+
+                        if (saved_errno == ENOMEM || saved_errno == ENOBUFS) {
+                                syslog(LOG_ERR, "send error: ignored");
+                                continue;
+                        }
+
                         exit(EXIT_FAILURE);
                 }
         }
diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c
index 6a213b8cd7b9..5e63f70bd956 100644
--- a/tools/hv/hv_vss_daemon.c
+++ b/tools/hv/hv_vss_daemon.c
@@ -36,6 +36,7 @@
 #include <linux/hyperv.h>
 #include <linux/netlink.h>
 #include <syslog.h>
+#include <getopt.h>
 
 static struct sockaddr_nl addr;
 
@@ -44,35 +45,51 @@ static struct sockaddr_nl addr;
 #endif
 
 
-static int vss_do_freeze(char *dir, unsigned int cmd, char *fs_op)
+/* Don't use syslog() in the function since that can cause write to disk */
+static int vss_do_freeze(char *dir, unsigned int cmd)
 {
         int ret, fd = open(dir, O_RDONLY);
 
         if (fd < 0)
                 return 1;
+
         ret = ioctl(fd, cmd, 0);
-        syslog(LOG_INFO, "VSS: %s of %s: %s\n", fs_op, dir, strerror(errno));
+
+        /*
+         * If a partition is mounted more than once, only the first
+         * FREEZE/THAW can succeed and the later ones will get
+         * EBUSY/EINVAL respectively: there could be 2 cases:
+         * 1) a user may mount the same partition to differnt directories
+         *  by mistake or on purpose;
+         * 2) The subvolume of btrfs appears to have the same partition
+         * mounted more than once.
+         */
+        if (ret) {
+                if ((cmd == FIFREEZE && errno == EBUSY) ||
+                    (cmd == FITHAW && errno == EINVAL)) {
+                        close(fd);
+                        return 0;
+                }
+        }
+
         close(fd);
         return !!ret;
 }
 
 static int vss_operate(int operation)
 {
-        char *fs_op;
         char match[] = "/dev/";
         FILE *mounts;
         struct mntent *ent;
         unsigned int cmd;
-        int error = 0, root_seen = 0;
+        int error = 0, root_seen = 0, save_errno = 0;
 
         switch (operation) {
         case VSS_OP_FREEZE:
                 cmd = FIFREEZE;
-                fs_op = "freeze";
                 break;
         case VSS_OP_THAW:
                 cmd = FITHAW;
-                fs_op = "thaw";
                 break;
         default:
                 return -1;
@@ -85,7 +102,7 @@ static int vss_operate(int operation)
         while ((ent = getmntent(mounts))) {
                 if (strncmp(ent->mnt_fsname, match, strlen(match)))
                         continue;
-                if (strcmp(ent->mnt_type, "iso9660") == 0)
+                if (hasmntopt(ent, MNTOPT_RO) != NULL)
                         continue;
                 if (strcmp(ent->mnt_type, "vfat") == 0)
                         continue;
@@ -93,14 +110,30 @@ static int vss_operate(int operation)
                         root_seen = 1;
                         continue;
                 }
-                error |= vss_do_freeze(ent->mnt_dir, cmd, fs_op);
+                error |= vss_do_freeze(ent->mnt_dir, cmd);
+                if (error && operation == VSS_OP_FREEZE)
+                        goto err;
         }
-        endmntent(mounts);
 
         if (root_seen) {
-                error |= vss_do_freeze("/", cmd, fs_op);
+                error |= vss_do_freeze("/", cmd);
+                if (error && operation == VSS_OP_FREEZE)
+                        goto err;
         }
 
+        goto out;
+err:
+        save_errno = errno;
+        vss_operate(VSS_OP_THAW);
+        /* Call syslog after we thaw all filesystems */
+        if (ent)
+                syslog(LOG_ERR, "FREEZE of %s failed; error:%d %s",
+                       ent->mnt_dir, save_errno, strerror(save_errno));
+        else
+                syslog(LOG_ERR, "FREEZE of / failed; error:%d %s", save_errno,
+                       strerror(save_errno));
+out:
+        endmntent(mounts);
         return error;
 }
 
@@ -131,7 +164,15 @@ static int netlink_send(int fd, struct cn_msg *msg)
         return sendmsg(fd, &message, 0);
 }
 
-int main(void)
+void print_usage(char *argv[])
+{
+        fprintf(stderr, "Usage: %s [options]\n"
+                "Options are:\n"
+                "  -n, --no-daemon        stay in foreground, don't daemonize\n"
+                "  -h, --help             print this help\n", argv[0]);
+}
+
+int main(int argc, char *argv[])
 {
         int fd, len, nl_group;
         int error;
@@ -143,8 +184,28 @@ int main(void)
         struct hv_vss_msg *vss_msg;
         char *vss_recv_buffer;
         size_t vss_recv_buffer_len;
+        int daemonize = 1, long_index = 0, opt;
+
+        static struct option long_options[] = {
+                {"help",        no_argument,       0,  'h' },
+                {"no-daemon",   no_argument,       0,  'n' },
+                {0,             0,                 0,  0   }
+        };
+
+        while ((opt = getopt_long(argc, argv, "hn", long_options,
+                                  &long_index)) != -1) {
+                switch (opt) {
+                case 'n':
+                        daemonize = 0;
+                        break;
+                case 'h':
+                default:
+                        print_usage(argv);
+                        exit(EXIT_FAILURE);
+                }
+        }
 
-        if (daemon(1, 0))
+        if (daemonize && daemon(1, 0))
                 return 1;
 
         openlog("Hyper-V VSS", 0, LOG_USER);
@@ -249,8 +310,16 @@ int main(void)
                 case VSS_OP_FREEZE:
                 case VSS_OP_THAW:
                         error = vss_operate(op);
-                        if (error)
+                        syslog(LOG_INFO, "VSS: op=%s: %s\n",
+                                op == VSS_OP_FREEZE ? "FREEZE" : "THAW",
+                                error ? "failed" : "succeeded");
+
+                        if (error) {
                                 error = HV_E_FAIL;
+                                syslog(LOG_ERR, "op=%d failed!", op);
+                                syslog(LOG_ERR, "report it with these files:");
+                                syslog(LOG_ERR, "/etc/fstab and /proc/mounts");
+                        }
                         break;
                 default:
                         syslog(LOG_ERR, "Illegal op:%d\n", op);
diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h
new file mode 100644
index 000000000000..653d1bad77de
--- /dev/null
+++ b/tools/include/asm-generic/bitops.h
@@ -0,0 +1,29 @@
+#ifndef __TOOLS_ASM_GENERIC_BITOPS_H
+#define __TOOLS_ASM_GENERIC_BITOPS_H
+
+/*
+ * tools/ copied this from include/asm-generic/bitops.h, bit by bit as it needed
+ * some functions.
+ *
+ * For the benefit of those who are trying to port Linux to another
+ * architecture, here are some C-language equivalents.  You should
+ * recode these in the native assembly language, if at all possible.
+ *
+ * C language equivalents written by Theodore Ts'o, 9/26/92
+ */
+
+#include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/find.h>
+
+#ifndef _TOOLS_LINUX_BITOPS_H_
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#include <asm-generic/bitops/hweight.h>
+
+#include <asm-generic/bitops/atomic.h>
+
+#endif /* __TOOLS_ASM_GENERIC_BITOPS_H */
diff --git a/tools/include/asm-generic/bitops/__ffs.h b/tools/include/asm-generic/bitops/__ffs.h
new file mode 100644
index 000000000000..c94175015a82
--- /dev/null
+++ b/tools/include/asm-generic/bitops/__ffs.h
@@ -0,0 +1,43 @@
+#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_
+#define _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_
+
+#include <asm/types.h>
+
+/**
+ * __ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static __always_inline unsigned long __ffs(unsigned long word)
+{
+        int num = 0;
+
+#if __BITS_PER_LONG == 64
+        if ((word & 0xffffffff) == 0) {
+                num += 32;
+                word >>= 32;
+        }
+#endif
+        if ((word & 0xffff) == 0) {
+                num += 16;
+                word >>= 16;
+        }
+        if ((word & 0xff) == 0) {
+                num += 8;
+                word >>= 8;
+        }
+        if ((word & 0xf) == 0) {
+                num += 4;
+                word >>= 4;
+        }
+        if ((word & 0x3) == 0) {
+                num += 2;
+                word >>= 2;
+        }
+        if ((word & 0x1) == 0)
+                num += 1;
+        return num;
+}
+
+#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_ */
diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h
new file mode 100644
index 000000000000..2218b9add4c1
--- /dev/null
+++ b/tools/include/asm-generic/bitops/__fls.h
@@ -0,0 +1 @@
+#include <../../../../include/asm-generic/bitops/__fls.h>
diff --git a/tools/include/asm-generic/bitops/arch_hweight.h b/tools/include/asm-generic/bitops/arch_hweight.h
new file mode 100644
index 000000000000..318bb2b202b0
--- /dev/null
+++ b/tools/include/asm-generic/bitops/arch_hweight.h
@@ -0,0 +1 @@
+#include "../../../../include/asm-generic/bitops/arch_hweight.h"
diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h
new file mode 100644
index 000000000000..4bccd7c3d5d6
--- /dev/null
+++ b/tools/include/asm-generic/bitops/atomic.h
@@ -0,0 +1,22 @@
+#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_
+#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_
+
+#include <asm/types.h>
+
+static inline void set_bit(int nr, unsigned long *addr)
+{
+        addr[nr / __BITS_PER_LONG] |= 1UL << (nr % __BITS_PER_LONG);
+}
+
+static inline void clear_bit(int nr, unsigned long *addr)
+{
+        addr[nr / __BITS_PER_LONG] &= ~(1UL << (nr % __BITS_PER_LONG));
+}
+
+static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
+{
+        return ((1UL << (nr % __BITS_PER_LONG)) &
+                (((unsigned long *)addr)[nr / __BITS_PER_LONG])) != 0;
+}
+
+#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ */
diff --git a/tools/include/asm-generic/bitops/const_hweight.h b/tools/include/asm-generic/bitops/const_hweight.h
new file mode 100644
index 000000000000..0afd644aff83
--- /dev/null
+++ b/tools/include/asm-generic/bitops/const_hweight.h
@@ -0,0 +1 @@
+#include "../../../../include/asm-generic/bitops/const_hweight.h"
diff --git a/tools/include/asm-generic/bitops/find.h b/tools/include/asm-generic/bitops/find.h
new file mode 100644
index 000000000000..31f51547fcd4
--- /dev/null
+++ b/tools/include/asm-generic/bitops/find.h
@@ -0,0 +1,33 @@
+#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_
+#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_
+
+#ifndef find_next_bit
+/**
+ * find_next_bit - find the next set bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ *
+ * Returns the bit number for the next set bit
+ * If no bits are set, returns @size.
+ */
+extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
+                size, unsigned long offset);
+#endif
+
+#ifndef find_first_bit
+
+/**
+ * find_first_bit - find the first set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum number of bits to search
+ *
+ * Returns the bit number of the first set bit.
+ * If no bits are set, returns @size.
+ */
+extern unsigned long find_first_bit(const unsigned long *addr,
+                                    unsigned long size);
+
+#endif /* find_first_bit */
+
+#endif /*_TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_ */
diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h
new file mode 100644
index 000000000000..dbf711a28f71
--- /dev/null
+++ b/tools/include/asm-generic/bitops/fls.h
@@ -0,0 +1 @@
+#include <../../../../include/asm-generic/bitops/fls.h>
diff --git a/tools/include/asm-generic/bitops/fls64.h b/tools/include/asm-generic/bitops/fls64.h
new file mode 100644
index 000000000000..980b1f63c047
--- /dev/null
+++ b/tools/include/asm-generic/bitops/fls64.h
@@ -0,0 +1 @@
+#include <../../../../include/asm-generic/bitops/fls64.h>
diff --git a/tools/include/asm-generic/bitops/hweight.h b/tools/include/asm-generic/bitops/hweight.h
new file mode 100644
index 000000000000..290120c01a8e
--- /dev/null
+++ b/tools/include/asm-generic/bitops/hweight.h
@@ -0,0 +1,7 @@
+#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_
+#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_
+
+#include <asm-generic/bitops/arch_hweight.h>
+#include <asm-generic/bitops/const_hweight.h>
+
+#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h
new file mode 100644
index 000000000000..5ad9ee1dd7f6
--- /dev/null
+++ b/tools/include/linux/bitops.h
@@ -0,0 +1,58 @@
+#ifndef _TOOLS_LINUX_BITOPS_H_
+#define _TOOLS_LINUX_BITOPS_H_
+
+#include <asm/types.h>
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+
+#ifndef __WORDSIZE
+#define __WORDSIZE (__SIZEOF_LONG__ * 8)
+#endif
+
+#define BITS_PER_LONG __WORDSIZE
+
+#define BIT_MASK(nr)            (1UL << ((nr) % BITS_PER_LONG))
+#define BIT_WORD(nr)            ((nr) / BITS_PER_LONG)
+#define BITS_PER_BYTE           8
+#define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
+#define BITS_TO_U64(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
+#define BITS_TO_U32(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
+#define BITS_TO_BYTES(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE)
+
+extern unsigned int __sw_hweight8(unsigned int w);
+extern unsigned int __sw_hweight16(unsigned int w);
+extern unsigned int __sw_hweight32(unsigned int w);
+extern unsigned long __sw_hweight64(__u64 w);
+
+/*
+ * Include this here because some architectures need generic_ffs/fls in
+ * scope
+ *
+ * XXX: this needs to be asm/bitops.h, when we get to per arch optimizations
+ */
+#include <asm-generic/bitops.h>
+
+#define for_each_set_bit(bit, addr, size) \
+        for ((bit) = find_first_bit((addr), (size));            \
+             (bit) < (size);                                    \
+             (bit) = find_next_bit((addr), (size), (bit) + 1))
+
+/* same as for_each_set_bit() but use bit as value to start with */
+#define for_each_set_bit_from(bit, addr, size) \
+        for ((bit) = find_next_bit((addr), (size), (bit));      \
+             (bit) < (size);                                    \
+             (bit) = find_next_bit((addr), (size), (bit) + 1))
+
+static inline unsigned long hweight_long(unsigned long w)
+{
+        return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
+}
+
+static inline unsigned fls_long(unsigned long l)
+{
+        if (sizeof(l) == 4)
+                return fls(l);
+        return fls64(l);
+}
+
+#endif
diff --git a/tools/include/linux/log2.h b/tools/include/linux/log2.h
new file mode 100644
index 000000000000..41446668ccce
--- /dev/null
+++ b/tools/include/linux/log2.h
@@ -0,0 +1,185 @@
+/* Integer base 2 logarithm calculation
+ *
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.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, or (at your option) any later version.
+ */
+
+#ifndef _TOOLS_LINUX_LOG2_H
+#define _TOOLS_LINUX_LOG2_H
+
+/*
+ * deal with unrepresentable constant logarithms
+ */
+extern __attribute__((const, noreturn))
+int ____ilog2_NaN(void);
+
+/*
+ * non-constant log of base 2 calculators
+ * - the arch may override these in asm/bitops.h if they can be implemented
+ *   more efficiently than using fls() and fls64()
+ * - the arch is not required to handle n==0 if implementing the fallback
+ */
+static inline __attribute__((const))
+int __ilog2_u32(u32 n)
+{
+        return fls(n) - 1;
+}
+
+static inline __attribute__((const))
+int __ilog2_u64(u64 n)
+{
+        return fls64(n) - 1;
+}
+
+/*
+ *  Determine whether some value is a power of two, where zero is
+ * *not* considered a power of two.
+ */
+
+static inline __attribute__((const))
+bool is_power_of_2(unsigned long n)
+{
+        return (n != 0 && ((n & (n - 1)) == 0));
+}
+
+/*
+ * round up to nearest power of two
+ */
+static inline __attribute__((const))
+unsigned long __roundup_pow_of_two(unsigned long n)
+{
+        return 1UL << fls_long(n - 1);
+}
+
+/*
+ * round down to nearest power of two
+ */
+static inline __attribute__((const))
+unsigned long __rounddown_pow_of_two(unsigned long n)
+{
+        return 1UL << (fls_long(n) - 1);
+}
+
+/**
+ * ilog2 - log of base 2 of 32-bit or a 64-bit unsigned value
+ * @n - parameter
+ *
+ * constant-capable log of base 2 calculation
+ * - this can be used to initialise global variables from constant data, hence
+ *   the massive ternary operator construction
+ *
+ * selects the appropriately-sized optimised version depending on sizeof(n)
+ */
+#define ilog2(n)                                \
+(                                               \
+        __builtin_constant_p(n) ? (             \
+                (n) < 1 ? ____ilog2_NaN() :     \
+                (n) & (1ULL << 63) ? 63 :       \
+                (n) & (1ULL << 62) ? 62 :       \
+                (n) & (1ULL << 61) ? 61 :       \
+                (n) & (1ULL << 60) ? 60 :       \
+                (n) & (1ULL << 59) ? 59 :       \
+                (n) & (1ULL << 58) ? 58 :       \
+                (n) & (1ULL << 57) ? 57 :       \
+                (n) & (1ULL << 56) ? 56 :       \
+                (n) & (1ULL << 55) ? 55 :       \
+                (n) & (1ULL << 54) ? 54 :       \
+                (n) & (1ULL << 53) ? 53 :       \
+                (n) & (1ULL << 52) ? 52 :       \
+                (n) & (1ULL << 51) ? 51 :       \
+                (n) & (1ULL << 50) ? 50 :       \
+                (n) & (1ULL << 49) ? 49 :       \
+                (n) & (1ULL << 48) ? 48 :       \
+                (n) & (1ULL << 47) ? 47 :       \
+                (n) & (1ULL << 46) ? 46 :       \
+                (n) & (1ULL << 45) ? 45 :       \
+                (n) & (1ULL << 44) ? 44 :       \
+                (n) & (1ULL << 43) ? 43 :       \
+                (n) & (1ULL << 42) ? 42 :       \
+                (n) & (1ULL << 41) ? 41 :       \
+                (n) & (1ULL << 40) ? 40 :       \
+                (n) & (1ULL << 39) ? 39 :       \
+                (n) & (1ULL << 38) ? 38 :       \
+                (n) & (1ULL << 37) ? 37 :       \
+                (n) & (1ULL << 36) ? 36 :       \
+                (n) & (1ULL << 35) ? 35 :       \
+                (n) & (1ULL << 34) ? 34 :       \
+                (n) & (1ULL << 33) ? 33 :       \
+                (n) & (1ULL << 32) ? 32 :       \
+                (n) & (1ULL << 31) ? 31 :       \
+                (n) & (1ULL << 30) ? 30 :       \
+                (n) & (1ULL << 29) ? 29 :       \
+                (n) & (1ULL << 28) ? 28 :       \
+                (n) & (1ULL << 27) ? 27 :       \
+                (n) & (1ULL << 26) ? 26 :       \
+                (n) & (1ULL << 25) ? 25 :       \
+                (n) & (1ULL << 24) ? 24 :       \
+                (n) & (1ULL << 23) ? 23 :       \
+                (n) & (1ULL << 22) ? 22 :       \
+                (n) & (1ULL << 21) ? 21 :       \
+                (n) & (1ULL << 20) ? 20 :       \
+                (n) & (1ULL << 19) ? 19 :       \
+                (n) & (1ULL << 18) ? 18 :       \
+                (n) & (1ULL << 17) ? 17 :       \
+                (n) & (1ULL << 16) ? 16 :       \
+                (n) & (1ULL << 15) ? 15 :       \
+                (n) & (1ULL << 14) ? 14 :       \
+                (n) & (1ULL << 13) ? 13 :       \
+                (n) & (1ULL << 12) ? 12 :       \
+                (n) & (1ULL << 11) ? 11 :       \
+                (n) & (1ULL << 10) ? 10 :       \
+                (n) & (1ULL <<  9) ?  9 :       \
+                (n) & (1ULL <<  8) ?  8 :       \
+                (n) & (1ULL <<  7) ?  7 :       \
+                (n) & (1ULL <<  6) ?  6 :       \
+                (n) & (1ULL <<  5) ?  5 :       \
+                (n) & (1ULL <<  4) ?  4 :       \
+                (n) & (1ULL <<  3) ?  3 :       \
+                (n) & (1ULL <<  2) ?  2 :       \
+                (n) & (1ULL <<  1) ?  1 :       \
+                (n) & (1ULL <<  0) ?  0 :       \
+                ____ilog2_NaN()                 \
+                                   ) :          \
+        (sizeof(n) <= 4) ?                      \
+        __ilog2_u32(n) :                        \
+        __ilog2_u64(n)                          \
+ )
+
+/**
+ * roundup_pow_of_two - round the given value up to nearest power of two
+ * @n - parameter
+ *
+ * round the given value up to the nearest power of two
+ * - the result is undefined when n == 0
+ * - this can be used to initialise global variables from constant data
+ */
+#define roundup_pow_of_two(n)                   \
+(                                               \
+        __builtin_constant_p(n) ? (             \
+                (n == 1) ? 1 :                  \
+                (1UL << (ilog2((n) - 1) + 1))   \
+                                   ) :          \
+        __roundup_pow_of_two(n)                 \
+ )
+
+/**
+ * rounddown_pow_of_two - round the given value down to nearest power of two
+ * @n - parameter
+ *
+ * round the given value down to the nearest power of two
+ * - the result is undefined when n == 0
+ * - this can be used to initialise global variables from constant data
+ */
+#define rounddown_pow_of_two(n)                 \
+(                                               \
+        __builtin_constant_p(n) ? (             \
+                (1UL << ilog2(n))) :            \
+        __rounddown_pow_of_two(n)               \
+ )
+
+#endif /* _TOOLS_LINUX_LOG2_H */
diff --git a/tools/lib/api/fs/debugfs.c b/tools/lib/api/fs/debugfs.c
index a74fba6d7743..86ea2d7b8845 100644
--- a/tools/lib/api/fs/debugfs.c
+++ b/tools/lib/api/fs/debugfs.c
@@ -67,7 +67,7 @@ int debugfs_valid_mountpoint(const char *debugfs)
 
         if (statfs(debugfs, &st_fs) < 0)
                 return -ENOENT;
-        else if (st_fs.f_type != (long) DEBUGFS_MAGIC)
+        else if ((long)st_fs.f_type != (long)DEBUGFS_MAGIC)
                 return -ENOENT;
 
         return 0;
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index c1b49c36a951..128ef6332a6b 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -7,6 +7,10 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/vfs.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
 
 #include "debugfs.h"
 #include "fs.h"
@@ -75,7 +79,7 @@ static int fs__valid_mount(const char *fs, long magic)
 
         if (statfs(fs, &st_fs) < 0)
                 return -ENOENT;
-        else if (st_fs.f_type != magic)
+        else if ((long)st_fs.f_type != magic)
                 return -ENOENT;
 
         return 0;
@@ -163,3 +167,33 @@ const char *name##__mountpoint(void)	\
 
 FS__MOUNTPOINT(sysfs,  FS__SYSFS);
 FS__MOUNTPOINT(procfs, FS__PROCFS);
+
+int filename__read_int(const char *filename, int *value)
+{
+        char line[64];
+        int fd = open(filename, O_RDONLY), err = -1;
+
+        if (fd < 0)
+                return -1;
+
+        if (read(fd, line, sizeof(line)) > 0) {
+                *value = atoi(line);
+                err = 0;
+        }
+
+        close(fd);
+        return err;
+}
+
+int sysctl__read_int(const char *sysctl, int *value)
+{
+        char path[PATH_MAX];
+        const char *procfs = procfs__mountpoint();
+
+        if (!procfs)
+                return -1;
+
+        snprintf(path, sizeof(path), "%s/sys/%s", procfs, sysctl);
+
+        return filename__read_int(path, value);
+}
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index cb7049551f33..6caa2bbc6cec 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -11,4 +11,7 @@
 
 const char *sysfs__mountpoint(void);
 const char *procfs__mountpoint(void);
+
+int filename__read_int(const char *filename, int *value);
+int sysctl__read_int(const char *sysctl, int *value);
 #endif /* __API_FS__ */
diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
index 6f803609e498..0b0112c80f22 100644
--- a/tools/lib/lockdep/preload.c
+++ b/tools/lib/lockdep/preload.c
@@ -317,7 +317,7 @@ int pthread_mutex_destroy(pthread_mutex_t *mutex)
          *
          * TODO: Hook into free() and add that check there as well.
          */
-        debug_check_no_locks_freed(mutex, mutex + sizeof(*mutex));
+        debug_check_no_locks_freed(mutex, sizeof(*mutex));
         __del_lock(__get_lock(mutex));
         return ll_pthread_mutex_destroy(mutex);
 }
@@ -341,7 +341,7 @@ int pthread_rwlock_destroy(pthread_rwlock_t *rwlock)
 {
         try_init_preload();
 
-        debug_check_no_locks_freed(rwlock, rwlock + sizeof(*rwlock));
+        debug_check_no_locks_freed(rwlock, sizeof(*rwlock));
         __del_lock(__get_lock(rwlock));
         return ll_pthread_rwlock_destroy(rwlock);
 }
diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c
index eda326fc8620..3727de48c8d5 100644
--- a/tools/lib/traceevent/plugin_scsi.c
+++ b/tools/lib/traceevent/plugin_scsi.c
@@ -85,8 +85,9 @@ typedef unsigned int u32;
 #define MOVE_MEDIUM                     0xa5
 #define EXCHANGE_MEDIUM                 0xa6
 #define READ_12                         0xa8
+#define SERVICE_ACTION_OUT_12           0xa9
 #define WRITE_12                        0xaa
-#define READ_MEDIA_SERIAL_NUMBER        0xab
+#define SERVICE_ACTION_IN_12            0xab
 #define WRITE_VERIFY_12                 0xae
 #define VERIFY_12                       0xaf
 #define SEARCH_HIGH_12                  0xb0
@@ -107,7 +108,9 @@ typedef unsigned int u32;
 #define VERIFY_16                       0x8f
 #define SYNCHRONIZE_CACHE_16            0x91
 #define WRITE_SAME_16                   0x93
-#define SERVICE_ACTION_IN               0x9e
+#define SERVICE_ACTION_BIDIRECTIONAL    0x9d
+#define SERVICE_ACTION_IN_16            0x9e
+#define SERVICE_ACTION_OUT_16           0x9f
 /* values for service action in */
 #define SAI_READ_CAPACITY_16            0x10
 #define SAI_GET_LBA_STATUS              0x12
@@ -393,7 +396,7 @@ scsi_trace_parse_cdb(struct trace_seq *p, unsigned char *cdb, int len)
                 return scsi_trace_rw16(p, cdb, len);
         case UNMAP:
                 return scsi_trace_unmap(p, cdb, len);
-        case SERVICE_ACTION_IN:
+        case SERVICE_ACTION_IN_16:
                 return scsi_trace_service_action_in(p, cdb, len);
         case VARIABLE_LENGTH_CMD:
                 return scsi_trace_varlen(p, cdb, len);
diff --git a/tools/lib/util/find_next_bit.c b/tools/lib/util/find_next_bit.c
new file mode 100644
index 000000000000..41b44f65a79e
--- /dev/null
+++ b/tools/lib/util/find_next_bit.c
@@ -0,0 +1,89 @@
+/* find_next_bit.c: fallback find next bit implementation
+ *
+ * Copied from lib/find_next_bit.c to tools/lib/next_bit.c
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.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, or (at your option) any later version.
+ */
+
+#include <linux/bitops.h>
+#include <asm/types.h>
+#include <asm/byteorder.h>
+
+#define BITOP_WORD(nr)          ((nr) / BITS_PER_LONG)
+
+#ifndef find_next_bit
+/*
+ * Find the next set bit in a memory region.
+ */
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+                            unsigned long offset)
+{
+        const unsigned long *p = addr + BITOP_WORD(offset);
+        unsigned long result = offset & ~(BITS_PER_LONG-1);
+        unsigned long tmp;
+
+        if (offset >= size)
+                return size;
+        size -= result;
+        offset %= BITS_PER_LONG;
+        if (offset) {
+                tmp = *(p++);
+                tmp &= (~0UL << offset);
+                if (size < BITS_PER_LONG)
+                        goto found_first;
+                if (tmp)
+                        goto found_middle;
+                size -= BITS_PER_LONG;
+                result += BITS_PER_LONG;
+        }
+        while (size & ~(BITS_PER_LONG-1)) {
+                if ((tmp = *(p++)))
+                        goto found_middle;
+                result += BITS_PER_LONG;
+                size -= BITS_PER_LONG;
+        }
+        if (!size)
+                return result;
+        tmp = *p;
+
+found_first:
+        tmp &= (~0UL >> (BITS_PER_LONG - size));
+        if (tmp == 0UL)         /* Are any bits set? */
+                return result + size;   /* Nope. */
+found_middle:
+        return result + __ffs(tmp);
+}
+#endif
+
+#ifndef find_first_bit
+/*
+ * Find the first set bit in a memory region.
+ */
+unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
+{
+        const unsigned long *p = addr;
+        unsigned long result = 0;
+        unsigned long tmp;
+
+        while (size & ~(BITS_PER_LONG-1)) {
+                if ((tmp = *(p++)))
+                        goto found;
+                result += BITS_PER_LONG;
+                size -= BITS_PER_LONG;
+        }
+        if (!size)
+                return result;
+
+        tmp = (*p) & (~0UL >> (BITS_PER_LONG - size));
+        if (tmp == 0UL)         /* Are any bits set? */
+                return result + size;   /* Nope. */
+found:
+        return result + __ffs(tmp);
+}
+#endif
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 717221e98450..40399c3d97d6 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -2,6 +2,8 @@ PERF-CFLAGS
 PERF-GUI-VARS
 PERF-VERSION-FILE
 perf
+perf-read-vdso32
+perf-read-vdsox32
 perf-help
 perf-record
 perf-report
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 398f8d53bd6d..af9a54ece024 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -214,6 +214,12 @@ if combined with -a or -C options.
 After starting the program, wait msecs before measuring. This is useful to
 filter out the startup phase of the program, which is often very different.
 
+-I::
+--intr-regs::
+Capture machine state (registers) at interrupt, i.e., on counter overflows for
+each sample. List of captured registers depends on the architecture. This option
+is off by default.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 0927bf4e6c2a..dd7cccdde498 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -159,7 +159,7 @@ OPTIONS
 --dump-raw-trace::
         Dump raw trace in ASCII.
 
--g [type,min[,limit],order[,key]]::
+-g [type,min[,limit],order[,key][,branch]]::
 --call-graph::
         Display call chains using type, min percent threshold, optional print
         limit and order.
@@ -177,6 +177,11 @@ OPTIONS
         - function: compare on functions
         - address: compare on individual code addresses
 
+        branch can be:
+        - branch: include last branch information in callgraph
+        when available. Usually more convenient to use --branch-history
+        for this.
+
         Default: fractal,0.5,callee,function.
 
 --children::
@@ -266,6 +271,11 @@ OPTIONS
         branch stacks and it will automatically switch to the branch view mode,
         unless --no-branch-stack is used.
 
+--branch-history::
+        Add the addresses of sampled taken branches to the callstack.
+        This allows to examine the path the program took to each sample.
+        The data collection must have used -b (or -j) and -g.
+
 --objdump=<path>::
         Path to objdump binary.
 
diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt
index d240bb2e5b22..1e8e400b4493 100644
--- a/tools/perf/Documentation/perf.txt
+++ b/tools/perf/Documentation/perf.txt
@@ -18,6 +18,10 @@ OPTIONS
           --debug verbose   # sets verbose = 1
           --debug verbose=2 # sets verbose = 2
 
+--buildid-dir::
+        Setup buildid cache directory. It has higher priority than
+        buildid.dir config file option.
+
 DESCRIPTION
 -----------
 Performance counters for Linux are a new kernel-based subsystem
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 344c4d3d0a4a..fbbfdc39271d 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -4,17 +4,37 @@ tools/lib/traceevent
 tools/lib/api
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
+tools/lib/util/find_next_bit.c
 tools/include/asm/bug.h
+tools/include/asm-generic/bitops/arch_hweight.h
+tools/include/asm-generic/bitops/atomic.h
+tools/include/asm-generic/bitops/const_hweight.h
+tools/include/asm-generic/bitops/__ffs.h
+tools/include/asm-generic/bitops/__fls.h
+tools/include/asm-generic/bitops/find.h
+tools/include/asm-generic/bitops/fls64.h
+tools/include/asm-generic/bitops/fls.h
+tools/include/asm-generic/bitops/hweight.h
+tools/include/asm-generic/bitops.h
+tools/include/linux/bitops.h
 tools/include/linux/compiler.h
-tools/include/linux/hash.h
 tools/include/linux/export.h
+tools/include/linux/hash.h
+tools/include/linux/log2.h
 tools/include/linux/types.h
+include/asm-generic/bitops/arch_hweight.h
+include/asm-generic/bitops/const_hweight.h
+include/asm-generic/bitops/fls64.h
+include/asm-generic/bitops/__fls.h
+include/asm-generic/bitops/fls.h
 include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
 include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
+lib/find_next_bit.c
+lib/hweight.c
 lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 262916f4a377..aa6a50447c32 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -60,6 +60,15 @@ include config/utilities.mak
 #
 # Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support
 # for dwarf backtrace post unwind.
+#
+# Define NO_PERF_READ_VDSO32 if you do not want to build perf-read-vdso32
+# for reading the 32-bit compatibility VDSO in 64-bit mode
+#
+# Define NO_PERF_READ_VDSOX32 if you do not want to build perf-read-vdsox32
+# for reading the x32 mode 32-bit compatibility VDSO in 64-bit mode
+#
+# Define NO_ZLIB if you do not want to support compressed kernel modules
+
 
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))
@@ -171,11 +180,16 @@ $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
 
 SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
 
-#
-# Single 'perf' binary right now:
-#
 PROGRAMS += $(OUTPUT)perf
 
+ifndef NO_PERF_READ_VDSO32
+PROGRAMS += $(OUTPUT)perf-read-vdso32
+endif
+
+ifndef NO_PERF_READ_VDSOX32
+PROGRAMS += $(OUTPUT)perf-read-vdsox32
+endif
+
 # what 'all' will build and 'install' will install, in perfexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
 
@@ -217,8 +231,19 @@ LIB_H += ../../include/uapi/linux/const.h
 LIB_H += ../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
-LIB_H += util/include/linux/bitops.h
+LIB_H += ../include/linux/bitops.h
+LIB_H += ../include/asm-generic/bitops/arch_hweight.h
+LIB_H += ../include/asm-generic/bitops/atomic.h
+LIB_H += ../include/asm-generic/bitops/const_hweight.h
+LIB_H += ../include/asm-generic/bitops/find.h
+LIB_H += ../include/asm-generic/bitops/fls64.h
+LIB_H += ../include/asm-generic/bitops/fls.h
+LIB_H += ../include/asm-generic/bitops/__ffs.h
+LIB_H += ../include/asm-generic/bitops/__fls.h
+LIB_H += ../include/asm-generic/bitops/hweight.h
+LIB_H += ../include/asm-generic/bitops.h
 LIB_H += ../include/linux/compiler.h
+LIB_H += ../include/linux/log2.h
 LIB_H += util/include/linux/const.h
 LIB_H += util/include/linux/ctype.h
 LIB_H += util/include/linux/kernel.h
@@ -233,7 +258,6 @@ LIB_H += util/include/linux/linkage.h
 LIB_H += util/include/asm/asm-offsets.h
 LIB_H += ../include/asm/bug.h
 LIB_H += util/include/asm/byteorder.h
-LIB_H += util/include/asm/hweight.h
 LIB_H += util/include/asm/swab.h
 LIB_H += util/include/asm/system.h
 LIB_H += util/include/asm/uaccess.h
@@ -247,12 +271,14 @@ LIB_H += util/annotate.h
 LIB_H += util/cache.h
 LIB_H += util/callchain.h
 LIB_H += util/build-id.h
+LIB_H += util/db-export.h
 LIB_H += util/debug.h
 LIB_H += util/pmu.h
 LIB_H += util/event.h
 LIB_H += util/evsel.h
 LIB_H += util/evlist.h
 LIB_H += util/exec_cmd.h
+LIB_H += util/find-vdso-map.c
 LIB_H += util/levenshtein.h
 LIB_H += util/machine.h
 LIB_H += util/map.h
@@ -304,6 +330,7 @@ LIB_H += ui/util.h
 LIB_H += ui/ui.h
 LIB_H += util/data.h
 LIB_H += util/kvm-stat.h
+LIB_H += util/thread-stack.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -311,12 +338,14 @@ LIB_OBJS += $(OUTPUT)util/annotate.o
 LIB_OBJS += $(OUTPUT)util/build-id.o
 LIB_OBJS += $(OUTPUT)util/config.o
 LIB_OBJS += $(OUTPUT)util/ctype.o
+LIB_OBJS += $(OUTPUT)util/db-export.o
 LIB_OBJS += $(OUTPUT)util/pmu.o
 LIB_OBJS += $(OUTPUT)util/environment.o
 LIB_OBJS += $(OUTPUT)util/event.o
 LIB_OBJS += $(OUTPUT)util/evlist.o
 LIB_OBJS += $(OUTPUT)util/evsel.o
 LIB_OBJS += $(OUTPUT)util/exec_cmd.o
+LIB_OBJS += $(OUTPUT)util/find_next_bit.o
 LIB_OBJS += $(OUTPUT)util/help.o
 LIB_OBJS += $(OUTPUT)util/kallsyms.o
 LIB_OBJS += $(OUTPUT)util/levenshtein.o
@@ -380,6 +409,7 @@ LIB_OBJS += $(OUTPUT)util/srcline.o
 LIB_OBJS += $(OUTPUT)util/data.o
 LIB_OBJS += $(OUTPUT)util/tsc.o
 LIB_OBJS += $(OUTPUT)util/cloexec.o
+LIB_OBJS += $(OUTPUT)util/thread-stack.o
 
 LIB_OBJS += $(OUTPUT)ui/setup.o
 LIB_OBJS += $(OUTPUT)ui/helpline.o
@@ -434,12 +464,13 @@ BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
 # Benchmark modules
 BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
 BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
-ifeq ($(RAW_ARCH),x86_64)
+ifeq ($(ARCH), x86)
+ifeq ($(IS_64_BIT), 1)
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o
 endif
+endif
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
-BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o
 BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o
 BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o
 BUILTIN_OBJS += $(OUTPUT)bench/futex-requeue.o
@@ -478,8 +509,6 @@ ifneq ($(OUTPUT),)
 endif
 
 ifdef NO_LIBELF
-EXTLIBS := $(filter-out -lelf,$(EXTLIBS))
-
 # Remove ELF/DWARF dependent codes
 LIB_OBJS := $(filter-out $(OUTPUT)util/symbol-elf.o,$(LIB_OBJS))
 LIB_OBJS := $(filter-out $(OUTPUT)util/dwarf-aux.o,$(LIB_OBJS))
@@ -568,6 +597,10 @@ ifndef NO_LIBNUMA
   BUILTIN_OBJS += $(OUTPUT)bench/numa.o
 endif
 
+ifndef NO_ZLIB
+  LIB_OBJS += $(OUTPUT)util/zlib.o
+endif
+
 ifdef ASCIIDOC8
   export ASCIIDOC8
 endif
@@ -714,6 +747,12 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c $(OUTPUT)PERF-CFLAGS
 $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
+$(OUTPUT)util/hweight.o: ../../lib/hweight.c $(OUTPUT)PERF-CFLAGS
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+
+$(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c $(OUTPUT)PERF-CFLAGS
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+
 $(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $<
 
@@ -732,6 +771,16 @@ $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Uti
 $(OUTPUT)perf-%: %.o $(PERFLIBS)
         $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS)
 
+ifndef NO_PERF_READ_VDSO32
+$(OUTPUT)perf-read-vdso32: perf-read-vdso.c util/find-vdso-map.c
+        $(QUIET_CC)$(CC) -m32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
+endif
+
+ifndef NO_PERF_READ_VDSOX32
+$(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-vdso-map.c
+        $(QUIET_CC)$(CC) -mx32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
+endif
+
 $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
 $(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
 
@@ -876,6 +925,14 @@ install-bin: all install-gtk
                 $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'; \
                 $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'; \
                 $(LN) '$(DESTDIR_SQ)$(bindir_SQ)/perf' '$(DESTDIR_SQ)$(bindir_SQ)/trace'
+ifndef NO_PERF_READ_VDSO32
+        $(call QUIET_INSTALL, perf-read-vdso32) \
+                $(INSTALL) $(OUTPUT)perf-read-vdso32 '$(DESTDIR_SQ)$(bindir_SQ)';
+endif
+ifndef NO_PERF_READ_VDSOX32
+        $(call QUIET_INSTALL, perf-read-vdsox32) \
+                $(INSTALL) $(OUTPUT)perf-read-vdsox32 '$(DESTDIR_SQ)$(bindir_SQ)';
+endif
         $(call QUIET_INSTALL, libexec) \
                 $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
         $(call QUIET_INSTALL, perf-archive) \
@@ -928,7 +985,7 @@ config-clean:
 
 clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean
         $(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
-        $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
+        $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
         $(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
         $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
         $(python-clean)
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index d73ef8bb08c7..0c370f81e002 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -103,7 +103,7 @@ static Dwarf_Frame *get_eh_frame(Dwfl_Module *mod, Dwarf_Addr pc)
                 return NULL;
         }
 
-        result = dwarf_cfi_addrframe(cfi, pc, &frame);
+        result = dwarf_cfi_addrframe(cfi, pc-bias, &frame);
         if (result) {
                 pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
                 return NULL;
@@ -128,7 +128,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
                 return NULL;
         }
 
-        result = dwarf_cfi_addrframe(cfi, pc, &frame);
+        result = dwarf_cfi_addrframe(cfi, pc-bias, &frame);
         if (result) {
                 pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
                 return NULL;
@@ -145,7 +145,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
  *              yet used)
  *      -1 in case of errors
  */
-static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
+static int check_return_addr(struct dso *dso, u64 map_start, Dwarf_Addr pc)
 {
         int             rc = -1;
         Dwfl            *dwfl;
@@ -155,16 +155,31 @@ static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
         Dwarf_Addr      start = pc;
         Dwarf_Addr      end = pc;
         bool            signalp;
+        const char      *exec_file = dso->long_name;
 
-        dwfl = dwfl_begin(&offline_callbacks);
-        if (!dwfl) {
-                pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1));
-                return -1;
-        }
+        dwfl = dso->dwfl;
 
-        if (dwfl_report_offline(dwfl, "",  exec_file, -1) == NULL) {
-                pr_debug("dwfl_report_offline() failed %s\n", dwarf_errmsg(-1));
-                goto out;
+        if (!dwfl) {
+                dwfl = dwfl_begin(&offline_callbacks);
+                if (!dwfl) {
+                        pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1));
+                        return -1;
+                }
+
+                mod = dwfl_report_elf(dwfl, exec_file, exec_file, -1,
+                                                map_start, false);
+                if (!mod) {
+                        pr_debug("dwfl_report_elf() failed %s\n",
+                                                dwarf_errmsg(-1));
+                        /*
+                         * We normally cache the DWARF debug info and never
+                         * call dwfl_end(). But to prevent fd leak, free in
+                         * case of error.
+                         */
+                        dwfl_end(dwfl);
+                        goto out;
+                }
+                dso->dwfl = dwfl;
         }
 
         mod = dwfl_addrmodule(dwfl, pc);
@@ -194,7 +209,6 @@ static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
         rc = check_return_reg(ra_regno, frame);
 
 out:
-        dwfl_end(dwfl);
         return rc;
 }
 
@@ -221,8 +235,7 @@ out:
  *      index:  of callchain entry that needs to be ignored (if any)
  *      -1      if no entry needs to be ignored or in case of errors
  */
-int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
-                                struct ip_callchain *chain)
+int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 {
         struct addr_location al;
         struct dso *dso = NULL;
@@ -235,7 +248,7 @@ int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
 
         ip = chain->ips[2];
 
-        thread__find_addr_location(thread, machine, PERF_RECORD_MISC_USER,
+        thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
                         MAP__FUNCTION, ip, &al);
 
         if (al.map)
@@ -246,10 +259,10 @@ int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
                 return skip_slot;
         }
 
-        rc = check_return_addr(dso->long_name, ip);
+        rc = check_return_addr(dso, al.map->start, ip);
 
-        pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n",
-                                dso->long_name, chain->nr, ip, rc);
+        pr_debug("[DSO %s, sym %s, ip 0x%" PRIx64 "] rc %d\n",
+                                dso->long_name, al.sym->name, ip, rc);
 
         if (rc == 0) {
                 /*
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 2465141b554b..6c14afe8c1b1 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -13,6 +13,7 @@
 #include "../util/cloexec.h"
 #include "bench.h"
 #include "mem-memcpy-arch.h"
+#include "mem-memset-arch.h"
 
 #include <stdio.h>
 #include <stdlib.h>
@@ -48,20 +49,24 @@ static const struct option options[] = {
 };
 
 typedef void *(*memcpy_t)(void *, const void *, size_t);
+typedef void *(*memset_t)(void *, int, size_t);
 
 struct routine {
         const char *name;
         const char *desc;
-        memcpy_t fn;
+        union {
+                memcpy_t memcpy;
+                memset_t memset;
+        } fn;
 };
 
-struct routine routines[] = {
-        { "default",
-          "Default memcpy() provided by glibc",
-          memcpy },
+struct routine memcpy_routines[] = {
+        { .name = "default",
+          .desc = "Default memcpy() provided by glibc",
+          .fn.memcpy = memcpy },
 #ifdef HAVE_ARCH_X86_64_SUPPORT
 
-#define MEMCPY_FN(fn, name, desc) { name, desc, fn },
+#define MEMCPY_FN(_fn, _name, _desc) {.name = _name, .desc = _desc, .fn.memcpy = _fn},
 #include "mem-memcpy-x86-64-asm-def.h"
 #undef MEMCPY_FN
 
@@ -69,7 +74,7 @@ struct routine routines[] = {
 
         { NULL,
           NULL,
-          NULL   }
+          {NULL}   }
 };
 
 static const char * const bench_mem_memcpy_usage[] = {
@@ -110,63 +115,6 @@ static double timeval2double(struct timeval *ts)
                 (double)ts->tv_usec / (double)1000000;
 }
 
-static void alloc_mem(void **dst, void **src, size_t length)
-{
-        *dst = zalloc(length);
-        if (!*dst)
-                die("memory allocation failed - maybe length is too large?\n");
-
-        *src = zalloc(length);
-        if (!*src)
-                die("memory allocation failed - maybe length is too large?\n");
-        /* Make sure to always replace the zero pages even if MMAP_THRESH is crossed */
-        memset(*src, 0, length);
-}
-
-static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault)
-{
-        u64 cycle_start = 0ULL, cycle_end = 0ULL;
-        void *src = NULL, *dst = NULL;
-        int i;
-
-        alloc_mem(&src, &dst, len);
-
-        if (prefault)
-                fn(dst, src, len);
-
-        cycle_start = get_cycle();
-        for (i = 0; i < iterations; ++i)
-                fn(dst, src, len);
-        cycle_end = get_cycle();
-
-        free(src);
-        free(dst);
-        return cycle_end - cycle_start;
-}
-
-static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
-{
-        struct timeval tv_start, tv_end, tv_diff;
-        void *src = NULL, *dst = NULL;
-        int i;
-
-        alloc_mem(&src, &dst, len);
-
-        if (prefault)
-                fn(dst, src, len);
-
-        BUG_ON(gettimeofday(&tv_start, NULL));
-        for (i = 0; i < iterations; ++i)
-                fn(dst, src, len);
-        BUG_ON(gettimeofday(&tv_end, NULL));
-
-        timersub(&tv_end, &tv_start, &tv_diff);
-
-        free(src);
-        free(dst);
-        return (double)((double)len / timeval2double(&tv_diff));
-}
-
 #define pf (no_prefault ? 0 : 1)
 
 #define print_bps(x) do {                                       \
@@ -180,16 +128,25 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
                         printf(" %14lf GB/Sec", x / K / K / K); \
         } while (0)
 
-int bench_mem_memcpy(int argc, const char **argv,
-                     const char *prefix __maybe_unused)
+struct bench_mem_info {
+        const struct routine *routines;
+        u64 (*do_cycle)(const struct routine *r, size_t len, bool prefault);
+        double (*do_gettimeofday)(const struct routine *r, size_t len, bool prefault);
+        const char *const *usage;
+};
+
+static int bench_mem_common(int argc, const char **argv,
+                     const char *prefix __maybe_unused,
+                     struct bench_mem_info *info)
 {
         int i;
         size_t len;
+        double totallen;
         double result_bps[2];
         u64 result_cycle[2];
 
         argc = parse_options(argc, argv, options,
-                             bench_mem_memcpy_usage, 0);
+                             info->usage, 0);
 
         if (no_prefault && only_prefault) {
                 fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
@@ -200,6 +157,7 @@ int bench_mem_memcpy(int argc, const char **argv,
                 init_cycle();
 
         len = (size_t)perf_atoll((char *)length_str);
+        totallen = (double)len * iterations;
 
         result_cycle[0] = result_cycle[1] = 0ULL;
         result_bps[0] = result_bps[1] = 0.0;
@@ -213,16 +171,16 @@ int bench_mem_memcpy(int argc, const char **argv,
         if (only_prefault && no_prefault)
                 only_prefault = no_prefault = false;
 
-        for (i = 0; routines[i].name; i++) {
-                if (!strcmp(routines[i].name, routine))
+        for (i = 0; info->routines[i].name; i++) {
+                if (!strcmp(info->routines[i].name, routine))
                         break;
         }
-        if (!routines[i].name) {
+        if (!info->routines[i].name) {
                 printf("Unknown routine:%s\n", routine);
                 printf("Available routines...\n");
-                for (i = 0; routines[i].name; i++) {
+                for (i = 0; info->routines[i].name; i++) {
                         printf("\t%s ... %s\n",
-                               routines[i].name, routines[i].desc);
+                               info->routines[i].name, info->routines[i].desc);
                 }
                 return 1;
         }
@@ -234,25 +192,25 @@ int bench_mem_memcpy(int argc, const char **argv,
                 /* show both of results */
                 if (use_cycle) {
                         result_cycle[0] =
-                                do_memcpy_cycle(routines[i].fn, len, false);
+                                info->do_cycle(&info->routines[i], len, false);
                         result_cycle[1] =
-                                do_memcpy_cycle(routines[i].fn, len, true);
+                                info->do_cycle(&info->routines[i], len, true);
                 } else {
                         result_bps[0] =
-                                do_memcpy_gettimeofday(routines[i].fn,
+                                info->do_gettimeofday(&info->routines[i],
                                                 len, false);
                         result_bps[1] =
-                                do_memcpy_gettimeofday(routines[i].fn,
+                                info->do_gettimeofday(&info->routines[i],
                                                 len, true);
                 }
         } else {
                 if (use_cycle) {
                         result_cycle[pf] =
-                                do_memcpy_cycle(routines[i].fn,
+                                info->do_cycle(&info->routines[i],
                                                 len, only_prefault);
                 } else {
                         result_bps[pf] =
-                                do_memcpy_gettimeofday(routines[i].fn,
+                                info->do_gettimeofday(&info->routines[i],
                                                 len, only_prefault);
                 }
         }
@@ -263,10 +221,10 @@ int bench_mem_memcpy(int argc, const char **argv,
                         if (use_cycle) {
                                 printf(" %14lf Cycle/Byte\n",
                                         (double)result_cycle[0]
-                                        / (double)len);
+                                        / totallen);
                                 printf(" %14lf Cycle/Byte (with prefault)\n",
                                         (double)result_cycle[1]
-                                        / (double)len);
+                                        / totallen);
                         } else {
                                 print_bps(result_bps[0]);
                                 printf("\n");
@@ -277,7 +235,7 @@ int bench_mem_memcpy(int argc, const char **argv,
                         if (use_cycle) {
                                 printf(" %14lf Cycle/Byte",
                                         (double)result_cycle[pf]
-                                        / (double)len);
+                                        / totallen);
                         } else
                                 print_bps(result_bps[pf]);
 
@@ -288,8 +246,8 @@ int bench_mem_memcpy(int argc, const char **argv,
                 if (!only_prefault && !no_prefault) {
                         if (use_cycle) {
                                 printf("%lf %lf\n",
-                                        (double)result_cycle[0] / (double)len,
-                                        (double)result_cycle[1] / (double)len);
+                                        (double)result_cycle[0] / totallen,
+                                        (double)result_cycle[1] / totallen);
                         } else {
                                 printf("%lf %lf\n",
                                         result_bps[0], result_bps[1]);
@@ -297,7 +255,7 @@ int bench_mem_memcpy(int argc, const char **argv,
                 } else {
                         if (use_cycle) {
                                 printf("%lf\n", (double)result_cycle[pf]
-                                        / (double)len);
+                                        / totallen);
                         } else
                                 printf("%lf\n", result_bps[pf]);
                 }
@@ -310,3 +268,163 @@ int bench_mem_memcpy(int argc, const char **argv,
 
         return 0;
 }
+
+static void memcpy_alloc_mem(void **dst, void **src, size_t length)
+{
+        *dst = zalloc(length);
+        if (!*dst)
+                die("memory allocation failed - maybe length is too large?\n");
+
+        *src = zalloc(length);
+        if (!*src)
+                die("memory allocation failed - maybe length is too large?\n");
+        /* Make sure to always replace the zero pages even if MMAP_THRESH is crossed */
+        memset(*src, 0, length);
+}
+
+static u64 do_memcpy_cycle(const struct routine *r, size_t len, bool prefault)
+{
+        u64 cycle_start = 0ULL, cycle_end = 0ULL;
+        void *src = NULL, *dst = NULL;
+        memcpy_t fn = r->fn.memcpy;
+        int i;
+
+        memcpy_alloc_mem(&src, &dst, len);
+
+        if (prefault)
+                fn(dst, src, len);
+
+        cycle_start = get_cycle();
+        for (i = 0; i < iterations; ++i)
+                fn(dst, src, len);
+        cycle_end = get_cycle();
+
+        free(src);
+        free(dst);
+        return cycle_end - cycle_start;
+}
+
+static double do_memcpy_gettimeofday(const struct routine *r, size_t len,
+                                     bool prefault)
+{
+        struct timeval tv_start, tv_end, tv_diff;
+        memcpy_t fn = r->fn.memcpy;
+        void *src = NULL, *dst = NULL;
+        int i;
+
+        memcpy_alloc_mem(&src, &dst, len);
+
+        if (prefault)
+                fn(dst, src, len);
+
+        BUG_ON(gettimeofday(&tv_start, NULL));
+        for (i = 0; i < iterations; ++i)
+                fn(dst, src, len);
+        BUG_ON(gettimeofday(&tv_end, NULL));
+
+        timersub(&tv_end, &tv_start, &tv_diff);
+
+        free(src);
+        free(dst);
+        return (double)(((double)len * iterations) / timeval2double(&tv_diff));
+}
+
+int bench_mem_memcpy(int argc, const char **argv,
+                     const char *prefix __maybe_unused)
+{
+        struct bench_mem_info info = {
+                .routines = memcpy_routines,
+                .do_cycle = do_memcpy_cycle,
+                .do_gettimeofday = do_memcpy_gettimeofday,
+                .usage = bench_mem_memcpy_usage,
+        };
+
+        return bench_mem_common(argc, argv, prefix, &info);
+}
+
+static void memset_alloc_mem(void **dst, size_t length)
+{
+        *dst = zalloc(length);
+        if (!*dst)
+                die("memory allocation failed - maybe length is too large?\n");
+}
+
+static u64 do_memset_cycle(const struct routine *r, size_t len, bool prefault)
+{
+        u64 cycle_start = 0ULL, cycle_end = 0ULL;
+        memset_t fn = r->fn.memset;
+        void *dst = NULL;
+        int i;
+
+        memset_alloc_mem(&dst, len);
+
+        if (prefault)
+                fn(dst, -1, len);
+
+        cycle_start = get_cycle();
+        for (i = 0; i < iterations; ++i)
+                fn(dst, i, len);
+        cycle_end = get_cycle();
+
+        free(dst);
+        return cycle_end - cycle_start;
+}
+
+static double do_memset_gettimeofday(const struct routine *r, size_t len,
+                                     bool prefault)
+{
+        struct timeval tv_start, tv_end, tv_diff;
+        memset_t fn = r->fn.memset;
+        void *dst = NULL;
+        int i;
+
+        memset_alloc_mem(&dst, len);
+
+        if (prefault)
+                fn(dst, -1, len);
+
+        BUG_ON(gettimeofday(&tv_start, NULL));
+        for (i = 0; i < iterations; ++i)
+                fn(dst, i, len);
+        BUG_ON(gettimeofday(&tv_end, NULL));
+
+        timersub(&tv_end, &tv_start, &tv_diff);
+
+        free(dst);
+        return (double)(((double)len * iterations) / timeval2double(&tv_diff));
+}
+
+static const char * const bench_mem_memset_usage[] = {
+        "perf bench mem memset <options>",
+        NULL
+};
+
+static const struct routine memset_routines[] = {
+        { .name ="default",
+          .desc = "Default memset() provided by glibc",
+          .fn.memset = memset },
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+
+#define MEMSET_FN(_fn, _name, _desc) { .name = _name, .desc = _desc, .fn.memset = _fn },
+#include "mem-memset-x86-64-asm-def.h"
+#undef MEMSET_FN
+
+#endif
+
+        { .name = NULL,
+          .desc = NULL,
+          .fn.memset = NULL   }
+};
+
+int bench_mem_memset(int argc, const char **argv,
+                     const char *prefix __maybe_unused)
+{
+        struct bench_mem_info info = {
+                .routines = memset_routines,
+                .do_cycle = do_memset_cycle,
+                .do_gettimeofday = do_memset_gettimeofday,
+                .usage = bench_mem_memset_usage,
+        };
+
+        return bench_mem_common(argc, argv, prefix, &info);
+}
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
deleted file mode 100644
index 75fc3e65fb2a..000000000000
--- a/tools/perf/bench/mem-memset.c
+++ /dev/null
@@ -1,304 +0,0 @@
-/*
- * mem-memset.c
- *
- * memset: Simple memory set in various ways
- *
- * Trivial clone of mem-memcpy.c.
- */
-
-#include "../perf.h"
-#include "../util/util.h"
-#include "../util/parse-options.h"
-#include "../util/header.h"
-#include "../util/cloexec.h"
-#include "bench.h"
-#include "mem-memset-arch.h"
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/time.h>
-#include <errno.h>
-
-#define K 1024
-
-static const char       *length_str     = "1MB";
-static const char       *routine        = "default";
-static int              iterations      = 1;
-static bool             use_cycle;
-static int              cycle_fd;
-static bool             only_prefault;
-static bool             no_prefault;
-
-static const struct option options[] = {
-        OPT_STRING('l', "length", &length_str, "1MB",
-                    "Specify length of memory to set. "
-                    "Available units: B, KB, MB, GB and TB (upper and lower)"),
-        OPT_STRING('r', "routine", &routine, "default",
-                    "Specify routine to set"),
-        OPT_INTEGER('i', "iterations", &iterations,
-                    "repeat memset() invocation this number of times"),
-        OPT_BOOLEAN('c', "cycle", &use_cycle,
-                    "Use cycles event instead of gettimeofday() for measuring"),
-        OPT_BOOLEAN('o', "only-prefault", &only_prefault,
-                    "Show only the result with page faults before memset()"),
-        OPT_BOOLEAN('n', "no-prefault", &no_prefault,
-                    "Show only the result without page faults before memset()"),
-        OPT_END()
-};
-
-typedef void *(*memset_t)(void *, int, size_t);
-
-struct routine {
-        const char *name;
-        const char *desc;
-        memset_t fn;
-};
-
-static const struct routine routines[] = {
-        { "default",
-          "Default memset() provided by glibc",
-          memset },
-#ifdef HAVE_ARCH_X86_64_SUPPORT
-
-#define MEMSET_FN(fn, name, desc) { name, desc, fn },
-#include "mem-memset-x86-64-asm-def.h"
-#undef MEMSET_FN
-
-#endif
-
-        { NULL,
-          NULL,
-          NULL   }
-};
-
-static const char * const bench_mem_memset_usage[] = {
-        "perf bench mem memset <options>",
-        NULL
-};
-
-static struct perf_event_attr cycle_attr = {
-        .type           = PERF_TYPE_HARDWARE,
-        .config         = PERF_COUNT_HW_CPU_CYCLES
-};
-
-static void init_cycle(void)
-{
-        cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1,
-                                       perf_event_open_cloexec_flag());
-
-        if (cycle_fd < 0 && errno == ENOSYS)
-                die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-        else
-                BUG_ON(cycle_fd < 0);
-}
-
-static u64 get_cycle(void)
-{
-        int ret;
-        u64 clk;
-
-        ret = read(cycle_fd, &clk, sizeof(u64));
-        BUG_ON(ret != sizeof(u64));
-
-        return clk;
-}
-
-static double timeval2double(struct timeval *ts)
-{
-        return (double)ts->tv_sec +
-                (double)ts->tv_usec / (double)1000000;
-}
-
-static void alloc_mem(void **dst, size_t length)
-{
-        *dst = zalloc(length);
-        if (!*dst)
-                die("memory allocation failed - maybe length is too large?\n");
-}
-
-static u64 do_memset_cycle(memset_t fn, size_t len, bool prefault)
-{
-        u64 cycle_start = 0ULL, cycle_end = 0ULL;
-        void *dst = NULL;
-        int i;
-
-        alloc_mem(&dst, len);
-
-        if (prefault)
-                fn(dst, -1, len);
-
-        cycle_start = get_cycle();
-        for (i = 0; i < iterations; ++i)
-                fn(dst, i, len);
-        cycle_end = get_cycle();
-
-        free(dst);
-        return cycle_end - cycle_start;
-}
-
-static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault)
-{
-        struct timeval tv_start, tv_end, tv_diff;
-        void *dst = NULL;
-        int i;
-
-        alloc_mem(&dst, len);
-
-        if (prefault)
-                fn(dst, -1, len);
-
-        BUG_ON(gettimeofday(&tv_start, NULL));
-        for (i = 0; i < iterations; ++i)
-                fn(dst, i, len);
-        BUG_ON(gettimeofday(&tv_end, NULL));
-
-        timersub(&tv_end, &tv_start, &tv_diff);
-
-        free(dst);
-        return (double)((double)len / timeval2double(&tv_diff));
-}
-
-#define pf (no_prefault ? 0 : 1)
-
-#define print_bps(x) do {                                       \
-                if (x < K)                                      \
-                        printf(" %14lf B/Sec", x);              \
-                else if (x < K * K)                             \
-                        printf(" %14lfd KB/Sec", x / K);        \
-                else if (x < K * K * K)                         \
-                        printf(" %14lf MB/Sec", x / K / K);     \
-                else                                            \
-                        printf(" %14lf GB/Sec", x / K / K / K); \
-        } while (0)
-
-int bench_mem_memset(int argc, const char **argv,
-                     const char *prefix __maybe_unused)
-{
-        int i;
-        size_t len;
-        double result_bps[2];
-        u64 result_cycle[2];
-
-        argc = parse_options(argc, argv, options,
-                             bench_mem_memset_usage, 0);
-
-        if (no_prefault && only_prefault) {
-                fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
-                return 1;
-        }
-
-        if (use_cycle)
-                init_cycle();
-
-        len = (size_t)perf_atoll((char *)length_str);
-
-        result_cycle[0] = result_cycle[1] = 0ULL;
-        result_bps[0] = result_bps[1] = 0.0;
-
-        if ((s64)len <= 0) {
-                fprintf(stderr, "Invalid length:%s\n", length_str);
-                return 1;
-        }
-
-        /* same to without specifying either of prefault and no-prefault */
-        if (only_prefault && no_prefault)
-                only_prefault = no_prefault = false;
-
-        for (i = 0; routines[i].name; i++) {
-                if (!strcmp(routines[i].name, routine))
-                        break;
-        }
-        if (!routines[i].name) {
-                printf("Unknown routine:%s\n", routine);
-                printf("Available routines...\n");
-                for (i = 0; routines[i].name; i++) {
-                        printf("\t%s ... %s\n",
-                               routines[i].name, routines[i].desc);
-                }
-                return 1;
-        }
-
-        if (bench_format == BENCH_FORMAT_DEFAULT)
-                printf("# Copying %s Bytes ...\n\n", length_str);
-
-        if (!only_prefault && !no_prefault) {
-                /* show both of results */
-                if (use_cycle) {
-                        result_cycle[0] =
-                                do_memset_cycle(routines[i].fn, len, false);
-                        result_cycle[1] =
-                                do_memset_cycle(routines[i].fn, len, true);
-                } else {
-                        result_bps[0] =
-                                do_memset_gettimeofday(routines[i].fn,
-                                                len, false);
-                        result_bps[1] =
-                                do_memset_gettimeofday(routines[i].fn,
-                                                len, true);
-                }
-        } else {
-                if (use_cycle) {
-                        result_cycle[pf] =
-                                do_memset_cycle(routines[i].fn,
-                                                len, only_prefault);
-                } else {
-                        result_bps[pf] =
-                                do_memset_gettimeofday(routines[i].fn,
-                                                len, only_prefault);
-                }
-        }
-
-        switch (bench_format) {
-        case BENCH_FORMAT_DEFAULT:
-                if (!only_prefault && !no_prefault) {
-                        if (use_cycle) {
-                                printf(" %14lf Cycle/Byte\n",
-                                        (double)result_cycle[0]
-                                        / (double)len);
-                                printf(" %14lf Cycle/Byte (with prefault)\n ",
-                                        (double)result_cycle[1]
-                                        / (double)len);
-                        } else {
-                                print_bps(result_bps[0]);
-                                printf("\n");
-                                print_bps(result_bps[1]);
-                                printf(" (with prefault)\n");
-                        }
-                } else {
-                        if (use_cycle) {
-                                printf(" %14lf Cycle/Byte",
-                                        (double)result_cycle[pf]
-                                        / (double)len);
-                        } else
-                                print_bps(result_bps[pf]);
-
-                        printf("%s\n", only_prefault ? " (with prefault)" : "");
-                }
-                break;
-        case BENCH_FORMAT_SIMPLE:
-                if (!only_prefault && !no_prefault) {
-                        if (use_cycle) {
-                                printf("%lf %lf\n",
-                                        (double)result_cycle[0] / (double)len,
-                                        (double)result_cycle[1] / (double)len);
-                        } else {
-                                printf("%lf %lf\n",
-                                        result_bps[0], result_bps[1]);
-                        }
-                } else {
-                        if (use_cycle) {
-                                printf("%lf\n", (double)result_cycle[pf]
-                                        / (double)len);
-                        } else
-                                printf("%lf\n", result_bps[pf]);
-                }
-                break;
-        default:
-                /* reaching this means there's some disaster: */
-                die("unknown format: %d\n", bench_format);
-                break;
-        }
-
-        return 0;
-}
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 07a8d7646a15..005cc283790c 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -19,12 +19,12 @@
 #include <stdlib.h>
 #include <signal.h>
 #include <sys/wait.h>
-#include <linux/unistd.h>
 #include <string.h>
 #include <errno.h>
 #include <assert.h>
 #include <sys/time.h>
 #include <sys/types.h>
+#include <sys/syscall.h>
 
 #include <pthread.h>
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index e7417fe97a97..747f86103599 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -232,7 +232,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
                 if (nr_samples > 0) {
                         total_nr_samples += nr_samples;
                         hists__collapse_resort(hists, NULL);
-                        hists__output_resort(hists);
+                        hists__output_resort(hists, NULL);
 
                         if (symbol_conf.event_group &&
                             !perf_evsel__is_group_leader(pos))
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 70385756da63..77d5cae54c6a 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -285,12 +285,11 @@ int cmd_buildid_cache(int argc, const char **argv,
         struct str_node *pos;
         int ret = 0;
         bool force = false;
-        char debugdir[PATH_MAX];
         char const *add_name_list_str = NULL,
                    *remove_name_list_str = NULL,
                    *missing_filename = NULL,
                    *update_name_list_str = NULL,
-                   *kcore_filename;
+                   *kcore_filename = NULL;
         char sbuf[STRERR_BUFSIZE];
 
         struct perf_data_file file = {
@@ -335,13 +334,11 @@ int cmd_buildid_cache(int argc, const char **argv,
 
         setup_pager();
 
-        snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
-
         if (add_name_list_str) {
                 list = strlist__new(true, add_name_list_str);
                 if (list) {
                         strlist__for_each(pos, list)
-                                if (build_id_cache__add_file(pos->s, debugdir)) {
+                                if (build_id_cache__add_file(pos->s, buildid_dir)) {
                                         if (errno == EEXIST) {
                                                 pr_debug("%s already in the cache\n",
                                                          pos->s);
@@ -359,7 +356,7 @@ int cmd_buildid_cache(int argc, const char **argv,
                 list = strlist__new(true, remove_name_list_str);
                 if (list) {
                         strlist__for_each(pos, list)
-                                if (build_id_cache__remove_file(pos->s, debugdir)) {
+                                if (build_id_cache__remove_file(pos->s, buildid_dir)) {
                                         if (errno == ENOENT) {
                                                 pr_debug("%s wasn't in the cache\n",
                                                          pos->s);
@@ -380,7 +377,7 @@ int cmd_buildid_cache(int argc, const char **argv,
                 list = strlist__new(true, update_name_list_str);
                 if (list) {
                         strlist__for_each(pos, list)
-                                if (build_id_cache__update_file(pos->s, debugdir)) {
+                                if (build_id_cache__update_file(pos->s, buildid_dir)) {
                                         if (errno == ENOENT) {
                                                 pr_debug("%s wasn't in the cache\n",
                                                          pos->s);
@@ -395,7 +392,7 @@ int cmd_buildid_cache(int argc, const char **argv,
         }
 
         if (kcore_filename &&
-            build_id_cache__add_kcore(kcore_filename, debugdir, force))
+            build_id_cache__add_kcore(kcore_filename, buildid_dir, force))
                 pr_warning("Couldn't add %s\n", kcore_filename);
 
 out:
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 25114c9a6801..1fd96c13f199 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -357,6 +357,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 static struct perf_tool tool = {
         .sample = diff__process_sample_event,
         .mmap   = perf_event__process_mmap,
+        .mmap2  = perf_event__process_mmap2,
         .comm   = perf_event__process_comm,
         .exit   = perf_event__process_exit,
         .fork   = perf_event__process_fork,
@@ -544,6 +545,42 @@ hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
         return __hist_entry__cmp_compute(p_left, p_right, c);
 }
 
+static int64_t
+hist_entry__cmp_nop(struct hist_entry *left __maybe_unused,
+                    struct hist_entry *right __maybe_unused)
+{
+        return 0;
+}
+
+static int64_t
+hist_entry__cmp_baseline(struct hist_entry *left, struct hist_entry *right)
+{
+        if (sort_compute)
+                return 0;
+
+        if (left->stat.period == right->stat.period)
+                return 0;
+        return left->stat.period > right->stat.period ? 1 : -1;
+}
+
+static int64_t
+hist_entry__cmp_delta(struct hist_entry *left, struct hist_entry *right)
+{
+        return hist_entry__cmp_compute(right, left, COMPUTE_DELTA);
+}
+
+static int64_t
+hist_entry__cmp_ratio(struct hist_entry *left, struct hist_entry *right)
+{
+        return hist_entry__cmp_compute(right, left, COMPUTE_RATIO);
+}
+
+static int64_t
+hist_entry__cmp_wdiff(struct hist_entry *left, struct hist_entry *right)
+{
+        return hist_entry__cmp_compute(right, left, COMPUTE_WEIGHTED_DIFF);
+}
+
 static void insert_hist_entry_by_compute(struct rb_root *root,
                                          struct hist_entry *he,
                                          int c)
@@ -604,7 +641,7 @@ static void hists__process(struct hists *hists)
                 hists__precompute(hists);
                 hists__compute_resort(hists);
         } else {
-                hists__output_resort(hists);
+                hists__output_resort(hists, NULL);
         }
 
         hists__fprintf(hists, true, 0, 0, 0, stdout);
@@ -1037,27 +1074,35 @@ static void data__hpp_register(struct data__file *d, int idx)
         fmt->header = hpp__header;
         fmt->width  = hpp__width;
         fmt->entry  = hpp__entry_global;
+        fmt->cmp    = hist_entry__cmp_nop;
+        fmt->collapse = hist_entry__cmp_nop;
 
         /* TODO more colors */
         switch (idx) {
         case PERF_HPP_DIFF__BASELINE:
                 fmt->color = hpp__color_baseline;
+                fmt->sort  = hist_entry__cmp_baseline;
                 break;
         case PERF_HPP_DIFF__DELTA:
                 fmt->color = hpp__color_delta;
+                fmt->sort  = hist_entry__cmp_delta;
                 break;
         case PERF_HPP_DIFF__RATIO:
                 fmt->color = hpp__color_ratio;
+                fmt->sort  = hist_entry__cmp_ratio;
                 break;
         case PERF_HPP_DIFF__WEIGHTED_DIFF:
                 fmt->color = hpp__color_wdiff;
+                fmt->sort  = hist_entry__cmp_wdiff;
                 break;
         default:
+                fmt->sort  = hist_entry__cmp_nop;
                 break;
         }
 
         init_header(d, dfmt);
         perf_hpp__column_register(fmt);
+        perf_hpp__register_sort_field(fmt);
 }
 
 static void ui_init(void)
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index de99ca1bb942..84df2deed988 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -217,8 +217,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
                 goto repipe;
         }
 
-        thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-                              sample->ip, &al);
+        thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al);
 
         if (al.map != NULL) {
                 if (!al.map->dso->hit) {
@@ -410,6 +409,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
                         .tracing_data   = perf_event__repipe_op2_synth,
                         .finished_round = perf_event__repipe_op2_synth,
                         .build_id       = perf_event__repipe_op2_synth,
+                        .id_index       = perf_event__repipe_op2_synth,
                 },
                 .input_name  = "-",
                 .samples = LIST_HEAD_INIT(inject.samples),
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index b65eb0507b38..0894a817f67e 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1132,6 +1132,10 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
                 "-m", "1024",
                 "-c", "1",
         };
+        const char * const kvm_stat_record_usage[] = {
+                "perf kvm stat record [<options>]",
+                NULL
+        };
         const char * const *events_tp;
         events_tp_size = 0;
 
@@ -1159,6 +1163,27 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
         for (j = 1; j < (unsigned int)argc; j++, i++)
                 rec_argv[i] = argv[j];
 
+        set_option_flag(record_options, 'e', "event", PARSE_OPT_HIDDEN);
+        set_option_flag(record_options, 0, "filter", PARSE_OPT_HIDDEN);
+        set_option_flag(record_options, 'R', "raw-samples", PARSE_OPT_HIDDEN);
+
+        set_option_flag(record_options, 'F', "freq", PARSE_OPT_DISABLED);
+        set_option_flag(record_options, 0, "group", PARSE_OPT_DISABLED);
+        set_option_flag(record_options, 'g', NULL, PARSE_OPT_DISABLED);
+        set_option_flag(record_options, 0, "call-graph", PARSE_OPT_DISABLED);
+        set_option_flag(record_options, 'd', "data", PARSE_OPT_DISABLED);
+        set_option_flag(record_options, 'T', "timestamp", PARSE_OPT_DISABLED);
+        set_option_flag(record_options, 'P', "period", PARSE_OPT_DISABLED);
+        set_option_flag(record_options, 'n', "no-samples", PARSE_OPT_DISABLED);
+        set_option_flag(record_options, 'N', "no-buildid-cache", PARSE_OPT_DISABLED);
+        set_option_flag(record_options, 'B', "no-buildid", PARSE_OPT_DISABLED);
+        set_option_flag(record_options, 'G', "cgroup", PARSE_OPT_DISABLED);
+        set_option_flag(record_options, 'b', "branch-any", PARSE_OPT_DISABLED);
+        set_option_flag(record_options, 'j', "branch-filter", PARSE_OPT_DISABLED);
+        set_option_flag(record_options, 'W', "weight", PARSE_OPT_DISABLED);
+        set_option_flag(record_options, 0, "transaction", PARSE_OPT_DISABLED);
+
+        record_usage = kvm_stat_record_usage;
         return cmd_record(i, rec_argv, NULL);
 }
 
@@ -1268,7 +1293,8 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
                 OPT_UINTEGER('d', "display", &kvm->display_time,
                         "time in seconds between display updates"),
                 OPT_STRING(0, "event", &kvm->report_event, "report event",
-                        "event for reporting: vmexit, mmio, ioport"),
+                        "event for reporting: "
+                        "vmexit, mmio (x86 only), ioport (x86 only)"),
                 OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu,
                         "vcpu id to report"),
                 OPT_STRING('k', "key", &kvm->sort_key, "sort-key",
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 011195e38f21..198f3c3aff95 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -19,7 +19,9 @@
 int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 {
         int i;
-        const struct option list_options[] = {
+        bool raw_dump = false;
+        struct option list_options[] = {
+                OPT_BOOLEAN(0, "raw-dump", &raw_dump, "Dump raw events"),
                 OPT_END()
         };
         const char * const list_usage[] = {
@@ -27,11 +29,18 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
                 NULL
         };
 
+        set_option_flag(list_options, 0, "raw-dump", PARSE_OPT_HIDDEN);
+
         argc = parse_options(argc, argv, list_options, list_usage,
                              PARSE_OPT_STOP_AT_NON_OPTION);
 
         setup_pager();
 
+        if (raw_dump) {
+                print_events(NULL, true);
+                return 0;
+        }
+
         if (argc == 0) {
                 print_events(NULL, false);
                 return 0;
@@ -53,8 +62,6 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
                         print_hwcache_events(NULL, false);
                 else if (strcmp(argv[i], "pmu") == 0)
                         print_pmu_events(NULL, false);
-                else if (strcmp(argv[i], "--raw-dump") == 0)
-                        print_events(NULL, true);
                 else {
                         char *sep = strchr(argv[i], ':'), *s;
                         int sep_idx;
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 7af26acf06d9..921bb6942503 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -55,6 +55,7 @@ static struct {
         bool show_funcs;
         bool mod_events;
         bool uprobes;
+        bool quiet;
         int nevents;
         struct perf_probe_event events[MAX_PROBES];
         struct strlist *dellist;
@@ -312,9 +313,11 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 #endif
                 NULL
 };
-        const struct option options[] = {
+        struct option options[] = {
         OPT_INCR('v', "verbose", &verbose,
                     "be more verbose (show parsed arguments, etc)"),
+        OPT_BOOLEAN('q', "quiet", &params.quiet,
+                    "be quiet (do not show any mesages)"),
         OPT_BOOLEAN('l', "list", &params.list_events,
                     "list up current probe events"),
         OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.",
@@ -382,6 +385,14 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
         };
         int ret;
 
+        set_option_flag(options, 'a', "add", PARSE_OPT_EXCLUSIVE);
+        set_option_flag(options, 'd', "del", PARSE_OPT_EXCLUSIVE);
+        set_option_flag(options, 'l', "list", PARSE_OPT_EXCLUSIVE);
+#ifdef HAVE_DWARF_SUPPORT
+        set_option_flag(options, 'L', "line", PARSE_OPT_EXCLUSIVE);
+        set_option_flag(options, 'V', "vars", PARSE_OPT_EXCLUSIVE);
+#endif
+
         argc = parse_options(argc, argv, options, probe_usage,
                              PARSE_OPT_STOP_AT_NON_OPTION);
         if (argc > 0) {
@@ -396,6 +407,14 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
                 }
         }
 
+        if (params.quiet) {
+                if (verbose != 0) {
+                        pr_err("  Error: -v and -q are exclusive.\n");
+                        return -EINVAL;
+                }
+                verbose = -1;
+        }
+
         if (params.max_probe_points == 0)
                 params.max_probe_points = MAX_PROBES;
 
@@ -409,22 +428,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
         symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 
         if (params.list_events) {
-                if (params.mod_events) {
-                        pr_err("  Error: Don't use --list with --add/--del.\n");
-                        usage_with_options(probe_usage, options);
-                }
-                if (params.show_lines) {
-                        pr_err("  Error: Don't use --list with --line.\n");
-                        usage_with_options(probe_usage, options);
-                }
-                if (params.show_vars) {
-                        pr_err(" Error: Don't use --list with --vars.\n");
-                        usage_with_options(probe_usage, options);
-                }
-                if (params.show_funcs) {
-                        pr_err("  Error: Don't use --list with --funcs.\n");
-                        usage_with_options(probe_usage, options);
-                }
                 if (params.uprobes) {
                         pr_warning("  Error: Don't use --list with --exec.\n");
                         usage_with_options(probe_usage, options);
@@ -435,19 +438,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
                 return ret;
         }
         if (params.show_funcs) {
-                if (params.nevents != 0 || params.dellist) {
-                        pr_err("  Error: Don't use --funcs with"
-                               " --add/--del.\n");
-                        usage_with_options(probe_usage, options);
-                }
-                if (params.show_lines) {
-                        pr_err("  Error: Don't use --funcs with --line.\n");
-                        usage_with_options(probe_usage, options);
-                }
-                if (params.show_vars) {
-                        pr_err("  Error: Don't use --funcs with --vars.\n");
-                        usage_with_options(probe_usage, options);
-                }
                 if (!params.filter)
                         params.filter = strfilter__new(DEFAULT_FUNC_FILTER,
                                                        NULL);
@@ -462,16 +452,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 
 #ifdef HAVE_DWARF_SUPPORT
         if (params.show_lines) {
-                if (params.mod_events) {
-                        pr_err("  Error: Don't use --line with"
-                               " --add/--del.\n");
-                        usage_with_options(probe_usage, options);
-                }
-                if (params.show_vars) {
-                        pr_err(" Error: Don't use --line with --vars.\n");
-                        usage_with_options(probe_usage, options);
-                }
-
                 ret = show_line_range(&params.line_range, params.target,
                                       params.uprobes);
                 if (ret < 0)
@@ -479,11 +459,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
                 return ret;
         }
         if (params.show_vars) {
-                if (params.mod_events) {
-                        pr_err("  Error: Don't use --vars with"
-                               " --add/--del.\n");
-                        usage_with_options(probe_usage, options);
-                }
                 if (!params.filter)
                         params.filter = strfilter__new(DEFAULT_VAR_FILTER,
                                                        NULL);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 2583a9b04317..8648c6d3003d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -200,6 +200,17 @@ static int process_buildids(struct record *rec)
         if (size == 0)
                 return 0;
 
+        /*
+         * During this process, it'll load kernel map and replace the
+         * dso->long_name to a real pathname it found.  In this case
+         * we prefer the vmlinux path like
+         *   /lib/modules/3.16.4/build/vmlinux
+         *
+         * rather than build-id path (in debug directory).
+         *   $HOME/.debug/.build-id/f0/6e17aa50adf4d00b88925e03775de107611551
+         */
+        symbol_conf.ignore_vmlinux_buildid = true;
+
         return __perf_session__process_events(session, start,
                                               size - start,
                                               size, &build_id__mark_dso_hit_ops);
@@ -680,11 +691,12 @@ static int perf_record_config(const char *var, const char *value, void *cb)
         return perf_default_config(var, value, cb);
 }
 
-static const char * const record_usage[] = {
+static const char * const __record_usage[] = {
         "perf record [<options>] [<command>]",
         "perf record [<options>] -- <command> [<options>]",
         NULL
 };
+const char * const *record_usage = __record_usage;
 
 /*
  * XXX Ideally would be local to cmd_record() and passed to a record__new
@@ -725,7 +737,7 @@ const char record_callchain_help[] = CALLCHAIN_HELP "fp";
  * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
  * using pipes, etc.
  */
-const struct option record_options[] = {
+struct option __record_options[] = {
         OPT_CALLBACK('e', "event", &record.evlist, "event",
                      "event selector. use 'perf list' to list available events",
                      parse_events_option),
@@ -799,9 +811,13 @@ const struct option record_options[] = {
                     "sample transaction flags (special events only)"),
         OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
                     "use per-thread mmaps"),
+        OPT_BOOLEAN('I', "intr-regs", &record.opts.sample_intr_regs,
+                    "Sample machine registers on interrupt"),
         OPT_END()
 };
 
+struct option *record_options = __record_options;
+
 int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 {
         int err = -ENOMEM;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 140a6cd88351..072ae8ad67fc 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -226,8 +226,9 @@ static int report__setup_sample_type(struct report *rep)
                         return -EINVAL;
                 }
                 if (symbol_conf.use_callchain) {
-                        ui__error("Selected -g but no callchain data. Did "
-                                    "you call 'perf record' without -g?\n");
+                        ui__error("Selected -g or --branch-history but no "
+                                  "callchain data. Did\n"
+                                  "you call 'perf record' without -g?\n");
                         return -1;
                 }
         } else if (!rep->dont_use_callchains &&
@@ -456,6 +457,19 @@ static void report__collapse_hists(struct report *rep)
         ui_progress__finish();
 }
 
+static void report__output_resort(struct report *rep)
+{
+        struct ui_progress prog;
+        struct perf_evsel *pos;
+
+        ui_progress__init(&prog, rep->nr_entries, "Sorting events for output...");
+
+        evlist__for_each(rep->session->evlist, pos)
+                hists__output_resort(evsel__hists(pos), &prog);
+
+        ui_progress__finish();
+}
+
 static int __cmd_report(struct report *rep)
 {
         int ret;
@@ -504,13 +518,20 @@ static int __cmd_report(struct report *rep)
         if (session_done())
                 return 0;
 
+        /*
+         * recalculate number of entries after collapsing since it
+         * might be changed during the collapse phase.
+         */
+        rep->nr_entries = 0;
+        evlist__for_each(session->evlist, pos)
+                rep->nr_entries += evsel__hists(pos)->nr_entries;
+
         if (rep->nr_entries == 0) {
                 ui__error("The %s file has no samples!\n", file->path);
                 return 0;
         }
 
-        evlist__for_each(session->evlist, pos)
-                hists__output_resort(evsel__hists(pos));
+        report__output_resort(rep);
 
         return report__browse_hists(rep);
 }
@@ -575,6 +596,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
         struct stat st;
         bool has_br_stack = false;
         int branch_mode = -1;
+        bool branch_call_mode = false;
         char callchain_default_opt[] = "fractal,0.5,callee";
         const char * const report_usage[] = {
                 "perf report [<options>]",
@@ -637,8 +659,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                    "regex filter to identify parent, see: '--sort parent'"),
         OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
                     "Only display entries with parent-match"),
-        OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
-                     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
+        OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order[,branch]",
+                     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address), add branches. "
                      "Default: fractal,0.5,callee,function", &report_parse_callchain_opt, callchain_default_opt),
         OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
                     "Accumulate callchains of children and show total overhead as well"),
@@ -684,7 +706,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
         OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
                     "Show event group information together"),
         OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "",
-                    "use branch records for histogram filling", parse_branch_mode),
+                    "use branch records for per branch histogram filling",
+                    parse_branch_mode),
+        OPT_BOOLEAN(0, "branch-history", &branch_call_mode,
+                    "add last branch records to call history"),
         OPT_STRING(0, "objdump", &objdump_path, "path",
                    "objdump binary to use for disassembly and annotations"),
         OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
@@ -745,10 +770,24 @@ repeat:
         has_br_stack = perf_header__has_feat(&session->header,
                                              HEADER_BRANCH_STACK);
 
-        if ((branch_mode == -1 && has_br_stack) || branch_mode == 1) {
+        /*
+         * Branch mode is a tristate:
+         * -1 means default, so decide based on the file having branch data.
+         * 0/1 means the user chose a mode.
+         */
+        if (((branch_mode == -1 && has_br_stack) || branch_mode == 1) &&
+            branch_call_mode == -1) {
                 sort__mode = SORT_MODE__BRANCH;
                 symbol_conf.cumulate_callchain = false;
         }
+        if (branch_call_mode) {
+                callchain_param.key = CCKEY_ADDRESS;
+                callchain_param.branch_callstack = 1;
+                symbol_conf.use_callchain = true;
+                callchain_register_param(&callchain_param);
+                if (sort_order == NULL)
+                        sort_order = "srcline,symbol,dso";
+        }
 
         if (report.mem_mode) {
                 if (sort__mode == SORT_MODE__BRANCH) {
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9708a1290571..ce304dfd962a 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -23,7 +23,6 @@ static char const		*generate_script_lang;
 static bool                     debug_mode;
 static u64                      last_timestamp;
 static u64                      nr_unordered;
-extern const struct option      record_options[];
 static bool                     no_callchain;
 static bool                     latency_format;
 static bool                     system_wide;
@@ -379,7 +378,6 @@ static void print_sample_start(struct perf_sample *sample,
 
 static void print_sample_addr(union perf_event *event,
                           struct perf_sample *sample,
-                          struct machine *machine,
                           struct thread *thread,
                           struct perf_event_attr *attr)
 {
@@ -390,7 +388,7 @@ static void print_sample_addr(union perf_event *event,
         if (!sample_addr_correlates_sym(attr))
                 return;
 
-        perf_event__preprocess_sample_addr(event, sample, machine, thread, &al);
+        perf_event__preprocess_sample_addr(event, sample, thread, &al);
 
         if (PRINT_FIELD(SYM)) {
                 printf(" ");
@@ -438,7 +436,7 @@ static void print_sample_bts(union perf_event *event,
             ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
              !output[attr->type].user_set)) {
                 printf(" => ");
-                print_sample_addr(event, sample, al->machine, thread, attr);
+                print_sample_addr(event, sample, thread, attr);
         }
 
         if (print_srcline_last)
@@ -475,7 +473,7 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
                 event_format__print(evsel->tp_format, sample->cpu,
                                     sample->raw_data, sample->raw_size);
         if (PRINT_FIELD(ADDR))
-                print_sample_addr(event, sample, al->machine, thread, attr);
+                print_sample_addr(event, sample, thread, attr);
 
         if (PRINT_FIELD(IP)) {
                 if (!symbol_conf.use_callchain)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 055ce9232c9e..891086376381 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -388,20 +388,102 @@ static void update_shadow_stats(struct perf_evsel *counter, u64 *count)
                 update_stats(&runtime_itlb_cache_stats[0], count[0]);
 }
 
+static void zero_per_pkg(struct perf_evsel *counter)
+{
+        if (counter->per_pkg_mask)
+                memset(counter->per_pkg_mask, 0, MAX_NR_CPUS);
+}
+
+static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
+{
+        unsigned long *mask = counter->per_pkg_mask;
+        struct cpu_map *cpus = perf_evsel__cpus(counter);
+        int s;
+
+        *skip = false;
+
+        if (!counter->per_pkg)
+                return 0;
+
+        if (cpu_map__empty(cpus))
+                return 0;
+
+        if (!mask) {
+                mask = zalloc(MAX_NR_CPUS);
+                if (!mask)
+                        return -ENOMEM;
+
+                counter->per_pkg_mask = mask;
+        }
+
+        s = cpu_map__get_socket(cpus, cpu);
+        if (s < 0)
+                return -1;
+
+        *skip = test_and_set_bit(s, mask) == 1;
+        return 0;
+}
+
+static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
+                   struct perf_counts_values *count)
+{
+        struct perf_counts_values *aggr = &evsel->counts->aggr;
+        static struct perf_counts_values zero;
+        bool skip = false;
+
+        if (check_per_pkg(evsel, cpu, &skip)) {
+                pr_err("failed to read per-pkg counter\n");
+                return -1;
+        }
+
+        if (skip)
+                count = &zero;
+
+        switch (aggr_mode) {
+        case AGGR_CORE:
+        case AGGR_SOCKET:
+        case AGGR_NONE:
+                if (!evsel->snapshot)
+                        perf_evsel__compute_deltas(evsel, cpu, count);
+                perf_counts_values__scale(count, scale, NULL);
+                evsel->counts->cpu[cpu] = *count;
+                update_shadow_stats(evsel, count->values);
+                break;
+        case AGGR_GLOBAL:
+                aggr->val += count->val;
+                if (scale) {
+                        aggr->ena += count->ena;
+                        aggr->run += count->run;
+                }
+        default:
+                break;
+        }
+
+        return 0;
+}
+
+static int read_counter(struct perf_evsel *counter);
+
 /*
  * Read out the results of a single counter:
  * aggregate counts across CPUs in system-wide mode
  */
 static int read_counter_aggr(struct perf_evsel *counter)
 {
+        struct perf_counts_values *aggr = &counter->counts->aggr;
         struct perf_stat *ps = counter->priv;
         u64 *count = counter->counts->aggr.values;
         int i;
 
-        if (__perf_evsel__read(counter, perf_evsel__nr_cpus(counter),
-                               thread_map__nr(evsel_list->threads), scale) < 0)
+        aggr->val = aggr->ena = aggr->run = 0;
+
+        if (read_counter(counter))
                 return -1;
 
+        if (!counter->snapshot)
+                perf_evsel__compute_deltas(counter, -1, aggr);
+        perf_counts_values__scale(aggr, scale, &counter->counts->scaled);
+
         for (i = 0; i < 3; i++)
                 update_stats(&ps->res_stats[i], count[i]);
 
@@ -424,16 +506,21 @@ static int read_counter_aggr(struct perf_evsel *counter)
  */
 static int read_counter(struct perf_evsel *counter)
 {
-        u64 *count;
-        int cpu;
+        int nthreads = thread_map__nr(evsel_list->threads);
+        int ncpus = perf_evsel__nr_cpus(counter);
+        int cpu, thread;
 
-        for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-                if (__perf_evsel__read_on_cpu(counter, cpu, 0, scale) < 0)
-                        return -1;
+        if (counter->system_wide)
+                nthreads = 1;
 
-                count = counter->counts->cpu[cpu].values;
+        if (counter->per_pkg)
+                zero_per_pkg(counter);
 
-                update_shadow_stats(counter, count);
+        for (thread = 0; thread < nthreads; thread++) {
+                for (cpu = 0; cpu < ncpus; cpu++) {
+                        if (perf_evsel__read_cb(counter, cpu, thread, read_cb))
+                                return -1;
+                }
         }
 
         return 0;
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 35b425b6293f..f3bb1a4bf060 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -528,7 +528,7 @@ static const char *cat_backtrace(union perf_event *event,
                 }
 
                 tal.filtered = 0;
-                thread__find_addr_location(al.thread, machine, cpumode,
+                thread__find_addr_location(al.thread, cpumode,
                                            MAP__FUNCTION, ip, &tal);
 
                 if (tal.sym)
@@ -1963,7 +1963,7 @@ int cmd_timechart(int argc, const char **argv,
                 NULL
         };
 
-        const struct option record_options[] = {
+        const struct option timechart_record_options[] = {
         OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
         OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
                     "output processes data only"),
@@ -1972,7 +1972,7 @@ int cmd_timechart(int argc, const char **argv,
         OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"),
         OPT_END()
         };
-        const char * const record_usage[] = {
+        const char * const timechart_record_usage[] = {
                 "perf timechart record [<options>]",
                 NULL
         };
@@ -1985,7 +1985,8 @@ int cmd_timechart(int argc, const char **argv,
         }
 
         if (argc && !strncmp(argv[0], "rec", 3)) {
-                argc = parse_options(argc, argv, record_options, record_usage,
+                argc = parse_options(argc, argv, timechart_record_options,
+                                     timechart_record_usage,
                                      PARSE_OPT_STOP_AT_NON_OPTION);
 
                 if (tchart.power_only && tchart.tasks_only) {
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 0aa7747ff139..616f0fcb4701 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -66,7 +66,6 @@
 #include <sys/utsname.h>
 #include <sys/mman.h>
 
-#include <linux/unistd.h>
 #include <linux/types.h>
 
 static volatile int done;
@@ -285,7 +284,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
         }
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists);
+        hists__output_resort(hists, NULL);
 
         hists__output_recalc_col_len(hists, top->print_entries - printed);
         putchar('\n');
@@ -554,7 +553,7 @@ static void perf_top__sort_new_samples(void *arg)
         }
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists);
+        hists__output_resort(hists, NULL);
 }
 
 static void *display_thread_tui(void *arg)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index fb126459b134..badfabc6a01f 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1846,7 +1846,7 @@ static int trace__pgfault(struct trace *trace,
         if (trace->summary_only)
                 return 0;
 
-        thread__find_addr_location(thread, trace->host, cpumode, MAP__FUNCTION,
+        thread__find_addr_location(thread, cpumode, MAP__FUNCTION,
                               sample->ip, &al);
 
         trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output);
@@ -1859,11 +1859,11 @@ static int trace__pgfault(struct trace *trace,
 
         fprintf(trace->output, "] => ");
 
-        thread__find_addr_location(thread, trace->host, cpumode, MAP__VARIABLE,
+        thread__find_addr_location(thread, cpumode, MAP__VARIABLE,
                                    sample->addr, &al);
 
         if (!al.map) {
-                thread__find_addr_location(thread, trace->host, cpumode,
+                thread__find_addr_location(thread, cpumode,
                                            MAP__FUNCTION, sample->addr, &al);
 
                 if (al.map)
@@ -2045,7 +2045,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
         unsigned long before;
         const bool forks = argc > 0;
         bool draining = false;
-        char sbuf[STRERR_BUFSIZE];
 
         trace->live = true;
 
@@ -2106,11 +2105,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
                 goto out_error_open;
 
         err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
-        if (err < 0) {
-                fprintf(trace->output, "Couldn't mmap the events: %s\n",
-                        strerror_r(errno, sbuf, sizeof(sbuf)));
-                goto out_delete_evlist;
-        }
+        if (err < 0)
+                goto out_error_mmap;
 
         perf_evlist__enable(evlist);
 
@@ -2210,6 +2206,10 @@ out_error_tp:
         perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf));
         goto out_error;
 
+out_error_mmap:
+        perf_evlist__strerror_mmap(evlist, errno, errbuf, sizeof(errbuf));
+        goto out_error;
+
 out_error_open:
         perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
 
@@ -2485,7 +2485,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                         .user_freq     = UINT_MAX,
                         .user_interval = ULLONG_MAX,
                         .no_buffering  = true,
-                        .mmap_pages    = 1024,
+                        .mmap_pages    = UINT_MAX,
                 },
                 .output = stdout,
                 .show_comm = true,
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 58f609198c6d..648e31ff4021 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -20,7 +20,7 @@ NO_PERF_REGS := 1
 
 # Additional ARCH settings for x86
 ifeq ($(ARCH),x86)
-  ifeq (${IS_X86_64}, 1)
+  ifeq (${IS_64_BIT}, 1)
     CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT
     ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
     LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
@@ -150,7 +150,7 @@ CFLAGS += -std=gnu99
 # adding assembler files missing the .GNU-stack linker note.
 LDFLAGS += -Wl,-z,noexecstack
 
-EXTLIBS = -lelf -lpthread -lrt -lm -ldl
+EXTLIBS = -lpthread -lrt -lm -ldl
 
 ifneq ($(OUTPUT),)
   OUTPUT_FEATURES = $(OUTPUT)config/feature-checks/
@@ -200,7 +200,8 @@ CORE_FEATURE_TESTS =			\
         libunwind                       \
         stackprotector-all              \
         timerfd                         \
-        libdw-dwarf-unwind
+        libdw-dwarf-unwind              \
+        zlib
 
 LIB_FEATURE_TESTS =                     \
         dwarf                           \
@@ -214,7 +215,8 @@ LIB_FEATURE_TESTS =			\
         libpython                       \
         libslang                        \
         libunwind                       \
-        libdw-dwarf-unwind
+        libdw-dwarf-unwind              \
+        zlib
 
 VF_FEATURE_TESTS =                      \
         backtrace                       \
@@ -230,7 +232,9 @@ VF_FEATURE_TESTS =			\
         bionic                          \
         liberty                         \
         liberty-z                       \
-        cplus-demangle
+        cplus-demangle                  \
+        compile-32                      \
+        compile-x32
 
 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all CORE_FEATURE_TESTS features.
 # If in the future we need per-feature checks/flags for features not
@@ -350,6 +354,7 @@ endif # NO_LIBELF
 
 ifndef NO_LIBELF
   CFLAGS += -DHAVE_LIBELF_SUPPORT
+  EXTLIBS += -lelf
 
   ifeq ($(feature-libelf-mmap), 1)
     CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT
@@ -369,7 +374,7 @@ ifndef NO_LIBELF
     else
       CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS)
       LDFLAGS += $(LIBDW_LDFLAGS)
-      EXTLIBS += -lelf -ldw
+      EXTLIBS += -ldw
     endif # PERF_HAVE_DWARF_REGS
   endif # NO_DWARF
 endif # NO_LIBELF
@@ -602,6 +607,15 @@ ifneq ($(filter -lbfd,$(EXTLIBS)),)
   CFLAGS += -DHAVE_LIBBFD_SUPPORT
 endif
 
+ifndef NO_ZLIB
+  ifeq ($(feature-zlib), 1)
+    CFLAGS += -DHAVE_ZLIB_SUPPORT
+    EXTLIBS += -lz
+  else
+    NO_ZLIB := 1
+  endif
+endif
+
 ifndef NO_BACKTRACE
   ifeq ($(feature-backtrace), 1)
     CFLAGS += -DHAVE_BACKTRACE_SUPPORT
@@ -622,6 +636,31 @@ ifdef HAVE_KVM_STAT_SUPPORT
     CFLAGS += -DHAVE_KVM_STAT_SUPPORT
 endif
 
+ifeq (${IS_64_BIT}, 1)
+  ifndef NO_PERF_READ_VDSO32
+    $(call feature_check,compile-32)
+    ifeq ($(feature-compile-32), 1)
+      CFLAGS += -DHAVE_PERF_READ_VDSO32
+    else
+      NO_PERF_READ_VDSO32 := 1
+    endif
+  endif
+  ifneq (${IS_X86_64}, 1)
+    NO_PERF_READ_VDSOX32 := 1
+  endif
+  ifndef NO_PERF_READ_VDSOX32
+    $(call feature_check,compile-x32)
+    ifeq ($(feature-compile-x32), 1)
+      CFLAGS += -DHAVE_PERF_READ_VDSOX32
+    else
+      NO_PERF_READ_VDSOX32 := 1
+    endif
+  endif
+else
+  NO_PERF_READ_VDSO32 := 1
+  NO_PERF_READ_VDSOX32 := 1
+endif
+
 # Among the variables below, these:
 #   perfexecdir
 #   template_dir
diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch
index 4b06719ee984..ff95a68741d1 100644
--- a/tools/perf/config/Makefile.arch
+++ b/tools/perf/config/Makefile.arch
@@ -1,7 +1,7 @@
 
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
+RAW_ARCH := $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
                                   -e s/arm.*/arm/ -e s/sa110/arm/ \
                                   -e s/s390x/s390/ -e s/parisc64/parisc/ \
                                   -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
@@ -9,15 +9,23 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
                                   -e s/tile.*/tile/ )
 
 # Additional ARCH settings for x86
-ifeq ($(ARCH),i386)
-  override ARCH := x86
+ifeq ($(RAW_ARCH),i386)
+  ARCH ?= x86
 endif
 
-ifeq ($(ARCH),x86_64)
-  override ARCH := x86
-  IS_X86_64 := 0
-  ifeq (, $(findstring m32,$(CFLAGS)))
-    IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
-    RAW_ARCH := x86_64
+ifeq ($(RAW_ARCH),x86_64)
+  ARCH ?= x86
+
+  ifneq (, $(findstring m32,$(CFLAGS)))
+    RAW_ARCH := x86_32
   endif
 endif
+
+ARCH ?= $(RAW_ARCH)
+
+LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+ifeq ($(LP64), 1)
+  IS_64_BIT := 1
+else
+  IS_64_BIT := 0
+endif
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 72ab2984718e..53f19b5dbc37 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -27,7 +27,10 @@ FILES=					\
         test-libunwind-debug-frame.bin  \
         test-stackprotector-all.bin     \
         test-timerfd.bin                \
-        test-libdw-dwarf-unwind.bin
+        test-libdw-dwarf-unwind.bin     \
+        test-compile-32.bin             \
+        test-compile-x32.bin            \
+        test-zlib.bin
 
 CC := $(CROSS_COMPILE)gcc -MD
 PKG_CONFIG := $(CROSS_COMPILE)pkg-config
@@ -39,7 +42,7 @@ BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS)
 ###############################
 
 test-all.bin:
-        $(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
+        $(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz
 
 test-hello.bin:
         $(BUILD)
@@ -131,6 +134,15 @@ test-libdw-dwarf-unwind.bin:
 test-sync-compare-and-swap.bin:
         $(BUILD) -Werror
 
+test-compile-32.bin:
+        $(CC) -m32 -o $(OUTPUT)$@ test-compile.c
+
+test-compile-x32.bin:
+        $(CC) -mx32 -o $(OUTPUT)$@ test-compile.c
+
+test-zlib.bin:
+        $(BUILD) -lz
+
 -include *.d
 
 ###############################
diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c
index a7d022e161c0..652e0098eba6 100644
--- a/tools/perf/config/feature-checks/test-all.c
+++ b/tools/perf/config/feature-checks/test-all.c
@@ -93,6 +93,10 @@
 # include "test-sync-compare-and-swap.c"
 #undef main
 
+#define main main_test_zlib
+# include "test-zlib.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
         main_test_libpython();
@@ -116,6 +120,7 @@ int main(int argc, char *argv[])
         main_test_stackprotector_all();
         main_test_libdw_dwarf_unwind();
         main_test_sync_compare_and_swap(argc, argv);
+        main_test_zlib();
 
         return 0;
 }
diff --git a/tools/perf/config/feature-checks/test-compile.c b/tools/perf/config/feature-checks/test-compile.c
new file mode 100644
index 000000000000..31dbf45bf99c
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-compile.c
@@ -0,0 +1,4 @@
+int main(void)
+{
+        return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-zlib.c b/tools/perf/config/feature-checks/test-zlib.c
new file mode 100644
index 000000000000..e111fff6240e
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-zlib.c
@@ -0,0 +1,9 @@
+#include <zlib.h>
+
+int main(void)
+{
+        z_stream zs;
+
+        inflateInit(&zs);
+        return 0;
+}
diff --git a/tools/perf/perf-read-vdso.c b/tools/perf/perf-read-vdso.c
new file mode 100644
index 000000000000..764e2547c25a
--- /dev/null
+++ b/tools/perf/perf-read-vdso.c
@@ -0,0 +1,34 @@
+#include <stdio.h>
+#include <string.h>
+
+#define VDSO__MAP_NAME "[vdso]"
+
+/*
+ * Include definition of find_vdso_map() also used in util/vdso.c for
+ * building perf.
+ */
+#include "util/find-vdso-map.c"
+
+int main(void)
+{
+        void *start, *end;
+        size_t size, written;
+
+        if (find_vdso_map(&start, &end))
+                return 1;
+
+        size = end - start;
+
+        while (size) {
+                written = fwrite(start, 1, size, stdout);
+                if (!written)
+                        return 1;
+                start += written;
+                size -= written;
+        }
+
+        if (fflush(stdout))
+                return 1;
+
+        return 0;
+}
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index a3b13d7dc1d4..6ef68165c9db 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -6,7 +6,6 @@
 #include <sys/syscall.h>
 #include <linux/types.h>
 #include <linux/perf_event.h>
-#include <asm/unistd.h>
 
 #if defined(__i386__)
 #define mb()            asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 452a8474d29d..3700a7faca6c 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -200,6 +200,16 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
                                 *envchanged = 1;
                         (*argv)++;
                         (*argc)--;
+                } else if (!strcmp(cmd, "--buildid-dir")) {
+                        if (*argc < 2) {
+                                fprintf(stderr, "No directory given for --buildid-dir.\n");
+                                usage(perf_usage_string);
+                        }
+                        set_buildid_dir((*argv)[1]);
+                        if (envchanged)
+                                *envchanged = 1;
+                        (*argv)++;
+                        (*argc)--;
                 } else if (!prefixcmp(cmd, CMD_DEBUGFS_DIR)) {
                         perf_debugfs_set_path(cmd + strlen(CMD_DEBUGFS_DIR));
                         fprintf(stderr, "dir: %s\n", debugfs_mountpoint);
@@ -499,7 +509,7 @@ int main(int argc, const char **argv)
         }
         if (!prefixcmp(cmd, "trace")) {
 #ifdef HAVE_LIBAUDIT_SUPPORT
-                set_buildid_dir();
+                set_buildid_dir(NULL);
                 setup_path();
                 argv[0] = "trace";
                 return cmd_trace(argc, argv, NULL);
@@ -514,7 +524,7 @@ int main(int argc, const char **argv)
         argc--;
         handle_options(&argv, &argc, NULL);
         commit_pager_choice();
-        set_buildid_dir();
+        set_buildid_dir(NULL);
 
         if (argc > 0) {
                 if (!prefixcmp(argv[0], "--"))
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 220d44e44c1b..1dabb8553499 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -52,6 +52,7 @@ struct record_opts {
         bool         sample_weight;
         bool         sample_time;
         bool         period;
+        bool         sample_intr_regs;
         unsigned int freq;
         unsigned int mmap_pages;
         unsigned int user_freq;
@@ -62,4 +63,7 @@ struct record_opts {
         unsigned     initial_delay;
 };
 
+struct option;
+extern const char * const *record_usage;
+extern struct option *record_options;
 #endif
diff --git a/tools/perf/scripts/python/bin/export-to-postgresql-record b/tools/perf/scripts/python/bin/export-to-postgresql-record
new file mode 100644
index 000000000000..221d66e05713
--- /dev/null
+++ b/tools/perf/scripts/python/bin/export-to-postgresql-record
@@ -0,0 +1,8 @@
+#!/bin/bash
+
+#
+# export perf data to a postgresql database. Can cover
+# perf ip samples (excluding the tracepoints). No special
+# record requirements, just record what you want to export.
+#
+perf record $@
diff --git a/tools/perf/scripts/python/bin/export-to-postgresql-report b/tools/perf/scripts/python/bin/export-to-postgresql-report
new file mode 100644
index 000000000000..cd335b6e2a01
--- /dev/null
+++ b/tools/perf/scripts/python/bin/export-to-postgresql-report
@@ -0,0 +1,29 @@
+#!/bin/bash
+# description: export perf data to a postgresql database
+# args: [database name] [columns] [calls]
+n_args=0
+for i in "$@"
+do
+    if expr match "$i" "-" > /dev/null ; then
+        break
+    fi
+    n_args=$(( $n_args + 1 ))
+done
+if [ "$n_args" -gt 3 ] ; then
+    echo "usage: export-to-postgresql-report [database name] [columns] [calls]"
+    exit
+fi
+if [ "$n_args" -gt 2 ] ; then
+    dbname=$1
+    columns=$2
+    calls=$3
+    shift 3
+elif [ "$n_args" -gt 1 ] ; then
+    dbname=$1
+    columns=$2
+    shift 2
+elif [ "$n_args" -gt 0 ] ; then
+    dbname=$1
+    shift
+fi
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-postgresql.py $dbname $columns $calls
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
new file mode 100644
index 000000000000..4cdafd880074
--- /dev/null
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -0,0 +1,444 @@
+# export-to-postgresql.py: export perf data to a postgresql database
+# Copyright (c) 2014, Intel Corporation.
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms and conditions of the GNU General Public License,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+# more details.
+
+import os
+import sys
+import struct
+import datetime
+
+from PySide.QtSql import *
+
+# Need to access PostgreSQL C library directly to use COPY FROM STDIN
+from ctypes import *
+libpq = CDLL("libpq.so.5")
+PQconnectdb = libpq.PQconnectdb
+PQconnectdb.restype = c_void_p
+PQfinish = libpq.PQfinish
+PQstatus = libpq.PQstatus
+PQexec = libpq.PQexec
+PQexec.restype = c_void_p
+PQresultStatus = libpq.PQresultStatus
+PQputCopyData = libpq.PQputCopyData
+PQputCopyData.argtypes = [ c_void_p, c_void_p, c_int ]
+PQputCopyEnd = libpq.PQputCopyEnd
+PQputCopyEnd.argtypes = [ c_void_p, c_void_p ]
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+# These perf imports are not used at present
+#from perf_trace_context import *
+#from Core import *
+
+perf_db_export_mode = True
+perf_db_export_calls = False
+
+def usage():
+        print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>]"
+        print >> sys.stderr, "where:    columns         'all' or 'branches'"
+        print >> sys.stderr, "          calls           'calls' => create calls table"
+        raise Exception("Too few arguments")
+
+if (len(sys.argv) < 2):
+        usage()
+
+dbname = sys.argv[1]
+
+if (len(sys.argv) >= 3):
+        columns = sys.argv[2]
+else:
+        columns = "all"
+
+if columns not in ("all", "branches"):
+        usage()
+
+branches = (columns == "branches")
+
+if (len(sys.argv) >= 4):
+        if (sys.argv[3] == "calls"):
+                perf_db_export_calls = True
+        else:
+                usage()
+
+output_dir_name = os.getcwd() + "/" + dbname + "-perf-data"
+os.mkdir(output_dir_name)
+
+def do_query(q, s):
+        if (q.exec_(s)):
+                return
+        raise Exception("Query failed: " + q.lastError().text())
+
+print datetime.datetime.today(), "Creating database..."
+
+db = QSqlDatabase.addDatabase('QPSQL')
+query = QSqlQuery(db)
+db.setDatabaseName('postgres')
+db.open()
+try:
+        do_query(query, 'CREATE DATABASE ' + dbname)
+except:
+        os.rmdir(output_dir_name)
+        raise
+query.finish()
+query.clear()
+db.close()
+
+db.setDatabaseName(dbname)
+db.open()
+
+query = QSqlQuery(db)
+do_query(query, 'SET client_min_messages TO WARNING')
+
+do_query(query, 'CREATE TABLE selected_events ('
+                'id             bigint          NOT NULL,'
+                'name           varchar(80))')
+do_query(query, 'CREATE TABLE machines ('
+                'id             bigint          NOT NULL,'
+                'pid            integer,'
+                'root_dir       varchar(4096))')
+do_query(query, 'CREATE TABLE threads ('
+                'id             bigint          NOT NULL,'
+                'machine_id     bigint,'
+                'process_id     bigint,'
+                'pid            integer,'
+                'tid            integer)')
+do_query(query, 'CREATE TABLE comms ('
+                'id             bigint          NOT NULL,'
+                'comm           varchar(16))')
+do_query(query, 'CREATE TABLE comm_threads ('
+                'id             bigint          NOT NULL,'
+                'comm_id        bigint,'
+                'thread_id      bigint)')
+do_query(query, 'CREATE TABLE dsos ('
+                'id             bigint          NOT NULL,'
+                'machine_id     bigint,'
+                'short_name     varchar(256),'
+                'long_name      varchar(4096),'
+                'build_id       varchar(64))')
+do_query(query, 'CREATE TABLE symbols ('
+                'id             bigint          NOT NULL,'
+                'dso_id         bigint,'
+                'sym_start      bigint,'
+                'sym_end        bigint,'
+                'binding        integer,'
+                'name           varchar(2048))')
+do_query(query, 'CREATE TABLE branch_types ('
+                'id             integer         NOT NULL,'
+                'name           varchar(80))')
+
+if branches:
+        do_query(query, 'CREATE TABLE samples ('
+                'id             bigint          NOT NULL,'
+                'evsel_id       bigint,'
+                'machine_id     bigint,'
+                'thread_id      bigint,'
+                'comm_id        bigint,'
+                'dso_id         bigint,'
+                'symbol_id      bigint,'
+                'sym_offset     bigint,'
+                'ip             bigint,'
+                'time           bigint,'
+                'cpu            integer,'
+                'to_dso_id      bigint,'
+                'to_symbol_id   bigint,'
+                'to_sym_offset  bigint,'
+                'to_ip          bigint,'
+                'branch_type    integer,'
+                'in_tx          boolean)')
+else:
+        do_query(query, 'CREATE TABLE samples ('
+                'id             bigint          NOT NULL,'
+                'evsel_id       bigint,'
+                'machine_id     bigint,'
+                'thread_id      bigint,'
+                'comm_id        bigint,'
+                'dso_id         bigint,'
+                'symbol_id      bigint,'
+                'sym_offset     bigint,'
+                'ip             bigint,'
+                'time           bigint,'
+                'cpu            integer,'
+                'to_dso_id      bigint,'
+                'to_symbol_id   bigint,'
+                'to_sym_offset  bigint,'
+                'to_ip          bigint,'
+                'period         bigint,'
+                'weight         bigint,'
+                'transaction    bigint,'
+                'data_src       bigint,'
+                'branch_type    integer,'
+                'in_tx          boolean)')
+
+if perf_db_export_calls:
+        do_query(query, 'CREATE TABLE call_paths ('
+                'id             bigint          NOT NULL,'
+                'parent_id      bigint,'
+                'symbol_id      bigint,'
+                'ip             bigint)')
+        do_query(query, 'CREATE TABLE calls ('
+                'id             bigint          NOT NULL,'
+                'thread_id      bigint,'
+                'comm_id        bigint,'
+                'call_path_id   bigint,'
+                'call_time      bigint,'
+                'return_time    bigint,'
+                'branch_count   bigint,'
+                'call_id        bigint,'
+                'return_id      bigint,'
+                'parent_call_path_id    bigint,'
+                'flags          integer)')
+
+do_query(query, 'CREATE VIEW samples_view AS '
+        'SELECT '
+                'id,'
+                'time,'
+                'cpu,'
+                '(SELECT pid FROM threads WHERE id = thread_id) AS pid,'
+                '(SELECT tid FROM threads WHERE id = thread_id) AS tid,'
+                '(SELECT comm FROM comms WHERE id = comm_id) AS command,'
+                '(SELECT name FROM selected_events WHERE id = evsel_id) AS event,'
+                'to_hex(ip) AS ip_hex,'
+                '(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,'
+                'sym_offset,'
+                '(SELECT short_name FROM dsos WHERE id = dso_id) AS dso_short_name,'
+                'to_hex(to_ip) AS to_ip_hex,'
+                '(SELECT name FROM symbols WHERE id = to_symbol_id) AS to_symbol,'
+                'to_sym_offset,'
+                '(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,'
+                '(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,'
+                'in_tx'
+        ' FROM samples')
+
+
+file_header = struct.pack("!11sii", "PGCOPY\n\377\r\n\0", 0, 0)
+file_trailer = "\377\377"
+
+def open_output_file(file_name):
+        path_name = output_dir_name + "/" + file_name
+        file = open(path_name, "w+")
+        file.write(file_header)
+        return file
+
+def close_output_file(file):
+        file.write(file_trailer)
+        file.close()
+
+def copy_output_file_direct(file, table_name):
+        close_output_file(file)
+        sql = "COPY " + table_name + " FROM '" + file.name + "' (FORMAT 'binary')"
+        do_query(query, sql)
+
+# Use COPY FROM STDIN because security may prevent postgres from accessing the files directly
+def copy_output_file(file, table_name):
+        conn = PQconnectdb("dbname = " + dbname)
+        if (PQstatus(conn)):
+                raise Exception("COPY FROM STDIN PQconnectdb failed")
+        file.write(file_trailer)
+        file.seek(0)
+        sql = "COPY " + table_name + " FROM STDIN (FORMAT 'binary')"
+        res = PQexec(conn, sql)
+        if (PQresultStatus(res) != 4):
+                raise Exception("COPY FROM STDIN PQexec failed")
+        data = file.read(65536)
+        while (len(data)):
+                ret = PQputCopyData(conn, data, len(data))
+                if (ret != 1):
+                        raise Exception("COPY FROM STDIN PQputCopyData failed, error " + str(ret))
+                data = file.read(65536)
+        ret = PQputCopyEnd(conn, None)
+        if (ret != 1):
+                raise Exception("COPY FROM STDIN PQputCopyEnd failed, error " + str(ret))
+        PQfinish(conn)
+
+def remove_output_file(file):
+        name = file.name
+        file.close()
+        os.unlink(name)
+
+evsel_file              = open_output_file("evsel_table.bin")
+machine_file            = open_output_file("machine_table.bin")
+thread_file             = open_output_file("thread_table.bin")
+comm_file               = open_output_file("comm_table.bin")
+comm_thread_file        = open_output_file("comm_thread_table.bin")
+dso_file                = open_output_file("dso_table.bin")
+symbol_file             = open_output_file("symbol_table.bin")
+branch_type_file        = open_output_file("branch_type_table.bin")
+sample_file             = open_output_file("sample_table.bin")
+if perf_db_export_calls:
+        call_path_file          = open_output_file("call_path_table.bin")
+        call_file               = open_output_file("call_table.bin")
+
+def trace_begin():
+        print datetime.datetime.today(), "Writing to intermediate files..."
+        # id == 0 means unknown.  It is easier to create records for them than replace the zeroes with NULLs
+        evsel_table(0, "unknown")
+        machine_table(0, 0, "unknown")
+        thread_table(0, 0, 0, -1, -1)
+        comm_table(0, "unknown")
+        dso_table(0, 0, "unknown", "unknown", "")
+        symbol_table(0, 0, 0, 0, 0, "unknown")
+        sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+        if perf_db_export_calls:
+                call_path_table(0, 0, 0, 0)
+
+unhandled_count = 0
+
+def trace_end():
+        print datetime.datetime.today(), "Copying to database..."
+        copy_output_file(evsel_file,            "selected_events")
+        copy_output_file(machine_file,          "machines")
+        copy_output_file(thread_file,           "threads")
+        copy_output_file(comm_file,             "comms")
+        copy_output_file(comm_thread_file,      "comm_threads")
+        copy_output_file(dso_file,              "dsos")
+        copy_output_file(symbol_file,           "symbols")
+        copy_output_file(branch_type_file,      "branch_types")
+        copy_output_file(sample_file,           "samples")
+        if perf_db_export_calls:
+                copy_output_file(call_path_file,        "call_paths")
+                copy_output_file(call_file,             "calls")
+
+        print datetime.datetime.today(), "Removing intermediate files..."
+        remove_output_file(evsel_file)
+        remove_output_file(machine_file)
+        remove_output_file(thread_file)
+        remove_output_file(comm_file)
+        remove_output_file(comm_thread_file)
+        remove_output_file(dso_file)
+        remove_output_file(symbol_file)
+        remove_output_file(branch_type_file)
+        remove_output_file(sample_file)
+        if perf_db_export_calls:
+                remove_output_file(call_path_file)
+                remove_output_file(call_file)
+        os.rmdir(output_dir_name)
+        print datetime.datetime.today(), "Adding primary keys"
+        do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)')
+        do_query(query, 'ALTER TABLE machines        ADD PRIMARY KEY (id)')
+        do_query(query, 'ALTER TABLE threads         ADD PRIMARY KEY (id)')
+        do_query(query, 'ALTER TABLE comms           ADD PRIMARY KEY (id)')
+        do_query(query, 'ALTER TABLE comm_threads    ADD PRIMARY KEY (id)')
+        do_query(query, 'ALTER TABLE dsos            ADD PRIMARY KEY (id)')
+        do_query(query, 'ALTER TABLE symbols         ADD PRIMARY KEY (id)')
+        do_query(query, 'ALTER TABLE branch_types    ADD PRIMARY KEY (id)')
+        do_query(query, 'ALTER TABLE samples         ADD PRIMARY KEY (id)')
+        if perf_db_export_calls:
+                do_query(query, 'ALTER TABLE call_paths      ADD PRIMARY KEY (id)')
+                do_query(query, 'ALTER TABLE calls           ADD PRIMARY KEY (id)')
+
+        print datetime.datetime.today(), "Adding foreign keys"
+        do_query(query, 'ALTER TABLE threads '
+                                        'ADD CONSTRAINT machinefk  FOREIGN KEY (machine_id)   REFERENCES machines   (id),'
+                                        'ADD CONSTRAINT processfk  FOREIGN KEY (process_id)   REFERENCES threads    (id)')
+        do_query(query, 'ALTER TABLE comm_threads '
+                                        'ADD CONSTRAINT commfk     FOREIGN KEY (comm_id)      REFERENCES comms      (id),'
+                                        'ADD CONSTRAINT threadfk   FOREIGN KEY (thread_id)    REFERENCES threads    (id)')
+        do_query(query, 'ALTER TABLE dsos '
+                                        'ADD CONSTRAINT machinefk  FOREIGN KEY (machine_id)   REFERENCES machines   (id)')
+        do_query(query, 'ALTER TABLE symbols '
+                                        'ADD CONSTRAINT dsofk      FOREIGN KEY (dso_id)       REFERENCES dsos       (id)')
+        do_query(query, 'ALTER TABLE samples '
+                                        'ADD CONSTRAINT evselfk    FOREIGN KEY (evsel_id)     REFERENCES selected_events (id),'
+                                        'ADD CONSTRAINT machinefk  FOREIGN KEY (machine_id)   REFERENCES machines   (id),'
+                                        'ADD CONSTRAINT threadfk   FOREIGN KEY (thread_id)    REFERENCES threads    (id),'
+                                        'ADD CONSTRAINT commfk     FOREIGN KEY (comm_id)      REFERENCES comms      (id),'
+                                        'ADD CONSTRAINT dsofk      FOREIGN KEY (dso_id)       REFERENCES dsos       (id),'
+                                        'ADD CONSTRAINT symbolfk   FOREIGN KEY (symbol_id)    REFERENCES symbols    (id),'
+                                        'ADD CONSTRAINT todsofk    FOREIGN KEY (to_dso_id)    REFERENCES dsos       (id),'
+                                        'ADD CONSTRAINT tosymbolfk FOREIGN KEY (to_symbol_id) REFERENCES symbols    (id)')
+        if perf_db_export_calls:
+                do_query(query, 'ALTER TABLE call_paths '
+                                        'ADD CONSTRAINT parentfk    FOREIGN KEY (parent_id)    REFERENCES call_paths (id),'
+                                        'ADD CONSTRAINT symbolfk    FOREIGN KEY (symbol_id)    REFERENCES symbols    (id)')
+                do_query(query, 'ALTER TABLE calls '
+                                        'ADD CONSTRAINT threadfk    FOREIGN KEY (thread_id)    REFERENCES threads    (id),'
+                                        'ADD CONSTRAINT commfk      FOREIGN KEY (comm_id)      REFERENCES comms      (id),'
+                                        'ADD CONSTRAINT call_pathfk FOREIGN KEY (call_path_id) REFERENCES call_paths (id),'
+                                        'ADD CONSTRAINT callfk      FOREIGN KEY (call_id)      REFERENCES samples    (id),'
+                                        'ADD CONSTRAINT returnfk    FOREIGN KEY (return_id)    REFERENCES samples    (id),'
+                                        'ADD CONSTRAINT parent_call_pathfk FOREIGN KEY (parent_call_path_id) REFERENCES call_paths (id)')
+                do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
+
+        if (unhandled_count):
+                print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events"
+        print datetime.datetime.today(), "Done"
+
+def trace_unhandled(event_name, context, event_fields_dict):
+        global unhandled_count
+        unhandled_count += 1
+
+def sched__sched_switch(*x):
+        pass
+
+def evsel_table(evsel_id, evsel_name, *x):
+        n = len(evsel_name)
+        fmt = "!hiqi" + str(n) + "s"
+        value = struct.pack(fmt, 2, 8, evsel_id, n, evsel_name)
+        evsel_file.write(value)
+
+def machine_table(machine_id, pid, root_dir, *x):
+        n = len(root_dir)
+        fmt = "!hiqiii" + str(n) + "s"
+        value = struct.pack(fmt, 3, 8, machine_id, 4, pid, n, root_dir)
+        machine_file.write(value)
+
+def thread_table(thread_id, machine_id, process_id, pid, tid, *x):
+        value = struct.pack("!hiqiqiqiiii", 5, 8, thread_id, 8, machine_id, 8, process_id, 4, pid, 4, tid)
+        thread_file.write(value)
+
+def comm_table(comm_id, comm_str, *x):
+        n = len(comm_str)
+        fmt = "!hiqi" + str(n) + "s"
+        value = struct.pack(fmt, 2, 8, comm_id, n, comm_str)
+        comm_file.write(value)
+
+def comm_thread_table(comm_thread_id, comm_id, thread_id, *x):
+        fmt = "!hiqiqiq"
+        value = struct.pack(fmt, 3, 8, comm_thread_id, 8, comm_id, 8, thread_id)
+        comm_thread_file.write(value)
+
+def dso_table(dso_id, machine_id, short_name, long_name, build_id, *x):
+        n1 = len(short_name)
+        n2 = len(long_name)
+        n3 = len(build_id)
+        fmt = "!hiqiqi" + str(n1) + "si"  + str(n2) + "si" + str(n3) + "s"
+        value = struct.pack(fmt, 5, 8, dso_id, 8, machine_id, n1, short_name, n2, long_name, n3, build_id)
+        dso_file.write(value)
+
+def symbol_table(symbol_id, dso_id, sym_start, sym_end, binding, symbol_name, *x):
+        n = len(symbol_name)
+        fmt = "!hiqiqiqiqiii" + str(n) + "s"
+        value = struct.pack(fmt, 6, 8, symbol_id, 8, dso_id, 8, sym_start, 8, sym_end, 4, binding, n, symbol_name)
+        symbol_file.write(value)
+
+def branch_type_table(branch_type, name, *x):
+        n = len(name)
+        fmt = "!hiii" + str(n) + "s"
+        value = struct.pack(fmt, 2, 4, branch_type, n, name)
+        branch_type_file.write(value)
+
+def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, *x):
+        if branches:
+                value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiB", 17, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx)
+        else:
+                value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiB", 21, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx)
+        sample_file.write(value)
+
+def call_path_table(cp_id, parent_id, symbol_id, ip, *x):
+        fmt = "!hiqiqiqiq"
+        value = struct.pack(fmt, 4, 8, cp_id, 8, parent_id, 8, symbol_id, 8, ip)
+        call_path_file.write(value)
+
+def call_return_table(cr_id, thread_id, comm_id, call_path_id, call_time, return_time, branch_count, call_id, return_id, parent_call_path_id, flags, *x):
+        fmt = "!hiqiqiqiqiqiqiqiqiqiqii"
+        value = struct.pack(fmt, 11, 8, cr_id, 8, thread_id, 8, comm_id, 8, call_path_id, 8, call_time, 8, return_time, 8, branch_count, 8, call_id, 8, return_id, 8, parent_call_path_id, 4, flags)
+        call_file.write(value)
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index f710b92ccff6..d3095dafed36 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -5,7 +5,7 @@ group_fd=-1
 flags=0|8
 cpu=*
 type=0|1
-size=96
+size=104
 config=0
 sample_period=4000
 sample_type=263
diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat
index dc3ada2470c0..872ed7e24c7c 100644
--- a/tools/perf/tests/attr/base-stat
+++ b/tools/perf/tests/attr/base-stat
@@ -5,7 +5,7 @@ group_fd=-1
 flags=0|8
 cpu=*
 type=0
-size=96
+size=104
 config=0
 sample_period=0
 sample_type=0
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 162c978f1491..4b7d9ab0f049 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -85,7 +85,7 @@ static struct test {
                 .func = test__hists_link,
         },
         {
-                .desc = "Try 'use perf' in python, checking link problems",
+                .desc = "Try 'import perf' in python, checking link problems",
                 .func = test__python_use,
         },
         {
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 67f2d6323558..f671ec37a7c4 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -133,8 +133,7 @@ static int read_via_objdump(const char *filename, u64 addr, void *buf,
 }
 
 static int read_object_code(u64 addr, size_t len, u8 cpumode,
-                            struct thread *thread, struct machine *machine,
-                            struct state *state)
+                            struct thread *thread, struct state *state)
 {
         struct addr_location al;
         unsigned char buf1[BUFSZ];
@@ -145,8 +144,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 
         pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
 
-        thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, addr,
-                              &al);
+        thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
         if (!al.map || !al.map->dso) {
                 pr_debug("thread__find_addr_map failed\n");
                 return -1;
@@ -170,8 +168,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
                 len = al.map->end - addr;
 
         /* Read the object code using perf */
-        ret_len = dso__data_read_offset(al.map->dso, machine, al.addr, buf1,
-                                        len);
+        ret_len = dso__data_read_offset(al.map->dso, thread->mg->machine,
+                                        al.addr, buf1, len);
         if (ret_len != len) {
                 pr_debug("dso__data_read_offset failed\n");
                 return -1;
@@ -264,8 +262,7 @@ static int process_sample_event(struct machine *machine,
 
         cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-        return read_object_code(sample.ip, READLEN, cpumode, thread, machine,
-                                state);
+        return read_object_code(sample.ip, READLEN, cpumode, thread, state);
 }
 
 static int process_event(struct machine *machine, struct perf_evlist *evlist,
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index fc25e57f4a5d..0bf06bec68c7 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -11,6 +11,9 @@
 #include "thread.h"
 #include "callchain.h"
 
+/* For bsearch. We try to unwind functions in shared object. */
+#include <stdlib.h>
+
 static int mmap_handler(struct perf_tool *tool __maybe_unused,
                         union perf_event *event,
                         struct perf_sample *sample __maybe_unused,
@@ -28,7 +31,7 @@ static int init_live_machine(struct machine *machine)
                                                   mmap_handler, machine, true);
 }
 
-#define MAX_STACK 6
+#define MAX_STACK 8
 
 static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
@@ -37,6 +40,8 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
         static const char *funcs[MAX_STACK] = {
                 "test__arch_unwind_sample",
                 "unwind_thread",
+                "compare",
+                "bsearch",
                 "krava_3",
                 "krava_2",
                 "krava_1",
@@ -59,7 +64,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 }
 
 __attribute__ ((noinline))
-static int unwind_thread(struct thread *thread, struct machine *machine)
+static int unwind_thread(struct thread *thread)
 {
         struct perf_sample sample;
         unsigned long cnt = 0;
@@ -72,7 +77,7 @@ static int unwind_thread(struct thread *thread, struct machine *machine)
                 goto out;
         }
 
-        err = unwind__get_entries(unwind_entry, &cnt, machine, thread,
+        err = unwind__get_entries(unwind_entry, &cnt, thread,
                                   &sample, MAX_STACK);
         if (err)
                 pr_debug("unwind failed\n");
@@ -88,22 +93,49 @@ static int unwind_thread(struct thread *thread, struct machine *machine)
         return err;
 }
 
+static int global_unwind_retval = -INT_MAX;
+
+__attribute__ ((noinline))
+static int compare(void *p1, void *p2)
+{
+        /* Any possible value should be 'thread' */
+        struct thread *thread = *(struct thread **)p1;
+
+        if (global_unwind_retval == -INT_MAX)
+                global_unwind_retval = unwind_thread(thread);
+
+        return p1 - p2;
+}
+
 __attribute__ ((noinline))
-static int krava_3(struct thread *thread, struct machine *machine)
+static int krava_3(struct thread *thread)
 {
-        return unwind_thread(thread, machine);
+        struct thread *array[2] = {thread, thread};
+        void *fp = &bsearch;
+        /*
+         * make _bsearch a volatile function pointer to
+         * prevent potential optimization, which may expand
+         * bsearch and call compare directly from this function,
+         * instead of libc shared object.
+         */
+        void *(*volatile _bsearch)(void *, void *, size_t,
+                        size_t, int (*)(void *, void *));
+
+        _bsearch = fp;
+        _bsearch(array, &thread, 2, sizeof(struct thread **), compare);
+        return global_unwind_retval;
 }
 
 __attribute__ ((noinline))
-static int krava_2(struct thread *thread, struct machine *machine)
+static int krava_2(struct thread *thread)
 {
-        return krava_3(thread, machine);
+        return krava_3(thread);
 }
 
 __attribute__ ((noinline))
-static int krava_1(struct thread *thread, struct machine *machine)
+static int krava_1(struct thread *thread)
 {
-        return krava_2(thread, machine);
+        return krava_2(thread);
 }
 
 int test__dwarf_unwind(void)
@@ -137,7 +169,7 @@ int test__dwarf_unwind(void)
                 goto out;
         }
 
-        err = krava_1(thread, machine);
+        err = krava_1(thread);
 
  out:
         machine__delete_threads(machine);
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 614d5c4978ab..8d110dec393e 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -187,7 +187,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec
          * function since TEST_ASSERT_VAL() returns in case of failure.
          */
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists);
+        hists__output_resort(hists, NULL);
 
         if (verbose > 2) {
                 pr_info("use callchain: %d, cumulate callchain: %d\n",
@@ -454,12 +454,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
          *   30.00%    10.00%     perf  perf           [.] cmd_record
          *   20.00%     0.00%     bash  libc           [.] malloc
          *   10.00%    10.00%     bash  [kernel]       [k] page_fault
-         *   10.00%    10.00%     perf  [kernel]       [k] schedule
-         *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
+         *   10.00%    10.00%     bash  bash           [.] xmalloc
          *   10.00%    10.00%     perf  [kernel]       [k] page_fault
-         *   10.00%    10.00%     perf  libc           [.] free
          *   10.00%    10.00%     perf  libc           [.] malloc
-         *   10.00%    10.00%     bash  bash           [.] xmalloc
+         *   10.00%    10.00%     perf  [kernel]       [k] schedule
+         *   10.00%    10.00%     perf  libc           [.] free
+         *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
          */
         struct result expected[] = {
                 { 7000, 2000, "perf", "perf",     "main" },
@@ -468,12 +468,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
                 { 3000, 1000, "perf", "perf",     "cmd_record" },
                 { 2000,    0, "bash", "libc",     "malloc" },
                 { 1000, 1000, "bash", "[kernel]", "page_fault" },
-                { 1000, 1000, "perf", "[kernel]", "schedule" },
-                { 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
+                { 1000, 1000, "bash", "bash",     "xmalloc" },
                 { 1000, 1000, "perf", "[kernel]", "page_fault" },
+                { 1000, 1000, "perf", "[kernel]", "schedule" },
                 { 1000, 1000, "perf", "libc",     "free" },
                 { 1000, 1000, "perf", "libc",     "malloc" },
-                { 1000, 1000, "bash", "bash",     "xmalloc" },
+                { 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
         };
 
         symbol_conf.use_callchain = false;
@@ -537,10 +537,13 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
          *                  malloc
          *                  main
          *
-         *   10.00%    10.00%     perf  [kernel]       [k] schedule
+         *   10.00%    10.00%     bash  bash           [.] xmalloc
          *              |
-         *              --- schedule
-         *                  run_command
+         *              --- xmalloc
+         *                  malloc
+         *                  xmalloc     <--- NOTE: there's a cycle
+         *                  malloc
+         *                  xmalloc
          *                  main
          *
          *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
@@ -556,6 +559,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
          *                  run_command
          *                  main
          *
+         *   10.00%    10.00%     perf  [kernel]       [k] schedule
+         *              |
+         *              --- schedule
+         *                  run_command
+         *                  main
+         *
          *   10.00%    10.00%     perf  libc           [.] free
          *              |
          *              --- free
@@ -570,15 +579,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
          *                  run_command
          *                  main
          *
-         *   10.00%    10.00%     bash  bash           [.] xmalloc
-         *              |
-         *              --- xmalloc
-         *                  malloc
-         *                  xmalloc     <--- NOTE: there's a cycle
-         *                  malloc
-         *                  xmalloc
-         *                  main
-         *
          */
         struct result expected[] = {
                 { 7000, 2000, "perf", "perf",     "main" },
@@ -587,12 +587,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                 { 3000, 1000, "perf", "perf",     "cmd_record" },
                 { 2000,    0, "bash", "libc",     "malloc" },
                 { 1000, 1000, "bash", "[kernel]", "page_fault" },
-                { 1000, 1000, "perf", "[kernel]", "schedule" },
+                { 1000, 1000, "bash", "bash",     "xmalloc" },
                 { 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
                 { 1000, 1000, "perf", "[kernel]", "page_fault" },
+                { 1000, 1000, "perf", "[kernel]", "schedule" },
                 { 1000, 1000, "perf", "libc",     "free" },
                 { 1000, 1000, "perf", "libc",     "malloc" },
-                { 1000, 1000, "bash", "bash",     "xmalloc" },
         };
         struct callchain_result expected_callchain[] = {
                 {
@@ -622,9 +622,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                                 { "bash",     "main" }, },
                 },
                 {
-                        3, {    { "[kernel]", "schedule" },
-                                { "perf",     "run_command" },
-                                { "perf",     "main" }, },
+                        6, {    { "bash",     "xmalloc" },
+                                { "libc",     "malloc" },
+                                { "bash",     "xmalloc" },
+                                { "libc",     "malloc" },
+                                { "bash",     "xmalloc" },
+                                { "bash",     "main" }, },
                 },
                 {
                         3, {    { "[kernel]", "sys_perf_event_open" },
@@ -638,6 +641,11 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                                 { "perf",     "main" }, },
                 },
                 {
+                        3, {    { "[kernel]", "schedule" },
+                                { "perf",     "run_command" },
+                                { "perf",     "main" }, },
+                },
+                {
                         4, {    { "libc",     "free" },
                                 { "perf",     "cmd_record" },
                                 { "perf",     "run_command" },
@@ -649,14 +657,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                                 { "perf",     "run_command" },
                                 { "perf",     "main" }, },
                 },
-                {
-                        6, {    { "bash",     "xmalloc" },
-                                { "libc",     "malloc" },
-                                { "bash",     "xmalloc" },
-                                { "libc",     "malloc" },
-                                { "bash",     "xmalloc" },
-                                { "bash",     "main" }, },
-                },
         };
 
         symbol_conf.use_callchain = true;
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 5a31787cc6b9..59e53db7914c 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -43,7 +43,7 @@ static struct sample fake_samples[] = {
 };
 
 static int add_hist_entries(struct perf_evlist *evlist,
-                            struct machine *machine __maybe_unused)
+                            struct machine *machine)
 {
         struct perf_evsel *evsel;
         struct addr_location al;
@@ -138,7 +138,7 @@ int test__hists_filter(void)
                 struct hists *hists = evsel__hists(evsel);
 
                 hists__collapse_resort(hists, NULL);
-                hists__output_resort(hists);
+                hists__output_resort(hists, NULL);
 
                 if (verbose > 2) {
                         pr_info("Normal histogram\n");
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index a748f2be1222..f5547610da02 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -152,7 +152,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine)
                 goto out;
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists);
+        hists__output_resort(hists, NULL);
 
         if (verbose > 2) {
                 pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -252,7 +252,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine)
                 goto out;
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists);
+        hists__output_resort(hists, NULL);
 
         if (verbose > 2) {
                 pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -306,7 +306,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
                 goto out;
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists);
+        hists__output_resort(hists, NULL);
 
         if (verbose > 2) {
                 pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -384,7 +384,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                 goto out;
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists);
+        hists__output_resort(hists, NULL);
 
         if (verbose > 2) {
                 pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -487,7 +487,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine)
                 goto out;
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists);
+        hists__output_resort(hists, NULL);
 
         if (verbose > 2) {
                 pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 4a456fef66ca..2113f1c8611f 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -187,7 +187,7 @@ static int mmap_events(synth_cb synth)
 
                 pr_debug("looking for map %p\n", td->map);
 
-                thread__find_addr_map(thread, machine,
+                thread__find_addr_map(thread,
                                       PERF_RECORD_MISC_USER, MAP__FUNCTION,
                                       (unsigned long) (td->map + 1), &al);
 
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index ca292f9a4ae2..4908c648a597 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -126,16 +126,28 @@ static bool samples_same(const struct perf_sample *s1,
         if (type & PERF_SAMPLE_TRANSACTION)
                 COMP(transaction);
 
+        if (type & PERF_SAMPLE_REGS_INTR) {
+                size_t sz = hweight_long(s1->intr_regs.mask) * sizeof(u64);
+
+                COMP(intr_regs.mask);
+                COMP(intr_regs.abi);
+                if (s1->intr_regs.abi &&
+                    (!s1->intr_regs.regs || !s2->intr_regs.regs ||
+                     memcmp(s1->intr_regs.regs, s2->intr_regs.regs, sz))) {
+                        pr_debug("Samples differ at 'intr_regs'\n");
+                        return false;
+                }
+        }
+
         return true;
 }
 
-static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
+static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 {
         struct perf_evsel evsel = {
                 .needs_swap = false,
                 .attr = {
                         .sample_type = sample_type,
-                        .sample_regs_user = sample_regs_user,
                         .read_format = read_format,
                 },
         };
@@ -154,7 +166,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
                 /* 1 branch_entry */
                 .data = {1, 211, 212, 213},
         };
-        u64 user_regs[64];
+        u64 regs[64];
         const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL};
         const u64 data[] = {0x2211443366558877ULL, 0, 0xaabbccddeeff4321ULL};
         struct perf_sample sample = {
@@ -176,8 +188,8 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
                 .branch_stack   = &branch_stack.branch_stack,
                 .user_regs      = {
                         .abi    = PERF_SAMPLE_REGS_ABI_64,
-                        .mask   = sample_regs_user,
-                        .regs   = user_regs,
+                        .mask   = sample_regs,
+                        .regs   = regs,
                 },
                 .user_stack     = {
                         .size   = sizeof(data),
@@ -187,14 +199,25 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
                         .time_enabled = 0x030a59d664fca7deULL,
                         .time_running = 0x011b6ae553eb98edULL,
                 },
+                .intr_regs      = {
+                        .abi    = PERF_SAMPLE_REGS_ABI_64,
+                        .mask   = sample_regs,
+                        .regs   = regs,
+                },
         };
         struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
         struct perf_sample sample_out;
         size_t i, sz, bufsz;
         int err, ret = -1;
 
-        for (i = 0; i < sizeof(user_regs); i++)
-                *(i + (u8 *)user_regs) = i & 0xfe;
+        if (sample_type & PERF_SAMPLE_REGS_USER)
+                evsel.attr.sample_regs_user = sample_regs;
+
+        if (sample_type & PERF_SAMPLE_REGS_INTR)
+                evsel.attr.sample_regs_intr = sample_regs;
+
+        for (i = 0; i < sizeof(regs); i++)
+                *(i + (u8 *)regs) = i & 0xfe;
 
         if (read_format & PERF_FORMAT_GROUP) {
                 sample.read.group.nr     = 4;
@@ -271,7 +294,7 @@ int test__sample_parsing(void)
 {
         const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
         u64 sample_type;
-        u64 sample_regs_user;
+        u64 sample_regs;
         size_t i;
         int err;
 
@@ -280,7 +303,7 @@ int test__sample_parsing(void)
          * were added.  Please actually update the test rather than just change
          * the condition below.
          */
-        if (PERF_SAMPLE_MAX > PERF_SAMPLE_TRANSACTION << 1) {
+        if (PERF_SAMPLE_MAX > PERF_SAMPLE_REGS_INTR << 1) {
                 pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
                 return -1;
         }
@@ -297,22 +320,24 @@ int test__sample_parsing(void)
                         }
                         continue;
                 }
+                sample_regs = 0;
 
                 if (sample_type == PERF_SAMPLE_REGS_USER)
-                        sample_regs_user = 0x3fff;
-                else
-                        sample_regs_user = 0;
+                        sample_regs = 0x3fff;
+
+                if (sample_type == PERF_SAMPLE_REGS_INTR)
+                        sample_regs = 0xff0fff;
 
-                err = do_test(sample_type, sample_regs_user, 0);
+                err = do_test(sample_type, sample_regs, 0);
                 if (err)
                         return err;
         }
 
         /* Test all sample format bits together */
         sample_type = PERF_SAMPLE_MAX - 1;
-        sample_regs_user = 0x3fff;
+        sample_regs = 0x3fff; /* shared yb intr and user regs */
         for (i = 0; i < ARRAY_SIZE(rf); i++) {
-                err = do_test(sample_type, sample_regs_user, rf[i]);
+                err = do_test(sample_type, sample_regs, rf[i]);
                 if (err)
                         return err;
         }
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index f0697a3aede0..1e0a2fd80115 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -27,6 +27,7 @@ static struct annotate_browser_opt {
         bool hide_src_code,
              use_offset,
              jump_arrows,
+             show_linenr,
              show_nr_jumps;
 } annotate_browser__opts = {
         .use_offset     = true,
@@ -128,7 +129,11 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
         if (!*dl->line)
                 slsmg_write_nstring(" ", width - pcnt_width);
         else if (dl->offset == -1) {
-                printed = scnprintf(bf, sizeof(bf), "%*s  ",
+                if (dl->line_nr && annotate_browser__opts.show_linenr)
+                        printed = scnprintf(bf, sizeof(bf), "%-*d ",
+                                        ab->addr_width + 1, dl->line_nr);
+                else
+                        printed = scnprintf(bf, sizeof(bf), "%*s  ",
                                     ab->addr_width, " ");
                 slsmg_write_nstring(bf, printed);
                 slsmg_write_nstring(dl->line, width - printed - pcnt_width + 1);
@@ -733,6 +738,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
                 "o             Toggle disassembler output/simplified view\n"
                 "s             Toggle source code view\n"
                 "/             Search string\n"
+                "k             Toggle line numbers\n"
                 "r             Run available scripts\n"
                 "?             Search string backwards\n");
                         continue;
@@ -741,6 +747,10 @@ static int annotate_browser__run(struct annotate_browser *browser,
                                 script_browse(NULL);
                                 continue;
                         }
+                case 'k':
+                        annotate_browser__opts.show_linenr =
+                                !annotate_browser__opts.show_linenr;
+                        break;
                 case 'H':
                         nd = browser->curr_hot;
                         break;
@@ -984,6 +994,7 @@ static struct annotate_config {
 } annotate__configs[] = {
         ANNOTATE_CFG(hide_src_code),
         ANNOTATE_CFG(jump_arrows),
+        ANNOTATE_CFG(show_linenr),
         ANNOTATE_CFG(show_nr_jumps),
         ANNOTATE_CFG(use_offset),
 };
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index cfb976b3de3a..788506eef567 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -227,10 +227,14 @@ static void callchain_node__init_have_children_rb_tree(struct callchain_node *no
         }
 }
 
-static void callchain_node__init_have_children(struct callchain_node *node)
+static void callchain_node__init_have_children(struct callchain_node *node,
+                                               bool has_sibling)
 {
         struct callchain_list *chain;
 
+        chain = list_entry(node->val.next, struct callchain_list, list);
+        chain->ms.has_children = has_sibling;
+
         if (!list_empty(&node->val)) {
                 chain = list_entry(node->val.prev, struct callchain_list, list);
                 chain->ms.has_children = !RB_EMPTY_ROOT(&node->rb_root);
@@ -241,11 +245,12 @@ static void callchain_node__init_have_children(struct callchain_node *node)
 
 static void callchain__init_have_children(struct rb_root *root)
 {
-        struct rb_node *nd;
+        struct rb_node *nd = rb_first(root);
+        bool has_sibling = nd && rb_next(nd);
 
         for (nd = rb_first(root); nd; nd = rb_next(nd)) {
                 struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
-                callchain_node__init_have_children(node);
+                callchain_node__init_have_children(node, has_sibling);
         }
 }
 
@@ -463,23 +468,6 @@ out:
         return key;
 }
 
-static char *callchain_list__sym_name(struct callchain_list *cl,
-                                      char *bf, size_t bfsize, bool show_dso)
-{
-        int printed;
-
-        if (cl->ms.sym)
-                printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
-        else
-                printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
-
-        if (show_dso)
-                scnprintf(bf + printed, bfsize - printed, " %s",
-                          cl->ms.map ? cl->ms.map->dso->short_name : "unknown");
-
-        return bf;
-}
-
 struct callchain_print_arg {
         /* for hists browser */
         off_t   row_offset;
@@ -559,8 +547,11 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
         struct rb_node *node;
         int first_row = row, offset = level * LEVEL_OFFSET_STEP;
         u64 new_total;
+        bool need_percent;
 
         node = rb_first(root);
+        need_percent = node && rb_next(node);
+
         while (node) {
                 struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
                 struct rb_node *next = rb_next(node);
@@ -577,7 +568,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 
                         if (first)
                                 first = false;
-                        else if (level > 1)
+                        else if (need_percent)
                                 extra_offset = LEVEL_OFFSET_STEP;
 
                         folded_sign = callchain_list__folded(chain);
@@ -590,7 +581,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
                         str = callchain_list__sym_name(chain, bf, sizeof(bf),
                                                        browser->show_dso);
 
-                        if (was_first && level > 1) {
+                        if (was_first && need_percent) {
                                 double percent = cumul * 100.0 / total;
 
                                 if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
@@ -807,6 +798,13 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                         .is_current_entry = current_entry,
                 };
 
+                if (callchain_param.mode == CHAIN_GRAPH_REL) {
+                        if (symbol_conf.cumulate_callchain)
+                                total = entry->stat_acc->period;
+                        else
+                                total = entry->stat.period;
+                }
+
                 printed += hist_browser__show_callchain(browser,
                                         &entry->sorted_chain, 1, row, total,
                                         hist_browser__show_callchain_entry, &arg,
@@ -1254,7 +1252,7 @@ static int hists__browser_title(struct hists *hists,
 
         nr_samples = convert_unit(nr_samples, &unit);
         printed = scnprintf(bf, size,
-                           "Samples: %lu%c of event '%s', Event count (approx.): %lu",
+                           "Samples: %lu%c of event '%s', Event count (approx.): %" PRIu64,
                            nr_samples, unit, ev_name, nr_events);
 
 
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index fc654fb77ace..4b3585eed1e8 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -89,15 +89,6 @@ void perf_gtk__init_hpp(void)
                                 perf_gtk__hpp_color_overhead_acc;
 }
 
-static void callchain_list__sym_name(struct callchain_list *cl,
-                                     char *bf, size_t bfsize)
-{
-        if (cl->ms.sym)
-                scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
-        else
-                scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
-}
-
 static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
                                     GtkTreeIter *parent, int col, u64 total)
 {
@@ -128,7 +119,7 @@ static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
                         scnprintf(buf, sizeof(buf), "%5.2f%%", percent);
                         gtk_tree_store_set(store, &iter, 0, buf, -1);
 
-                        callchain_list__sym_name(chain, buf, sizeof(buf));
+                        callchain_list__sym_name(chain, buf, sizeof(buf), false);
                         gtk_tree_store_set(store, &iter, col, buf, -1);
 
                         if (need_new_parent) {
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 2af18376b077..482adae3cc44 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -162,8 +162,8 @@ static int __hpp__sort(struct hist_entry *a, struct hist_entry *b,
                 return ret;
 
         nr_members = evsel->nr_members;
-        fields_a = calloc(sizeof(*fields_a), nr_members);
-        fields_b = calloc(sizeof(*fields_b), nr_members);
+        fields_a = calloc(nr_members, sizeof(*fields_a));
+        fields_b = calloc(nr_members, sizeof(*fields_b));
 
         if (!fields_a || !fields_b)
                 goto out;
@@ -204,6 +204,9 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
                 if (ret)
                         return ret;
 
+                if (a->thread != b->thread || !symbol_conf.use_callchain)
+                        return 0;
+
                 ret = b->callchain->max_depth - a->callchain->max_depth;
         }
         return ret;
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 15b451acbde6..dfcbc90146ef 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -41,6 +41,7 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
 {
         int i;
         size_t ret = 0;
+        char bf[1024];
 
         ret += callchain__fprintf_left_margin(fp, left_margin);
         for (i = 0; i < depth; i++) {
@@ -56,11 +57,8 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
                 } else
                         ret += fprintf(fp, "%s", "          ");
         }
-        if (chain->ms.sym)
-                ret += fprintf(fp, "%s\n", chain->ms.sym->name);
-        else
-                ret += fprintf(fp, "0x%0" PRIx64 "\n", chain->ip);
-
+        fputs(callchain_list__sym_name(chain, bf, sizeof(bf), false), fp);
+        fputc('\n', fp);
         return ret;
 }
 
@@ -168,6 +166,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
         struct rb_node *node;
         int i = 0;
         int ret = 0;
+        char bf[1024];
 
         /*
          * If have one single callchain root, don't bother printing
@@ -196,10 +195,8 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
                         } else
                                 ret += callchain__fprintf_left_margin(fp, left_margin);
 
-                        if (chain->ms.sym)
-                                ret += fprintf(fp, " %s\n", chain->ms.sym->name);
-                        else
-                                ret += fprintf(fp, " %p\n", (void *)(long)chain->ip);
+                        ret += fprintf(fp, "%s\n", callchain_list__sym_name(chain, bf, sizeof(bf),
+                                                        false));
 
                         if (++entries_printed == callchain_param.print_limit)
                                 break;
@@ -219,6 +216,7 @@ static size_t __callchain__fprintf_flat(FILE *fp, struct callchain_node *node,
 {
         struct callchain_list *chain;
         size_t ret = 0;
+        char bf[1024];
 
         if (!node)
                 return 0;
@@ -229,11 +227,8 @@ static size_t __callchain__fprintf_flat(FILE *fp, struct callchain_node *node,
         list_for_each_entry(chain, &node->val, list) {
                 if (chain->ip >= PERF_CONTEXT_MAX)
                         continue;
-                if (chain->ms.sym)
-                        ret += fprintf(fp, "                %s\n", chain->ms.sym->name);
-                else
-                        ret += fprintf(fp, "                %p\n",
-                                        (void *)(long)chain->ip);
+                ret += fprintf(fp, "                %s\n", callchain_list__sym_name(chain,
+                                        bf, sizeof(bf), false));
         }
 
         return ret;
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 2f612562978c..3c38f25b1695 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -1,5 +1,8 @@
 #include <signal.h>
 #include <stdbool.h>
+#ifdef HAVE_BACKTRACE_SUPPORT
+#include <execinfo.h>
+#endif
 
 #include "../../util/cache.h"
 #include "../../util/debug.h"
@@ -88,6 +91,25 @@ int ui__getch(int delay_secs)
         return SLkp_getkey();
 }
 
+#ifdef HAVE_BACKTRACE_SUPPORT
+static void ui__signal_backtrace(int sig)
+{
+        void *stackdump[32];
+        size_t size;
+
+        ui__exit(false);
+        psignal(sig, "perf");
+
+        printf("-------- backtrace --------\n");
+        size = backtrace(stackdump, ARRAY_SIZE(stackdump));
+        backtrace_symbols_fd(stackdump, size, STDOUT_FILENO);
+
+        exit(0);
+}
+#else
+# define ui__signal_backtrace  ui__signal
+#endif
+
 static void ui__signal(int sig)
 {
         ui__exit(false);
@@ -122,8 +144,8 @@ int ui__init(void)
         ui_browser__init();
         tui_progress__init();
 
-        signal(SIGSEGV, ui__signal);
-        signal(SIGFPE, ui__signal);
+        signal(SIGSEGV, ui__signal_backtrace);
+        signal(SIGFPE, ui__signal_backtrace);
         signal(SIGINT, ui__signal);
         signal(SIGQUIT, ui__signal);
         signal(SIGTERM, ui__signal);
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 7dabde14ea54..79999ceaf2be 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -17,11 +17,13 @@
 #include "debug.h"
 #include "annotate.h"
 #include "evsel.h"
+#include <regex.h>
 #include <pthread.h>
 #include <linux/bitops.h>
 
 const char      *disassembler_style;
 const char      *objdump_path;
+static regex_t   file_lineno;
 
 static struct ins *ins__find(const char *name);
 static int disasm_line__parse(char *line, char **namep, char **rawp);
@@ -570,13 +572,15 @@ out_free_name:
         return -1;
 }
 
-static struct disasm_line *disasm_line__new(s64 offset, char *line, size_t privsize)
+static struct disasm_line *disasm_line__new(s64 offset, char *line,
+                                        size_t privsize, int line_nr)
 {
         struct disasm_line *dl = zalloc(sizeof(*dl) + privsize);
 
         if (dl != NULL) {
                 dl->offset = offset;
                 dl->line = strdup(line);
+                dl->line_nr = line_nr;
                 if (dl->line == NULL)
                         goto out_delete;
 
@@ -788,13 +792,15 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
  * The ops.raw part will be parsed further according to type of the instruction.
  */
 static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
-                                      FILE *file, size_t privsize)
+                                      FILE *file, size_t privsize,
+                                      int *line_nr)
 {
         struct annotation *notes = symbol__annotation(sym);
         struct disasm_line *dl;
         char *line = NULL, *parsed_line, *tmp, *tmp2, *c;
         size_t line_len;
         s64 line_ip, offset = -1;
+        regmatch_t match[2];
 
         if (getline(&line, &line_len, file) < 0)
                 return -1;
@@ -812,6 +818,12 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
         line_ip = -1;
         parsed_line = line;
 
+        /* /filename:linenr ? Save line number and ignore. */
+        if (regexec(&file_lineno, line, 2, match, 0) == 0) {
+                *line_nr = atoi(line + match[1].rm_so);
+                return 0;
+        }
+
         /*
          * Strip leading spaces:
          */
@@ -842,8 +854,9 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
                         parsed_line = tmp2 + 1;
         }
 
-        dl = disasm_line__new(offset, parsed_line, privsize);
+        dl = disasm_line__new(offset, parsed_line, privsize, *line_nr);
         free(line);
+        (*line_nr)++;
 
         if (dl == NULL)
                 return -1;
@@ -869,6 +882,11 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
         return 0;
 }
 
+static __attribute__((constructor)) void symbol__init_regexpr(void)
+{
+        regcomp(&file_lineno, "^/[^:]+:([0-9]+)", REG_EXTENDED);
+}
+
 static void delete_last_nop(struct symbol *sym)
 {
         struct annotation *notes = symbol__annotation(sym);
@@ -904,6 +922,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
         char symfs_filename[PATH_MAX];
         struct kcore_extract kce;
         bool delete_extract = false;
+        int lineno = 0;
 
         if (filename)
                 symbol__join_symfs(symfs_filename, filename);
@@ -915,6 +934,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
                         return -ENOMEM;
                 }
                 goto fallback;
+        } else if (dso__is_kcore(dso)) {
+                goto fallback;
         } else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
                    strstr(command, "[kernel.kallsyms]") ||
                    access(symfs_filename, R_OK)) {
@@ -982,7 +1003,7 @@ fallback:
         snprintf(command, sizeof(command),
                  "%s %s%s --start-address=0x%016" PRIx64
                  " --stop-address=0x%016" PRIx64
-                 " -d %s %s -C %s 2>/dev/null|grep -v %s|expand",
+                 " -l -d %s %s -C %s 2>/dev/null|grep -v %s|expand",
                  objdump_path ? objdump_path : "objdump",
                  disassembler_style ? "-M " : "",
                  disassembler_style ? disassembler_style : "",
@@ -999,7 +1020,8 @@ fallback:
                 goto out_free_filename;
 
         while (!feof(file))
-                if (symbol__parse_objdump_line(sym, map, file, privsize) < 0)
+                if (symbol__parse_objdump_line(sym, map, file, privsize,
+                            &lineno) < 0)
                         break;
 
         /*
@@ -1170,7 +1192,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
                         goto next;
 
                 offset = start + i;
-                src_line->path = get_srcline(map->dso, offset);
+                src_line->path = get_srcline(map->dso, offset, NULL, false);
                 insert_source_line(&tmp_root, src_line);
 
         next:
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 112d6e268150..cadbdc90a5cb 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -58,6 +58,7 @@ struct disasm_line {
         char                *line;
         char                *name;
         struct ins          *ins;
+        int                 line_nr;
         struct ins_operands ops;
 };
 
@@ -115,11 +116,6 @@ struct annotation {
         struct annotated_source *src;
 };
 
-struct sannotation {
-        struct annotation annotation;
-        struct symbol     symbol;
-};
-
 static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx)
 {
         return (((void *)&notes->src->histograms) +
@@ -128,8 +124,7 @@ static inline struct sym_hist *annotation__histogram(struct annotation *notes, i
 
 static inline struct annotation *symbol__annotation(struct symbol *sym)
 {
-        struct sannotation *a = container_of(sym, struct sannotation, symbol);
-        return &a->annotation;
+        return (void *)sym - symbol_conf.priv_size;
 }
 
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx);
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index a904a4cfe7d3..0c72680a977f 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -15,6 +15,11 @@
 #include "debug.h"
 #include "session.h"
 #include "tool.h"
+#include "header.h"
+#include "vdso.h"
+
+
+static bool no_buildid_cache;
 
 int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
                            union perf_event *event,
@@ -33,8 +38,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
                 return -1;
         }
 
-        thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-                              sample->ip, &al);
+        thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al);
 
         if (al.map != NULL)
                 al.map->dso->hit = 1;
@@ -106,3 +110,340 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
                          build_id_hex, build_id_hex + 2);
         return bf;
 }
+
+#define dsos__for_each_with_build_id(pos, head) \
+        list_for_each_entry(pos, head, node)    \
+                if (!pos->has_build_id)         \
+                        continue;               \
+                else
+
+static int write_buildid(const char *name, size_t name_len, u8 *build_id,
+                         pid_t pid, u16 misc, int fd)
+{
+        int err;
+        struct build_id_event b;
+        size_t len;
+
+        len = name_len + 1;
+        len = PERF_ALIGN(len, NAME_ALIGN);
+
+        memset(&b, 0, sizeof(b));
+        memcpy(&b.build_id, build_id, BUILD_ID_SIZE);
+        b.pid = pid;
+        b.header.misc = misc;
+        b.header.size = sizeof(b) + len;
+
+        err = writen(fd, &b, sizeof(b));
+        if (err < 0)
+                return err;
+
+        return write_padded(fd, name, name_len + 1, len);
+}
+
+static int __dsos__write_buildid_table(struct list_head *head,
+                                       struct machine *machine,
+                                       pid_t pid, u16 misc, int fd)
+{
+        char nm[PATH_MAX];
+        struct dso *pos;
+
+        dsos__for_each_with_build_id(pos, head) {
+                int err;
+                const char *name;
+                size_t name_len;
+
+                if (!pos->hit)
+                        continue;
+
+                if (dso__is_vdso(pos)) {
+                        name = pos->short_name;
+                        name_len = pos->short_name_len + 1;
+                } else if (dso__is_kcore(pos)) {
+                        machine__mmap_name(machine, nm, sizeof(nm));
+                        name = nm;
+                        name_len = strlen(nm) + 1;
+                } else {
+                        name = pos->long_name;
+                        name_len = pos->long_name_len + 1;
+                }
+
+                err = write_buildid(name, name_len, pos->build_id,
+                                    pid, misc, fd);
+                if (err)
+                        return err;
+        }
+
+        return 0;
+}
+
+static int machine__write_buildid_table(struct machine *machine, int fd)
+{
+        int err;
+        u16 kmisc = PERF_RECORD_MISC_KERNEL,
+            umisc = PERF_RECORD_MISC_USER;
+
+        if (!machine__is_host(machine)) {
+                kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
+                umisc = PERF_RECORD_MISC_GUEST_USER;
+        }
+
+        err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine,
+                                          machine->pid, kmisc, fd);
+        if (err == 0)
+                err = __dsos__write_buildid_table(&machine->user_dsos.head,
+                                                  machine, machine->pid, umisc,
+                                                  fd);
+        return err;
+}
+
+int perf_session__write_buildid_table(struct perf_session *session, int fd)
+{
+        struct rb_node *nd;
+        int err = machine__write_buildid_table(&session->machines.host, fd);
+
+        if (err)
+                return err;
+
+        for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+                struct machine *pos = rb_entry(nd, struct machine, rb_node);
+                err = machine__write_buildid_table(pos, fd);
+                if (err)
+                        break;
+        }
+        return err;
+}
+
+static int __dsos__hit_all(struct list_head *head)
+{
+        struct dso *pos;
+
+        list_for_each_entry(pos, head, node)
+                pos->hit = true;
+
+        return 0;
+}
+
+static int machine__hit_all_dsos(struct machine *machine)
+{
+        int err;
+
+        err = __dsos__hit_all(&machine->kernel_dsos.head);
+        if (err)
+                return err;
+
+        return __dsos__hit_all(&machine->user_dsos.head);
+}
+
+int dsos__hit_all(struct perf_session *session)
+{
+        struct rb_node *nd;
+        int err;
+
+        err = machine__hit_all_dsos(&session->machines.host);
+        if (err)
+                return err;
+
+        for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+                struct machine *pos = rb_entry(nd, struct machine, rb_node);
+
+                err = machine__hit_all_dsos(pos);
+                if (err)
+                        return err;
+        }
+
+        return 0;
+}
+
+void disable_buildid_cache(void)
+{
+        no_buildid_cache = true;
+}
+
+int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
+                          const char *name, bool is_kallsyms, bool is_vdso)
+{
+        const size_t size = PATH_MAX;
+        char *realname, *filename = zalloc(size),
+             *linkname = zalloc(size), *targetname;
+        int len, err = -1;
+        bool slash = is_kallsyms || is_vdso;
+
+        if (is_kallsyms) {
+                if (symbol_conf.kptr_restrict) {
+                        pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
+                        err = 0;
+                        goto out_free;
+                }
+                realname = (char *) name;
+        } else
+                realname = realpath(name, NULL);
+
+        if (realname == NULL || filename == NULL || linkname == NULL)
+                goto out_free;
+
+        len = scnprintf(filename, size, "%s%s%s",
+                       debugdir, slash ? "/" : "",
+                       is_vdso ? DSO__NAME_VDSO : realname);
+        if (mkdir_p(filename, 0755))
+                goto out_free;
+
+        snprintf(filename + len, size - len, "/%s", sbuild_id);
+
+        if (access(filename, F_OK)) {
+                if (is_kallsyms) {
+                         if (copyfile("/proc/kallsyms", filename))
+                                goto out_free;
+                } else if (link(realname, filename) && copyfile(name, filename))
+                        goto out_free;
+        }
+
+        len = scnprintf(linkname, size, "%s/.build-id/%.2s",
+                       debugdir, sbuild_id);
+
+        if (access(linkname, X_OK) && mkdir_p(linkname, 0755))
+                goto out_free;
+
+        snprintf(linkname + len, size - len, "/%s", sbuild_id + 2);
+        targetname = filename + strlen(debugdir) - 5;
+        memcpy(targetname, "../..", 5);
+
+        if (symlink(targetname, linkname) == 0)
+                err = 0;
+out_free:
+        if (!is_kallsyms)
+                free(realname);
+        free(filename);
+        free(linkname);
+        return err;
+}
+
+static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
+                                 const char *name, const char *debugdir,
+                                 bool is_kallsyms, bool is_vdso)
+{
+        char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+        build_id__sprintf(build_id, build_id_size, sbuild_id);
+
+        return build_id_cache__add_s(sbuild_id, debugdir, name,
+                                     is_kallsyms, is_vdso);
+}
+
+int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
+{
+        const size_t size = PATH_MAX;
+        char *filename = zalloc(size),
+             *linkname = zalloc(size);
+        int err = -1;
+
+        if (filename == NULL || linkname == NULL)
+                goto out_free;
+
+        snprintf(linkname, size, "%s/.build-id/%.2s/%s",
+                 debugdir, sbuild_id, sbuild_id + 2);
+
+        if (access(linkname, F_OK))
+                goto out_free;
+
+        if (readlink(linkname, filename, size - 1) < 0)
+                goto out_free;
+
+        if (unlink(linkname))
+                goto out_free;
+
+        /*
+         * Since the link is relative, we must make it absolute:
+         */
+        snprintf(linkname, size, "%s/.build-id/%.2s/%s",
+                 debugdir, sbuild_id, filename);
+
+        if (unlink(linkname))
+                goto out_free;
+
+        err = 0;
+out_free:
+        free(filename);
+        free(linkname);
+        return err;
+}
+
+static int dso__cache_build_id(struct dso *dso, struct machine *machine,
+                               const char *debugdir)
+{
+        bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
+        bool is_vdso = dso__is_vdso(dso);
+        const char *name = dso->long_name;
+        char nm[PATH_MAX];
+
+        if (dso__is_kcore(dso)) {
+                is_kallsyms = true;
+                machine__mmap_name(machine, nm, sizeof(nm));
+                name = nm;
+        }
+        return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
+                                     debugdir, is_kallsyms, is_vdso);
+}
+
+static int __dsos__cache_build_ids(struct list_head *head,
+                                   struct machine *machine, const char *debugdir)
+{
+        struct dso *pos;
+        int err = 0;
+
+        dsos__for_each_with_build_id(pos, head)
+                if (dso__cache_build_id(pos, machine, debugdir))
+                        err = -1;
+
+        return err;
+}
+
+static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
+{
+        int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine,
+                                          debugdir);
+        ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine,
+                                       debugdir);
+        return ret;
+}
+
+int perf_session__cache_build_ids(struct perf_session *session)
+{
+        struct rb_node *nd;
+        int ret;
+
+        if (no_buildid_cache)
+                return 0;
+
+        if (mkdir(buildid_dir, 0755) != 0 && errno != EEXIST)
+                return -1;
+
+        ret = machine__cache_build_ids(&session->machines.host, buildid_dir);
+
+        for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+                struct machine *pos = rb_entry(nd, struct machine, rb_node);
+                ret |= machine__cache_build_ids(pos, buildid_dir);
+        }
+        return ret ? -1 : 0;
+}
+
+static bool machine__read_build_ids(struct machine *machine, bool with_hits)
+{
+        bool ret;
+
+        ret  = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits);
+        ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits);
+        return ret;
+}
+
+bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
+{
+        struct rb_node *nd;
+        bool ret = machine__read_build_ids(&session->machines.host, with_hits);
+
+        for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+                struct machine *pos = rb_entry(nd, struct machine, rb_node);
+                ret |= machine__read_build_ids(pos, with_hits);
+        }
+
+        return ret;
+}
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index ae392561470b..8236319514d5 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -15,4 +15,16 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
                            struct perf_sample *sample, struct perf_evsel *evsel,
                            struct machine *machine);
+
+int dsos__hit_all(struct perf_session *session);
+
+bool perf_session__read_build_ids(struct perf_session *session, bool with_hits);
+int perf_session__write_buildid_table(struct perf_session *session, int fd);
+int perf_session__cache_build_ids(struct perf_session *session);
+
+int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
+                          const char *name, bool is_kallsyms, bool is_vdso);
+int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
+void disable_buildid_cache(void);
+
 #endif
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 5cf9e1b5989d..d04d770d90f6 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -71,7 +71,9 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2
 extern char *perf_pathdup(const char *fmt, ...)
         __attribute__((format (printf, 1, 2)));
 
+#ifndef __UCLIBC__
 /* Matches the libc/libbsd function attribute so we declare this unconditionally: */
 extern size_t strlcpy(char *dest, const char *src, size_t size);
+#endif
 
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index c84d3f8dcb75..14e7a123d43b 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -77,7 +77,7 @@ int parse_callchain_record_opt(const char *arg)
                                 ret = 0;
                         } else
                                 pr_err("callchain: No more arguments "
-                                       "needed for -g fp\n");
+                                       "needed for --call-graph fp\n");
                         break;
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
@@ -149,6 +149,10 @@ static int parse_callchain_sort_key(const char *value)
                 callchain_param.key = CCKEY_ADDRESS;
                 return 0;
         }
+        if (!strncmp(value, "branch", strlen(value))) {
+                callchain_param.branch_callstack = 1;
+                return 0;
+        }
         return -1;
 }
 
@@ -754,8 +758,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 
         if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
             sort__has_parent) {
-                return machine__resolve_callchain(al->machine, evsel, al->thread,
-                                                  sample, parent, al, max_stack);
+                return thread__resolve_callchain(al->thread, evsel, sample,
+                                                 parent, al, max_stack);
         }
         return 0;
 }
@@ -808,3 +812,62 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *
 out:
         return 1;
 }
+
+char *callchain_list__sym_name(struct callchain_list *cl,
+                               char *bf, size_t bfsize, bool show_dso)
+{
+        int printed;
+
+        if (cl->ms.sym) {
+                if (callchain_param.key == CCKEY_ADDRESS &&
+                    cl->ms.map && !cl->srcline)
+                        cl->srcline = get_srcline(cl->ms.map->dso,
+                                                  map__rip_2objdump(cl->ms.map,
+                                                                    cl->ip),
+                                                  cl->ms.sym, false);
+                if (cl->srcline)
+                        printed = scnprintf(bf, bfsize, "%s %s",
+                                        cl->ms.sym->name, cl->srcline);
+                else
+                        printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
+        } else
+                printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
+
+        if (show_dso)
+                scnprintf(bf + printed, bfsize - printed, " %s",
+                          cl->ms.map ?
+                          cl->ms.map->dso->short_name :
+                          "unknown");
+
+        return bf;
+}
+
+static void free_callchain_node(struct callchain_node *node)
+{
+        struct callchain_list *list, *tmp;
+        struct callchain_node *child;
+        struct rb_node *n;
+
+        list_for_each_entry_safe(list, tmp, &node->val, list) {
+                list_del(&list->list);
+                free(list);
+        }
+
+        n = rb_first(&node->rb_root_in);
+        while (n) {
+                child = container_of(n, struct callchain_node, rb_node_in);
+                n = rb_next(n);
+                rb_erase(&child->rb_node_in, &node->rb_root_in);
+
+                free_callchain_node(child);
+                free(child);
+        }
+}
+
+void free_callchain(struct callchain_root *root)
+{
+        if (!symbol_conf.use_callchain)
+                return;
+
+        free_callchain_node(&root->node);
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 94cfefddf4db..c0ec1acc38e4 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -63,6 +63,7 @@ struct callchain_param {
         sort_chain_func_t       sort;
         enum chain_order        order;
         enum chain_key          key;
+        bool                    branch_callstack;
 };
 
 extern struct callchain_param callchain_param;
@@ -70,6 +71,7 @@ extern struct callchain_param callchain_param;
 struct callchain_list {
         u64                     ip;
         struct map_symbol       ms;
+        char                   *srcline;
         struct list_head        list;
 };
 
@@ -184,15 +186,18 @@ static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
 }
 
 #ifdef HAVE_SKIP_CALLCHAIN_IDX
-extern int arch_skip_callchain_idx(struct machine *machine,
-                        struct thread *thread, struct ip_callchain *chain);
+extern int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain);
 #else
-static inline int arch_skip_callchain_idx(struct machine *machine __maybe_unused,
-                        struct thread *thread __maybe_unused,
+static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
                         struct ip_callchain *chain __maybe_unused)
 {
         return -1;
 }
 #endif
 
+char *callchain_list__sym_name(struct callchain_list *cl,
+                               char *bf, size_t bfsize, bool show_dso);
+
+void free_callchain(struct callchain_root *root);
+
 #endif  /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
index 51c10ab257f8..71c9c39340d4 100644
--- a/tools/perf/util/comm.h
+++ b/tools/perf/util/comm.h
@@ -12,6 +12,10 @@ struct comm {
         u64 start;
         struct list_head list;
         bool exec;
+        union { /* Tool specific area */
+                void    *priv;
+                u64     db_id;
+        };
 };
 
 void comm__free(struct comm *comm);
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 57ff826f150b..e18f653cd7db 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -522,7 +522,7 @@ static int buildid_dir_command_config(const char *var, const char *value,
         const char *v;
 
         /* same dir for all commands */
-        if (!prefixcmp(var, "buildid.") && !strcmp(var + 8, "dir")) {
+        if (!strcmp(var, "buildid.dir")) {
                 v = perf_config_dirname(var, value);
                 if (!v)
                         return -1;
@@ -539,12 +539,14 @@ static void check_buildid_dir_config(void)
         perf_config(buildid_dir_command_config, &c);
 }
 
-void set_buildid_dir(void)
+void set_buildid_dir(const char *dir)
 {
-        buildid_dir[0] = '\0';
+        if (dir)
+                scnprintf(buildid_dir, MAXPATHLEN-1, "%s", dir);
 
         /* try config file */
-        check_buildid_dir_config();
+        if (buildid_dir[0] == '\0')
+                check_buildid_dir_config();
 
         /* default to $HOME/.debug */
         if (buildid_dir[0] == '\0') {
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
new file mode 100644
index 000000000000..c81dae399763
--- /dev/null
+++ b/tools/perf/util/db-export.c
@@ -0,0 +1,428 @@
+/*
+ * db-export.c: Support for exporting data suitable for import to a database
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <errno.h>
+
+#include "evsel.h"
+#include "machine.h"
+#include "thread.h"
+#include "comm.h"
+#include "symbol.h"
+#include "event.h"
+#include "util.h"
+#include "thread-stack.h"
+#include "db-export.h"
+
+struct deferred_export {
+        struct list_head node;
+        struct comm *comm;
+};
+
+static int db_export__deferred(struct db_export *dbe)
+{
+        struct deferred_export *de;
+        int err;
+
+        while (!list_empty(&dbe->deferred)) {
+                de = list_entry(dbe->deferred.next, struct deferred_export,
+                                node);
+                err = dbe->export_comm(dbe, de->comm);
+                list_del(&de->node);
+                free(de);
+                if (err)
+                        return err;
+        }
+
+        return 0;
+}
+
+static void db_export__free_deferred(struct db_export *dbe)
+{
+        struct deferred_export *de;
+
+        while (!list_empty(&dbe->deferred)) {
+                de = list_entry(dbe->deferred.next, struct deferred_export,
+                                node);
+                list_del(&de->node);
+                free(de);
+        }
+}
+
+static int db_export__defer_comm(struct db_export *dbe, struct comm *comm)
+{
+        struct deferred_export *de;
+
+        de = zalloc(sizeof(struct deferred_export));
+        if (!de)
+                return -ENOMEM;
+
+        de->comm = comm;
+        list_add_tail(&de->node, &dbe->deferred);
+
+        return 0;
+}
+
+int db_export__init(struct db_export *dbe)
+{
+        memset(dbe, 0, sizeof(struct db_export));
+        INIT_LIST_HEAD(&dbe->deferred);
+        return 0;
+}
+
+int db_export__flush(struct db_export *dbe)
+{
+        return db_export__deferred(dbe);
+}
+
+void db_export__exit(struct db_export *dbe)
+{
+        db_export__free_deferred(dbe);
+        call_return_processor__free(dbe->crp);
+        dbe->crp = NULL;
+}
+
+int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel)
+{
+        if (evsel->db_id)
+                return 0;
+
+        evsel->db_id = ++dbe->evsel_last_db_id;
+
+        if (dbe->export_evsel)
+                return dbe->export_evsel(dbe, evsel);
+
+        return 0;
+}
+
+int db_export__machine(struct db_export *dbe, struct machine *machine)
+{
+        if (machine->db_id)
+                return 0;
+
+        machine->db_id = ++dbe->machine_last_db_id;
+
+        if (dbe->export_machine)
+                return dbe->export_machine(dbe, machine);
+
+        return 0;
+}
+
+int db_export__thread(struct db_export *dbe, struct thread *thread,
+                      struct machine *machine, struct comm *comm)
+{
+        u64 main_thread_db_id = 0;
+        int err;
+
+        if (thread->db_id)
+                return 0;
+
+        thread->db_id = ++dbe->thread_last_db_id;
+
+        if (thread->pid_ != -1) {
+                struct thread *main_thread;
+
+                if (thread->pid_ == thread->tid) {
+                        main_thread = thread;
+                } else {
+                        main_thread = machine__findnew_thread(machine,
+                                                              thread->pid_,
+                                                              thread->pid_);
+                        if (!main_thread)
+                                return -ENOMEM;
+                        err = db_export__thread(dbe, main_thread, machine,
+                                                comm);
+                        if (err)
+                                return err;
+                        if (comm) {
+                                err = db_export__comm_thread(dbe, comm, thread);
+                                if (err)
+                                        return err;
+                        }
+                }
+                main_thread_db_id = main_thread->db_id;
+        }
+
+        if (dbe->export_thread)
+                return dbe->export_thread(dbe, thread, main_thread_db_id,
+                                          machine);
+
+        return 0;
+}
+
+int db_export__comm(struct db_export *dbe, struct comm *comm,
+                    struct thread *main_thread)
+{
+        int err;
+
+        if (comm->db_id)
+                return 0;
+
+        comm->db_id = ++dbe->comm_last_db_id;
+
+        if (dbe->export_comm) {
+                if (main_thread->comm_set)
+                        err = dbe->export_comm(dbe, comm);
+                else
+                        err = db_export__defer_comm(dbe, comm);
+                if (err)
+                        return err;
+        }
+
+        return db_export__comm_thread(dbe, comm, main_thread);
+}
+
+int db_export__comm_thread(struct db_export *dbe, struct comm *comm,
+                           struct thread *thread)
+{
+        u64 db_id;
+
+        db_id = ++dbe->comm_thread_last_db_id;
+
+        if (dbe->export_comm_thread)
+                return dbe->export_comm_thread(dbe, db_id, comm, thread);
+
+        return 0;
+}
+
+int db_export__dso(struct db_export *dbe, struct dso *dso,
+                   struct machine *machine)
+{
+        if (dso->db_id)
+                return 0;
+
+        dso->db_id = ++dbe->dso_last_db_id;
+
+        if (dbe->export_dso)
+                return dbe->export_dso(dbe, dso, machine);
+
+        return 0;
+}
+
+int db_export__symbol(struct db_export *dbe, struct symbol *sym,
+                      struct dso *dso)
+{
+        u64 *sym_db_id = symbol__priv(sym);
+
+        if (*sym_db_id)
+                return 0;
+
+        *sym_db_id = ++dbe->symbol_last_db_id;
+
+        if (dbe->export_symbol)
+                return dbe->export_symbol(dbe, sym, dso);
+
+        return 0;
+}
+
+static struct thread *get_main_thread(struct machine *machine, struct thread *thread)
+{
+        if (thread->pid_ == thread->tid)
+                return thread;
+
+        if (thread->pid_ == -1)
+                return NULL;
+
+        return machine__find_thread(machine, thread->pid_, thread->pid_);
+}
+
+static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
+                          u64 *dso_db_id, u64 *sym_db_id, u64 *offset)
+{
+        int err;
+
+        if (al->map) {
+                struct dso *dso = al->map->dso;
+
+                err = db_export__dso(dbe, dso, al->machine);
+                if (err)
+                        return err;
+                *dso_db_id = dso->db_id;
+
+                if (!al->sym) {
+                        al->sym = symbol__new(al->addr, 0, 0, "unknown");
+                        if (al->sym)
+                                symbols__insert(&dso->symbols[al->map->type],
+                                                al->sym);
+                }
+
+                if (al->sym) {
+                        u64 *db_id = symbol__priv(al->sym);
+
+                        err = db_export__symbol(dbe, al->sym, dso);
+                        if (err)
+                                return err;
+                        *sym_db_id = *db_id;
+                        *offset = al->addr - al->sym->start;
+                }
+        }
+
+        return 0;
+}
+
+int db_export__branch_type(struct db_export *dbe, u32 branch_type,
+                           const char *name)
+{
+        if (dbe->export_branch_type)
+                return dbe->export_branch_type(dbe, branch_type, name);
+
+        return 0;
+}
+
+int db_export__sample(struct db_export *dbe, union perf_event *event,
+                      struct perf_sample *sample, struct perf_evsel *evsel,
+                      struct thread *thread, struct addr_location *al)
+{
+        struct export_sample es = {
+                .event = event,
+                .sample = sample,
+                .evsel = evsel,
+                .thread = thread,
+                .al = al,
+        };
+        struct thread *main_thread;
+        struct comm *comm = NULL;
+        int err;
+
+        err = db_export__evsel(dbe, evsel);
+        if (err)
+                return err;
+
+        err = db_export__machine(dbe, al->machine);
+        if (err)
+                return err;
+
+        main_thread = get_main_thread(al->machine, thread);
+        if (main_thread)
+                comm = machine__thread_exec_comm(al->machine, main_thread);
+
+        err = db_export__thread(dbe, thread, al->machine, comm);
+        if (err)
+                return err;
+
+        if (comm) {
+                err = db_export__comm(dbe, comm, main_thread);
+                if (err)
+                        return err;
+                es.comm_db_id = comm->db_id;
+        }
+
+        es.db_id = ++dbe->sample_last_db_id;
+
+        err = db_ids_from_al(dbe, al, &es.dso_db_id, &es.sym_db_id, &es.offset);
+        if (err)
+                return err;
+
+        if ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
+            sample_addr_correlates_sym(&evsel->attr)) {
+                struct addr_location addr_al;
+
+                perf_event__preprocess_sample_addr(event, sample, thread, &addr_al);
+                err = db_ids_from_al(dbe, &addr_al, &es.addr_dso_db_id,
+                                     &es.addr_sym_db_id, &es.addr_offset);
+                if (err)
+                        return err;
+                if (dbe->crp) {
+                        err = thread_stack__process(thread, comm, sample, al,
+                                                    &addr_al, es.db_id,
+                                                    dbe->crp);
+                        if (err)
+                                return err;
+                }
+        }
+
+        if (dbe->export_sample)
+                return dbe->export_sample(dbe, &es);
+
+        return 0;
+}
+
+static struct {
+        u32 branch_type;
+        const char *name;
+} branch_types[] = {
+        {0, "no branch"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "conditional jump"},
+        {PERF_IP_FLAG_BRANCH, "unconditional jump"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT,
+         "software interrupt"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT,
+         "return from interrupt"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET,
+         "system call"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET,
+         "return from system call"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "asynchronous branch"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
+         PERF_IP_FLAG_INTERRUPT, "hardware interrupt"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "transaction abort"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "trace begin"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "trace end"},
+        {0, NULL}
+};
+
+int db_export__branch_types(struct db_export *dbe)
+{
+        int i, err = 0;
+
+        for (i = 0; branch_types[i].name ; i++) {
+                err = db_export__branch_type(dbe, branch_types[i].branch_type,
+                                             branch_types[i].name);
+                if (err)
+                        break;
+        }
+        return err;
+}
+
+int db_export__call_path(struct db_export *dbe, struct call_path *cp)
+{
+        int err;
+
+        if (cp->db_id)
+                return 0;
+
+        if (cp->parent) {
+                err = db_export__call_path(dbe, cp->parent);
+                if (err)
+                        return err;
+        }
+
+        cp->db_id = ++dbe->call_path_last_db_id;
+
+        if (dbe->export_call_path)
+                return dbe->export_call_path(dbe, cp);
+
+        return 0;
+}
+
+int db_export__call_return(struct db_export *dbe, struct call_return *cr)
+{
+        int err;
+
+        if (cr->db_id)
+                return 0;
+
+        err = db_export__call_path(dbe, cr->cp);
+        if (err)
+                return err;
+
+        cr->db_id = ++dbe->call_return_last_db_id;
+
+        if (dbe->export_call_return)
+                return dbe->export_call_return(dbe, cr);
+
+        return 0;
+}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
new file mode 100644
index 000000000000..adbd22d66798
--- /dev/null
+++ b/tools/perf/util/db-export.h
@@ -0,0 +1,107 @@
+/*
+ * db-export.h: Support for exporting data suitable for import to a database
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __PERF_DB_EXPORT_H
+#define __PERF_DB_EXPORT_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+
+struct perf_evsel;
+struct machine;
+struct thread;
+struct comm;
+struct dso;
+struct perf_sample;
+struct addr_location;
+struct call_return_processor;
+struct call_path;
+struct call_return;
+
+struct export_sample {
+        union perf_event        *event;
+        struct perf_sample      *sample;
+        struct perf_evsel       *evsel;
+        struct thread           *thread;
+        struct addr_location    *al;
+        u64                     db_id;
+        u64                     comm_db_id;
+        u64                     dso_db_id;
+        u64                     sym_db_id;
+        u64                     offset; /* ip offset from symbol start */
+        u64                     addr_dso_db_id;
+        u64                     addr_sym_db_id;
+        u64                     addr_offset; /* addr offset from symbol start */
+};
+
+struct db_export {
+        int (*export_evsel)(struct db_export *dbe, struct perf_evsel *evsel);
+        int (*export_machine)(struct db_export *dbe, struct machine *machine);
+        int (*export_thread)(struct db_export *dbe, struct thread *thread,
+                             u64 main_thread_db_id, struct machine *machine);
+        int (*export_comm)(struct db_export *dbe, struct comm *comm);
+        int (*export_comm_thread)(struct db_export *dbe, u64 db_id,
+                                  struct comm *comm, struct thread *thread);
+        int (*export_dso)(struct db_export *dbe, struct dso *dso,
+                          struct machine *machine);
+        int (*export_symbol)(struct db_export *dbe, struct symbol *sym,
+                             struct dso *dso);
+        int (*export_branch_type)(struct db_export *dbe, u32 branch_type,
+                                  const char *name);
+        int (*export_sample)(struct db_export *dbe, struct export_sample *es);
+        int (*export_call_path)(struct db_export *dbe, struct call_path *cp);
+        int (*export_call_return)(struct db_export *dbe,
+                                  struct call_return *cr);
+        struct call_return_processor *crp;
+        u64 evsel_last_db_id;
+        u64 machine_last_db_id;
+        u64 thread_last_db_id;
+        u64 comm_last_db_id;
+        u64 comm_thread_last_db_id;
+        u64 dso_last_db_id;
+        u64 symbol_last_db_id;
+        u64 sample_last_db_id;
+        u64 call_path_last_db_id;
+        u64 call_return_last_db_id;
+        struct list_head deferred;
+};
+
+int db_export__init(struct db_export *dbe);
+int db_export__flush(struct db_export *dbe);
+void db_export__exit(struct db_export *dbe);
+int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel);
+int db_export__machine(struct db_export *dbe, struct machine *machine);
+int db_export__thread(struct db_export *dbe, struct thread *thread,
+                      struct machine *machine, struct comm *comm);
+int db_export__comm(struct db_export *dbe, struct comm *comm,
+                    struct thread *main_thread);
+int db_export__comm_thread(struct db_export *dbe, struct comm *comm,
+                           struct thread *thread);
+int db_export__dso(struct db_export *dbe, struct dso *dso,
+                   struct machine *machine);
+int db_export__symbol(struct db_export *dbe, struct symbol *sym,
+                      struct dso *dso);
+int db_export__branch_type(struct db_export *dbe, u32 branch_type,
+                           const char *name);
+int db_export__sample(struct db_export *dbe, union perf_event *event,
+                      struct perf_sample *sample, struct perf_evsel *evsel,
+                      struct thread *thread, struct addr_location *al);
+
+int db_export__branch_types(struct db_export *dbe);
+
+int db_export__call_path(struct db_export *dbe, struct call_path *cp);
+int db_export__call_return(struct db_export *dbe, struct call_return *cr);
+
+#endif
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index ba357f3226c6..ad60b2f20258 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -19,13 +19,14 @@
 int verbose;
 bool dump_trace = false, quiet = false;
 int debug_ordered_events;
+static int redirect_to_stderr;
 
 static int _eprintf(int level, int var, const char *fmt, va_list args)
 {
         int ret = 0;
 
         if (var >= level) {
-                if (use_browser >= 1)
+                if (use_browser >= 1 && !redirect_to_stderr)
                         ui_helpline__vshow(fmt, args);
                 else
                         ret = vfprintf(stderr, fmt, args);
@@ -145,6 +146,7 @@ static struct debug_variable {
 } debug_variables[] = {
         { .name = "verbose",            .ptr = &verbose },
         { .name = "ordered-events",     .ptr = &debug_ordered_events},
+        { .name = "stderr",             .ptr = &redirect_to_stderr},
         { .name = NULL, }
 };
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 0247acfdfaca..45be944d450a 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -21,8 +21,10 @@ char dso__symtab_origin(const struct dso *dso)
                 [DSO_BINARY_TYPE__BUILDID_DEBUGINFO]            = 'b',
                 [DSO_BINARY_TYPE__SYSTEM_PATH_DSO]              = 'd',
                 [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE]          = 'K',
+                [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP]     = 'm',
                 [DSO_BINARY_TYPE__GUEST_KALLSYMS]               = 'g',
                 [DSO_BINARY_TYPE__GUEST_KMODULE]                = 'G',
+                [DSO_BINARY_TYPE__GUEST_KMODULE_COMP]           = 'M',
                 [DSO_BINARY_TYPE__GUEST_VMLINUX]                = 'V',
         };
 
@@ -112,11 +114,13 @@ int dso__read_binary_type_filename(const struct dso *dso,
                 break;
 
         case DSO_BINARY_TYPE__GUEST_KMODULE:
+        case DSO_BINARY_TYPE__GUEST_KMODULE_COMP:
                 path__join3(filename, size, symbol_conf.symfs,
                             root_dir, dso->long_name);
                 break;
 
         case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+        case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
                 __symbol__join_symfs(filename, size, dso->long_name);
                 break;
 
@@ -137,6 +141,73 @@ int dso__read_binary_type_filename(const struct dso *dso,
         return ret;
 }
 
+static const struct {
+        const char *fmt;
+        int (*decompress)(const char *input, int output);
+} compressions[] = {
+#ifdef HAVE_ZLIB_SUPPORT
+        { "gz", gzip_decompress_to_file },
+#endif
+        { NULL, NULL },
+};
+
+bool is_supported_compression(const char *ext)
+{
+        unsigned i;
+
+        for (i = 0; compressions[i].fmt; i++) {
+                if (!strcmp(ext, compressions[i].fmt))
+                        return true;
+        }
+        return false;
+}
+
+bool is_kmodule_extension(const char *ext)
+{
+        if (strncmp(ext, "ko", 2))
+                return false;
+
+        if (ext[2] == '\0' || (ext[2] == '.' && is_supported_compression(ext+3)))
+                return true;
+
+        return false;
+}
+
+bool is_kernel_module(const char *pathname, bool *compressed)
+{
+        const char *ext = strrchr(pathname, '.');
+
+        if (ext == NULL)
+                return false;
+
+        if (is_supported_compression(ext + 1)) {
+                if (compressed)
+                        *compressed = true;
+                ext -= 3;
+        } else if (compressed)
+                *compressed = false;
+
+        return is_kmodule_extension(ext + 1);
+}
+
+bool decompress_to_file(const char *ext, const char *filename, int output_fd)
+{
+        unsigned i;
+
+        for (i = 0; compressions[i].fmt; i++) {
+                if (!strcmp(ext, compressions[i].fmt))
+                        return !compressions[i].decompress(filename,
+                                                           output_fd);
+        }
+        return false;
+}
+
+bool dso__needs_decompress(struct dso *dso)
+{
+        return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
+                dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
+}
+
 /*
  * Global list of open DSOs and the counter.
  */
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index acb651acc7fd..3782c82c6e44 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -22,7 +22,9 @@ enum dso_binary_type {
         DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
         DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
         DSO_BINARY_TYPE__GUEST_KMODULE,
+        DSO_BINARY_TYPE__GUEST_KMODULE_COMP,
         DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+        DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP,
         DSO_BINARY_TYPE__KCORE,
         DSO_BINARY_TYPE__GUEST_KCORE,
         DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
@@ -127,6 +129,7 @@ struct dso {
         const char       *long_name;
         u16              long_name_len;
         u16              short_name_len;
+        void            *dwfl;                  /* DWARF debug info */
 
         /* dso data file */
         struct {
@@ -138,6 +141,11 @@ struct dso {
                 struct list_head open_entry;
         } data;
 
+        union { /* Tool specific area */
+                void     *priv;
+                u64      db_id;
+        };
+
         char             name[0];
 };
 
@@ -179,6 +187,11 @@ int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir);
 char dso__symtab_origin(const struct dso *dso);
 int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
                                    char *root_dir, char *filename, size_t size);
+bool is_supported_compression(const char *ext);
+bool is_kmodule_extension(const char *ext);
+bool is_kernel_module(const char *pathname, bool *compressed);
+bool decompress_to_file(const char *ext, const char *filename, int output_fd);
+bool dso__needs_decompress(struct dso *dso);
 
 /*
  * The dso__data_* external interface provides following functions:
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 4af6b279e34a..6c6d044e959a 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -28,6 +28,7 @@ static const char *perf_event__names[] = {
         [PERF_RECORD_HEADER_TRACING_DATA]       = "TRACING_DATA",
         [PERF_RECORD_HEADER_BUILD_ID]           = "BUILD_ID",
         [PERF_RECORD_FINISHED_ROUND]            = "FINISHED_ROUND",
+        [PERF_RECORD_ID_INDEX]                  = "ID_INDEX",
 };
 
 const char *perf_event__name(unsigned int id)
@@ -730,12 +731,12 @@ int perf_event__process(struct perf_tool *tool __maybe_unused,
         return machine__process_event(machine, event, sample);
 }
 
-void thread__find_addr_map(struct thread *thread,
-                           struct machine *machine, u8 cpumode,
+void thread__find_addr_map(struct thread *thread, u8 cpumode,
                            enum map_type type, u64 addr,
                            struct addr_location *al)
 {
         struct map_groups *mg = thread->mg;
+        struct machine *machine = mg->machine;
         bool load_map = false;
 
         al->machine = machine;
@@ -806,14 +807,14 @@ try_again:
         }
 }
 
-void thread__find_addr_location(struct thread *thread, struct machine *machine,
+void thread__find_addr_location(struct thread *thread,
                                 u8 cpumode, enum map_type type, u64 addr,
                                 struct addr_location *al)
 {
-        thread__find_addr_map(thread, machine, cpumode, type, addr, al);
+        thread__find_addr_map(thread, cpumode, type, addr, al);
         if (al->map != NULL)
                 al->sym = map__find_symbol(al->map, al->addr,
-                                           machine->symbol_filter);
+                                           thread->mg->machine->symbol_filter);
         else
                 al->sym = NULL;
 }
@@ -842,8 +843,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
             machine->vmlinux_maps[MAP__FUNCTION] == NULL)
                 machine__create_kernel_maps(machine);
 
-        thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-                              sample->ip, al);
+        thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, al);
         dump_printf(" ...... dso: %s\n",
                     al->map ? al->map->dso->long_name :
                         al->level == 'H' ? "[hypervisor]" : "<not found>");
@@ -902,16 +902,14 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr)
 
 void perf_event__preprocess_sample_addr(union perf_event *event,
                                         struct perf_sample *sample,
-                                        struct machine *machine,
                                         struct thread *thread,
                                         struct addr_location *al)
 {
         u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-        thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-                              sample->addr, al);
+        thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->addr, al);
         if (!al->map)
-                thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE,
+                thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
                                       sample->addr, al);
 
         al->cpu = sample->cpu;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 5699e7e2a790..c4ffe2bd0738 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -143,6 +143,32 @@ struct branch_stack {
         struct branch_entry     entries[0];
 };
 
+enum {
+        PERF_IP_FLAG_BRANCH             = 1ULL << 0,
+        PERF_IP_FLAG_CALL               = 1ULL << 1,
+        PERF_IP_FLAG_RETURN             = 1ULL << 2,
+        PERF_IP_FLAG_CONDITIONAL        = 1ULL << 3,
+        PERF_IP_FLAG_SYSCALLRET         = 1ULL << 4,
+        PERF_IP_FLAG_ASYNC              = 1ULL << 5,
+        PERF_IP_FLAG_INTERRUPT          = 1ULL << 6,
+        PERF_IP_FLAG_TX_ABORT           = 1ULL << 7,
+        PERF_IP_FLAG_TRACE_BEGIN        = 1ULL << 8,
+        PERF_IP_FLAG_TRACE_END          = 1ULL << 9,
+        PERF_IP_FLAG_IN_TX              = 1ULL << 10,
+};
+
+#define PERF_BRANCH_MASK                (\
+        PERF_IP_FLAG_BRANCH             |\
+        PERF_IP_FLAG_CALL               |\
+        PERF_IP_FLAG_RETURN             |\
+        PERF_IP_FLAG_CONDITIONAL        |\
+        PERF_IP_FLAG_SYSCALLRET         |\
+        PERF_IP_FLAG_ASYNC              |\
+        PERF_IP_FLAG_INTERRUPT          |\
+        PERF_IP_FLAG_TX_ABORT           |\
+        PERF_IP_FLAG_TRACE_BEGIN        |\
+        PERF_IP_FLAG_TRACE_END)
+
 struct perf_sample {
         u64 ip;
         u32 pid, tid;
@@ -162,6 +188,7 @@ struct perf_sample {
         struct ip_callchain *callchain;
         struct branch_stack *branch_stack;
         struct regs_dump  user_regs;
+        struct regs_dump  intr_regs;
         struct stack_dump user_stack;
         struct sample_read read;
 };
@@ -187,6 +214,7 @@ enum perf_user_event_type { /* above any possible kernel type */
         PERF_RECORD_HEADER_TRACING_DATA         = 66,
         PERF_RECORD_HEADER_BUILD_ID             = 67,
         PERF_RECORD_FINISHED_ROUND              = 68,
+        PERF_RECORD_ID_INDEX                    = 69,
         PERF_RECORD_HEADER_MAX
 };
 
@@ -214,6 +242,7 @@ struct events_stats {
         u32 nr_invalid_chains;
         u32 nr_unknown_id;
         u32 nr_unprocessable_samples;
+        u32 nr_unordered_events;
 };
 
 struct attr_event {
@@ -239,6 +268,19 @@ struct tracing_data_event {
         u32 size;
 };
 
+struct id_index_entry {
+        u64 id;
+        u64 idx;
+        u64 cpu;
+        u64 tid;
+};
+
+struct id_index_event {
+        struct perf_event_header header;
+        u64 nr;
+        struct id_index_entry entries[0];
+};
+
 union perf_event {
         struct perf_event_header        header;
         struct mmap_event               mmap;
@@ -253,6 +295,7 @@ union perf_event {
         struct event_type_event         event_type;
         struct tracing_data_event       tracing_data;
         struct build_id_event           build_id;
+        struct id_index_event           id_index;
 };
 
 void perf_event__print_totals(void);
@@ -322,7 +365,6 @@ bool is_bts_event(struct perf_event_attr *attr);
 bool sample_addr_correlates_sym(struct perf_event_attr *attr);
 void perf_event__preprocess_sample_addr(union perf_event *event,
                                         struct perf_sample *sample,
-                                        struct machine *machine,
                                         struct thread *thread,
                                         struct addr_location *al);
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 3c9e77d6b4c2..cbab1fb77b1d 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -8,6 +8,7 @@
  */
 #include "util.h"
 #include <api/fs/debugfs.h>
+#include <api/fs/fs.h>
 #include <poll.h>
 #include "cpumap.h"
 #include "thread_map.h"
@@ -24,6 +25,7 @@
 
 #include <linux/bitops.h>
 #include <linux/hash.h>
+#include <linux/log2.h>
 
 static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx);
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx);
@@ -413,7 +415,7 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
         int nfds = 0;
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if (evsel->system_wide)
                         nfds += nr_cpus;
                 else
@@ -527,6 +529,22 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
         return 0;
 }
 
+static void perf_evlist__set_sid_idx(struct perf_evlist *evlist,
+                                     struct perf_evsel *evsel, int idx, int cpu,
+                                     int thread)
+{
+        struct perf_sample_id *sid = SID(evsel, cpu, thread);
+        sid->idx = idx;
+        if (evlist->cpus && cpu >= 0)
+                sid->cpu = evlist->cpus->map[cpu];
+        else
+                sid->cpu = -1;
+        if (!evsel->system_wide && evlist->threads && thread >= 0)
+                sid->tid = evlist->threads->map[thread];
+        else
+                sid->tid = -1;
+}
+
 struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id)
 {
         struct hlist_head *head;
@@ -800,14 +818,26 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
                         perf_evlist__mmap_get(evlist, idx);
                 }
 
-                if (__perf_evlist__add_pollfd(evlist, fd, idx) < 0) {
+                /*
+                 * The system_wide flag causes a selected event to be opened
+                 * always without a pid.  Consequently it will never get a
+                 * POLLHUP, but it is used for tracking in combination with
+                 * other events, so it should not need to be polled anyway.
+                 * Therefore don't add it for polling.
+                 */
+                if (!evsel->system_wide &&
+                    __perf_evlist__add_pollfd(evlist, fd, idx) < 0) {
                         perf_evlist__mmap_put(evlist, idx);
                         return -1;
                 }
 
-                if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
-                    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
-                        return -1;
+                if (evsel->attr.read_format & PERF_FORMAT_ID) {
+                        if (perf_evlist__id_add_fd(evlist, evsel, cpu, thread,
+                                                   fd) < 0)
+                                return -1;
+                        perf_evlist__set_sid_idx(evlist, evsel, idx, cpu,
+                                                 thread);
+                }
         }
 
         return 0;
@@ -864,10 +894,24 @@ out_unmap:
 
 static size_t perf_evlist__mmap_size(unsigned long pages)
 {
-        /* 512 kiB: default amount of unprivileged mlocked memory */
-        if (pages == UINT_MAX)
-                pages = (512 * 1024) / page_size;
-        else if (!is_power_of_2(pages))
+        if (pages == UINT_MAX) {
+                int max;
+
+                if (sysctl__read_int("kernel/perf_event_mlock_kb", &max) < 0) {
+                        /*
+                         * Pick a once upon a time good value, i.e. things look
+                         * strange since we can't read a sysctl value, but lets not
+                         * die yet...
+                         */
+                        max = 512;
+                } else {
+                        max -= (page_size / 1024);
+                }
+
+                pages = (max * 1024) / page_size;
+                if (!is_power_of_2(pages))
+                        pages = rounddown_pow_of_two(pages);
+        } else if (!is_power_of_2(pages))
                 return 0;
 
         return (pages + 1) * page_size;
@@ -904,7 +948,7 @@ static long parse_pages_arg(const char *str, unsigned long min,
                 /* leave number of pages at 0 */
         } else if (!is_power_of_2(pages)) {
                 /* round pages up to next power of 2 */
-                pages = next_pow2_l(pages);
+                pages = roundup_pow_of_two(pages);
                 if (!pages)
                         return -EINVAL;
                 pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n",
@@ -1455,6 +1499,37 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
         return 0;
 }
 
+int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size)
+{
+        char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+        int pages_attempted = evlist->mmap_len / 1024, pages_max_per_user, printed = 0;
+
+        switch (err) {
+        case EPERM:
+                sysctl__read_int("kernel/perf_event_mlock_kb", &pages_max_per_user);
+                printed += scnprintf(buf + printed, size - printed,
+                                     "Error:\t%s.\n"
+                                     "Hint:\tCheck /proc/sys/kernel/perf_event_mlock_kb (%d kB) setting.\n"
+                                     "Hint:\tTried using %zd kB.\n",
+                                     emsg, pages_max_per_user, pages_attempted);
+
+                if (pages_attempted >= pages_max_per_user) {
+                        printed += scnprintf(buf + printed, size - printed,
+                                             "Hint:\tTry 'sudo sh -c \"echo %d > /proc/sys/kernel/perf_event_mlock_kb\"', or\n",
+                                             pages_max_per_user + pages_attempted);
+                }
+
+                printed += scnprintf(buf + printed, size - printed,
+                                     "Hint:\tTry using a smaller -m/--mmap-pages value.");
+                break;
+        default:
+                scnprintf(buf, size, "%s", emsg);
+                break;
+        }
+
+        return 0;
+}
+
 void perf_evlist__to_front(struct perf_evlist *evlist,
                            struct perf_evsel *move_evsel)
 {
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 649b0c597283..0ba93f67ab94 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -185,6 +185,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp);
 
 int perf_evlist__strerror_tp(struct perf_evlist *evlist, int err, char *buf, size_t size);
 int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size);
+int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size);
 
 static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm)
 {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 2f9e68025ede..1e90c8557ede 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -658,9 +658,22 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
                 attr->mmap_data = track;
         }
 
+        /*
+         * We don't allow user space callchains for  function trace
+         * event, due to issues with page faults while tracing page
+         * fault handler and its overall trickiness nature.
+         */
+        if (perf_evsel__is_function_event(evsel))
+                evsel->attr.exclude_callchain_user = 1;
+
         if (callchain_param.enabled && !evsel->no_aux_samples)
                 perf_evsel__config_callgraph(evsel);
 
+        if (opts->sample_intr_regs) {
+                attr->sample_regs_intr = PERF_REGS_MASK;
+                perf_evsel__set_sample_bit(evsel, REGS_INTR);
+        }
+
         if (target__has_cpu(&opts->target))
                 perf_evsel__set_sample_bit(evsel, CPU);
 
@@ -853,8 +866,6 @@ void perf_evsel__exit(struct perf_evsel *evsel)
         perf_evsel__free_id(evsel);
         close_cgroup(evsel->cgrp);
         zfree(&evsel->group_name);
-        if (evsel->tp_format)
-                pevent_free_format(evsel->tp_format);
         zfree(&evsel->name);
         perf_evsel__object.fini(evsel);
 }
@@ -865,9 +876,8 @@ void perf_evsel__delete(struct perf_evsel *evsel)
         free(evsel);
 }
 
-static inline void compute_deltas(struct perf_evsel *evsel,
-                                  int cpu,
-                                  struct perf_counts_values *count)
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+                                struct perf_counts_values *count)
 {
         struct perf_counts_values tmp;
 
@@ -887,81 +897,60 @@ static inline void compute_deltas(struct perf_evsel *evsel,
         count->run = count->run - tmp.run;
 }
 
-int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
-                              int cpu, int thread, bool scale)
+void perf_counts_values__scale(struct perf_counts_values *count,
+                               bool scale, s8 *pscaled)
 {
-        struct perf_counts_values count;
-        size_t nv = scale ? 3 : 1;
-
-        if (FD(evsel, cpu, thread) < 0)
-                return -EINVAL;
-
-        if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0)
-                return -ENOMEM;
-
-        if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
-                return -errno;
-
-        compute_deltas(evsel, cpu, &count);
+        s8 scaled = 0;
 
         if (scale) {
-                if (count.run == 0)
-                        count.val = 0;
-                else if (count.run < count.ena)
-                        count.val = (u64)((double)count.val * count.ena / count.run + 0.5);
+                if (count->run == 0) {
+                        scaled = -1;
+                        count->val = 0;
+                } else if (count->run < count->ena) {
+                        scaled = 1;
+                        count->val = (u64)((double) count->val * count->ena / count->run + 0.5);
+                }
         } else
-                count.ena = count.run = 0;
+                count->ena = count->run = 0;
 
-        evsel->counts->cpu[cpu] = count;
-        return 0;
+        if (pscaled)
+                *pscaled = scaled;
 }
 
-int __perf_evsel__read(struct perf_evsel *evsel,
-                       int ncpus, int nthreads, bool scale)
+int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
+                        perf_evsel__read_cb_t cb)
 {
-        size_t nv = scale ? 3 : 1;
-        int cpu, thread;
-        struct perf_counts_values *aggr = &evsel->counts->aggr, count;
+        struct perf_counts_values count;
 
-        if (evsel->system_wide)
-                nthreads = 1;
+        memset(&count, 0, sizeof(count));
 
-        aggr->val = aggr->ena = aggr->run = 0;
+        if (FD(evsel, cpu, thread) < 0)
+                return -EINVAL;
 
-        for (cpu = 0; cpu < ncpus; cpu++) {
-                for (thread = 0; thread < nthreads; thread++) {
-                        if (FD(evsel, cpu, thread) < 0)
-                                continue;
+        if (readn(FD(evsel, cpu, thread), &count, sizeof(count)) < 0)
+                return -errno;
 
-                        if (readn(FD(evsel, cpu, thread),
-                                  &count, nv * sizeof(u64)) < 0)
-                                return -errno;
+        return cb(evsel, cpu, thread, &count);
+}
 
-                        aggr->val += count.val;
-                        if (scale) {
-                                aggr->ena += count.ena;
-                                aggr->run += count.run;
-                        }
-                }
-        }
+int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
+                              int cpu, int thread, bool scale)
+{
+        struct perf_counts_values count;
+        size_t nv = scale ? 3 : 1;
 
-        compute_deltas(evsel, -1, aggr);
+        if (FD(evsel, cpu, thread) < 0)
+                return -EINVAL;
 
-        evsel->counts->scaled = 0;
-        if (scale) {
-                if (aggr->run == 0) {
-                        evsel->counts->scaled = -1;
-                        aggr->val = 0;
-                        return 0;
-                }
+        if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0)
+                return -ENOMEM;
 
-                if (aggr->run < aggr->ena) {
-                        evsel->counts->scaled = 1;
-                        aggr->val = (u64)((double)aggr->val * aggr->ena / aggr->run + 0.5);
-                }
-        } else
-                aggr->ena = aggr->run = 0;
+        if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
+                return -errno;
 
+        perf_evsel__compute_deltas(evsel, cpu, &count);
+        perf_counts_values__scale(&count, scale, NULL);
+        evsel->counts->cpu[cpu] = count;
         return 0;
 }
 
@@ -1039,6 +1028,7 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
         ret += PRINT_ATTR_X64(branch_sample_type);
         ret += PRINT_ATTR_X64(sample_regs_user);
         ret += PRINT_ATTR_U32(sample_stack_user);
+        ret += PRINT_ATTR_X64(sample_regs_intr);
 
         ret += fprintf(fp, "%.60s\n", graph_dotted_line);
 
@@ -1538,6 +1528,23 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                 array++;
         }
 
+        data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE;
+        if (type & PERF_SAMPLE_REGS_INTR) {
+                OVERFLOW_CHECK_u64(array);
+                data->intr_regs.abi = *array;
+                array++;
+
+                if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
+                        u64 mask = evsel->attr.sample_regs_intr;
+
+                        sz = hweight_long(mask) * sizeof(u64);
+                        OVERFLOW_CHECK(array, sz, max_size);
+                        data->intr_regs.mask = mask;
+                        data->intr_regs.regs = (u64 *)array;
+                        array = (void *)array + sz;
+                }
+        }
+
         return 0;
 }
 
@@ -1633,6 +1640,16 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
         if (type & PERF_SAMPLE_TRANSACTION)
                 result += sizeof(u64);
 
+        if (type & PERF_SAMPLE_REGS_INTR) {
+                if (sample->intr_regs.abi) {
+                        result += sizeof(u64);
+                        sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+                        result += sz;
+                } else {
+                        result += sizeof(u64);
+                }
+        }
+
         return result;
 }
 
@@ -1811,6 +1828,17 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
                 array++;
         }
 
+        if (type & PERF_SAMPLE_REGS_INTR) {
+                if (sample->intr_regs.abi) {
+                        *array++ = sample->intr_regs.abi;
+                        sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+                        memcpy(array, sample->intr_regs.regs, sz);
+                        array = (void *)array + sz;
+                } else {
+                        *array++ = 0;
+                }
+        }
+
         return 0;
 }
 
@@ -1940,7 +1968,7 @@ static int sample_type__fprintf(FILE *fp, bool *first, u64 value)
                 bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
                 bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
                 bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
-                bit_name(IDENTIFIER),
+                bit_name(IDENTIFIER), bit_name(REGS_INTR),
                 { .name = NULL, }
         };
 #undef bit_name
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 163c5604e5d1..38622747d130 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -36,6 +36,9 @@ struct perf_sample_id {
         struct hlist_node       node;
         u64                     id;
         struct perf_evsel       *evsel;
+        int                     idx;
+        int                     cpu;
+        pid_t                   tid;
 
         /* Holds total ID period value for PERF_SAMPLE_READ processing. */
         u64                     period;
@@ -54,6 +57,7 @@ struct cgroup_sel;
  * @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID or
  *          PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if sample_id_all
  *          is used there is an id sample appended to non-sample events
+ * @priv:   And what is in its containing unnamed union are tool specific
  */
 struct perf_evsel {
         struct list_head        node;
@@ -69,10 +73,12 @@ struct perf_evsel {
         char                    *name;
         double                  scale;
         const char              *unit;
+        bool                    snapshot;
         struct event_format     *tp_format;
         union {
                 void            *priv;
                 off_t           id_offset;
+                u64             db_id;
         };
         struct cgroup_sel       *cgrp;
         void                    *handler;
@@ -86,6 +92,8 @@ struct perf_evsel {
         bool                    immediate;
         bool                    system_wide;
         bool                    tracking;
+        bool                    per_pkg;
+        unsigned long           *per_pkg_mask;
         /* parse modifier helper */
         int                     exclude_GH;
         int                     nr_members;
@@ -105,6 +113,12 @@ struct thread_map;
 struct perf_evlist;
 struct record_opts;
 
+void perf_counts_values__scale(struct perf_counts_values *count,
+                               bool scale, s8 *pscaled);
+
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+                                struct perf_counts_values *count);
+
 int perf_evsel__object_config(size_t object_size,
                               int (*init)(struct perf_evsel *evsel),
                               void (*fini)(struct perf_evsel *evsel));
@@ -222,6 +236,13 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1,
          (a)->attr.type == (b)->attr.type &&    \
          (a)->attr.config == (b)->attr.config)
 
+typedef int (perf_evsel__read_cb_t)(struct perf_evsel *evsel,
+                                    int cpu, int thread,
+                                    struct perf_counts_values *count);
+
+int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
+                        perf_evsel__read_cb_t cb);
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
                               int cpu, int thread, bool scale);
 
@@ -251,35 +272,6 @@ static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel,
         return __perf_evsel__read_on_cpu(evsel, cpu, thread, true);
 }
 
-int __perf_evsel__read(struct perf_evsel *evsel, int ncpus, int nthreads,
-                       bool scale);
-
-/**
- * perf_evsel__read - Read the aggregate results on all CPUs
- *
- * @evsel - event selector to read value
- * @ncpus - Number of cpus affected, from zero
- * @nthreads - Number of threads affected, from zero
- */
-static inline int perf_evsel__read(struct perf_evsel *evsel,
-                                    int ncpus, int nthreads)
-{
-        return __perf_evsel__read(evsel, ncpus, nthreads, false);
-}
-
-/**
- * perf_evsel__read_scaled - Read the aggregate results on all CPUs, scaled
- *
- * @evsel - event selector to read value
- * @ncpus - Number of cpus affected, from zero
- * @nthreads - Number of threads affected, from zero
- */
-static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
-                                          int ncpus, int nthreads)
-{
-        return __perf_evsel__read(evsel, ncpus, nthreads, true);
-}
-
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                              struct perf_sample *sample);
 
diff --git a/tools/perf/util/find-vdso-map.c b/tools/perf/util/find-vdso-map.c
new file mode 100644
index 000000000000..95ef1cffc056
--- /dev/null
+++ b/tools/perf/util/find-vdso-map.c
@@ -0,0 +1,30 @@
+static int find_vdso_map(void **start, void **end)
+{
+        FILE *maps;
+        char line[128];
+        int found = 0;
+
+        maps = fopen("/proc/self/maps", "r");
+        if (!maps) {
+                fprintf(stderr, "vdso: cannot open maps\n");
+                return -1;
+        }
+
+        while (!found && fgets(line, sizeof(line), maps)) {
+                int m = -1;
+
+                /* We care only about private r-x mappings. */
+                if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n",
+                                start, end, &m))
+                        continue;
+                if (m < 0)
+                        continue;
+
+                if (!strncmp(&line[m], VDSO__MAP_NAME,
+                             sizeof(VDSO__MAP_NAME) - 1))
+                        found = 1;
+        }
+
+        fclose(maps);
+        return !found;
+}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 26f5b2fe5dc8..b20e40c74468 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -24,8 +24,6 @@
 #include "build-id.h"
 #include "data.h"
 
-static bool no_buildid_cache = false;
-
 static u32 header_argc;
 static const char **header_argv;
 
@@ -79,10 +77,7 @@ static int do_write(int fd, const void *buf, size_t size)
         return 0;
 }
 
-#define NAME_ALIGN 64
-
-static int write_padded(int fd, const void *bf, size_t count,
-                        size_t count_aligned)
+int write_padded(int fd, const void *bf, size_t count, size_t count_aligned)
 {
         static const char zero_buf[NAME_ALIGN];
         int err = do_write(fd, bf, count);
@@ -171,340 +166,6 @@ perf_header__set_cmdline(int argc, const char **argv)
         return 0;
 }
 
-#define dsos__for_each_with_build_id(pos, head) \
-        list_for_each_entry(pos, head, node)    \
-                if (!pos->has_build_id)         \
-                        continue;               \
-                else
-
-static int write_buildid(const char *name, size_t name_len, u8 *build_id,
-                         pid_t pid, u16 misc, int fd)
-{
-        int err;
-        struct build_id_event b;
-        size_t len;
-
-        len = name_len + 1;
-        len = PERF_ALIGN(len, NAME_ALIGN);
-
-        memset(&b, 0, sizeof(b));
-        memcpy(&b.build_id, build_id, BUILD_ID_SIZE);
-        b.pid = pid;
-        b.header.misc = misc;
-        b.header.size = sizeof(b) + len;
-
-        err = do_write(fd, &b, sizeof(b));
-        if (err < 0)
-                return err;
-
-        return write_padded(fd, name, name_len + 1, len);
-}
-
-static int __dsos__hit_all(struct list_head *head)
-{
-        struct dso *pos;
-
-        list_for_each_entry(pos, head, node)
-                pos->hit = true;
-
-        return 0;
-}
-
-static int machine__hit_all_dsos(struct machine *machine)
-{
-        int err;
-
-        err = __dsos__hit_all(&machine->kernel_dsos.head);
-        if (err)
-                return err;
-
-        return __dsos__hit_all(&machine->user_dsos.head);
-}
-
-int dsos__hit_all(struct perf_session *session)
-{
-        struct rb_node *nd;
-        int err;
-
-        err = machine__hit_all_dsos(&session->machines.host);
-        if (err)
-                return err;
-
-        for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
-                struct machine *pos = rb_entry(nd, struct machine, rb_node);
-
-                err = machine__hit_all_dsos(pos);
-                if (err)
-                        return err;
-        }
-
-        return 0;
-}
-
-static int __dsos__write_buildid_table(struct list_head *head,
-                                       struct machine *machine,
-                                       pid_t pid, u16 misc, int fd)
-{
-        char nm[PATH_MAX];
-        struct dso *pos;
-
-        dsos__for_each_with_build_id(pos, head) {
-                int err;
-                const char *name;
-                size_t name_len;
-
-                if (!pos->hit)
-                        continue;
-
-                if (dso__is_vdso(pos)) {
-                        name = pos->short_name;
-                        name_len = pos->short_name_len + 1;
-                } else if (dso__is_kcore(pos)) {
-                        machine__mmap_name(machine, nm, sizeof(nm));
-                        name = nm;
-                        name_len = strlen(nm) + 1;
-                } else {
-                        name = pos->long_name;
-                        name_len = pos->long_name_len + 1;
-                }
-
-                err = write_buildid(name, name_len, pos->build_id,
-                                    pid, misc, fd);
-                if (err)
-                        return err;
-        }
-
-        return 0;
-}
-
-static int machine__write_buildid_table(struct machine *machine, int fd)
-{
-        int err;
-        u16 kmisc = PERF_RECORD_MISC_KERNEL,
-            umisc = PERF_RECORD_MISC_USER;
-
-        if (!machine__is_host(machine)) {
-                kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
-                umisc = PERF_RECORD_MISC_GUEST_USER;
-        }
-
-        err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine,
-                                          machine->pid, kmisc, fd);
-        if (err == 0)
-                err = __dsos__write_buildid_table(&machine->user_dsos.head,
-                                                  machine, machine->pid, umisc,
-                                                  fd);
-        return err;
-}
-
-static int dsos__write_buildid_table(struct perf_header *header, int fd)
-{
-        struct perf_session *session = container_of(header,
-                        struct perf_session, header);
-        struct rb_node *nd;
-        int err = machine__write_buildid_table(&session->machines.host, fd);
-
-        if (err)
-                return err;
-
-        for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
-                struct machine *pos = rb_entry(nd, struct machine, rb_node);
-                err = machine__write_buildid_table(pos, fd);
-                if (err)
-                        break;
-        }
-        return err;
-}
-
-int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
-                          const char *name, bool is_kallsyms, bool is_vdso)
-{
-        const size_t size = PATH_MAX;
-        char *realname, *filename = zalloc(size),
-             *linkname = zalloc(size), *targetname;
-        int len, err = -1;
-        bool slash = is_kallsyms || is_vdso;
-
-        if (is_kallsyms) {
-                if (symbol_conf.kptr_restrict) {
-                        pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
-                        err = 0;
-                        goto out_free;
-                }
-                realname = (char *) name;
-        } else
-                realname = realpath(name, NULL);
-
-        if (realname == NULL || filename == NULL || linkname == NULL)
-                goto out_free;
-
-        len = scnprintf(filename, size, "%s%s%s",
-                       debugdir, slash ? "/" : "",
-                       is_vdso ? DSO__NAME_VDSO : realname);
-        if (mkdir_p(filename, 0755))
-                goto out_free;
-
-        snprintf(filename + len, size - len, "/%s", sbuild_id);
-
-        if (access(filename, F_OK)) {
-                if (is_kallsyms) {
-                         if (copyfile("/proc/kallsyms", filename))
-                                goto out_free;
-                } else if (link(realname, filename) && copyfile(name, filename))
-                        goto out_free;
-        }
-
-        len = scnprintf(linkname, size, "%s/.build-id/%.2s",
-                       debugdir, sbuild_id);
-
-        if (access(linkname, X_OK) && mkdir_p(linkname, 0755))
-                goto out_free;
-
-        snprintf(linkname + len, size - len, "/%s", sbuild_id + 2);
-        targetname = filename + strlen(debugdir) - 5;
-        memcpy(targetname, "../..", 5);
-
-        if (symlink(targetname, linkname) == 0)
-                err = 0;
-out_free:
-        if (!is_kallsyms)
-                free(realname);
-        free(filename);
-        free(linkname);
-        return err;
-}
-
-static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
-                                 const char *name, const char *debugdir,
-                                 bool is_kallsyms, bool is_vdso)
-{
-        char sbuild_id[BUILD_ID_SIZE * 2 + 1];
-
-        build_id__sprintf(build_id, build_id_size, sbuild_id);
-
-        return build_id_cache__add_s(sbuild_id, debugdir, name,
-                                     is_kallsyms, is_vdso);
-}
-
-int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
-{
-        const size_t size = PATH_MAX;
-        char *filename = zalloc(size),
-             *linkname = zalloc(size);
-        int err = -1;
-
-        if (filename == NULL || linkname == NULL)
-                goto out_free;
-
-        snprintf(linkname, size, "%s/.build-id/%.2s/%s",
-                 debugdir, sbuild_id, sbuild_id + 2);
-
-        if (access(linkname, F_OK))
-                goto out_free;
-
-        if (readlink(linkname, filename, size - 1) < 0)
-                goto out_free;
-
-        if (unlink(linkname))
-                goto out_free;
-
-        /*
-         * Since the link is relative, we must make it absolute:
-         */
-        snprintf(linkname, size, "%s/.build-id/%.2s/%s",
-                 debugdir, sbuild_id, filename);
-
-        if (unlink(linkname))
-                goto out_free;
-
-        err = 0;
-out_free:
-        free(filename);
-        free(linkname);
-        return err;
-}
-
-static int dso__cache_build_id(struct dso *dso, struct machine *machine,
-                               const char *debugdir)
-{
-        bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
-        bool is_vdso = dso__is_vdso(dso);
-        const char *name = dso->long_name;
-        char nm[PATH_MAX];
-
-        if (dso__is_kcore(dso)) {
-                is_kallsyms = true;
-                machine__mmap_name(machine, nm, sizeof(nm));
-                name = nm;
-        }
-        return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
-                                     debugdir, is_kallsyms, is_vdso);
-}
-
-static int __dsos__cache_build_ids(struct list_head *head,
-                                   struct machine *machine, const char *debugdir)
-{
-        struct dso *pos;
-        int err = 0;
-
-        dsos__for_each_with_build_id(pos, head)
-                if (dso__cache_build_id(pos, machine, debugdir))
-                        err = -1;
-
-        return err;
-}
-
-static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
-{
-        int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine,
-                                          debugdir);
-        ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine,
-                                       debugdir);
-        return ret;
-}
-
-static int perf_session__cache_build_ids(struct perf_session *session)
-{
-        struct rb_node *nd;
-        int ret;
-        char debugdir[PATH_MAX];
-
-        snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
-
-        if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
-                return -1;
-
-        ret = machine__cache_build_ids(&session->machines.host, debugdir);
-
-        for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
-                struct machine *pos = rb_entry(nd, struct machine, rb_node);
-                ret |= machine__cache_build_ids(pos, debugdir);
-        }
-        return ret ? -1 : 0;
-}
-
-static bool machine__read_build_ids(struct machine *machine, bool with_hits)
-{
-        bool ret;
-
-        ret  = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits);
-        ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits);
-        return ret;
-}
-
-static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
-{
-        struct rb_node *nd;
-        bool ret = machine__read_build_ids(&session->machines.host, with_hits);
-
-        for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
-                struct machine *pos = rb_entry(nd, struct machine, rb_node);
-                ret |= machine__read_build_ids(pos, with_hits);
-        }
-
-        return ret;
-}
-
 static int write_tracing_data(int fd, struct perf_header *h __maybe_unused,
                             struct perf_evlist *evlist)
 {
@@ -523,13 +184,12 @@ static int write_build_id(int fd, struct perf_header *h,
         if (!perf_session__read_build_ids(session, true))
                 return -1;
 
-        err = dsos__write_buildid_table(h, fd);
+        err = perf_session__write_buildid_table(session, fd);
         if (err < 0) {
                 pr_debug("failed to write buildid table\n");
                 return err;
         }
-        if (!no_buildid_cache)
-                perf_session__cache_build_ids(session);
+        perf_session__cache_build_ids(session);
 
         return 0;
 }
@@ -601,8 +261,10 @@ static int __write_cpudesc(int fd, const char *cpuinfo_proc)
                         break;
         }
 
-        if (ret)
+        if (ret) {
+                ret = -1;
                 goto done;
+        }
 
         s = buf;
 
@@ -965,7 +627,8 @@ static int write_total_mem(int fd, struct perf_header *h __maybe_unused,
                 n = sscanf(buf, "%*s %"PRIu64, &mem);
                 if (n == 1)
                         ret = do_write(fd, &mem, sizeof(mem));
-        }
+        } else
+                ret = -1;
         free(buf);
         fclose(fp);
         return ret;
@@ -1603,7 +1266,7 @@ static int __event_process_build_id(struct build_id_event *bev,
 
                 dso__set_build_id(dso, &bev->build_id);
 
-                if (filename[0] == '[')
+                if (!is_kernel_module(filename, NULL))
                         dso->kernel = dso_type;
 
                 build_id__sprintf(dso->build_id, sizeof(dso->build_id),
@@ -2477,6 +2140,7 @@ static const int attr_file_abi_sizes[] = {
         [1] = PERF_ATTR_SIZE_VER1,
         [2] = PERF_ATTR_SIZE_VER2,
         [3] = PERF_ATTR_SIZE_VER3,
+        [4] = PERF_ATTR_SIZE_VER4,
         0,
 };
 
@@ -3124,8 +2788,3 @@ int perf_event__process_build_id(struct perf_tool *tool __maybe_unused,
                                  session);
         return 0;
 }
-
-void disable_buildid_cache(void)
-{
-        no_buildid_cache = true;
-}
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 8f5cbaea64a5..3bb90ac172a1 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -122,10 +122,6 @@ int perf_header__process_sections(struct perf_header *header, int fd,
 
 int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full);
 
-int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
-                          const char *name, bool is_kallsyms, bool is_vdso);
-int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
-
 int perf_event__synthesize_attr(struct perf_tool *tool,
                                 struct perf_event_attr *attr, u32 ids, u64 *id,
                                 perf_event__handler_t process);
@@ -151,7 +147,9 @@ int perf_event__process_build_id(struct perf_tool *tool,
                                  struct perf_session *session);
 bool is_perf_magic(u64 magic);
 
-int dsos__hit_all(struct perf_session *session);
+#define NAME_ALIGN 64
+
+int write_padded(int fd, const void *bf, size_t count, size_t count_aligned);
 
 /*
  * arch specific callback
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6e88b9e395df..182395546ddc 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -6,6 +6,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "annotate.h"
+#include "ui/progress.h"
 #include <math.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -303,7 +304,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
         size_t callchain_size = 0;
         struct hist_entry *he;
 
-        if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain)
+        if (symbol_conf.use_callchain)
                 callchain_size = sizeof(struct callchain_root);
 
         he = zalloc(sizeof(*he) + callchain_size);
@@ -736,7 +737,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
         iter->he = he;
         he_cache[iter->curr++] = he;
 
-        callchain_append(he->callchain, &callchain_cursor, sample->period);
+        hist_entry__append_callchain(he, sample);
 
         /*
          * We need to re-initialize the cursor since callchain_append()
@@ -809,7 +810,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
         iter->he = he;
         he_cache[iter->curr++] = he;
 
-        callchain_append(he->callchain, &cursor, sample->period);
+        if (symbol_conf.use_callchain)
+                callchain_append(he->callchain, &cursor, sample->period);
         return 0;
 }
 
@@ -945,6 +947,7 @@ void hist_entry__free(struct hist_entry *he)
         zfree(&he->mem_info);
         zfree(&he->stat_acc);
         free_srcline(he->srcline);
+        free_callchain(he->callchain);
         free(he);
 }
 
@@ -987,6 +990,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
                 else
                         p = &(*p)->rb_right;
         }
+        hists->nr_entries++;
 
         rb_link_node(&he->rb_node_in, parent, p);
         rb_insert_color(&he->rb_node_in, root);
@@ -1024,7 +1028,10 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
         if (!sort__need_collapse)
                 return;
 
+        hists->nr_entries = 0;
+
         root = hists__get_rotate_entries_in(hists);
+
         next = rb_first(root);
 
         while (next) {
@@ -1119,7 +1126,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
         rb_insert_color(&he->rb_node, entries);
 }
 
-void hists__output_resort(struct hists *hists)
+void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 {
         struct rb_root *root;
         struct rb_node *next;
@@ -1148,6 +1155,9 @@ void hists__output_resort(struct hists *hists)
 
                 if (!n->filtered)
                         hists__calc_col_len(hists, n);
+
+                if (prog)
+                        ui_progress__update(prog, 1);
         }
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d0ef9a19a744..46bd50344f85 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -121,7 +121,7 @@ int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size,
                               struct hists *hists);
 void hist_entry__free(struct hist_entry *);
 
-void hists__output_resort(struct hists *hists);
+void hists__output_resort(struct hists *hists, struct ui_progress *prog);
 void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
diff --git a/tools/perf/util/hweight.c b/tools/perf/util/hweight.c
deleted file mode 100644
index 5c1d0d099f0d..000000000000
--- a/tools/perf/util/hweight.c
+++ /dev/null
@@ -1,31 +0,0 @@
-#include <linux/bitops.h>
-
-/**
- * hweightN - returns the hamming weight of a N-bit word
- * @x: the word to weigh
- *
- * The Hamming Weight of a number is the total number of bits set in it.
- */
-
-unsigned int hweight32(unsigned int w)
-{
-        unsigned int res = w - ((w >> 1) & 0x55555555);
-        res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
-        res = (res + (res >> 4)) & 0x0F0F0F0F;
-        res = res + (res >> 8);
-        return (res + (res >> 16)) & 0x000000FF;
-}
-
-unsigned long hweight64(__u64 w)
-{
-#if BITS_PER_LONG == 32
-        return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w);
-#elif BITS_PER_LONG == 64
-        __u64 res = w - ((w >> 1) & 0x5555555555555555ul);
-        res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
-        res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
-        res = res + (res >> 8);
-        res = res + (res >> 16);
-        return (res + (res >> 32)) & 0x00000000000000FFul;
-#endif
-}
diff --git a/tools/perf/util/include/asm/hash.h b/tools/perf/util/include/asm/hash.h
deleted file mode 100644
index d82b170bb216..000000000000
--- a/tools/perf/util/include/asm/hash.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_GENERIC_HASH_H
-#define __ASM_GENERIC_HASH_H
-
-/* Stub */
-
-#endif /* __ASM_GENERIC_HASH_H */
diff --git a/tools/perf/util/include/asm/hweight.h b/tools/perf/util/include/asm/hweight.h
deleted file mode 100644
index 36cf26d434a5..000000000000
--- a/tools/perf/util/include/asm/hweight.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef PERF_HWEIGHT_H
-#define PERF_HWEIGHT_H
-
-#include <linux/types.h>
-unsigned int hweight32(unsigned int w);
-unsigned long hweight64(__u64 w);
-
-#endif /* PERF_HWEIGHT_H */
diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h
index 01ffd12dc791..40bd21488032 100644
--- a/tools/perf/util/include/linux/bitmap.h
+++ b/tools/perf/util/include/linux/bitmap.h
@@ -46,4 +46,21 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
                 __bitmap_or(dst, src1, src2, nbits);
 }
 
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ */
+static inline int test_and_set_bit(int nr, unsigned long *addr)
+{
+        unsigned long mask = BIT_MASK(nr);
+        unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+        unsigned long old;
+
+        old = *p;
+        *p = old | mask;
+
+        return (old & mask) != 0;
+}
+
 #endif /* _PERF_BITOPS_H */
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
deleted file mode 100644
index dadfa7e54287..000000000000
--- a/tools/perf/util/include/linux/bitops.h
+++ /dev/null
@@ -1,160 +0,0 @@
-#ifndef _PERF_LINUX_BITOPS_H_
-#define _PERF_LINUX_BITOPS_H_
-
-#include <linux/kernel.h>
-#include <linux/compiler.h>
-#include <asm/hweight.h>
-
-#ifndef __WORDSIZE
-#define __WORDSIZE (__SIZEOF_LONG__ * 8)
-#endif
-
-#define BITS_PER_LONG __WORDSIZE
-#define BITS_PER_BYTE           8
-#define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
-#define BITS_TO_U64(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
-#define BITS_TO_U32(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
-#define BITS_TO_BYTES(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE)
-
-#define for_each_set_bit(bit, addr, size) \
-        for ((bit) = find_first_bit((addr), (size));            \
-             (bit) < (size);                                    \
-             (bit) = find_next_bit((addr), (size), (bit) + 1))
-
-/* same as for_each_set_bit() but use bit as value to start with */
-#define for_each_set_bit_from(bit, addr, size) \
-        for ((bit) = find_next_bit((addr), (size), (bit));      \
-             (bit) < (size);                                    \
-             (bit) = find_next_bit((addr), (size), (bit) + 1))
-
-static inline void set_bit(int nr, unsigned long *addr)
-{
-        addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG);
-}
-
-static inline void clear_bit(int nr, unsigned long *addr)
-{
-        addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG));
-}
-
-static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
-{
-        return ((1UL << (nr % BITS_PER_LONG)) &
-                (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
-}
-
-static inline unsigned long hweight_long(unsigned long w)
-{
-        return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
-}
-
-#define BITOP_WORD(nr)          ((nr) / BITS_PER_LONG)
-
-/**
- * __ffs - find first bit in word.
- * @word: The word to search
- *
- * Undefined if no bit exists, so code should check against 0 first.
- */
-static __always_inline unsigned long __ffs(unsigned long word)
-{
-        int num = 0;
-
-#if BITS_PER_LONG == 64
-        if ((word & 0xffffffff) == 0) {
-                num += 32;
-                word >>= 32;
-        }
-#endif
-        if ((word & 0xffff) == 0) {
-                num += 16;
-                word >>= 16;
-        }
-        if ((word & 0xff) == 0) {
-                num += 8;
-                word >>= 8;
-        }
-        if ((word & 0xf) == 0) {
-                num += 4;
-                word >>= 4;
-        }
-        if ((word & 0x3) == 0) {
-                num += 2;
-                word >>= 2;
-        }
-        if ((word & 0x1) == 0)
-                num += 1;
-        return num;
-}
-
-typedef const unsigned long __attribute__((__may_alias__)) long_alias_t;
-
-/*
- * Find the first set bit in a memory region.
- */
-static inline unsigned long
-find_first_bit(const unsigned long *addr, unsigned long size)
-{
-        long_alias_t *p = (long_alias_t *) addr;
-        unsigned long result = 0;
-        unsigned long tmp;
-
-        while (size & ~(BITS_PER_LONG-1)) {
-                if ((tmp = *(p++)))
-                        goto found;
-                result += BITS_PER_LONG;
-                size -= BITS_PER_LONG;
-        }
-        if (!size)
-                return result;
-
-        tmp = (*p) & (~0UL >> (BITS_PER_LONG - size));
-        if (tmp == 0UL)         /* Are any bits set? */
-                return result + size;   /* Nope. */
-found:
-        return result + __ffs(tmp);
-}
-
-/*
- * Find the next set bit in a memory region.
- */
-static inline unsigned long
-find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset)
-{
-        const unsigned long *p = addr + BITOP_WORD(offset);
-        unsigned long result = offset & ~(BITS_PER_LONG-1);
-        unsigned long tmp;
-
-        if (offset >= size)
-                return size;
-        size -= result;
-        offset %= BITS_PER_LONG;
-        if (offset) {
-                tmp = *(p++);
-                tmp &= (~0UL << offset);
-                if (size < BITS_PER_LONG)
-                        goto found_first;
-                if (tmp)
-                        goto found_middle;
-                size -= BITS_PER_LONG;
-                result += BITS_PER_LONG;
-        }
-        while (size & ~(BITS_PER_LONG-1)) {
-                if ((tmp = *(p++)))
-                        goto found_middle;
-                result += BITS_PER_LONG;
-                size -= BITS_PER_LONG;
-        }
-        if (!size)
-                return result;
-        tmp = *p;
-
-found_first:
-        tmp &= (~0UL >> (BITS_PER_LONG - size));
-        if (tmp == 0UL)         /* Are any bits set? */
-                return result + size;   /* Nope. */
-found_middle:
-        return result + __ffs(tmp);
-}
-
-#endif
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 34fc7c8672e4..1bca3a9f2b16 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -12,6 +12,7 @@
 #include <stdbool.h>
 #include <symbol/kallsyms.h>
 #include "unwind.h"
+#include "linux/hash.h"
 
 static void dsos__init(struct dsos *dsos)
 {
@@ -21,7 +22,7 @@ static void dsos__init(struct dsos *dsos)
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
-        map_groups__init(&machine->kmaps);
+        map_groups__init(&machine->kmaps, machine);
         RB_CLEAR_NODE(&machine->rb_node);
         dsos__init(&machine->user_dsos);
         dsos__init(&machine->kernel_dsos);
@@ -32,7 +33,6 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
         machine->vdso_info = NULL;
 
-        machine->kmaps.machine = machine;
         machine->pid = pid;
 
         machine->symbol_filter = NULL;
@@ -319,7 +319,7 @@ static void machine__update_thread_pid(struct machine *machine,
                 goto out_err;
 
         if (!leader->mg)
-                leader->mg = map_groups__new();
+                leader->mg = map_groups__new(machine);
 
         if (!leader->mg)
                 goto out_err;
@@ -389,7 +389,6 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
         if (th != NULL) {
                 rb_link_node(&th->rb_node, parent, p);
                 rb_insert_color(&th->rb_node, &machine->threads);
-                machine->last_match = th;
 
                 /*
                  * We have to initialize map_groups separately
@@ -400,9 +399,12 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
                  * leader and that would screwed the rb tree.
                  */
                 if (thread__init_map_groups(th, machine)) {
+                        rb_erase(&th->rb_node, &machine->threads);
                         thread__delete(th);
                         return NULL;
                 }
+
+                machine->last_match = th;
         }
 
         return th;
@@ -465,6 +467,7 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 {
         struct map *map;
         struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename);
+        bool compressed;
 
         if (dso == NULL)
                 return NULL;
@@ -477,6 +480,11 @@ struct map *machine__new_module(struct machine *machine, u64 start,
                 dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
         else
                 dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
+
+        /* _KMODULE_COMP should be next to _KMODULE */
+        if (is_kernel_module(filename, &compressed) && compressed)
+                dso->symtab_type++;
+
         map_groups__insert(&machine->kmaps, map);
         return map;
 }
@@ -862,8 +870,14 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg,
                         struct map *map;
                         char *long_name;
 
-                        if (dot == NULL || strcmp(dot, ".ko"))
+                        if (dot == NULL)
                                 continue;
+
+                        /* On some system, modules are compressed like .ko.gz */
+                        if (is_supported_compression(dot + 1) &&
+                            is_kmodule_extension(dot - 2))
+                                dot -= 3;
+
                         snprintf(dso_name, sizeof(dso_name), "[%.*s]",
                                  (int)(dot - dent->d_name), dent->d_name);
 
@@ -1045,6 +1059,11 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
                         dot = strrchr(name, '.');
                         if (dot == NULL)
                                 goto out_problem;
+                        /* On some system, modules are compressed like .ko.gz */
+                        if (is_supported_compression(dot + 1))
+                                dot -= 3;
+                        if (!is_kmodule_extension(dot + 1))
+                                goto out_problem;
                         snprintf(short_module_name, sizeof(short_module_name),
                                         "[%.*s]", (int)(dot - name), name);
                         strxfrchar(short_module_name, '-', '_');
@@ -1069,8 +1088,20 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
                  * Should be there already, from the build-id table in
                  * the header.
                  */
-                struct dso *kernel = __dsos__findnew(&machine->kernel_dsos,
-                                                     kmmap_prefix);
+                struct dso *kernel = NULL;
+                struct dso *dso;
+
+                list_for_each_entry(dso, &machine->kernel_dsos.head, node) {
+                        if (is_kernel_module(dso->long_name, NULL))
+                                continue;
+
+                        kernel = dso;
+                        break;
+                }
+
+                if (kernel == NULL)
+                        kernel = __dsos__findnew(&machine->kernel_dsos,
+                                                 kmmap_prefix);
                 if (kernel == NULL)
                         goto out_problem;
 
@@ -1078,6 +1109,9 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
                 if (__machine__create_kernel_maps(machine, kernel) < 0)
                         goto out_problem;
 
+                if (strstr(kernel->long_name, "vmlinux"))
+                        dso__set_short_name(kernel, "[kernel.vmlinux]", false);
+
                 machine__set_kernel_mmap_len(machine, event);
 
                 /*
@@ -1290,7 +1324,7 @@ static bool symbol__match_regex(struct symbol *sym, regex_t *regex)
         return 0;
 }
 
-static void ip__resolve_ams(struct machine *machine, struct thread *thread,
+static void ip__resolve_ams(struct thread *thread,
                             struct addr_map_symbol *ams,
                             u64 ip)
 {
@@ -1304,7 +1338,7 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread,
          * Thus, we have to try consecutively until we find a match
          * or else, the symbol is unknown
          */
-        thread__find_cpumode_addr_location(thread, machine, MAP__FUNCTION, ip, &al);
+        thread__find_cpumode_addr_location(thread, MAP__FUNCTION, ip, &al);
 
         ams->addr = ip;
         ams->al_addr = al.addr;
@@ -1312,23 +1346,21 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread,
         ams->map = al.map;
 }
 
-static void ip__resolve_data(struct machine *machine, struct thread *thread,
+static void ip__resolve_data(struct thread *thread,
                              u8 m, struct addr_map_symbol *ams, u64 addr)
 {
         struct addr_location al;
 
         memset(&al, 0, sizeof(al));
 
-        thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr,
-                                   &al);
+        thread__find_addr_location(thread, m, MAP__VARIABLE, addr, &al);
         if (al.map == NULL) {
                 /*
                  * some shared data regions have execute bit set which puts
                  * their mapping in the MAP__FUNCTION type array.
                  * Check there as a fallback option before dropping the sample.
                  */
-                thread__find_addr_location(thread, machine, m, MAP__FUNCTION, addr,
-                                           &al);
+                thread__find_addr_location(thread, m, MAP__FUNCTION, addr, &al);
         }
 
         ams->addr = addr;
@@ -1345,14 +1377,72 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
         if (!mi)
                 return NULL;
 
-        ip__resolve_ams(al->machine, al->thread, &mi->iaddr, sample->ip);
-        ip__resolve_data(al->machine, al->thread, al->cpumode,
-                         &mi->daddr, sample->addr);
+        ip__resolve_ams(al->thread, &mi->iaddr, sample->ip);
+        ip__resolve_data(al->thread, al->cpumode, &mi->daddr, sample->addr);
         mi->data_src.val = sample->data_src;
 
         return mi;
 }
 
+static int add_callchain_ip(struct thread *thread,
+                            struct symbol **parent,
+                            struct addr_location *root_al,
+                            bool branch_history,
+                            u64 ip)
+{
+        struct addr_location al;
+
+        al.filtered = 0;
+        al.sym = NULL;
+        if (branch_history)
+                thread__find_cpumode_addr_location(thread, MAP__FUNCTION,
+                                                   ip, &al);
+        else {
+                u8 cpumode = PERF_RECORD_MISC_USER;
+
+                if (ip >= PERF_CONTEXT_MAX) {
+                        switch (ip) {
+                        case PERF_CONTEXT_HV:
+                                cpumode = PERF_RECORD_MISC_HYPERVISOR;
+                                break;
+                        case PERF_CONTEXT_KERNEL:
+                                cpumode = PERF_RECORD_MISC_KERNEL;
+                                break;
+                        case PERF_CONTEXT_USER:
+                                cpumode = PERF_RECORD_MISC_USER;
+                                break;
+                        default:
+                                pr_debug("invalid callchain context: "
+                                         "%"PRId64"\n", (s64) ip);
+                                /*
+                                 * It seems the callchain is corrupted.
+                                 * Discard all.
+                                 */
+                                callchain_cursor_reset(&callchain_cursor);
+                                return 1;
+                        }
+                        return 0;
+                }
+                thread__find_addr_location(thread, cpumode, MAP__FUNCTION,
+                                   ip, &al);
+        }
+
+        if (al.sym != NULL) {
+                if (sort__has_parent && !*parent &&
+                    symbol__match_regex(al.sym, &parent_regex))
+                        *parent = al.sym;
+                else if (have_ignore_callees && root_al &&
+                  symbol__match_regex(al.sym, &ignore_callees_regex)) {
+                        /* Treat this symbol as the root,
+                           forgetting its callees. */
+                        *root_al = al;
+                        callchain_cursor_reset(&callchain_cursor);
+                }
+        }
+
+        return callchain_cursor_append(&callchain_cursor, al.addr, al.map, al.sym);
+}
+
 struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
                                            struct addr_location *al)
 {
@@ -1364,43 +1454,140 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
                 return NULL;
 
         for (i = 0; i < bs->nr; i++) {
-                ip__resolve_ams(al->machine, al->thread, &bi[i].to, bs->entries[i].to);
-                ip__resolve_ams(al->machine, al->thread, &bi[i].from, bs->entries[i].from);
+                ip__resolve_ams(al->thread, &bi[i].to, bs->entries[i].to);
+                ip__resolve_ams(al->thread, &bi[i].from, bs->entries[i].from);
                 bi[i].flags = bs->entries[i].flags;
         }
         return bi;
 }
 
-static int machine__resolve_callchain_sample(struct machine *machine,
-                                             struct thread *thread,
+#define CHASHSZ 127
+#define CHASHBITS 7
+#define NO_ENTRY 0xff
+
+#define PERF_MAX_BRANCH_DEPTH 127
+
+/* Remove loops. */
+static int remove_loops(struct branch_entry *l, int nr)
+{
+        int i, j, off;
+        unsigned char chash[CHASHSZ];
+
+        memset(chash, NO_ENTRY, sizeof(chash));
+
+        BUG_ON(PERF_MAX_BRANCH_DEPTH > 255);
+
+        for (i = 0; i < nr; i++) {
+                int h = hash_64(l[i].from, CHASHBITS) % CHASHSZ;
+
+                /* no collision handling for now */
+                if (chash[h] == NO_ENTRY) {
+                        chash[h] = i;
+                } else if (l[chash[h]].from == l[i].from) {
+                        bool is_loop = true;
+                        /* check if it is a real loop */
+                        off = 0;
+                        for (j = chash[h]; j < i && i + off < nr; j++, off++)
+                                if (l[j].from != l[i + off].from) {
+                                        is_loop = false;
+                                        break;
+                                }
+                        if (is_loop) {
+                                memmove(l + i, l + i + off,
+                                        (nr - (i + off)) * sizeof(*l));
+                                nr -= off;
+                        }
+                }
+        }
+        return nr;
+}
+
+static int thread__resolve_callchain_sample(struct thread *thread,
                                              struct ip_callchain *chain,
+                                             struct branch_stack *branch,
                                              struct symbol **parent,
                                              struct addr_location *root_al,
                                              int max_stack)
 {
-        u8 cpumode = PERF_RECORD_MISC_USER;
         int chain_nr = min(max_stack, (int)chain->nr);
-        int i;
-        int j;
-        int err;
-        int skip_idx __maybe_unused;
+        int i, j, err;
+        int skip_idx = -1;
+        int first_call = 0;
+
+        /*
+         * Based on DWARF debug information, some architectures skip
+         * a callchain entry saved by the kernel.
+         */
+        if (chain->nr < PERF_MAX_STACK_DEPTH)
+                skip_idx = arch_skip_callchain_idx(thread, chain);
 
         callchain_cursor_reset(&callchain_cursor);
 
+        /*
+         * Add branches to call stack for easier browsing. This gives
+         * more context for a sample than just the callers.
+         *
+         * This uses individual histograms of paths compared to the
+         * aggregated histograms the normal LBR mode uses.
+         *
+         * Limitations for now:
+         * - No extra filters
+         * - No annotations (should annotate somehow)
+         */
+
+        if (branch && callchain_param.branch_callstack) {
+                int nr = min(max_stack, (int)branch->nr);
+                struct branch_entry be[nr];
+
+                if (branch->nr > PERF_MAX_BRANCH_DEPTH) {
+                        pr_warning("corrupted branch chain. skipping...\n");
+                        goto check_calls;
+                }
+
+                for (i = 0; i < nr; i++) {
+                        if (callchain_param.order == ORDER_CALLEE) {
+                                be[i] = branch->entries[i];
+                                /*
+                                 * Check for overlap into the callchain.
+                                 * The return address is one off compared to
+                                 * the branch entry. To adjust for this
+                                 * assume the calling instruction is not longer
+                                 * than 8 bytes.
+                                 */
+                                if (i == skip_idx ||
+                                    chain->ips[first_call] >= PERF_CONTEXT_MAX)
+                                        first_call++;
+                                else if (be[i].from < chain->ips[first_call] &&
+                                    be[i].from >= chain->ips[first_call] - 8)
+                                        first_call++;
+                        } else
+                                be[i] = branch->entries[branch->nr - i - 1];
+                }
+
+                nr = remove_loops(be, nr);
+
+                for (i = 0; i < nr; i++) {
+                        err = add_callchain_ip(thread, parent, root_al,
+                                               true, be[i].to);
+                        if (!err)
+                                err = add_callchain_ip(thread, parent, root_al,
+                                                       true, be[i].from);
+                        if (err == -EINVAL)
+                                break;
+                        if (err)
+                                return err;
+                }
+                chain_nr -= nr;
+        }
+
+check_calls:
         if (chain->nr > PERF_MAX_STACK_DEPTH) {
                 pr_warning("corrupted callchain. skipping...\n");
                 return 0;
         }
 
-        /*
-         * Based on DWARF debug information, some architectures skip
-         * a callchain entry saved by the kernel.
-         */
-        skip_idx = arch_skip_callchain_idx(machine, thread, chain);
-
-        for (i = 0; i < chain_nr; i++) {
+        for (i = first_call; i < chain_nr; i++) {
                 u64 ip;
-                struct addr_location al;
 
                 if (callchain_param.order == ORDER_CALLEE)
                         j = i;
@@ -1413,50 +1600,10 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 #endif
                 ip = chain->ips[j];
 
-                if (ip >= PERF_CONTEXT_MAX) {
-                        switch (ip) {
-                        case PERF_CONTEXT_HV:
-                                cpumode = PERF_RECORD_MISC_HYPERVISOR;
-                                break;
-                        case PERF_CONTEXT_KERNEL:
-                                cpumode = PERF_RECORD_MISC_KERNEL;
-                                break;
-                        case PERF_CONTEXT_USER:
-                                cpumode = PERF_RECORD_MISC_USER;
-                                break;
-                        default:
-                                pr_debug("invalid callchain context: "
-                                         "%"PRId64"\n", (s64) ip);
-                                /*
-                                 * It seems the callchain is corrupted.
-                                 * Discard all.
-                                 */
-                                callchain_cursor_reset(&callchain_cursor);
-                                return 0;
-                        }
-                        continue;
-                }
+                err = add_callchain_ip(thread, parent, root_al, false, ip);
 
-                al.filtered = 0;
-                thread__find_addr_location(thread, machine, cpumode,
-                                           MAP__FUNCTION, ip, &al);
-                if (al.sym != NULL) {
-                        if (sort__has_parent && !*parent &&
-                            symbol__match_regex(al.sym, &parent_regex))
-                                *parent = al.sym;
-                        else if (have_ignore_callees && root_al &&
-                          symbol__match_regex(al.sym, &ignore_callees_regex)) {
-                                /* Treat this symbol as the root,
-                                   forgetting its callees. */
-                                *root_al = al;
-                                callchain_cursor_reset(&callchain_cursor);
-                        }
-                }
-
-                err = callchain_cursor_append(&callchain_cursor,
-                                              ip, al.map, al.sym);
                 if (err)
-                        return err;
+                        return (err < 0) ? err : 0;
         }
 
         return 0;
@@ -1469,19 +1616,16 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
                                        entry->map, entry->sym);
 }
 
-int machine__resolve_callchain(struct machine *machine,
-                               struct perf_evsel *evsel,
-                               struct thread *thread,
-                               struct perf_sample *sample,
-                               struct symbol **parent,
-                               struct addr_location *root_al,
-                               int max_stack)
+int thread__resolve_callchain(struct thread *thread,
+                              struct perf_evsel *evsel,
+                              struct perf_sample *sample,
+                              struct symbol **parent,
+                              struct addr_location *root_al,
+                              int max_stack)
 {
-        int ret;
-
-        ret = machine__resolve_callchain_sample(machine, thread,
-                                                sample->callchain, parent,
-                                                root_al, max_stack);
+        int ret = thread__resolve_callchain_sample(thread, sample->callchain,
+                                                   sample->branch_stack,
+                                                   parent, root_al, max_stack);
         if (ret)
                 return ret;
 
@@ -1495,7 +1639,7 @@ int machine__resolve_callchain(struct machine *machine,
             (!sample->user_stack.size))
                 return 0;
 
-        return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
+        return unwind__get_entries(unwind_entry, &callchain_cursor,
                                    thread, sample, max_stack);
 
 }
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 2b651a7f5d0d..e8b7779a0a3f 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -40,6 +40,10 @@ struct machine {
         u64               kernel_start;
         symbol_filter_t   symbol_filter;
         pid_t             *current_tid;
+        union { /* Tool specific area */
+                void      *priv;
+                u64       db_id;
+        };
 };
 
 static inline
@@ -122,13 +126,12 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
                                            struct addr_location *al);
 struct mem_info *sample__resolve_mem(struct perf_sample *sample,
                                      struct addr_location *al);
-int machine__resolve_callchain(struct machine *machine,
-                               struct perf_evsel *evsel,
-                               struct thread *thread,
-                               struct perf_sample *sample,
-                               struct symbol **parent,
-                               struct addr_location *root_al,
-                               int max_stack);
+int thread__resolve_callchain(struct thread *thread,
+                              struct perf_evsel *evsel,
+                              struct perf_sample *sample,
+                              struct symbol **parent,
+                              struct addr_location *root_al,
+                              int max_stack);
 
 /*
  * Default guest kernel is defined by parameter --guestkallsyms
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 2137c4596ec7..62ca9f2607d5 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -360,7 +360,7 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 
         if (map && map->dso) {
                 srcline = get_srcline(map->dso,
-                                      map__rip_2objdump(map, addr));
+                                      map__rip_2objdump(map, addr), NULL, true);
                 if (srcline != SRCLINE_UNKNOWN)
                         ret = fprintf(fp, "%s%s", prefix, srcline);
                 free_srcline(srcline);
@@ -413,14 +413,14 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
         return ip + map->reloc;
 }
 
-void map_groups__init(struct map_groups *mg)
+void map_groups__init(struct map_groups *mg, struct machine *machine)
 {
         int i;
         for (i = 0; i < MAP__NR_TYPES; ++i) {
                 mg->maps[i] = RB_ROOT;
                 INIT_LIST_HEAD(&mg->removed_maps[i]);
         }
-        mg->machine = NULL;
+        mg->machine = machine;
         mg->refcnt = 1;
 }
 
@@ -471,12 +471,12 @@ bool map_groups__empty(struct map_groups *mg)
         return true;
 }
 
-struct map_groups *map_groups__new(void)
+struct map_groups *map_groups__new(struct machine *machine)
 {
         struct map_groups *mg = malloc(sizeof(*mg));
 
         if (mg != NULL)
-                map_groups__init(mg);
+                map_groups__init(mg, machine);
 
         return mg;
 }
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 2f83954af050..6951a9d42339 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -64,7 +64,7 @@ struct map_groups {
         int              refcnt;
 };
 
-struct map_groups *map_groups__new(void);
+struct map_groups *map_groups__new(struct machine *machine);
 void map_groups__delete(struct map_groups *mg);
 bool map_groups__empty(struct map_groups *mg);
 
@@ -150,7 +150,7 @@ void maps__remove(struct rb_root *maps, struct map *map);
 struct map *maps__find(struct rb_root *maps, u64 addr);
 struct map *maps__first(struct rb_root *maps);
 struct map *maps__next(struct map *map);
-void map_groups__init(struct map_groups *mg);
+void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct map_groups *mg,
                       struct map_groups *parent, enum map_type type);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c659a3ca1283..77b43fe43d55 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -681,6 +681,8 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
         if (evsel) {
                 evsel->unit = info.unit;
                 evsel->scale = info.scale;
+                evsel->per_pkg = info.per_pkg;
+                evsel->snapshot = info.snapshot;
         }
 
         return evsel ? 0 : -ENOMEM;
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index bf48092983c6..f62dee7bd924 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -42,7 +42,26 @@ static int get_value(struct parse_opt_ctx_t *p,
                 return opterror(opt, "takes no value", flags);
         if (unset && (opt->flags & PARSE_OPT_NONEG))
                 return opterror(opt, "isn't available", flags);
-
+        if (opt->flags & PARSE_OPT_DISABLED)
+                return opterror(opt, "is not usable", flags);
+
+        if (opt->flags & PARSE_OPT_EXCLUSIVE) {
+                if (p->excl_opt) {
+                        char msg[128];
+
+                        if (((flags & OPT_SHORT) && p->excl_opt->short_name) ||
+                            p->excl_opt->long_name == NULL) {
+                                scnprintf(msg, sizeof(msg), "cannot be used with switch `%c'",
+                                          p->excl_opt->short_name);
+                        } else {
+                                scnprintf(msg, sizeof(msg), "cannot be used with %s",
+                                          p->excl_opt->long_name);
+                        }
+                        opterror(opt, msg, flags);
+                        return -3;
+                }
+                p->excl_opt = opt;
+        }
         if (!(flags & OPT_SHORT) && p->opt) {
                 switch (opt->type) {
                 case OPTION_CALLBACK:
@@ -343,13 +362,14 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
                        const char * const usagestr[])
 {
         int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP);
+        int excl_short_opt = 1;
+        const char *arg;
 
         /* we must reset ->opt, unknown short option leave it dangling */
         ctx->opt = NULL;
 
         for (; ctx->argc; ctx->argc--, ctx->argv++) {
-                const char *arg = ctx->argv[0];
-
+                arg = ctx->argv[0];
                 if (*arg != '-' || !arg[1]) {
                         if (ctx->flags & PARSE_OPT_STOP_AT_NON_OPTION)
                                 break;
@@ -358,19 +378,21 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
                 }
 
                 if (arg[1] != '-') {
-                        ctx->opt = arg + 1;
+                        ctx->opt = ++arg;
                         if (internal_help && *ctx->opt == 'h')
                                 return usage_with_options_internal(usagestr, options, 0);
                         switch (parse_short_opt(ctx, options)) {
                         case -1:
-                                return parse_options_usage(usagestr, options, arg + 1, 1);
+                                return parse_options_usage(usagestr, options, arg, 1);
                         case -2:
                                 goto unknown;
+                        case -3:
+                                goto exclusive;
                         default:
                                 break;
                         }
                         if (ctx->opt)
-                                check_typos(arg + 1, options);
+                                check_typos(arg, options);
                         while (ctx->opt) {
                                 if (internal_help && *ctx->opt == 'h')
                                         return usage_with_options_internal(usagestr, options, 0);
@@ -387,6 +409,8 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
                                         ctx->argv[0] = strdup(ctx->opt - 1);
                                         *(char *)ctx->argv[0] = '-';
                                         goto unknown;
+                                case -3:
+                                        goto exclusive;
                                 default:
                                         break;
                                 }
@@ -402,19 +426,23 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
                         break;
                 }
 
-                if (internal_help && !strcmp(arg + 2, "help-all"))
+                arg += 2;
+                if (internal_help && !strcmp(arg, "help-all"))
                         return usage_with_options_internal(usagestr, options, 1);
-                if (internal_help && !strcmp(arg + 2, "help"))
+                if (internal_help && !strcmp(arg, "help"))
                         return usage_with_options_internal(usagestr, options, 0);
-                if (!strcmp(arg + 2, "list-opts"))
+                if (!strcmp(arg, "list-opts"))
                         return PARSE_OPT_LIST_OPTS;
-                if (!strcmp(arg + 2, "list-cmds"))
+                if (!strcmp(arg, "list-cmds"))
                         return PARSE_OPT_LIST_SUBCMDS;
-                switch (parse_long_opt(ctx, arg + 2, options)) {
+                switch (parse_long_opt(ctx, arg, options)) {
                 case -1:
-                        return parse_options_usage(usagestr, options, arg + 2, 0);
+                        return parse_options_usage(usagestr, options, arg, 0);
                 case -2:
                         goto unknown;
+                case -3:
+                        excl_short_opt = 0;
+                        goto exclusive;
                 default:
                         break;
                 }
@@ -426,6 +454,17 @@ unknown:
                 ctx->opt = NULL;
         }
         return PARSE_OPT_DONE;
+
+exclusive:
+        parse_options_usage(usagestr, options, arg, excl_short_opt);
+        if ((excl_short_opt && ctx->excl_opt->short_name) ||
+            ctx->excl_opt->long_name == NULL) {
+                char opt = ctx->excl_opt->short_name;
+                parse_options_usage(NULL, options, &opt, 1);
+        } else {
+                parse_options_usage(NULL, options, ctx->excl_opt->long_name, 0);
+        }
+        return PARSE_OPT_HELP;
 }
 
 int parse_options_end(struct parse_opt_ctx_t *ctx)
@@ -509,6 +548,8 @@ static void print_option_help(const struct option *opts, int full)
         }
         if (!full && (opts->flags & PARSE_OPT_HIDDEN))
                 return;
+        if (opts->flags & PARSE_OPT_DISABLED)
+                return;
 
         pos = fprintf(stderr, "    ");
         if (opts->short_name)
@@ -679,3 +720,16 @@ int parse_opt_verbosity_cb(const struct option *opt,
         }
         return 0;
 }
+
+void set_option_flag(struct option *opts, int shortopt, const char *longopt,
+                     int flag)
+{
+        for (; opts->type != OPTION_END; opts++) {
+                if ((shortopt && opts->short_name == shortopt) ||
+                    (opts->long_name && longopt &&
+                     !strcmp(opts->long_name, longopt))) {
+                        opts->flags |= flag;
+                        break;
+                }
+        }
+}
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index b59ba858e73d..97b153fb4999 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -38,6 +38,8 @@ enum parse_opt_option_flags {
         PARSE_OPT_NONEG   = 4,
         PARSE_OPT_HIDDEN  = 8,
         PARSE_OPT_LASTARG_DEFAULT = 16,
+        PARSE_OPT_DISABLED = 32,
+        PARSE_OPT_EXCLUSIVE = 64,
 };
 
 struct option;
@@ -173,6 +175,7 @@ struct parse_opt_ctx_t {
         const char **out;
         int argc, cpidx;
         const char *opt;
+        const struct option *excl_opt;
         int flags;
 };
 
@@ -211,4 +214,5 @@ extern int parse_opt_verbosity_cb(const struct option *, const char *, int);
 
 extern const char *parse_options_fix_filename(const char *prefix, const char *file);
 
+void set_option_flag(struct option *opts, int sopt, const char *lopt, int flag);
 #endif /* __PERF_PARSE_OPTIONS_H */
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index e243ad962a4d..5c9c4947cfb4 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -163,6 +163,41 @@ error:
         return -1;
 }
 
+static int
+perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+        char path[PATH_MAX];
+        int fd;
+
+        snprintf(path, PATH_MAX, "%s/%s.per-pkg", dir, name);
+
+        fd = open(path, O_RDONLY);
+        if (fd == -1)
+                return -1;
+
+        close(fd);
+
+        alias->per_pkg = true;
+        return 0;
+}
+
+static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
+                                    char *dir, char *name)
+{
+        char path[PATH_MAX];
+        int fd;
+
+        snprintf(path, PATH_MAX, "%s/%s.snapshot", dir, name);
+
+        fd = open(path, O_RDONLY);
+        if (fd == -1)
+                return -1;
+
+        alias->snapshot = true;
+        close(fd);
+        return 0;
+}
+
 static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
 {
         struct perf_pmu_alias *alias;
@@ -181,6 +216,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
         INIT_LIST_HEAD(&alias->terms);
         alias->scale = 1.0;
         alias->unit[0] = '\0';
+        alias->per_pkg = false;
 
         ret = parse_events_terms(&alias->terms, buf);
         if (ret) {
@@ -194,6 +230,8 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
          */
         perf_pmu__parse_unit(alias, dir, name);
         perf_pmu__parse_scale(alias, dir, name);
+        perf_pmu__parse_per_pkg(alias, dir, name);
+        perf_pmu__parse_snapshot(alias, dir, name);
 
         list_add_tail(&alias->list, list);
 
@@ -209,6 +247,10 @@ static inline bool pmu_alias_info_file(char *name)
                 return true;
         if (len > 6 && !strcmp(name + len - 6, ".scale"))
                 return true;
+        if (len > 8 && !strcmp(name + len - 8, ".per-pkg"))
+                return true;
+        if (len > 9 && !strcmp(name + len - 9, ".snapshot"))
+                return true;
 
         return false;
 }
@@ -617,23 +659,27 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 }
 
 
-static int check_unit_scale(struct perf_pmu_alias *alias,
-                            const char **unit, double *scale)
+static int check_info_data(struct perf_pmu_alias *alias,
+                           struct perf_pmu_info *info)
 {
         /*
          * Only one term in event definition can
-         * define unit and scale, fail if there's
-         * more than one.
+         * define unit, scale and snapshot, fail
+         * if there's more than one.
          */
-        if ((*unit && alias->unit) ||
-            (*scale && alias->scale))
+        if ((info->unit && alias->unit) ||
+            (info->scale && alias->scale) ||
+            (info->snapshot && alias->snapshot))
                 return -EINVAL;
 
         if (alias->unit)
-                *unit = alias->unit;
+                info->unit = alias->unit;
 
         if (alias->scale)
-                *scale = alias->scale;
+                info->scale = alias->scale;
+
+        if (alias->snapshot)
+                info->snapshot = alias->snapshot;
 
         return 0;
 }
@@ -649,12 +695,15 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
         struct perf_pmu_alias *alias;
         int ret;
 
+        info->per_pkg = false;
+
         /*
          * Mark unit and scale as not set
          * (different from default values, see below)
          */
-        info->unit   = NULL;
-        info->scale  = 0.0;
+        info->unit     = NULL;
+        info->scale    = 0.0;
+        info->snapshot = false;
 
         list_for_each_entry_safe(term, h, head_terms, list) {
                 alias = pmu_find_alias(pmu, term);
@@ -664,10 +713,13 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
                 if (ret)
                         return ret;
 
-                ret = check_unit_scale(alias, &info->unit, &info->scale);
+                ret = check_info_data(alias, info);
                 if (ret)
                         return ret;
 
+                if (alias->per_pkg)
+                        info->per_pkg = true;
+
                 list_del(&term->list);
                 free(term);
         }
@@ -747,15 +799,18 @@ void print_pmu_events(const char *event_glob, bool name_only)
 
         pmu = NULL;
         len = 0;
-        while ((pmu = perf_pmu__scan(pmu)) != NULL)
+        while ((pmu = perf_pmu__scan(pmu)) != NULL) {
                 list_for_each_entry(alias, &pmu->aliases, list)
                         len++;
-        aliases = malloc(sizeof(char *) * len);
+                if (pmu->selectable)
+                        len++;
+        }
+        aliases = zalloc(sizeof(char *) * len);
         if (!aliases)
-                return;
+                goto out_enomem;
         pmu = NULL;
         j = 0;
-        while ((pmu = perf_pmu__scan(pmu)) != NULL)
+        while ((pmu = perf_pmu__scan(pmu)) != NULL) {
                 list_for_each_entry(alias, &pmu->aliases, list) {
                         char *name = format_alias(buf, sizeof(buf), pmu, alias);
                         bool is_cpu = !strcmp(pmu->name, "cpu");
@@ -765,13 +820,23 @@ void print_pmu_events(const char *event_glob, bool name_only)
                               (!is_cpu && strglobmatch(alias->name,
                                                        event_glob))))
                                 continue;
-                        aliases[j] = name;
+
                         if (is_cpu && !name_only)
-                                aliases[j] = format_alias_or(buf, sizeof(buf),
-                                                              pmu, alias);
-                        aliases[j] = strdup(aliases[j]);
+                                name = format_alias_or(buf, sizeof(buf), pmu, alias);
+
+                        aliases[j] = strdup(name);
+                        if (aliases[j] == NULL)
+                                goto out_enomem;
                         j++;
                 }
+                if (pmu->selectable) {
+                        char *s;
+                        if (asprintf(&s, "%s//", pmu->name) < 0)
+                                goto out_enomem;
+                        aliases[j] = s;
+                        j++;
+                }
+        }
         len = j;
         qsort(aliases, len, sizeof(char *), cmp_string);
         for (j = 0; j < len; j++) {
@@ -780,12 +845,20 @@ void print_pmu_events(const char *event_glob, bool name_only)
                         continue;
                 }
                 printf("  %-50s [Kernel PMU event]\n", aliases[j]);
-                zfree(&aliases[j]);
                 printed++;
         }
         if (printed)
                 printf("\n");
-        free(aliases);
+out_free:
+        for (j = 0; j < len; j++)
+                zfree(&aliases[j]);
+        zfree(&aliases);
+        return;
+
+out_enomem:
+        printf("FATAL: not enough memory to print PMU events\n");
+        if (aliases)
+                goto out_free;
 }
 
 bool pmu_have_event(const char *pname, const char *name)
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index fe9dfbee8eed..6b1249fbdb5f 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -18,6 +18,7 @@ struct perf_event_attr;
 struct perf_pmu {
         char *name;
         __u32 type;
+        bool selectable;
         struct perf_event_attr *default_config;
         struct cpu_map *cpus;
         struct list_head format;  /* HEAD struct perf_pmu_format -> list */
@@ -28,6 +29,8 @@ struct perf_pmu {
 struct perf_pmu_info {
         const char *unit;
         double scale;
+        bool per_pkg;
+        bool snapshot;
 };
 
 #define UNIT_MAX_LEN    31 /* max length for event unit name */
@@ -38,6 +41,8 @@ struct perf_pmu_alias {
         struct list_head list;  /* ELEM */
         char unit[UNIT_MAX_LEN+1];
         double scale;
+        bool per_pkg;
+        bool snapshot;
 };
 
 struct perf_pmu *perf_pmu__find(const char *name);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index c150ca4343eb..94a717bf007d 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -495,9 +495,11 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
         }
 
         if (ntevs == 0) {       /* No error but failed to find probe point. */
-                pr_warning("Probe point '%s' not found.\n",
+                pr_warning("Probe point '%s' not found in debuginfo.\n",
                            synthesize_perf_probe_point(&pev->point));
-                return -ENOENT;
+                if (need_dwarf)
+                        return -ENOENT;
+                return 0;
         }
         /* Error path : ntevs < 0 */
         pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
@@ -1910,21 +1912,21 @@ static int show_perf_probe_event(struct perf_probe_event *pev,
         if (ret < 0)
                 return ret;
 
-        printf("  %-20s (on %s", buf, place);
+        pr_info("  %-20s (on %s", buf, place);
         if (module)
-                printf(" in %s", module);
+                pr_info(" in %s", module);
 
         if (pev->nargs > 0) {
-                printf(" with");
+                pr_info(" with");
                 for (i = 0; i < pev->nargs; i++) {
                         ret = synthesize_perf_probe_arg(&pev->args[i],
                                                         buf, 128);
                         if (ret < 0)
                                 break;
-                        printf(" %s", buf);
+                        pr_info(" %s", buf);
                 }
         }
-        printf(")\n");
+        pr_info(")\n");
         free(place);
         return ret;
 }
@@ -2050,9 +2052,11 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev)
         pr_debug("Writing event: %s\n", buf);
         if (!probe_event_dry_run) {
                 ret = write(fd, buf, strlen(buf));
-                if (ret <= 0)
+                if (ret <= 0) {
+                        ret = -errno;
                         pr_warning("Failed to write event: %s\n",
                                    strerror_r(errno, sbuf, sizeof(sbuf)));
+                }
         }
         free(buf);
         return ret;
@@ -2124,7 +2128,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
         }
 
         ret = 0;
-        printf("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
+        pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
         for (i = 0; i < ntevs; i++) {
                 tev = &tevs[i];
                 if (pev->event)
@@ -2179,8 +2183,8 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 
         if (ret >= 0) {
                 /* Show how to use the event. */
-                printf("\nYou can now use it in all perf tools, such as:\n\n");
-                printf("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group,
+                pr_info("\nYou can now use it in all perf tools, such as:\n\n");
+                pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group,
                          tev->event);
         }
 
@@ -2444,7 +2448,7 @@ static int __del_trace_probe_event(int fd, struct str_node *ent)
                 goto error;
         }
 
-        printf("Removed event: %s\n", ent->s);
+        pr_info("Removed event: %s\n", ent->s);
         return 0;
 error:
         pr_warning("Failed to delete event: %s\n",
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index c7918f83b300..b5247d777f0e 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -989,8 +989,24 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
         int ret = 0;
 
 #if _ELFUTILS_PREREQ(0, 142)
+        Elf *elf;
+        GElf_Ehdr ehdr;
+        GElf_Shdr shdr;
+
         /* Get the call frame information from this dwarf */
-        pf->cfi = dwarf_getcfi_elf(dwarf_getelf(dbg->dbg));
+        elf = dwarf_getelf(dbg->dbg);
+        if (elf == NULL)
+                return -EINVAL;
+
+        if (gelf_getehdr(elf, &ehdr) == NULL)
+                return -EINVAL;
+
+        if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
+            shdr.sh_type == SHT_PROGBITS) {
+                pf->cfi = dwarf_getcfi_elf(elf);
+        } else {
+                pf->cfi = dwarf_getcfi(dbg->dbg);
+        }
 #endif
 
         off = 0;
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 16a475a7d492..6c6a6953fa93 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,7 +10,7 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
-util/hweight.c
+../../lib/hweight.c
 util/thread_map.c
 util/util.c
 util/xyarray.c
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index cf69325b985f..8acd0df88b5c 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -137,16 +137,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 
 static int get_max_rate(unsigned int *rate)
 {
-        char path[PATH_MAX];
-        const char *procfs = procfs__mountpoint();
-
-        if (!procfs)
-                return -1;
-
-        snprintf(path, PATH_MAX,
-                 "%s/sys/kernel/perf_event_max_sample_rate", procfs);
-
-        return filename__read_int(path, (int *) rate);
+        return sysctl__read_int("kernel/perf_event_max_sample_rate", (int *)rate);
 }
 
 static int record_opts__config_freq(struct record_opts *opts)
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 0a01bac4ce02..22ebc46226e7 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -24,6 +24,7 @@
 #include <string.h>
 #include <ctype.h>
 #include <errno.h>
+#include <linux/bitmap.h>
 
 #include "../util.h"
 #include <EXTERN.h>
@@ -57,7 +58,7 @@ INTERP my_perl;
 #define FTRACE_MAX_EVENT                                \
         ((1 << (sizeof(unsigned short) * 8)) - 1)
 
-struct event_format *events[FTRACE_MAX_EVENT];
+static DECLARE_BITMAP(events_defined, FTRACE_MAX_EVENT);
 
 extern struct scripting_context *scripting_context;
 
@@ -238,35 +239,15 @@ static void define_event_symbols(struct event_format *event,
                 define_event_symbols(event, ev_name, args->next);
 }
 
-static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
-{
-        static char ev_name[256];
-        struct event_format *event;
-        int type = evsel->attr.config;
-
-        if (events[type])
-                return events[type];
-
-        events[type] = event = evsel->tp_format;
-        if (!event)
-                return NULL;
-
-        sprintf(ev_name, "%s::%s", event->system, event->name);
-
-        define_event_symbols(event, ev_name, event->print_fmt.args);
-
-        return event;
-}
-
 static void perl_process_tracepoint(struct perf_sample *sample,
                                     struct perf_evsel *evsel,
                                     struct thread *thread)
 {
+        struct event_format *event = evsel->tp_format;
         struct format_field *field;
         static char handler[256];
         unsigned long long val;
         unsigned long s, ns;
-        struct event_format *event;
         int pid;
         int cpu = sample->cpu;
         void *data = sample->raw_data;
@@ -278,7 +259,6 @@ static void perl_process_tracepoint(struct perf_sample *sample,
         if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
                 return;
 
-        event = find_cache_event(evsel);
         if (!event)
                 die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
 
@@ -286,6 +266,9 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 
         sprintf(handler, "%s::%s", event->system, event->name);
 
+        if (!test_and_set_bit(event->id, events_defined))
+                define_event_symbols(event, handler, event->print_fmt.args);
+
         s = nsecs / NSECS_PER_SEC;
         ns = nsecs - s * NSECS_PER_SEC;
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 496f21cadd97..d808a328f4dc 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -24,7 +24,9 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <stdbool.h>
 #include <errno.h>
+#include <linux/bitmap.h>
 
 #include "../../perf.h"
 #include "../debug.h"
@@ -33,6 +35,10 @@
 #include "../util.h"
 #include "../event.h"
 #include "../thread.h"
+#include "../comm.h"
+#include "../machine.h"
+#include "../db-export.h"
+#include "../thread-stack.h"
 #include "../trace-event.h"
 #include "../machine.h"
 
@@ -41,7 +47,7 @@ PyMODINIT_FUNC initperf_trace_context(void);
 #define FTRACE_MAX_EVENT                                \
         ((1 << (sizeof(unsigned short) * 8)) - 1)
 
-struct event_format *events[FTRACE_MAX_EVENT];
+static DECLARE_BITMAP(events_defined, FTRACE_MAX_EVENT);
 
 #define MAX_FIELDS      64
 #define N_COMMON_FIELDS 7
@@ -53,6 +59,24 @@ static int zero_flag_atom;
 
 static PyObject *main_module, *main_dict;
 
+struct tables {
+        struct db_export        dbe;
+        PyObject                *evsel_handler;
+        PyObject                *machine_handler;
+        PyObject                *thread_handler;
+        PyObject                *comm_handler;
+        PyObject                *comm_thread_handler;
+        PyObject                *dso_handler;
+        PyObject                *symbol_handler;
+        PyObject                *branch_type_handler;
+        PyObject                *sample_handler;
+        PyObject                *call_path_handler;
+        PyObject                *call_return_handler;
+        bool                    db_export_mode;
+};
+
+static struct tables tables_global;
+
 static void handler_call_die(const char *handler_name) NORETURN;
 static void handler_call_die(const char *handler_name)
 {
@@ -232,31 +256,6 @@ static void define_event_symbols(struct event_format *event,
                 define_event_symbols(event, ev_name, args->next);
 }
 
-static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
-{
-        static char ev_name[256];
-        struct event_format *event;
-        int type = evsel->attr.config;
-
-        /*
-         * XXX: Do we really need to cache this since now we have evsel->tp_format
-         * cached already? Need to re-read this "cache" routine that as well calls
-         * define_event_symbols() :-\
-         */
-        if (events[type])
-                return events[type];
-
-        events[type] = event = evsel->tp_format;
-        if (!event)
-                return NULL;
-
-        sprintf(ev_name, "%s__%s", event->system, event->name);
-
-        define_event_symbols(event, ev_name, event->print_fmt.args);
-
-        return event;
-}
-
 static PyObject *get_field_numeric_entry(struct event_format *event,
                 struct format_field *field, void *data)
 {
@@ -312,9 +311,9 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
         if (!symbol_conf.use_callchain || !sample->callchain)
                 goto exit;
 
-        if (machine__resolve_callchain(al->machine, evsel, al->thread,
-                                           sample, NULL, NULL,
-                                           PERF_MAX_STACK_DEPTH) != 0) {
+        if (thread__resolve_callchain(al->thread, evsel,
+                                      sample, NULL, NULL,
+                                      PERF_MAX_STACK_DEPTH) != 0) {
                 pr_err("Failed to resolve callchain. Skipping\n");
                 goto exit;
         }
@@ -380,12 +379,12 @@ static void python_process_tracepoint(struct perf_sample *sample,
                                       struct thread *thread,
                                       struct addr_location *al)
 {
+        struct event_format *event = evsel->tp_format;
         PyObject *handler, *context, *t, *obj, *callchain;
         PyObject *dict = NULL;
         static char handler_name[256];
         struct format_field *field;
         unsigned long s, ns;
-        struct event_format *event;
         unsigned n = 0;
         int pid;
         int cpu = sample->cpu;
@@ -397,7 +396,6 @@ static void python_process_tracepoint(struct perf_sample *sample,
         if (!t)
                 Py_FatalError("couldn't create Python tuple");
 
-        event = find_cache_event(evsel);
         if (!event)
                 die("ug! no event found for type %d", (int)evsel->attr.config);
 
@@ -405,6 +403,9 @@ static void python_process_tracepoint(struct perf_sample *sample,
 
         sprintf(handler_name, "%s__%s", event->system, event->name);
 
+        if (!test_and_set_bit(event->id, events_defined))
+                define_event_symbols(event, handler_name, event->print_fmt.args);
+
         handler = get_handler(handler_name);
         if (!handler) {
                 dict = PyDict_New();
@@ -475,6 +476,289 @@ static void python_process_tracepoint(struct perf_sample *sample,
         Py_DECREF(t);
 }
 
+static PyObject *tuple_new(unsigned int sz)
+{
+        PyObject *t;
+
+        t = PyTuple_New(sz);
+        if (!t)
+                Py_FatalError("couldn't create Python tuple");
+        return t;
+}
+
+static int tuple_set_u64(PyObject *t, unsigned int pos, u64 val)
+{
+#if BITS_PER_LONG == 64
+        return PyTuple_SetItem(t, pos, PyInt_FromLong(val));
+#endif
+#if BITS_PER_LONG == 32
+        return PyTuple_SetItem(t, pos, PyLong_FromLongLong(val));
+#endif
+}
+
+static int tuple_set_s32(PyObject *t, unsigned int pos, s32 val)
+{
+        return PyTuple_SetItem(t, pos, PyInt_FromLong(val));
+}
+
+static int tuple_set_string(PyObject *t, unsigned int pos, const char *s)
+{
+        return PyTuple_SetItem(t, pos, PyString_FromString(s));
+}
+
+static int python_export_evsel(struct db_export *dbe, struct perf_evsel *evsel)
+{
+        struct tables *tables = container_of(dbe, struct tables, dbe);
+        PyObject *t;
+
+        t = tuple_new(2);
+
+        tuple_set_u64(t, 0, evsel->db_id);
+        tuple_set_string(t, 1, perf_evsel__name(evsel));
+
+        call_object(tables->evsel_handler, t, "evsel_table");
+
+        Py_DECREF(t);
+
+        return 0;
+}
+
+static int python_export_machine(struct db_export *dbe,
+                                 struct machine *machine)
+{
+        struct tables *tables = container_of(dbe, struct tables, dbe);
+        PyObject *t;
+
+        t = tuple_new(3);
+
+        tuple_set_u64(t, 0, machine->db_id);
+        tuple_set_s32(t, 1, machine->pid);
+        tuple_set_string(t, 2, machine->root_dir ? machine->root_dir : "");
+
+        call_object(tables->machine_handler, t, "machine_table");
+
+        Py_DECREF(t);
+
+        return 0;
+}
+
+static int python_export_thread(struct db_export *dbe, struct thread *thread,
+                                u64 main_thread_db_id, struct machine *machine)
+{
+        struct tables *tables = container_of(dbe, struct tables, dbe);
+        PyObject *t;
+
+        t = tuple_new(5);
+
+        tuple_set_u64(t, 0, thread->db_id);
+        tuple_set_u64(t, 1, machine->db_id);
+        tuple_set_u64(t, 2, main_thread_db_id);
+        tuple_set_s32(t, 3, thread->pid_);
+        tuple_set_s32(t, 4, thread->tid);
+
+        call_object(tables->thread_handler, t, "thread_table");
+
+        Py_DECREF(t);
+
+        return 0;
+}
+
+static int python_export_comm(struct db_export *dbe, struct comm *comm)
+{
+        struct tables *tables = container_of(dbe, struct tables, dbe);
+        PyObject *t;
+
+        t = tuple_new(2);
+
+        tuple_set_u64(t, 0, comm->db_id);
+        tuple_set_string(t, 1, comm__str(comm));
+
+        call_object(tables->comm_handler, t, "comm_table");
+
+        Py_DECREF(t);
+
+        return 0;
+}
+
+static int python_export_comm_thread(struct db_export *dbe, u64 db_id,
+                                     struct comm *comm, struct thread *thread)
+{
+        struct tables *tables = container_of(dbe, struct tables, dbe);
+        PyObject *t;
+
+        t = tuple_new(3);
+
+        tuple_set_u64(t, 0, db_id);
+        tuple_set_u64(t, 1, comm->db_id);
+        tuple_set_u64(t, 2, thread->db_id);
+
+        call_object(tables->comm_thread_handler, t, "comm_thread_table");
+
+        Py_DECREF(t);
+
+        return 0;
+}
+
+static int python_export_dso(struct db_export *dbe, struct dso *dso,
+                             struct machine *machine)
+{
+        struct tables *tables = container_of(dbe, struct tables, dbe);
+        char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+        PyObject *t;
+
+        build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+
+        t = tuple_new(5);
+
+        tuple_set_u64(t, 0, dso->db_id);
+        tuple_set_u64(t, 1, machine->db_id);
+        tuple_set_string(t, 2, dso->short_name);
+        tuple_set_string(t, 3, dso->long_name);
+        tuple_set_string(t, 4, sbuild_id);
+
+        call_object(tables->dso_handler, t, "dso_table");
+
+        Py_DECREF(t);
+
+        return 0;
+}
+
+static int python_export_symbol(struct db_export *dbe, struct symbol *sym,
+                                struct dso *dso)
+{
+        struct tables *tables = container_of(dbe, struct tables, dbe);
+        u64 *sym_db_id = symbol__priv(sym);
+        PyObject *t;
+
+        t = tuple_new(6);
+
+        tuple_set_u64(t, 0, *sym_db_id);
+        tuple_set_u64(t, 1, dso->db_id);
+        tuple_set_u64(t, 2, sym->start);
+        tuple_set_u64(t, 3, sym->end);
+        tuple_set_s32(t, 4, sym->binding);
+        tuple_set_string(t, 5, sym->name);
+
+        call_object(tables->symbol_handler, t, "symbol_table");
+
+        Py_DECREF(t);
+
+        return 0;
+}
+
+static int python_export_branch_type(struct db_export *dbe, u32 branch_type,
+                                     const char *name)
+{
+        struct tables *tables = container_of(dbe, struct tables, dbe);
+        PyObject *t;
+
+        t = tuple_new(2);
+
+        tuple_set_s32(t, 0, branch_type);
+        tuple_set_string(t, 1, name);
+
+        call_object(tables->branch_type_handler, t, "branch_type_table");
+
+        Py_DECREF(t);
+
+        return 0;
+}
+
+static int python_export_sample(struct db_export *dbe,
+                                struct export_sample *es)
+{
+        struct tables *tables = container_of(dbe, struct tables, dbe);
+        PyObject *t;
+
+        t = tuple_new(21);
+
+        tuple_set_u64(t, 0, es->db_id);
+        tuple_set_u64(t, 1, es->evsel->db_id);
+        tuple_set_u64(t, 2, es->al->machine->db_id);
+        tuple_set_u64(t, 3, es->thread->db_id);
+        tuple_set_u64(t, 4, es->comm_db_id);
+        tuple_set_u64(t, 5, es->dso_db_id);
+        tuple_set_u64(t, 6, es->sym_db_id);
+        tuple_set_u64(t, 7, es->offset);
+        tuple_set_u64(t, 8, es->sample->ip);
+        tuple_set_u64(t, 9, es->sample->time);
+        tuple_set_s32(t, 10, es->sample->cpu);
+        tuple_set_u64(t, 11, es->addr_dso_db_id);
+        tuple_set_u64(t, 12, es->addr_sym_db_id);
+        tuple_set_u64(t, 13, es->addr_offset);
+        tuple_set_u64(t, 14, es->sample->addr);
+        tuple_set_u64(t, 15, es->sample->period);
+        tuple_set_u64(t, 16, es->sample->weight);
+        tuple_set_u64(t, 17, es->sample->transaction);
+        tuple_set_u64(t, 18, es->sample->data_src);
+        tuple_set_s32(t, 19, es->sample->flags & PERF_BRANCH_MASK);
+        tuple_set_s32(t, 20, !!(es->sample->flags & PERF_IP_FLAG_IN_TX));
+
+        call_object(tables->sample_handler, t, "sample_table");
+
+        Py_DECREF(t);
+
+        return 0;
+}
+
+static int python_export_call_path(struct db_export *dbe, struct call_path *cp)
+{
+        struct tables *tables = container_of(dbe, struct tables, dbe);
+        PyObject *t;
+        u64 parent_db_id, sym_db_id;
+
+        parent_db_id = cp->parent ? cp->parent->db_id : 0;
+        sym_db_id = cp->sym ? *(u64 *)symbol__priv(cp->sym) : 0;
+
+        t = tuple_new(4);
+
+        tuple_set_u64(t, 0, cp->db_id);
+        tuple_set_u64(t, 1, parent_db_id);
+        tuple_set_u64(t, 2, sym_db_id);
+        tuple_set_u64(t, 3, cp->ip);
+
+        call_object(tables->call_path_handler, t, "call_path_table");
+
+        Py_DECREF(t);
+
+        return 0;
+}
+
+static int python_export_call_return(struct db_export *dbe,
+                                     struct call_return *cr)
+{
+        struct tables *tables = container_of(dbe, struct tables, dbe);
+        u64 comm_db_id = cr->comm ? cr->comm->db_id : 0;
+        PyObject *t;
+
+        t = tuple_new(11);
+
+        tuple_set_u64(t, 0, cr->db_id);
+        tuple_set_u64(t, 1, cr->thread->db_id);
+        tuple_set_u64(t, 2, comm_db_id);
+        tuple_set_u64(t, 3, cr->cp->db_id);
+        tuple_set_u64(t, 4, cr->call_time);
+        tuple_set_u64(t, 5, cr->return_time);
+        tuple_set_u64(t, 6, cr->branch_count);
+        tuple_set_u64(t, 7, cr->call_ref);
+        tuple_set_u64(t, 8, cr->return_ref);
+        tuple_set_u64(t, 9, cr->cp->parent->db_id);
+        tuple_set_s32(t, 10, cr->flags);
+
+        call_object(tables->call_return_handler, t, "call_return_table");
+
+        Py_DECREF(t);
+
+        return 0;
+}
+
+static int python_process_call_return(struct call_return *cr, void *data)
+{
+        struct db_export *dbe = data;
+
+        return db_export__call_return(dbe, cr);
+}
+
 static void python_process_general_event(struct perf_sample *sample,
                                          struct perf_evsel *evsel,
                                          struct thread *thread,
@@ -551,19 +835,25 @@ exit:
         Py_DECREF(t);
 }
 
-static void python_process_event(union perf_event *event __maybe_unused,
+static void python_process_event(union perf_event *event,
                                  struct perf_sample *sample,
                                  struct perf_evsel *evsel,
                                  struct thread *thread,
                                  struct addr_location *al)
 {
+        struct tables *tables = &tables_global;
+
         switch (evsel->attr.type) {
         case PERF_TYPE_TRACEPOINT:
                 python_process_tracepoint(sample, evsel, thread, al);
                 break;
         /* Reserve for future process_hw/sw/raw APIs */
         default:
-                python_process_general_event(sample, evsel, thread, al);
+                if (tables->db_export_mode)
+                        db_export__sample(&tables->dbe, event, sample, evsel,
+                                          thread, al);
+                else
+                        python_process_general_event(sample, evsel, thread, al);
         }
 }
 
@@ -589,11 +879,79 @@ error:
         return -1;
 }
 
+#define SET_TABLE_HANDLER_(name, handler_name, table_name) do {         \
+        tables->handler_name = get_handler(#table_name);                \
+        if (tables->handler_name)                                       \
+                tables->dbe.export_ ## name = python_export_ ## name;   \
+} while (0)
+
+#define SET_TABLE_HANDLER(name) \
+        SET_TABLE_HANDLER_(name, name ## _handler, name ## _table)
+
+static void set_table_handlers(struct tables *tables)
+{
+        const char *perf_db_export_mode = "perf_db_export_mode";
+        const char *perf_db_export_calls = "perf_db_export_calls";
+        PyObject *db_export_mode, *db_export_calls;
+        bool export_calls = false;
+        int ret;
+
+        memset(tables, 0, sizeof(struct tables));
+        if (db_export__init(&tables->dbe))
+                Py_FatalError("failed to initialize export");
+
+        db_export_mode = PyDict_GetItemString(main_dict, perf_db_export_mode);
+        if (!db_export_mode)
+                return;
+
+        ret = PyObject_IsTrue(db_export_mode);
+        if (ret == -1)
+                handler_call_die(perf_db_export_mode);
+        if (!ret)
+                return;
+
+        tables->dbe.crp = NULL;
+        db_export_calls = PyDict_GetItemString(main_dict, perf_db_export_calls);
+        if (db_export_calls) {
+                ret = PyObject_IsTrue(db_export_calls);
+                if (ret == -1)
+                        handler_call_die(perf_db_export_calls);
+                export_calls = !!ret;
+        }
+
+        if (export_calls) {
+                tables->dbe.crp =
+                        call_return_processor__new(python_process_call_return,
+                                                   &tables->dbe);
+                if (!tables->dbe.crp)
+                        Py_FatalError("failed to create calls processor");
+        }
+
+        tables->db_export_mode = true;
+        /*
+         * Reserve per symbol space for symbol->db_id via symbol__priv()
+         */
+        symbol_conf.priv_size = sizeof(u64);
+
+        SET_TABLE_HANDLER(evsel);
+        SET_TABLE_HANDLER(machine);
+        SET_TABLE_HANDLER(thread);
+        SET_TABLE_HANDLER(comm);
+        SET_TABLE_HANDLER(comm_thread);
+        SET_TABLE_HANDLER(dso);
+        SET_TABLE_HANDLER(symbol);
+        SET_TABLE_HANDLER(branch_type);
+        SET_TABLE_HANDLER(sample);
+        SET_TABLE_HANDLER(call_path);
+        SET_TABLE_HANDLER(call_return);
+}
+
 /*
  * Start trace script
  */
 static int python_start_script(const char *script, int argc, const char **argv)
 {
+        struct tables *tables = &tables_global;
         const char **command_line;
         char buf[PATH_MAX];
         int i, err = 0;
@@ -632,6 +990,14 @@ static int python_start_script(const char *script, int argc, const char **argv)
 
         free(command_line);
 
+        set_table_handlers(tables);
+
+        if (tables->db_export_mode) {
+                err = db_export__branch_types(&tables->dbe);
+                if (err)
+                        goto error;
+        }
+
         return err;
 error:
         Py_Finalize();
@@ -642,7 +1008,9 @@ error:
 
 static int python_flush_script(void)
 {
-        return 0;
+        struct tables *tables = &tables_global;
+
+        return db_export__flush(&tables->dbe);
 }
 
 /*
@@ -650,8 +1018,12 @@ static int python_flush_script(void)
  */
 static int python_stop_script(void)
 {
+        struct tables *tables = &tables_global;
+
         try_call_object("trace_end", NULL);
 
+        db_export__exit(&tables->dbe);
+
         Py_XDECREF(main_dict);
         Py_XDECREF(main_module);
         Py_Finalize();
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 6702ac28754b..5f0e05a76c05 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -228,6 +228,15 @@ static int process_finished_round(struct perf_tool *tool,
                                   union perf_event *event,
                                   struct perf_session *session);
 
+static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
+                                 union perf_event *event __maybe_unused,
+                                 struct perf_session *perf_session
+                                 __maybe_unused)
+{
+        dump_printf(": unhandled!\n");
+        return 0;
+}
+
 void perf_tool__fill_defaults(struct perf_tool *tool)
 {
         if (tool->sample == NULL)
@@ -262,6 +271,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
                 else
                         tool->finished_round = process_finished_round_stub;
         }
+        if (tool->id_index == NULL)
+                tool->id_index = process_id_index_stub;
 }
  
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -460,6 +471,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
         [PERF_RECORD_HEADER_EVENT_TYPE]   = perf_event__event_type_swap,
         [PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
         [PERF_RECORD_HEADER_BUILD_ID]     = NULL,
+        [PERF_RECORD_ID_INDEX]            = perf_event__all64_swap,
         [PERF_RECORD_HEADER_MAX]          = NULL,
 };
 
@@ -521,15 +533,11 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event,
                 return -ETIME;
 
         if (timestamp < oe->last_flush) {
-                WARN_ONCE(1, "Timestamp below last timeslice flush\n");
-
-                pr_oe_time(timestamp,      "out of order event");
+                pr_oe_time(timestamp,      "out of order event\n");
                 pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n",
                            oe->last_flush_type);
 
-                /* We could get out of order messages after forced flush. */
-                if (oe->last_flush_type != OE_FLUSH__HALF)
-                        return -EINVAL;
+                s->stats.nr_unordered_events++;
         }
 
         new = ordered_events__new(oe, timestamp, event);
@@ -580,15 +588,46 @@ static void regs_dump__printf(u64 mask, u64 *regs)
         }
 }
 
+static const char *regs_abi[] = {
+        [PERF_SAMPLE_REGS_ABI_NONE] = "none",
+        [PERF_SAMPLE_REGS_ABI_32] = "32-bit",
+        [PERF_SAMPLE_REGS_ABI_64] = "64-bit",
+};
+
+static inline const char *regs_dump_abi(struct regs_dump *d)
+{
+        if (d->abi > PERF_SAMPLE_REGS_ABI_64)
+                return "unknown";
+
+        return regs_abi[d->abi];
+}
+
+static void regs__printf(const char *type, struct regs_dump *regs)
+{
+        u64 mask = regs->mask;
+
+        printf("... %s regs: mask 0x%" PRIx64 " ABI %s\n",
+               type,
+               mask,
+               regs_dump_abi(regs));
+
+        regs_dump__printf(mask, regs->regs);
+}
+
 static void regs_user__printf(struct perf_sample *sample)
 {
         struct regs_dump *user_regs = &sample->user_regs;
 
-        if (user_regs->regs) {
-                u64 mask = user_regs->mask;
-                printf("... user regs: mask 0x%" PRIx64 "\n", mask);
-                regs_dump__printf(mask, user_regs->regs);
-        }
+        if (user_regs->regs)
+                regs__printf("user", user_regs);
+}
+
+static void regs_intr__printf(struct perf_sample *sample)
+{
+        struct regs_dump *intr_regs = &sample->intr_regs;
+
+        if (intr_regs->regs)
+                regs__printf("intr", intr_regs);
 }
 
 static void stack_user__printf(struct stack_dump *dump)
@@ -687,6 +726,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
         if (sample_type & PERF_SAMPLE_REGS_USER)
                 regs_user__printf(sample);
 
+        if (sample_type & PERF_SAMPLE_REGS_INTR)
+                regs_intr__printf(sample);
+
         if (sample_type & PERF_SAMPLE_STACK_USER)
                 stack_user__printf(&sample->user_stack);
 
@@ -888,11 +930,26 @@ static s64 perf_session__process_user_event(struct perf_session *session,
                 return tool->build_id(tool, event, session);
         case PERF_RECORD_FINISHED_ROUND:
                 return tool->finished_round(tool, event, session);
+        case PERF_RECORD_ID_INDEX:
+                return tool->id_index(tool, event, session);
         default:
                 return -EINVAL;
         }
 }
 
+int perf_session__deliver_synth_event(struct perf_session *session,
+                                      union perf_event *event,
+                                      struct perf_sample *sample,
+                                      struct perf_tool *tool)
+{
+        events_stats__inc(&session->stats, event->header.type);
+
+        if (event->header.type >= PERF_RECORD_USER_TYPE_START)
+                return perf_session__process_user_event(session, event, tool, 0);
+
+        return perf_session__deliver_event(session, event, sample, tool, 0);
+}
+
 static void event_swap(union perf_event *event, bool sample_id_all)
 {
         perf_event__swap_op swap;
@@ -1057,6 +1114,9 @@ static void perf_session__warn_about_errors(const struct perf_session *session,
                             "Do you have a KVM guest running and not using 'perf kvm'?\n",
                             session->stats.nr_unprocessable_samples);
         }
+
+        if (session->stats.nr_unordered_events != 0)
+                ui__warning("%u out of order events recorded.\n", session->stats.nr_unordered_events);
 }
 
 volatile int session_done;
@@ -1417,9 +1477,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
         if (symbol_conf.use_callchain && sample->callchain) {
                 struct addr_location node_al;
 
-                if (machine__resolve_callchain(al->machine, evsel, al->thread,
-                                               sample, NULL, NULL,
-                                               PERF_MAX_STACK_DEPTH) != 0) {
+                if (thread__resolve_callchain(al->thread, evsel,
+                                              sample, NULL, NULL,
+                                              PERF_MAX_STACK_DEPTH) != 0) {
                         if (verbose)
                                 error("Failed to resolve callchain. Skipping\n");
                         return;
@@ -1594,3 +1654,111 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 out:
         return err;
 }
+
+int perf_event__process_id_index(struct perf_tool *tool __maybe_unused,
+                                 union perf_event *event,
+                                 struct perf_session *session)
+{
+        struct perf_evlist *evlist = session->evlist;
+        struct id_index_event *ie = &event->id_index;
+        size_t i, nr, max_nr;
+
+        max_nr = (ie->header.size - sizeof(struct id_index_event)) /
+                 sizeof(struct id_index_entry);
+        nr = ie->nr;
+        if (nr > max_nr)
+                return -EINVAL;
+
+        if (dump_trace)
+                fprintf(stdout, " nr: %zu\n", nr);
+
+        for (i = 0; i < nr; i++) {
+                struct id_index_entry *e = &ie->entries[i];
+                struct perf_sample_id *sid;
+
+                if (dump_trace) {
+                        fprintf(stdout, " ... id: %"PRIu64, e->id);
+                        fprintf(stdout, "  idx: %"PRIu64, e->idx);
+                        fprintf(stdout, "  cpu: %"PRId64, e->cpu);
+                        fprintf(stdout, "  tid: %"PRId64"\n", e->tid);
+                }
+
+                sid = perf_evlist__id2sid(evlist, e->id);
+                if (!sid)
+                        return -ENOENT;
+                sid->idx = e->idx;
+                sid->cpu = e->cpu;
+                sid->tid = e->tid;
+        }
+        return 0;
+}
+
+int perf_event__synthesize_id_index(struct perf_tool *tool,
+                                    perf_event__handler_t process,
+                                    struct perf_evlist *evlist,
+                                    struct machine *machine)
+{
+        union perf_event *ev;
+        struct perf_evsel *evsel;
+        size_t nr = 0, i = 0, sz, max_nr, n;
+        int err;
+
+        pr_debug2("Synthesizing id index\n");
+
+        max_nr = (UINT16_MAX - sizeof(struct id_index_event)) /
+                 sizeof(struct id_index_entry);
+
+        evlist__for_each(evlist, evsel)
+                nr += evsel->ids;
+
+        n = nr > max_nr ? max_nr : nr;
+        sz = sizeof(struct id_index_event) + n * sizeof(struct id_index_entry);
+        ev = zalloc(sz);
+        if (!ev)
+                return -ENOMEM;
+
+        ev->id_index.header.type = PERF_RECORD_ID_INDEX;
+        ev->id_index.header.size = sz;
+        ev->id_index.nr = n;
+
+        evlist__for_each(evlist, evsel) {
+                u32 j;
+
+                for (j = 0; j < evsel->ids; j++) {
+                        struct id_index_entry *e;
+                        struct perf_sample_id *sid;
+
+                        if (i >= n) {
+                                err = process(tool, ev, NULL, machine);
+                                if (err)
+                                        goto out_err;
+                                nr -= n;
+                                i = 0;
+                        }
+
+                        e = &ev->id_index.entries[i++];
+
+                        e->id = evsel->id[j];
+
+                        sid = perf_evlist__id2sid(evlist, e->id);
+                        if (!sid) {
+                                free(ev);
+                                return -ENOENT;
+                        }
+
+                        e->idx = sid->idx;
+                        e->cpu = sid->cpu;
+                        e->tid = sid->tid;
+                }
+        }
+
+        sz = sizeof(struct id_index_event) + nr * sizeof(struct id_index_entry);
+        ev->id_index.header.size = sz;
+        ev->id_index.nr = nr;
+
+        err = process(tool, ev, NULL, machine);
+out_err:
+        free(ev);
+
+        return err;
+}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index a4be851f1a90..dc26ebf60fe4 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -126,4 +126,19 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 extern volatile int session_done;
 
 #define session_done()  ACCESS_ONCE(session_done)
+
+int perf_session__deliver_synth_event(struct perf_session *session,
+                                      union perf_event *event,
+                                      struct perf_sample *sample,
+                                      struct perf_tool *tool);
+
+int perf_event__process_id_index(struct perf_tool *tool,
+                                 union perf_event *event,
+                                 struct perf_session *session);
+
+int perf_event__synthesize_id_index(struct perf_tool *tool,
+                                    perf_event__handler_t process,
+                                    struct perf_evlist *evlist,
+                                    struct machine *machine);
+
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 9402885a77f3..9139dda9f9a3 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -291,7 +291,8 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
                 else {
                         struct map *map = left->ms.map;
                         left->srcline = get_srcline(map->dso,
-                                            map__rip_2objdump(map, left->ip));
+                                           map__rip_2objdump(map, left->ip),
+                                                    left->ms.sym, true);
                 }
         }
         if (!right->srcline) {
@@ -300,7 +301,8 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
                 else {
                         struct map *map = right->ms.map;
                         right->srcline = get_srcline(map->dso,
-                                            map__rip_2objdump(map, right->ip));
+                                             map__rip_2objdump(map, right->ip),
+                                                     right->ms.sym, true);
                 }
         }
         return strcmp(right->srcline, left->srcline);
@@ -309,7 +311,7 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
                                         size_t size, unsigned int width)
 {
-        return repsep_snprintf(bf, size, "%*.*-s", width, width, he->srcline);
+        return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcline);
 }
 
 struct sort_entry sort_srcline = {
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index f3e4bc5fe5d2..c93fb0c5bd0b 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -8,6 +8,8 @@
 #include "util/util.h"
 #include "util/debug.h"
 
+#include "symbol.h"
+
 #ifdef HAVE_LIBBFD_SUPPORT
 
 /*
@@ -18,7 +20,7 @@
 
 struct a2l_data {
         const char      *input;
-        unsigned long   addr;
+        u64             addr;
 
         bool            found;
         const char      *filename;
@@ -145,7 +147,7 @@ static void addr2line_cleanup(struct a2l_data *a2l)
         free(a2l);
 }
 
-static int addr2line(const char *dso_name, unsigned long addr,
+static int addr2line(const char *dso_name, u64 addr,
                      char **file, unsigned int *line, struct dso *dso)
 {
         int ret = 0;
@@ -191,7 +193,7 @@ void dso__free_a2l(struct dso *dso)
 
 #else /* HAVE_LIBBFD_SUPPORT */
 
-static int addr2line(const char *dso_name, unsigned long addr,
+static int addr2line(const char *dso_name, u64 addr,
                      char **file, unsigned int *line_nr,
                      struct dso *dso __maybe_unused)
 {
@@ -250,7 +252,8 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
  */
 #define A2L_FAIL_LIMIT 123
 
-char *get_srcline(struct dso *dso, unsigned long addr)
+char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
+                  bool show_sym)
 {
         char *file = NULL;
         unsigned line = 0;
@@ -258,7 +261,7 @@ char *get_srcline(struct dso *dso, unsigned long addr)
         const char *dso_name;
 
         if (!dso->has_srcline)
-                return SRCLINE_UNKNOWN;
+                goto out;
 
         if (dso->symsrc_filename)
                 dso_name = dso->symsrc_filename;
@@ -274,7 +277,7 @@ char *get_srcline(struct dso *dso, unsigned long addr)
         if (!addr2line(dso_name, addr, &file, &line, dso))
                 goto out;
 
-        if (asprintf(&srcline, "%s:%u", file, line) < 0) {
+        if (asprintf(&srcline, "%s:%u", basename(file), line) < 0) {
                 free(file);
                 goto out;
         }
@@ -289,7 +292,13 @@ out:
                 dso->has_srcline = 0;
                 dso__free_a2l(dso);
         }
-        return SRCLINE_UNKNOWN;
+        if (sym) {
+                if (asprintf(&srcline, "%s+%" PRIu64, show_sym ? sym->name : "",
+                                        addr - sym->start) < 0)
+                        return SRCLINE_UNKNOWN;
+        } else if (asprintf(&srcline, "%s[%" PRIx64 "]", dso->short_name, addr) < 0)
+                return SRCLINE_UNKNOWN;
+        return srcline;
 }
 
 void free_srcline(char *srcline)
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 1e23a5bfb044..06fcd1bf98b6 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -11,6 +11,27 @@
 #include <symbol/kallsyms.h>
 #include "debug.h"
 
+#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
+extern char *cplus_demangle(const char *, int);
+
+static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i)
+{
+        return cplus_demangle(c, i);
+}
+#else
+#ifdef NO_DEMANGLE
+static inline char *bfd_demangle(void __maybe_unused *v,
+                                 const char __maybe_unused *c,
+                                 int __maybe_unused i)
+{
+        return NULL;
+}
+#else
+#define PACKAGE 'perf'
+#include <bfd.h>
+#endif
+#endif
+
 #ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
 static int elf_getphdrnum(Elf *elf, size_t *dst)
 {
@@ -546,6 +567,35 @@ static int dso__swap_init(struct dso *dso, unsigned char eidata)
         return 0;
 }
 
+static int decompress_kmodule(struct dso *dso, const char *name,
+                              enum dso_binary_type type)
+{
+        int fd;
+        const char *ext = strrchr(name, '.');
+        char tmpbuf[] = "/tmp/perf-kmod-XXXXXX";
+
+        if ((type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP &&
+             type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP) ||
+            type != dso->symtab_type)
+                return -1;
+
+        if (!ext || !is_supported_compression(ext + 1))
+                return -1;
+
+        fd = mkstemp(tmpbuf);
+        if (fd < 0)
+                return -1;
+
+        if (!decompress_to_file(ext + 1, name, fd)) {
+                close(fd);
+                fd = -1;
+        }
+
+        unlink(tmpbuf);
+
+        return fd;
+}
+
 bool symsrc__possibly_runtime(struct symsrc *ss)
 {
         return ss->dynsym || ss->opdsec;
@@ -571,7 +621,11 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
         Elf *elf;
         int fd;
 
-        fd = open(name, O_RDONLY);
+        if (dso__needs_decompress(dso))
+                fd = decompress_kmodule(dso, name, type);
+        else
+                fd = open(name, O_RDONLY);
+
         if (fd < 0)
                 return -1;
 
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index c9541fea9514..d7efb03b3f9a 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -129,6 +129,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
 
                 for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
                         void *tmp;
+                        long offset;
 
                         if (need_swap) {
                                 phdr->p_type = bswap_32(phdr->p_type);
@@ -140,12 +141,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
                                 continue;
 
                         buf_size = phdr->p_filesz;
+                        offset = phdr->p_offset;
                         tmp = realloc(buf, buf_size);
                         if (tmp == NULL)
                                 goto out_free;
 
                         buf = tmp;
-                        fseek(fp, phdr->p_offset, SEEK_SET);
+                        fseek(fp, offset, SEEK_SET);
                         if (fread(buf, buf_size, 1, fp) != 1)
                                 goto out_free;
 
@@ -178,6 +180,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
 
                 for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
                         void *tmp;
+                        long offset;
 
                         if (need_swap) {
                                 phdr->p_type = bswap_32(phdr->p_type);
@@ -189,12 +192,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
                                 continue;
 
                         buf_size = phdr->p_filesz;
+                        offset = phdr->p_offset;
                         tmp = realloc(buf, buf_size);
                         if (tmp == NULL)
                                 goto out_free;
 
                         buf = tmp;
-                        fseek(fp, phdr->p_offset, SEEK_SET);
+                        fseek(fp, offset, SEEK_SET);
                         if (fread(buf, buf_size, 1, fp) != 1)
                                 goto out_free;
 
@@ -341,7 +345,6 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
 
         if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) {
                 dso__set_build_id(dso, build_id);
-                return 1;
         }
         return 0;
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 078331140d8c..c24c5b83156c 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -51,7 +51,9 @@ static enum dso_binary_type binary_type_symtab[] = {
         DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
         DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
         DSO_BINARY_TYPE__GUEST_KMODULE,
+        DSO_BINARY_TYPE__GUEST_KMODULE_COMP,
         DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+        DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP,
         DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
         DSO_BINARY_TYPE__NOT_FOUND,
 };
@@ -1300,7 +1302,9 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
                 return dso->kernel == DSO_TYPE_GUEST_KERNEL;
 
         case DSO_BINARY_TYPE__GUEST_KMODULE:
+        case DSO_BINARY_TYPE__GUEST_KMODULE_COMP:
         case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+        case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
                 /*
                  * kernel modules know their symtab type - it's set when
                  * creating a module dso in machine__new_module().
@@ -1368,7 +1372,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
                 return -1;
 
         kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
-                dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE;
+                dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
+                dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE ||
+                dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
 
         /*
          * Iterate over candidate debug images.
@@ -1505,12 +1511,10 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
                            symbol_filter_t filter)
 {
         int i, err = 0;
-        char *filename;
+        char *filename = NULL;
 
-        pr_debug("Looking at the vmlinux_path (%d entries long)\n",
-                 vmlinux_path__nr_entries + 1);
-
-        filename = dso__build_id_filename(dso, NULL, 0);
+        if (!symbol_conf.ignore_vmlinux_buildid)
+                filename = dso__build_id_filename(dso, NULL, 0);
         if (filename != NULL) {
                 err = dso__load_vmlinux(dso, map, filename, true, filter);
                 if (err > 0)
@@ -1518,6 +1522,9 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
                 free(filename);
         }
 
+        pr_debug("Looking at the vmlinux_path (%d entries long)\n",
+                 vmlinux_path__nr_entries + 1);
+
         for (i = 0; i < vmlinux_path__nr_entries; ++i) {
                 err = dso__load_vmlinux(dso, map, vmlinux_path[i], false, filter);
                 if (err > 0)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index eb2c19bf8d90..9d602e9c6f59 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -23,27 +23,6 @@
 
 #include "dso.h"
 
-#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
-extern char *cplus_demangle(const char *, int);
-
-static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i)
-{
-        return cplus_demangle(c, i);
-}
-#else
-#ifdef NO_DEMANGLE
-static inline char *bfd_demangle(void __maybe_unused *v,
-                                 const char __maybe_unused *c,
-                                 int __maybe_unused i)
-{
-        return NULL;
-}
-#else
-#define PACKAGE 'perf'
-#include <bfd.h>
-#endif
-#endif
-
 /*
  * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP;
  * for newer versions we can use mmap to reduce memory usage:
@@ -105,6 +84,7 @@ struct symbol_conf {
         unsigned short  nr_events;
         bool            try_vmlinux_path,
                         ignore_vmlinux,
+                        ignore_vmlinux_buildid,
                         show_kernel_path,
                         use_modules,
                         sort_by_name,
@@ -122,7 +102,8 @@ struct symbol_conf {
                         demangle,
                         demangle_kernel,
                         filter_relative,
-                        show_hist_headers;
+                        show_hist_headers,
+                        branch_callstack;
         const char      *vmlinux_name,
                         *kallsyms_name,
                         *source_prefix,
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
new file mode 100644
index 000000000000..9ed59a452d1f
--- /dev/null
+++ b/tools/perf/util/thread-stack.c
@@ -0,0 +1,747 @@
+/*
+ * thread-stack.c: Synthesize a thread's stack using call / return events
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <linux/rbtree.h>
+#include <linux/list.h>
+#include "thread.h"
+#include "event.h"
+#include "machine.h"
+#include "util.h"
+#include "debug.h"
+#include "symbol.h"
+#include "comm.h"
+#include "thread-stack.h"
+
+#define CALL_PATH_BLOCK_SHIFT 8
+#define CALL_PATH_BLOCK_SIZE (1 << CALL_PATH_BLOCK_SHIFT)
+#define CALL_PATH_BLOCK_MASK (CALL_PATH_BLOCK_SIZE - 1)
+
+struct call_path_block {
+        struct call_path cp[CALL_PATH_BLOCK_SIZE];
+        struct list_head node;
+};
+
+/**
+ * struct call_path_root - root of all call paths.
+ * @call_path: root call path
+ * @blocks: list of blocks to store call paths
+ * @next: next free space
+ * @sz: number of spaces
+ */
+struct call_path_root {
+        struct call_path call_path;
+        struct list_head blocks;
+        size_t next;
+        size_t sz;
+};
+
+/**
+ * struct call_return_processor - provides a call-back to consume call-return
+ *                                information.
+ * @cpr: call path root
+ * @process: call-back that accepts call/return information
+ * @data: anonymous data for call-back
+ */
+struct call_return_processor {
+        struct call_path_root *cpr;
+        int (*process)(struct call_return *cr, void *data);
+        void *data;
+};
+
+#define STACK_GROWTH 2048
+
+/**
+ * struct thread_stack_entry - thread stack entry.
+ * @ret_addr: return address
+ * @timestamp: timestamp (if known)
+ * @ref: external reference (e.g. db_id of sample)
+ * @branch_count: the branch count when the entry was created
+ * @cp: call path
+ * @no_call: a 'call' was not seen
+ */
+struct thread_stack_entry {
+        u64 ret_addr;
+        u64 timestamp;
+        u64 ref;
+        u64 branch_count;
+        struct call_path *cp;
+        bool no_call;
+};
+
+/**
+ * struct thread_stack - thread stack constructed from 'call' and 'return'
+ *                       branch samples.
+ * @stack: array that holds the stack
+ * @cnt: number of entries in the stack
+ * @sz: current maximum stack size
+ * @trace_nr: current trace number
+ * @branch_count: running branch count
+ * @kernel_start: kernel start address
+ * @last_time: last timestamp
+ * @crp: call/return processor
+ * @comm: current comm
+ */
+struct thread_stack {
+        struct thread_stack_entry *stack;
+        size_t cnt;
+        size_t sz;
+        u64 trace_nr;
+        u64 branch_count;
+        u64 kernel_start;
+        u64 last_time;
+        struct call_return_processor *crp;
+        struct comm *comm;
+};
+
+static int thread_stack__grow(struct thread_stack *ts)
+{
+        struct thread_stack_entry *new_stack;
+        size_t sz, new_sz;
+
+        new_sz = ts->sz + STACK_GROWTH;
+        sz = new_sz * sizeof(struct thread_stack_entry);
+
+        new_stack = realloc(ts->stack, sz);
+        if (!new_stack)
+                return -ENOMEM;
+
+        ts->stack = new_stack;
+        ts->sz = new_sz;
+
+        return 0;
+}
+
+static struct thread_stack *thread_stack__new(struct thread *thread,
+                                              struct call_return_processor *crp)
+{
+        struct thread_stack *ts;
+
+        ts = zalloc(sizeof(struct thread_stack));
+        if (!ts)
+                return NULL;
+
+        if (thread_stack__grow(ts)) {
+                free(ts);
+                return NULL;
+        }
+
+        if (thread->mg && thread->mg->machine)
+                ts->kernel_start = machine__kernel_start(thread->mg->machine);
+        else
+                ts->kernel_start = 1ULL << 63;
+        ts->crp = crp;
+
+        return ts;
+}
+
+static int thread_stack__push(struct thread_stack *ts, u64 ret_addr)
+{
+        int err = 0;
+
+        if (ts->cnt == ts->sz) {
+                err = thread_stack__grow(ts);
+                if (err) {
+                        pr_warning("Out of memory: discarding thread stack\n");
+                        ts->cnt = 0;
+                }
+        }
+
+        ts->stack[ts->cnt++].ret_addr = ret_addr;
+
+        return err;
+}
+
+static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr)
+{
+        size_t i;
+
+        /*
+         * In some cases there may be functions which are not seen to return.
+         * For example when setjmp / longjmp has been used.  Or the perf context
+         * switch in the kernel which doesn't stop and start tracing in exactly
+         * the same code path.  When that happens the return address will be
+         * further down the stack.  If the return address is not found at all,
+         * we assume the opposite (i.e. this is a return for a call that wasn't
+         * seen for some reason) and leave the stack alone.
+         */
+        for (i = ts->cnt; i; ) {
+                if (ts->stack[--i].ret_addr == ret_addr) {
+                        ts->cnt = i;
+                        return;
+                }
+        }
+}
+
+static bool thread_stack__in_kernel(struct thread_stack *ts)
+{
+        if (!ts->cnt)
+                return false;
+
+        return ts->stack[ts->cnt - 1].cp->in_kernel;
+}
+
+static int thread_stack__call_return(struct thread *thread,
+                                     struct thread_stack *ts, size_t idx,
+                                     u64 timestamp, u64 ref, bool no_return)
+{
+        struct call_return_processor *crp = ts->crp;
+        struct thread_stack_entry *tse;
+        struct call_return cr = {
+                .thread = thread,
+                .comm = ts->comm,
+                .db_id = 0,
+        };
+
+        tse = &ts->stack[idx];
+        cr.cp = tse->cp;
+        cr.call_time = tse->timestamp;
+        cr.return_time = timestamp;
+        cr.branch_count = ts->branch_count - tse->branch_count;
+        cr.call_ref = tse->ref;
+        cr.return_ref = ref;
+        if (tse->no_call)
+                cr.flags |= CALL_RETURN_NO_CALL;
+        if (no_return)
+                cr.flags |= CALL_RETURN_NO_RETURN;
+
+        return crp->process(&cr, crp->data);
+}
+
+static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
+{
+        struct call_return_processor *crp = ts->crp;
+        int err;
+
+        if (!crp) {
+                ts->cnt = 0;
+                return 0;
+        }
+
+        while (ts->cnt) {
+                err = thread_stack__call_return(thread, ts, --ts->cnt,
+                                                ts->last_time, 0, true);
+                if (err) {
+                        pr_err("Error flushing thread stack!\n");
+                        ts->cnt = 0;
+                        return err;
+                }
+        }
+
+        return 0;
+}
+
+int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+                        u64 to_ip, u16 insn_len, u64 trace_nr)
+{
+        if (!thread)
+                return -EINVAL;
+
+        if (!thread->ts) {
+                thread->ts = thread_stack__new(thread, NULL);
+                if (!thread->ts) {
+                        pr_warning("Out of memory: no thread stack\n");
+                        return -ENOMEM;
+                }
+                thread->ts->trace_nr = trace_nr;
+        }
+
+        /*
+         * When the trace is discontinuous, the trace_nr changes.  In that case
+         * the stack might be completely invalid.  Better to report nothing than
+         * to report something misleading, so flush the stack.
+         */
+        if (trace_nr != thread->ts->trace_nr) {
+                if (thread->ts->trace_nr)
+                        thread_stack__flush(thread, thread->ts);
+                thread->ts->trace_nr = trace_nr;
+        }
+
+        /* Stop here if thread_stack__process() is in use */
+        if (thread->ts->crp)
+                return 0;
+
+        if (flags & PERF_IP_FLAG_CALL) {
+                u64 ret_addr;
+
+                if (!to_ip)
+                        return 0;
+                ret_addr = from_ip + insn_len;
+                if (ret_addr == to_ip)
+                        return 0; /* Zero-length calls are excluded */
+                return thread_stack__push(thread->ts, ret_addr);
+        } else if (flags & PERF_IP_FLAG_RETURN) {
+                if (!from_ip)
+                        return 0;
+                thread_stack__pop(thread->ts, to_ip);
+        }
+
+        return 0;
+}
+
+void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
+{
+        if (!thread || !thread->ts)
+                return;
+
+        if (trace_nr != thread->ts->trace_nr) {
+                if (thread->ts->trace_nr)
+                        thread_stack__flush(thread, thread->ts);
+                thread->ts->trace_nr = trace_nr;
+        }
+}
+
+void thread_stack__free(struct thread *thread)
+{
+        if (thread->ts) {
+                thread_stack__flush(thread, thread->ts);
+                zfree(&thread->ts->stack);
+                zfree(&thread->ts);
+        }
+}
+
+void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+                          size_t sz, u64 ip)
+{
+        size_t i;
+
+        if (!thread || !thread->ts)
+                chain->nr = 1;
+        else
+                chain->nr = min(sz, thread->ts->cnt + 1);
+
+        chain->ips[0] = ip;
+
+        for (i = 1; i < chain->nr; i++)
+                chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
+}
+
+static void call_path__init(struct call_path *cp, struct call_path *parent,
+                            struct symbol *sym, u64 ip, bool in_kernel)
+{
+        cp->parent = parent;
+        cp->sym = sym;
+        cp->ip = sym ? 0 : ip;
+        cp->db_id = 0;
+        cp->in_kernel = in_kernel;
+        RB_CLEAR_NODE(&cp->rb_node);
+        cp->children = RB_ROOT;
+}
+
+static struct call_path_root *call_path_root__new(void)
+{
+        struct call_path_root *cpr;
+
+        cpr = zalloc(sizeof(struct call_path_root));
+        if (!cpr)
+                return NULL;
+        call_path__init(&cpr->call_path, NULL, NULL, 0, false);
+        INIT_LIST_HEAD(&cpr->blocks);
+        return cpr;
+}
+
+static void call_path_root__free(struct call_path_root *cpr)
+{
+        struct call_path_block *pos, *n;
+
+        list_for_each_entry_safe(pos, n, &cpr->blocks, node) {
+                list_del(&pos->node);
+                free(pos);
+        }
+        free(cpr);
+}
+
+static struct call_path *call_path__new(struct call_path_root *cpr,
+                                        struct call_path *parent,
+                                        struct symbol *sym, u64 ip,
+                                        bool in_kernel)
+{
+        struct call_path_block *cpb;
+        struct call_path *cp;
+        size_t n;
+
+        if (cpr->next < cpr->sz) {
+                cpb = list_last_entry(&cpr->blocks, struct call_path_block,
+                                      node);
+        } else {
+                cpb = zalloc(sizeof(struct call_path_block));
+                if (!cpb)
+                        return NULL;
+                list_add_tail(&cpb->node, &cpr->blocks);
+                cpr->sz += CALL_PATH_BLOCK_SIZE;
+        }
+
+        n = cpr->next++ & CALL_PATH_BLOCK_MASK;
+        cp = &cpb->cp[n];
+
+        call_path__init(cp, parent, sym, ip, in_kernel);
+
+        return cp;
+}
+
+static struct call_path *call_path__findnew(struct call_path_root *cpr,
+                                            struct call_path *parent,
+                                            struct symbol *sym, u64 ip, u64 ks)
+{
+        struct rb_node **p;
+        struct rb_node *node_parent = NULL;
+        struct call_path *cp;
+        bool in_kernel = ip >= ks;
+
+        if (sym)
+                ip = 0;
+
+        if (!parent)
+                return call_path__new(cpr, parent, sym, ip, in_kernel);
+
+        p = &parent->children.rb_node;
+        while (*p != NULL) {
+                node_parent = *p;
+                cp = rb_entry(node_parent, struct call_path, rb_node);
+
+                if (cp->sym == sym && cp->ip == ip)
+                        return cp;
+
+                if (sym < cp->sym || (sym == cp->sym && ip < cp->ip))
+                        p = &(*p)->rb_left;
+                else
+                        p = &(*p)->rb_right;
+        }
+
+        cp = call_path__new(cpr, parent, sym, ip, in_kernel);
+        if (!cp)
+                return NULL;
+
+        rb_link_node(&cp->rb_node, node_parent, p);
+        rb_insert_color(&cp->rb_node, &parent->children);
+
+        return cp;
+}
+
+struct call_return_processor *
+call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+                           void *data)
+{
+        struct call_return_processor *crp;
+
+        crp = zalloc(sizeof(struct call_return_processor));
+        if (!crp)
+                return NULL;
+        crp->cpr = call_path_root__new();
+        if (!crp->cpr)
+                goto out_free;
+        crp->process = process;
+        crp->data = data;
+        return crp;
+
+out_free:
+        free(crp);
+        return NULL;
+}
+
+void call_return_processor__free(struct call_return_processor *crp)
+{
+        if (crp) {
+                call_path_root__free(crp->cpr);
+                free(crp);
+        }
+}
+
+static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
+                                 u64 timestamp, u64 ref, struct call_path *cp,
+                                 bool no_call)
+{
+        struct thread_stack_entry *tse;
+        int err;
+
+        if (ts->cnt == ts->sz) {
+                err = thread_stack__grow(ts);
+                if (err)
+                        return err;
+        }
+
+        tse = &ts->stack[ts->cnt++];
+        tse->ret_addr = ret_addr;
+        tse->timestamp = timestamp;
+        tse->ref = ref;
+        tse->branch_count = ts->branch_count;
+        tse->cp = cp;
+        tse->no_call = no_call;
+
+        return 0;
+}
+
+static int thread_stack__pop_cp(struct thread *thread, struct thread_stack *ts,
+                                u64 ret_addr, u64 timestamp, u64 ref,
+                                struct symbol *sym)
+{
+        int err;
+
+        if (!ts->cnt)
+                return 1;
+
+        if (ts->cnt == 1) {
+                struct thread_stack_entry *tse = &ts->stack[0];
+
+                if (tse->cp->sym == sym)
+                        return thread_stack__call_return(thread, ts, --ts->cnt,
+                                                         timestamp, ref, false);
+        }
+
+        if (ts->stack[ts->cnt - 1].ret_addr == ret_addr) {
+                return thread_stack__call_return(thread, ts, --ts->cnt,
+                                                 timestamp, ref, false);
+        } else {
+                size_t i = ts->cnt - 1;
+
+                while (i--) {
+                        if (ts->stack[i].ret_addr != ret_addr)
+                                continue;
+                        i += 1;
+                        while (ts->cnt > i) {
+                                err = thread_stack__call_return(thread, ts,
+                                                                --ts->cnt,
+                                                                timestamp, ref,
+                                                                true);
+                                if (err)
+                                        return err;
+                        }
+                        return thread_stack__call_return(thread, ts, --ts->cnt,
+                                                         timestamp, ref, false);
+                }
+        }
+
+        return 1;
+}
+
+static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts,
+                                struct perf_sample *sample,
+                                struct addr_location *from_al,
+                                struct addr_location *to_al, u64 ref)
+{
+        struct call_path_root *cpr = ts->crp->cpr;
+        struct call_path *cp;
+        struct symbol *sym;
+        u64 ip;
+
+        if (sample->ip) {
+                ip = sample->ip;
+                sym = from_al->sym;
+        } else if (sample->addr) {
+                ip = sample->addr;
+                sym = to_al->sym;
+        } else {
+                return 0;
+        }
+
+        cp = call_path__findnew(cpr, &cpr->call_path, sym, ip,
+                                ts->kernel_start);
+        if (!cp)
+                return -ENOMEM;
+
+        return thread_stack__push_cp(thread->ts, ip, sample->time, ref, cp,
+                                     true);
+}
+
+static int thread_stack__no_call_return(struct thread *thread,
+                                        struct thread_stack *ts,
+                                        struct perf_sample *sample,
+                                        struct addr_location *from_al,
+                                        struct addr_location *to_al, u64 ref)
+{
+        struct call_path_root *cpr = ts->crp->cpr;
+        struct call_path *cp, *parent;
+        u64 ks = ts->kernel_start;
+        int err;
+
+        if (sample->ip >= ks && sample->addr < ks) {
+                /* Return to userspace, so pop all kernel addresses */
+                while (thread_stack__in_kernel(ts)) {
+                        err = thread_stack__call_return(thread, ts, --ts->cnt,
+                                                        sample->time, ref,
+                                                        true);
+                        if (err)
+                                return err;
+                }
+
+                /* If the stack is empty, push the userspace address */
+                if (!ts->cnt) {
+                        cp = call_path__findnew(cpr, &cpr->call_path,
+                                                to_al->sym, sample->addr,
+                                                ts->kernel_start);
+                        if (!cp)
+                                return -ENOMEM;
+                        return thread_stack__push_cp(ts, 0, sample->time, ref,
+                                                     cp, true);
+                }
+        } else if (thread_stack__in_kernel(ts) && sample->ip < ks) {
+                /* Return to userspace, so pop all kernel addresses */
+                while (thread_stack__in_kernel(ts)) {
+                        err = thread_stack__call_return(thread, ts, --ts->cnt,
+                                                        sample->time, ref,
+                                                        true);
+                        if (err)
+                                return err;
+                }
+        }
+
+        if (ts->cnt)
+                parent = ts->stack[ts->cnt - 1].cp;
+        else
+                parent = &cpr->call_path;
+
+        /* This 'return' had no 'call', so push and pop top of stack */
+        cp = call_path__findnew(cpr, parent, from_al->sym, sample->ip,
+                                ts->kernel_start);
+        if (!cp)
+                return -ENOMEM;
+
+        err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp,
+                                    true);
+        if (err)
+                return err;
+
+        return thread_stack__pop_cp(thread, ts, sample->addr, sample->time, ref,
+                                    to_al->sym);
+}
+
+static int thread_stack__trace_begin(struct thread *thread,
+                                     struct thread_stack *ts, u64 timestamp,
+                                     u64 ref)
+{
+        struct thread_stack_entry *tse;
+        int err;
+
+        if (!ts->cnt)
+                return 0;
+
+        /* Pop trace end */
+        tse = &ts->stack[ts->cnt - 1];
+        if (tse->cp->sym == NULL && tse->cp->ip == 0) {
+                err = thread_stack__call_return(thread, ts, --ts->cnt,
+                                                timestamp, ref, false);
+                if (err)
+                        return err;
+        }
+
+        return 0;
+}
+
+static int thread_stack__trace_end(struct thread_stack *ts,
+                                   struct perf_sample *sample, u64 ref)
+{
+        struct call_path_root *cpr = ts->crp->cpr;
+        struct call_path *cp;
+        u64 ret_addr;
+
+        /* No point having 'trace end' on the bottom of the stack */
+        if (!ts->cnt || (ts->cnt == 1 && ts->stack[0].ref == ref))
+                return 0;
+
+        cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp, NULL, 0,
+                                ts->kernel_start);
+        if (!cp)
+                return -ENOMEM;
+
+        ret_addr = sample->ip + sample->insn_len;
+
+        return thread_stack__push_cp(ts, ret_addr, sample->time, ref, cp,
+                                     false);
+}
+
+int thread_stack__process(struct thread *thread, struct comm *comm,
+                          struct perf_sample *sample,
+                          struct addr_location *from_al,
+                          struct addr_location *to_al, u64 ref,
+                          struct call_return_processor *crp)
+{
+        struct thread_stack *ts = thread->ts;
+        int err = 0;
+
+        if (ts) {
+                if (!ts->crp) {
+                        /* Supersede thread_stack__event() */
+                        thread_stack__free(thread);
+                        thread->ts = thread_stack__new(thread, crp);
+                        if (!thread->ts)
+                                return -ENOMEM;
+                        ts = thread->ts;
+                        ts->comm = comm;
+                }
+        } else {
+                thread->ts = thread_stack__new(thread, crp);
+                if (!thread->ts)
+                        return -ENOMEM;
+                ts = thread->ts;
+                ts->comm = comm;
+        }
+
+        /* Flush stack on exec */
+        if (ts->comm != comm && thread->pid_ == thread->tid) {
+                err = thread_stack__flush(thread, ts);
+                if (err)
+                        return err;
+                ts->comm = comm;
+        }
+
+        /* If the stack is empty, put the current symbol on the stack */
+        if (!ts->cnt) {
+                err = thread_stack__bottom(thread, ts, sample, from_al, to_al,
+                                           ref);
+                if (err)
+                        return err;
+        }
+
+        ts->branch_count += 1;
+        ts->last_time = sample->time;
+
+        if (sample->flags & PERF_IP_FLAG_CALL) {
+                struct call_path_root *cpr = ts->crp->cpr;
+                struct call_path *cp;
+                u64 ret_addr;
+
+                if (!sample->ip || !sample->addr)
+                        return 0;
+
+                ret_addr = sample->ip + sample->insn_len;
+                if (ret_addr == sample->addr)
+                        return 0; /* Zero-length calls are excluded */
+
+                cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp,
+                                        to_al->sym, sample->addr,
+                                        ts->kernel_start);
+                if (!cp)
+                        return -ENOMEM;
+                err = thread_stack__push_cp(ts, ret_addr, sample->time, ref,
+                                            cp, false);
+        } else if (sample->flags & PERF_IP_FLAG_RETURN) {
+                if (!sample->ip || !sample->addr)
+                        return 0;
+
+                err = thread_stack__pop_cp(thread, ts, sample->addr,
+                                           sample->time, ref, from_al->sym);
+                if (err) {
+                        if (err < 0)
+                                return err;
+                        err = thread_stack__no_call_return(thread, ts, sample,
+                                                           from_al, to_al, ref);
+                }
+        } else if (sample->flags & PERF_IP_FLAG_TRACE_BEGIN) {
+                err = thread_stack__trace_begin(thread, ts, sample->time, ref);
+        } else if (sample->flags & PERF_IP_FLAG_TRACE_END) {
+                err = thread_stack__trace_end(ts, sample, ref);
+        }
+
+        return err;
+}
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
new file mode 100644
index 000000000000..b843bbef8ba2
--- /dev/null
+++ b/tools/perf/util/thread-stack.h
@@ -0,0 +1,111 @@
+/*
+ * thread-stack.h: Synthesize a thread's stack using call / return events
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __PERF_THREAD_STACK_H
+#define __PERF_THREAD_STACK_H
+
+#include <sys/types.h>
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+
+struct thread;
+struct comm;
+struct ip_callchain;
+struct symbol;
+struct dso;
+struct call_return_processor;
+struct comm;
+struct perf_sample;
+struct addr_location;
+
+/*
+ * Call/Return flags.
+ *
+ * CALL_RETURN_NO_CALL: 'return' but no matching 'call'
+ * CALL_RETURN_NO_RETURN: 'call' but no matching 'return'
+ */
+enum {
+        CALL_RETURN_NO_CALL     = 1 << 0,
+        CALL_RETURN_NO_RETURN   = 1 << 1,
+};
+
+/**
+ * struct call_return - paired call/return information.
+ * @thread: thread in which call/return occurred
+ * @comm: comm in which call/return occurred
+ * @cp: call path
+ * @call_time: timestamp of call (if known)
+ * @return_time: timestamp of return (if known)
+ * @branch_count: number of branches seen between call and return
+ * @call_ref: external reference to 'call' sample (e.g. db_id)
+ * @return_ref:  external reference to 'return' sample (e.g. db_id)
+ * @db_id: id used for db-export
+ * @flags: Call/Return flags
+ */
+struct call_return {
+        struct thread *thread;
+        struct comm *comm;
+        struct call_path *cp;
+        u64 call_time;
+        u64 return_time;
+        u64 branch_count;
+        u64 call_ref;
+        u64 return_ref;
+        u64 db_id;
+        u32 flags;
+};
+
+/**
+ * struct call_path - node in list of calls leading to a function call.
+ * @parent: call path to the parent function call
+ * @sym: symbol of function called
+ * @ip: only if sym is null, the ip of the function
+ * @db_id: id used for db-export
+ * @in_kernel: whether function is a in the kernel
+ * @rb_node: node in parent's tree of called functions
+ * @children: tree of call paths of functions called
+ *
+ * In combination with the call_return structure, the call_path structure
+ * defines a context-sensitve call-graph.
+ */
+struct call_path {
+        struct call_path *parent;
+        struct symbol *sym;
+        u64 ip;
+        u64 db_id;
+        bool in_kernel;
+        struct rb_node rb_node;
+        struct rb_root children;
+};
+
+int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+                        u64 to_ip, u16 insn_len, u64 trace_nr);
+void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
+void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+                          size_t sz, u64 ip);
+void thread_stack__free(struct thread *thread);
+
+struct call_return_processor *
+call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+                           void *data);
+void call_return_processor__free(struct call_return_processor *crp);
+int thread_stack__process(struct thread *thread, struct comm *comm,
+                          struct perf_sample *sample,
+                          struct addr_location *from_al,
+                          struct addr_location *to_al, u64 ref,
+                          struct call_return_processor *crp);
+
+#endif
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index c41411726c7a..9ebc8b1f9be5 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -4,6 +4,7 @@
 #include <string.h>
 #include "session.h"
 #include "thread.h"
+#include "thread-stack.h"
 #include "util.h"
 #include "debug.h"
 #include "comm.h"
@@ -15,7 +16,7 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine)
         pid_t pid = thread->pid_;
 
         if (pid == thread->tid || pid == -1) {
-                thread->mg = map_groups__new();
+                thread->mg = map_groups__new(machine);
         } else {
                 leader = machine__findnew_thread(machine, pid, pid);
                 if (leader)
@@ -66,6 +67,8 @@ void thread__delete(struct thread *thread)
 {
         struct comm *comm, *tmp;
 
+        thread_stack__free(thread);
+
         if (thread->mg) {
                 map_groups__put(thread->mg);
                 thread->mg = NULL;
@@ -100,15 +103,14 @@ struct comm *thread__exec_comm(const struct thread *thread)
         return last;
 }
 
-/* CHECKME: time should always be 0 if event aren't ordered */
 int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
                        bool exec)
 {
         struct comm *new, *curr = thread__comm(thread);
         int err;
 
-        /* Override latest entry if it had no specific time coverage */
-        if (!curr->start && !curr->exec) {
+        /* Override the default :tid entry */
+        if (!thread->comm_set) {
                 err = comm__override(curr, str, timestamp, exec);
                 if (err)
                         return err;
@@ -198,7 +200,6 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 }
 
 void thread__find_cpumode_addr_location(struct thread *thread,
-                                        struct machine *machine,
                                         enum map_type type, u64 addr,
                                         struct addr_location *al)
 {
@@ -211,8 +212,7 @@ void thread__find_cpumode_addr_location(struct thread *thread,
         };
 
         for (i = 0; i < ARRAY_SIZE(cpumodes); i++) {
-                thread__find_addr_location(thread, machine, cpumodes[i], type,
-                                           addr, al);
+                thread__find_addr_location(thread, cpumodes[i], type, addr, al);
                 if (al->map)
                         break;
         }
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 8c75fa774706..160fd066a7d1 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -8,6 +8,8 @@
 #include "symbol.h"
 #include <strlist.h>
 
+struct thread_stack;
+
 struct thread {
         union {
                 struct rb_node   rb_node;
@@ -23,8 +25,10 @@ struct thread {
         bool                    dead; /* if set thread has exited */
         struct list_head        comm_list;
         int                     comm_len;
+        u64                     db_id;
 
         void                    *priv;
+        struct thread_stack     *ts;
 };
 
 struct machine;
@@ -54,16 +58,15 @@ void thread__insert_map(struct thread *thread, struct map *map);
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
-void thread__find_addr_map(struct thread *thread, struct machine *machine,
+void thread__find_addr_map(struct thread *thread,
                            u8 cpumode, enum map_type type, u64 addr,
                            struct addr_location *al);
 
-void thread__find_addr_location(struct thread *thread, struct machine *machine,
+void thread__find_addr_location(struct thread *thread,
                                 u8 cpumode, enum map_type type, u64 addr,
                                 struct addr_location *al);
 
 void thread__find_cpumode_addr_location(struct thread *thread,
-                                        struct machine *machine,
                                         enum map_type type, u64 addr,
                                         struct addr_location *al);
 
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index f11636966a0f..bb2708bbfaca 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -39,7 +39,8 @@ struct perf_tool {
         event_attr_op   attr;
         event_op2       tracing_data;
         event_op2       finished_round,
-                        build_id;
+                        build_id,
+                        id_index;
         bool            ordered_events;
         bool            ordering_requires_timestamps;
 };
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 7419768c38b1..2dcfe9a7c8d0 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -26,7 +26,7 @@ static int __report_module(struct addr_location *al, u64 ip,
         Dwfl_Module *mod;
         struct dso *dso = NULL;
 
-        thread__find_addr_location(ui->thread, ui->machine,
+        thread__find_addr_location(ui->thread,
                                    PERF_RECORD_MISC_USER,
                                    MAP__FUNCTION, ip, al);
 
@@ -89,7 +89,7 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
         struct addr_location al;
         ssize_t size;
 
-        thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+        thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
                               MAP__FUNCTION, addr, &al);
         if (!al.map) {
                 pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
@@ -164,14 +164,14 @@ frame_callback(Dwfl_Frame *state, void *arg)
 }
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
-                        struct machine *machine, struct thread *thread,
+                        struct thread *thread,
                         struct perf_sample *data,
                         int max_stack)
 {
         struct unwind_info ui = {
                 .sample         = data,
                 .thread         = thread,
-                .machine        = machine,
+                .machine        = thread->mg->machine,
                 .cb             = cb,
                 .arg            = arg,
                 .max_stack      = max_stack,
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 4d45c0dfe343..6edf535f65c2 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -185,6 +185,28 @@ static u64 elf_section_offset(int fd, const char *name)
         return offset;
 }
 
+#ifndef NO_LIBUNWIND_DEBUG_FRAME
+static int elf_is_exec(int fd, const char *name)
+{
+        Elf *elf;
+        GElf_Ehdr ehdr;
+        int retval = 0;
+
+        elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+        if (elf == NULL)
+                return 0;
+        if (gelf_getehdr(elf, &ehdr) == NULL)
+                goto out;
+
+        retval = (ehdr.e_type == ET_EXEC);
+
+out:
+        elf_end(elf);
+        pr_debug("unwind: elf_is_exec(%s): %d\n", name, retval);
+        return retval;
+}
+#endif
+
 struct table_entry {
         u32 start_ip_offset;
         u32 fde_offset;
@@ -284,7 +306,7 @@ static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
 {
         struct addr_location al;
 
-        thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+        thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
                               MAP__FUNCTION, ip, &al);
         return al.map;
 }
@@ -322,8 +344,12 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
 #ifndef NO_LIBUNWIND_DEBUG_FRAME
         /* Check the .debug_frame section for unwinding info */
         if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
+                int fd = dso__data_fd(map->dso, ui->machine);
+                int is_exec = elf_is_exec(fd, map->dso->name);
+                unw_word_t base = is_exec ? 0 : map->start;
+
                 memset(&di, 0, sizeof(di));
-                if (dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name,
+                if (dwarf_find_debug_frame(0, &di, ip, base, map->dso->name,
                                            map->start, map->end))
                         return dwarf_search_unwind_table(as, ip, &di, pi,
                                                          need_unwind_info, arg);
@@ -374,7 +400,7 @@ static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
         struct addr_location al;
         ssize_t size;
 
-        thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+        thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
                               MAP__FUNCTION, addr, &al);
         if (!al.map) {
                 pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
@@ -476,14 +502,13 @@ static void put_unwind_info(unw_addr_space_t __maybe_unused as,
         pr_debug("unwind: put_unwind_info called\n");
 }
 
-static int entry(u64 ip, struct thread *thread, struct machine *machine,
+static int entry(u64 ip, struct thread *thread,
                  unwind_entry_cb_t cb, void *arg)
 {
         struct unwind_entry e;
         struct addr_location al;
 
-        thread__find_addr_location(thread, machine,
-                                   PERF_RECORD_MISC_USER,
+        thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
                                    MAP__FUNCTION, ip, &al);
 
         e.ip = ip;
@@ -586,21 +611,21 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
                 unw_word_t ip;
 
                 unw_get_reg(&c, UNW_REG_IP, &ip);
-                ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0;
+                ret = ip ? entry(ip, ui->thread, cb, arg) : 0;
         }
 
         return ret;
 }
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
-                        struct machine *machine, struct thread *thread,
+                        struct thread *thread,
                         struct perf_sample *data, int max_stack)
 {
         u64 ip;
         struct unwind_info ui = {
                 .sample       = data,
                 .thread       = thread,
-                .machine      = machine,
+                .machine      = thread->mg->machine,
         };
         int ret;
 
@@ -611,7 +636,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
         if (ret)
                 return ret;
 
-        ret = entry(ip, thread, machine, cb, arg);
+        ret = entry(ip, thread, cb, arg);
         if (ret)
                 return -ENOMEM;
 
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index f50b737235eb..12790cf94618 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -16,7 +16,6 @@ typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
-                        struct machine *machine,
                         struct thread *thread,
                         struct perf_sample *data, int max_stack);
 /* libunwind specific */
@@ -38,7 +37,6 @@ static inline void unwind__finish_access(struct thread *thread __maybe_unused) {
 static inline int
 unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
                     void *arg __maybe_unused,
-                    struct machine *machine __maybe_unused,
                     struct thread *thread __maybe_unused,
                     struct perf_sample *data __maybe_unused,
                     int max_stack __maybe_unused)
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index d5eab3f3323f..b86744f29eef 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -442,23 +442,6 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags)
         return (unsigned long) -1;
 }
 
-int filename__read_int(const char *filename, int *value)
-{
-        char line[64];
-        int fd = open(filename, O_RDONLY), err = -1;
-
-        if (fd < 0)
-                return -1;
-
-        if (read(fd, line, sizeof(line)) > 0) {
-                *value = atoi(line);
-                err = 0;
-        }
-
-        close(fd);
-        return err;
-}
-
 int filename__read_str(const char *filename, char **buf, size_t *sizep)
 {
         size_t size = 0, alloc_size = 0;
@@ -523,16 +506,9 @@ const char *get_filename_for_perf_kvm(void)
 
 int perf_event_paranoid(void)
 {
-        char path[PATH_MAX];
-        const char *procfs = procfs__mountpoint();
         int value;
 
-        if (!procfs)
-                return INT_MAX;
-
-        scnprintf(path, PATH_MAX, "%s/sys/kernel/perf_event_paranoid", procfs);
-
-        if (filename__read_int(path, &value))
+        if (sysctl__read_int("kernel/perf_event_paranoid", &value))
                 return INT_MAX;
 
         return value;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 80bfdaa0e2a4..027a5153495c 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -153,8 +153,7 @@ extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2)))
 extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN);
 
 extern int prefixcmp(const char *str, const char *prefix);
-extern void set_buildid_dir(void);
-extern void disable_buildid_cache(void);
+extern void set_buildid_dir(const char *dir);
 
 static inline const char *skip_prefix(const char *str, const char *prefix)
 {
@@ -270,35 +269,6 @@ void event_attr_init(struct perf_event_attr *attr);
 #define _STR(x) #x
 #define STR(x) _STR(x)
 
-/*
- *  Determine whether some value is a power of two, where zero is
- * *not* considered a power of two.
- */
-
-static inline __attribute__((const))
-bool is_power_of_2(unsigned long n)
-{
-        return (n != 0 && ((n & (n - 1)) == 0));
-}
-
-static inline unsigned next_pow2(unsigned x)
-{
-        if (!x)
-                return 1;
-        return 1ULL << (32 - __builtin_clz(x - 1));
-}
-
-static inline unsigned long next_pow2_l(unsigned long x)
-{
-#if BITS_PER_LONG == 64
-        if (x <= (1UL << 31))
-                return next_pow2(x);
-        return (unsigned long)next_pow2(x >> 32) << 32;
-#else
-        return next_pow2(x);
-#endif
-}
-
 size_t hex_width(u64 v);
 int hex2u64(const char *ptr, u64 *val);
 
@@ -338,11 +308,12 @@ static inline int path__join3(char *bf, size_t size,
 }
 
 struct dso;
+struct symbol;
 
-char *get_srcline(struct dso *dso, unsigned long addr);
+char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
+                  bool show_sym);
 void free_srcline(char *srcline);
 
-int filename__read_int(const char *filename, int *value);
 int filename__read_str(const char *filename, char **buf, size_t *sizep);
 int perf_event_paranoid(void);
 
@@ -351,4 +322,9 @@ void mem_bswap_32(void *src, int byte_size);
 
 const char *get_filename_for_perf_kvm(void);
 bool find_process(const char *name);
+
+#ifdef HAVE_ZLIB_SUPPORT
+int gzip_decompress_to_file(const char *input, int output_fd);
+#endif
+
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index adca69384fcc..5c7dd796979d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -12,9 +12,16 @@
 #include "util.h"
 #include "symbol.h"
 #include "machine.h"
+#include "thread.h"
 #include "linux/string.h"
 #include "debug.h"
 
+/*
+ * Include definition of find_vdso_map() also used in perf-read-vdso.c for
+ * building perf-read-vdso32 and perf-read-vdsox32.
+ */
+#include "find-vdso-map.c"
+
 #define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX"
 
 struct vdso_file {
@@ -22,10 +29,15 @@ struct vdso_file {
         bool error;
         char temp_file_name[sizeof(VDSO__TEMP_FILE_NAME)];
         const char *dso_name;
+        const char *read_prog;
 };
 
 struct vdso_info {
         struct vdso_file vdso;
+#if BITS_PER_LONG == 64
+        struct vdso_file vdso32;
+        struct vdso_file vdsox32;
+#endif
 };
 
 static struct vdso_info *vdso_info__new(void)
@@ -35,42 +47,23 @@ static struct vdso_info *vdso_info__new(void)
                         .temp_file_name = VDSO__TEMP_FILE_NAME,
                         .dso_name = DSO__NAME_VDSO,
                 },
+#if BITS_PER_LONG == 64
+                .vdso32  = {
+                        .temp_file_name = VDSO__TEMP_FILE_NAME,
+                        .dso_name = DSO__NAME_VDSO32,
+                        .read_prog = "perf-read-vdso32",
+                },
+                .vdsox32  = {
+                        .temp_file_name = VDSO__TEMP_FILE_NAME,
+                        .dso_name = DSO__NAME_VDSOX32,
+                        .read_prog = "perf-read-vdsox32",
+                },
+#endif
         };
 
         return memdup(&vdso_info_init, sizeof(vdso_info_init));
 }
 
-static int find_vdso_map(void **start, void **end)
-{
-        FILE *maps;
-        char line[128];
-        int found = 0;
-
-        maps = fopen("/proc/self/maps", "r");
-        if (!maps) {
-                pr_err("vdso: cannot open maps\n");
-                return -1;
-        }
-
-        while (!found && fgets(line, sizeof(line), maps)) {
-                int m = -1;
-
-                /* We care only about private r-x mappings. */
-                if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n",
-                                start, end, &m))
-                        continue;
-                if (m < 0)
-                        continue;
-
-                if (!strncmp(&line[m], VDSO__MAP_NAME,
-                             sizeof(VDSO__MAP_NAME) - 1))
-                        found = 1;
-        }
-
-        fclose(maps);
-        return !found;
-}
-
 static char *get_file(struct vdso_file *vdso_file)
 {
         char *vdso = NULL;
@@ -117,6 +110,12 @@ void vdso__exit(struct machine *machine)
 
         if (vdso_info->vdso.found)
                 unlink(vdso_info->vdso.temp_file_name);
+#if BITS_PER_LONG == 64
+        if (vdso_info->vdso32.found)
+                unlink(vdso_info->vdso32.temp_file_name);
+        if (vdso_info->vdsox32.found)
+                unlink(vdso_info->vdsox32.temp_file_name);
+#endif
 
         zfree(&machine->vdso_info);
 }
@@ -135,6 +134,153 @@ static struct dso *vdso__new(struct machine *machine, const char *short_name,
         return dso;
 }
 
+#if BITS_PER_LONG == 64
+
+static enum dso_type machine__thread_dso_type(struct machine *machine,
+                                              struct thread *thread)
+{
+        enum dso_type dso_type = DSO__TYPE_UNKNOWN;
+        struct map *map;
+        struct dso *dso;
+
+        map = map_groups__first(thread->mg, MAP__FUNCTION);
+        for (; map ; map = map_groups__next(map)) {
+                dso = map->dso;
+                if (!dso || dso->long_name[0] != '/')
+                        continue;
+                dso_type = dso__type(dso, machine);
+                if (dso_type != DSO__TYPE_UNKNOWN)
+                        break;
+        }
+
+        return dso_type;
+}
+
+static int vdso__do_copy_compat(FILE *f, int fd)
+{
+        char buf[4096];
+        size_t count;
+
+        while (1) {
+                count = fread(buf, 1, sizeof(buf), f);
+                if (ferror(f))
+                        return -errno;
+                if (feof(f))
+                        break;
+                if (count && writen(fd, buf, count) != (ssize_t)count)
+                        return -errno;
+        }
+
+        return 0;
+}
+
+static int vdso__copy_compat(const char *prog, int fd)
+{
+        FILE *f;
+        int err;
+
+        f = popen(prog, "r");
+        if (!f)
+                return -errno;
+
+        err = vdso__do_copy_compat(f, fd);
+
+        if (pclose(f) == -1)
+                return -errno;
+
+        return err;
+}
+
+static int vdso__create_compat_file(const char *prog, char *temp_name)
+{
+        int fd, err;
+
+        fd = mkstemp(temp_name);
+        if (fd < 0)
+                return -errno;
+
+        err = vdso__copy_compat(prog, fd);
+
+        if (close(fd) == -1)
+                return -errno;
+
+        return err;
+}
+
+static const char *vdso__get_compat_file(struct vdso_file *vdso_file)
+{
+        int err;
+
+        if (vdso_file->found)
+                return vdso_file->temp_file_name;
+
+        if (vdso_file->error)
+                return NULL;
+
+        err = vdso__create_compat_file(vdso_file->read_prog,
+                                       vdso_file->temp_file_name);
+        if (err) {
+                pr_err("%s failed, error %d\n", vdso_file->read_prog, err);
+                vdso_file->error = true;
+                return NULL;
+        }
+
+        vdso_file->found = true;
+
+        return vdso_file->temp_file_name;
+}
+
+static struct dso *vdso__findnew_compat(struct machine *machine,
+                                        struct vdso_file *vdso_file)
+{
+        const char *file_name;
+        struct dso *dso;
+
+        dso = dsos__find(&machine->user_dsos, vdso_file->dso_name, true);
+        if (dso)
+                return dso;
+
+        file_name = vdso__get_compat_file(vdso_file);
+        if (!file_name)
+                return NULL;
+
+        return vdso__new(machine, vdso_file->dso_name, file_name);
+}
+
+static int vdso__dso_findnew_compat(struct machine *machine,
+                                    struct thread *thread,
+                                    struct vdso_info *vdso_info,
+                                    struct dso **dso)
+{
+        enum dso_type dso_type;
+
+        dso_type = machine__thread_dso_type(machine, thread);
+
+#ifndef HAVE_PERF_READ_VDSO32
+        if (dso_type == DSO__TYPE_32BIT)
+                return 0;
+#endif
+#ifndef HAVE_PERF_READ_VDSOX32
+        if (dso_type == DSO__TYPE_X32BIT)
+                return 0;
+#endif
+
+        switch (dso_type) {
+        case DSO__TYPE_32BIT:
+                *dso = vdso__findnew_compat(machine, &vdso_info->vdso32);
+                return 1;
+        case DSO__TYPE_X32BIT:
+                *dso = vdso__findnew_compat(machine, &vdso_info->vdsox32);
+                return 1;
+        case DSO__TYPE_UNKNOWN:
+        case DSO__TYPE_64BIT:
+        default:
+                return 0;
+        }
+}
+
+#endif
+
 struct dso *vdso__dso_findnew(struct machine *machine,
                               struct thread *thread __maybe_unused)
 {
@@ -148,6 +294,11 @@ struct dso *vdso__dso_findnew(struct machine *machine,
         if (!vdso_info)
                 return NULL;
 
+#if BITS_PER_LONG == 64
+        if (vdso__dso_findnew_compat(machine, thread, vdso_info, &dso))
+                return dso;
+#endif
+
         dso = dsos__find(&machine->user_dsos, DSO__NAME_VDSO, true);
         if (!dso) {
                 char *file;
@@ -164,5 +315,7 @@ struct dso *vdso__dso_findnew(struct machine *machine,
 
 bool dso__is_vdso(struct dso *dso)
 {
-        return !strcmp(dso->short_name, DSO__NAME_VDSO);
+        return !strcmp(dso->short_name, DSO__NAME_VDSO) ||
+               !strcmp(dso->short_name, DSO__NAME_VDSO32) ||
+               !strcmp(dso->short_name, DSO__NAME_VDSOX32);
 }
diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h
index af9d6929a215..d97da1616f0c 100644
--- a/tools/perf/util/vdso.h
+++ b/tools/perf/util/vdso.h
@@ -7,7 +7,9 @@
 
 #define VDSO__MAP_NAME "[vdso]"
 
-#define DSO__NAME_VDSO "[vdso]"
+#define DSO__NAME_VDSO    "[vdso]"
+#define DSO__NAME_VDSO32  "[vdso32]"
+#define DSO__NAME_VDSOX32 "[vdsox32]"
 
 static inline bool is_vdso_map(const char *filename)
 {
diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c
new file mode 100644
index 000000000000..495a449fc25c
--- /dev/null
+++ b/tools/perf/util/zlib.c
@@ -0,0 +1,78 @@
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <zlib.h>
+
+#include "util/util.h"
+#include "util/debug.h"
+
+
+#define CHUNK_SIZE  16384
+
+int gzip_decompress_to_file(const char *input, int output_fd)
+{
+        int ret = Z_STREAM_ERROR;
+        int input_fd;
+        void *ptr;
+        int len;
+        struct stat stbuf;
+        unsigned char buf[CHUNK_SIZE];
+        z_stream zs = {
+                .zalloc         = Z_NULL,
+                .zfree          = Z_NULL,
+                .opaque         = Z_NULL,
+                .avail_in       = 0,
+                .next_in        = Z_NULL,
+        };
+
+        input_fd = open(input, O_RDONLY);
+        if (input_fd < 0)
+                return -1;
+
+        if (fstat(input_fd, &stbuf) < 0)
+                goto out_close;
+
+        ptr = mmap(NULL, stbuf.st_size, PROT_READ, MAP_PRIVATE, input_fd, 0);
+        if (ptr == MAP_FAILED)
+                goto out_close;
+
+        if (inflateInit2(&zs, 16 + MAX_WBITS) != Z_OK)
+                goto out_unmap;
+
+        zs.next_in = ptr;
+        zs.avail_in = stbuf.st_size;
+
+        do {
+                zs.next_out = buf;
+                zs.avail_out = CHUNK_SIZE;
+
+                ret = inflate(&zs, Z_NO_FLUSH);
+                switch (ret) {
+                case Z_NEED_DICT:
+                        ret = Z_DATA_ERROR;
+                        /* fall through */
+                case Z_DATA_ERROR:
+                case Z_MEM_ERROR:
+                        goto out;
+                default:
+                        break;
+                }
+
+                len = CHUNK_SIZE - zs.avail_out;
+                if (writen(output_fd, buf, len) != len) {
+                        ret = Z_DATA_ERROR;
+                        goto out;
+                }
+
+        } while (ret != Z_STREAM_END);
+
+out:
+        inflateEnd(&zs);
+out_unmap:
+        munmap(ptr, stbuf.st_size);
+out_close:
+        close(input_fd);
+
+        return ret == Z_STREAM_END ? 0 : -1;
+}
diff --git a/tools/power/cpupower/utils/cpupower.c b/tools/power/cpupower/utils/cpupower.c
index 7cdcf88659c7..9ea914378985 100644
--- a/tools/power/cpupower/utils/cpupower.c
+++ b/tools/power/cpupower/utils/cpupower.c
@@ -199,7 +199,7 @@ int main(int argc, const char *argv[])
         }
 
         get_cpu_info(0, &cpupower_cpu_info);
-        run_as_root = !getuid();
+        run_as_root = !geteuid();
         if (run_as_root) {
                 ret = uname(&uts);
                 if (!ret && !strcmp(uts.machine, "x86_64") &&
diff --git a/tools/power/cpupower/utils/helpers/sysfs.c b/tools/power/cpupower/utils/helpers/sysfs.c
index 09afe5d87f2b..4e8fe2c7b054 100644
--- a/tools/power/cpupower/utils/helpers/sysfs.c
+++ b/tools/power/cpupower/utils/helpers/sysfs.c
@@ -361,7 +361,7 @@ unsigned int sysfs_get_idlestate_count(unsigned int cpu)
 
         snprintf(file, SYSFS_PATH_MAX, PATH_TO_CPU "cpuidle");
         if (stat(file, &statbuf) != 0 || !S_ISDIR(statbuf.st_mode))
-                return -ENODEV;
+                return 0;
 
         snprintf(file, SYSFS_PATH_MAX, PATH_TO_CPU "cpu%u/cpuidle/state0", cpu);
         if (stat(file, &statbuf) != 0 || !S_ISDIR(statbuf.st_mode))
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index bf1398180785..b9cd036f0442 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -684,11 +684,8 @@ sub set_value {
         }
         ${$overrides}{$lvalue} = $prvalue;
     }
-    if ($rvalue =~ /^\s*$/) {
-        delete $opt{$lvalue};
-    } else {
-        $opt{$lvalue} = $prvalue;
-    }
+
+    $opt{$lvalue} = $prvalue;
 }
 
 sub set_eval {
@@ -2005,7 +2002,7 @@ sub get_version {
     # get the release name
     return if ($have_version);
     doprint "$make kernelrelease ... ";
-    $version = `$make kernelrelease | tail -1`;
+    $version = `$make -s kernelrelease | tail -1`;
     chomp($version);
     doprint "$version\n";
     $have_version = 1;
@@ -3571,7 +3568,9 @@ sub test_this_config {
     undef %configs;
     assign_configs \%configs, $output_config;
 
-    return $config if (!defined($configs{$config}));
+    if (!defined($configs{$config}) || $configs{$config} =~ /^#/) {
+        return $config;
+    }
 
     doprint "disabling config $config did not change .config\n";
 
@@ -3945,12 +3944,22 @@ for (my $i = 0, my $repeat = 1; $i <= $opt{"NUM_TESTS"}; $i += $repeat) {
     }
 }
 
+sub option_defined {
+    my ($option) = @_;
+
+    if (defined($opt{$option}) && $opt{$option} !~ /^\s*$/) {
+        return 1;
+    }
+
+    return 0;
+}
+
 sub __set_test_option {
     my ($name, $i) = @_;
 
     my $option = "$name\[$i\]";
 
-    if (defined($opt{$option})) {
+    if (option_defined($option)) {
         return $opt{$option};
     }
 
@@ -3958,13 +3967,13 @@ sub __set_test_option {
         if ($i >= $test &&
             $i < $test + $repeat_tests{$test}) {
             $option = "$name\[$test\]";
-            if (defined($opt{$option})) {
+            if (option_defined($option)) {
                 return $opt{$option};
             }
         }
     }
 
-    if (defined($opt{$name})) {
+    if (option_defined($name)) {
         return $opt{$name};
     }
 
@@ -4077,8 +4086,14 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
     my $installme = "";
     $installme = " no_install" if ($no_install);
 
+    my $name = "";
+
+    if (defined($test_name)) {
+        $name = " ($test_name)";
+    }
+
     doprint "\n\n";
-    doprint "RUNNING TEST $i of $opt{NUM_TESTS} with option $test_type $run_type$installme\n\n";
+    doprint "RUNNING TEST $i of $opt{NUM_TESTS}$name with option $test_type $run_type$installme\n\n";
 
     if (defined($pre_test)) {
         run_command $pre_test;
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 45f145c6f843..4e511221a0c1 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,20 +1,23 @@
 TARGETS = breakpoints
 TARGETS += cpu-hotplug
 TARGETS += efivarfs
+TARGETS += exec
+TARGETS += firmware
+TARGETS += ftrace
 TARGETS += kcmp
 TARGETS += memfd
 TARGETS += memory-hotplug
-TARGETS += mqueue
 TARGETS += mount
+TARGETS += mqueue
 TARGETS += net
+TARGETS += powerpc
 TARGETS += ptrace
+TARGETS += size
+TARGETS += sysctl
 TARGETS += timers
-TARGETS += vm
-TARGETS += powerpc
 TARGETS += user
-TARGETS += sysctl
-TARGETS += firmware
-TARGETS += ftrace
+TARGETS += vm
+#Please keep the TARGETS list alphabetically sorted
 
 TARGETS_HOTPLUG = cpu-hotplug
 TARGETS_HOTPLUG += memory-hotplug
diff --git a/tools/testing/selftests/README.txt b/tools/testing/selftests/README.txt
deleted file mode 100644
index 2660d5ff9179..000000000000
--- a/tools/testing/selftests/README.txt
+++ /dev/null
@@ -1,61 +0,0 @@
-Linux Kernel Selftests
-
-The kernel contains a set of "self tests" under the tools/testing/selftests/
-directory. These are intended to be small unit tests to exercise individual
-code paths in the kernel.
-
-On some systems, hot-plug tests could hang forever waiting for cpu and
-memory to be ready to be offlined. A special hot-plug target is created
-to run full range of hot-plug tests. In default mode, hot-plug tests run
-in safe mode with a limited scope. In limited mode, cpu-hotplug test is
-run on a single cpu as opposed to all hotplug capable cpus, and memory
-hotplug test is run on 2% of hotplug capable memory instead of 10%.
-
-Running the selftests (hotplug tests are run in limited mode)
-=============================================================
-
-To build the tests:
-
-  $ make -C tools/testing/selftests
-
-
-To run the tests:
-
-  $ make -C tools/testing/selftests run_tests
-
-- note that some tests will require root privileges.
-
-To run only tests targeted for a single subsystem: (including
-hotplug targets in limited mode)
-
-  $  make -C tools/testing/selftests TARGETS=cpu-hotplug run_tests
-
-See the top-level tools/testing/selftests/Makefile for the list of all possible
-targets.
-
-Running the full range hotplug selftests
-========================================
-
-To build the tests:
-
-  $ make -C tools/testing/selftests hotplug
-
-To run the tests:
-
-  $ make -C tools/testing/selftests run_hotplug
-
-- note that some tests will require root privileges.
-
-Contributing new tests
-======================
-
-In general, the rules for for selftests are
-
- * Do as much as you can if you're not root;
-
- * Don't take too long;
-
- * Don't break the build on any architecture, and
-
- * Don't cause the top-level "make run_tests" to fail if your feature is
-   unconfigured.
diff --git a/tools/testing/selftests/breakpoints/breakpoint_test.c b/tools/testing/selftests/breakpoints/breakpoint_test.c
index a0743f3b2b57..120895ab5505 100644
--- a/tools/testing/selftests/breakpoints/breakpoint_test.c
+++ b/tools/testing/selftests/breakpoints/breakpoint_test.c
@@ -17,6 +17,8 @@
 #include <sys/types.h>
 #include <sys/wait.h>
 
+#include "../kselftest.h"
+
 
 /* Breakpoint access modes */
 enum {
@@ -42,7 +44,7 @@ static void set_breakpoint_addr(void *addr, int n)
                      offsetof(struct user, u_debugreg[n]), addr);
         if (ret) {
                 perror("Can't set breakpoint addr\n");
-                exit(-1);
+                ksft_exit_fail();
         }
 }
 
@@ -105,7 +107,7 @@ static void toggle_breakpoint(int n, int type, int len,
                      offsetof(struct user, u_debugreg[7]), dr7);
         if (ret) {
                 perror("Can't set dr7");
-                exit(-1);
+                ksft_exit_fail();
         }
 }
 
@@ -275,7 +277,7 @@ static void check_success(const char *msg)
                         msg2 = "Ok";
                 if (ptrace(PTRACE_POKEDATA, child_pid, &trapped, 1)) {
                         perror("Can't poke\n");
-                        exit(-1);
+                        ksft_exit_fail();
                 }
         }
 
@@ -390,5 +392,5 @@ int main(int argc, char **argv)
 
         wait(NULL);
 
-        return 0;
+        return ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/exec/.gitignore b/tools/testing/selftests/exec/.gitignore
new file mode 100644
index 000000000000..64073e050c6a
--- /dev/null
+++ b/tools/testing/selftests/exec/.gitignore
@@ -0,0 +1,9 @@
+subdir*
+script*
+execveat
+execveat.symlink
+execveat.moved
+execveat.path.ephemeral
+execveat.ephemeral
+execveat.denatured
+xxxxxxxx*
\ No newline at end of file
diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile
new file mode 100644
index 000000000000..66dfc2ce1788
--- /dev/null
+++ b/tools/testing/selftests/exec/Makefile
@@ -0,0 +1,25 @@
+CC = $(CROSS_COMPILE)gcc
+CFLAGS = -Wall
+BINARIES = execveat
+DEPS = execveat.symlink execveat.denatured script subdir
+all: $(BINARIES) $(DEPS)
+
+subdir:
+        mkdir -p $@
+script:
+        echo '#!/bin/sh' > $@
+        echo 'exit $$*' >> $@
+        chmod +x $@
+execveat.symlink: execveat
+        ln -s -f $< $@
+execveat.denatured: execveat
+        cp $< $@
+        chmod -x $@
+%: %.c
+        $(CC) $(CFLAGS) -o $@ $^
+
+run_tests: all
+        ./execveat
+
+clean:
+        rm -rf $(BINARIES) $(DEPS) subdir.moved execveat.moved xxxxx*
diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c
new file mode 100644
index 000000000000..e238c9559caf
--- /dev/null
+++ b/tools/testing/selftests/exec/execveat.c
@@ -0,0 +1,404 @@
+/*
+ * Copyright (c) 2014 Google, Inc.
+ *
+ * Licensed under the terms of the GNU GPL License version 2
+ *
+ * Selftests for execveat(2).
+ */
+
+#define _GNU_SOURCE  /* to get O_PATH, AT_EMPTY_PATH */
+#include <sys/sendfile.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+static char longpath[2 * PATH_MAX] = "";
+static char *envp[] = { "IN_TEST=yes", NULL, NULL };
+static char *argv[] = { "execveat", "99", NULL };
+
+static int execveat_(int fd, const char *path, char **argv, char **envp,
+                     int flags)
+{
+#ifdef __NR_execveat
+        return syscall(__NR_execveat, fd, path, argv, envp, flags);
+#else
+        errno = -ENOSYS;
+        return -1;
+#endif
+}
+
+#define check_execveat_fail(fd, path, flags, errno)     \
+        _check_execveat_fail(fd, path, flags, errno, #errno)
+static int _check_execveat_fail(int fd, const char *path, int flags,
+                                int expected_errno, const char *errno_str)
+{
+        int rc;
+
+        errno = 0;
+        printf("Check failure of execveat(%d, '%s', %d) with %s... ",
+                fd, path?:"(null)", flags, errno_str);
+        rc = execveat_(fd, path, argv, envp, flags);
+
+        if (rc > 0) {
+                printf("[FAIL] (unexpected success from execveat(2))\n");
+                return 1;
+        }
+        if (errno != expected_errno) {
+                printf("[FAIL] (expected errno %d (%s) not %d (%s)\n",
+                        expected_errno, strerror(expected_errno),
+                        errno, strerror(errno));
+                return 1;
+        }
+        printf("[OK]\n");
+        return 0;
+}
+
+static int check_execveat_invoked_rc(int fd, const char *path, int flags,
+                                     int expected_rc, int expected_rc2)
+{
+        int status;
+        int rc;
+        pid_t child;
+        int pathlen = path ? strlen(path) : 0;
+
+        if (pathlen > 40)
+                printf("Check success of execveat(%d, '%.20s...%s', %d)... ",
+                        fd, path, (path + pathlen - 20), flags);
+        else
+                printf("Check success of execveat(%d, '%s', %d)... ",
+                        fd, path?:"(null)", flags);
+        child = fork();
+        if (child < 0) {
+                printf("[FAIL] (fork() failed)\n");
+                return 1;
+        }
+        if (child == 0) {
+                /* Child: do execveat(). */
+                rc = execveat_(fd, path, argv, envp, flags);
+                printf("[FAIL]: execveat() failed, rc=%d errno=%d (%s)\n",
+                        rc, errno, strerror(errno));
+                exit(1);  /* should not reach here */
+        }
+        /* Parent: wait for & check child's exit status. */
+        rc = waitpid(child, &status, 0);
+        if (rc != child) {
+                printf("[FAIL] (waitpid(%d,...) returned %d)\n", child, rc);
+                return 1;
+        }
+        if (!WIFEXITED(status)) {
+                printf("[FAIL] (child %d did not exit cleanly, status=%08x)\n",
+                        child, status);
+                return 1;
+        }
+        if ((WEXITSTATUS(status) != expected_rc) &&
+            (WEXITSTATUS(status) != expected_rc2)) {
+                printf("[FAIL] (child %d exited with %d not %d nor %d)\n",
+                        child, WEXITSTATUS(status), expected_rc, expected_rc2);
+                return 1;
+        }
+        printf("[OK]\n");
+        return 0;
+}
+
+static int check_execveat(int fd, const char *path, int flags)
+{
+        return check_execveat_invoked_rc(fd, path, flags, 99, 99);
+}
+
+static char *concat(const char *left, const char *right)
+{
+        char *result = malloc(strlen(left) + strlen(right) + 1);
+
+        strcpy(result, left);
+        strcat(result, right);
+        return result;
+}
+
+static int open_or_die(const char *filename, int flags)
+{
+        int fd = open(filename, flags);
+
+        if (fd < 0) {
+                printf("Failed to open '%s'; "
+                        "check prerequisites are available\n", filename);
+                exit(1);
+        }
+        return fd;
+}
+
+static void exe_cp(const char *src, const char *dest)
+{
+        int in_fd = open_or_die(src, O_RDONLY);
+        int out_fd = open(dest, O_RDWR|O_CREAT|O_TRUNC, 0755);
+        struct stat info;
+
+        fstat(in_fd, &info);
+        sendfile(out_fd, in_fd, NULL, info.st_size);
+        close(in_fd);
+        close(out_fd);
+}
+
+#define XX_DIR_LEN 200
+static int check_execveat_pathmax(int dot_dfd, const char *src, int is_script)
+{
+        int fail = 0;
+        int ii, count, len;
+        char longname[XX_DIR_LEN + 1];
+        int fd;
+
+        if (*longpath == '\0') {
+                /* Create a filename close to PATH_MAX in length */
+                memset(longname, 'x', XX_DIR_LEN - 1);
+                longname[XX_DIR_LEN - 1] = '/';
+                longname[XX_DIR_LEN] = '\0';
+                count = (PATH_MAX - 3) / XX_DIR_LEN;
+                for (ii = 0; ii < count; ii++) {
+                        strcat(longpath, longname);
+                        mkdir(longpath, 0755);
+                }
+                len = (PATH_MAX - 3) - (count * XX_DIR_LEN);
+                if (len <= 0)
+                        len = 1;
+                memset(longname, 'y', len);
+                longname[len] = '\0';
+                strcat(longpath, longname);
+        }
+        exe_cp(src, longpath);
+
+        /*
+         * Execute as a pre-opened file descriptor, which works whether this is
+         * a script or not (because the interpreter sees a filename like
+         * "/dev/fd/20").
+         */
+        fd = open(longpath, O_RDONLY);
+        if (fd > 0) {
+                printf("Invoke copy of '%s' via filename of length %zu:\n",
+                        src, strlen(longpath));
+                fail += check_execveat(fd, "", AT_EMPTY_PATH);
+        } else {
+                printf("Failed to open length %zu filename, errno=%d (%s)\n",
+                        strlen(longpath), errno, strerror(errno));
+                fail++;
+        }
+
+        /*
+         * Execute as a long pathname relative to ".".  If this is a script,
+         * the interpreter will launch but fail to open the script because its
+         * name ("/dev/fd/5/xxx....") is bigger than PATH_MAX.
+         *
+         * The failure code is usually 127 (POSIX: "If a command is not found,
+         * the exit status shall be 127."), but some systems give 126 (POSIX:
+         * "If the command name is found, but it is not an executable utility,
+         * the exit status shall be 126."), so allow either.
+         */
+        if (is_script)
+                fail += check_execveat_invoked_rc(dot_dfd, longpath, 0,
+                                                  127, 126);
+        else
+                fail += check_execveat(dot_dfd, longpath, 0);
+
+        return fail;
+}
+
+static int run_tests(void)
+{
+        int fail = 0;
+        char *fullname = realpath("execveat", NULL);
+        char *fullname_script = realpath("script", NULL);
+        char *fullname_symlink = concat(fullname, ".symlink");
+        int subdir_dfd = open_or_die("subdir", O_DIRECTORY|O_RDONLY);
+        int subdir_dfd_ephemeral = open_or_die("subdir.ephemeral",
+                                               O_DIRECTORY|O_RDONLY);
+        int dot_dfd = open_or_die(".", O_DIRECTORY|O_RDONLY);
+        int dot_dfd_path = open_or_die(".", O_DIRECTORY|O_RDONLY|O_PATH);
+        int dot_dfd_cloexec = open_or_die(".", O_DIRECTORY|O_RDONLY|O_CLOEXEC);
+        int fd = open_or_die("execveat", O_RDONLY);
+        int fd_path = open_or_die("execveat", O_RDONLY|O_PATH);
+        int fd_symlink = open_or_die("execveat.symlink", O_RDONLY);
+        int fd_denatured = open_or_die("execveat.denatured", O_RDONLY);
+        int fd_denatured_path = open_or_die("execveat.denatured",
+                                            O_RDONLY|O_PATH);
+        int fd_script = open_or_die("script", O_RDONLY);
+        int fd_ephemeral = open_or_die("execveat.ephemeral", O_RDONLY);
+        int fd_ephemeral_path = open_or_die("execveat.path.ephemeral",
+                                            O_RDONLY|O_PATH);
+        int fd_script_ephemeral = open_or_die("script.ephemeral", O_RDONLY);
+        int fd_cloexec = open_or_die("execveat", O_RDONLY|O_CLOEXEC);
+        int fd_script_cloexec = open_or_die("script", O_RDONLY|O_CLOEXEC);
+
+        /* Change file position to confirm it doesn't affect anything */
+        lseek(fd, 10, SEEK_SET);
+
+        /* Normal executable file: */
+        /*   dfd + path */
+        fail += check_execveat(subdir_dfd, "../execveat", 0);
+        fail += check_execveat(dot_dfd, "execveat", 0);
+        fail += check_execveat(dot_dfd_path, "execveat", 0);
+        /*   absolute path */
+        fail += check_execveat(AT_FDCWD, fullname, 0);
+        /*   absolute path with nonsense dfd */
+        fail += check_execveat(99, fullname, 0);
+        /*   fd + no path */
+        fail += check_execveat(fd, "", AT_EMPTY_PATH);
+        /*   O_CLOEXEC fd + no path */
+        fail += check_execveat(fd_cloexec, "", AT_EMPTY_PATH);
+        /*   O_PATH fd */
+        fail += check_execveat(fd_path, "", AT_EMPTY_PATH);
+
+        /* Mess with executable file that's already open: */
+        /*   fd + no path to a file that's been renamed */
+        rename("execveat.ephemeral", "execveat.moved");
+        fail += check_execveat(fd_ephemeral, "", AT_EMPTY_PATH);
+        /*   fd + no path to a file that's been deleted */
+        unlink("execveat.moved"); /* remove the file now fd open */
+        fail += check_execveat(fd_ephemeral, "", AT_EMPTY_PATH);
+
+        /* Mess with executable file that's already open with O_PATH */
+        /*   fd + no path to a file that's been deleted */
+        unlink("execveat.path.ephemeral");
+        fail += check_execveat(fd_ephemeral_path, "", AT_EMPTY_PATH);
+
+        /* Invalid argument failures */
+        fail += check_execveat_fail(fd, "", 0, ENOENT);
+        fail += check_execveat_fail(fd, NULL, AT_EMPTY_PATH, EFAULT);
+
+        /* Symlink to executable file: */
+        /*   dfd + path */
+        fail += check_execveat(dot_dfd, "execveat.symlink", 0);
+        fail += check_execveat(dot_dfd_path, "execveat.symlink", 0);
+        /*   absolute path */
+        fail += check_execveat(AT_FDCWD, fullname_symlink, 0);
+        /*   fd + no path, even with AT_SYMLINK_NOFOLLOW (already followed) */
+        fail += check_execveat(fd_symlink, "", AT_EMPTY_PATH);
+        fail += check_execveat(fd_symlink, "",
+                               AT_EMPTY_PATH|AT_SYMLINK_NOFOLLOW);
+
+        /* Symlink fails when AT_SYMLINK_NOFOLLOW set: */
+        /*   dfd + path */
+        fail += check_execveat_fail(dot_dfd, "execveat.symlink",
+                                    AT_SYMLINK_NOFOLLOW, ELOOP);
+        fail += check_execveat_fail(dot_dfd_path, "execveat.symlink",
+                                    AT_SYMLINK_NOFOLLOW, ELOOP);
+        /*   absolute path */
+        fail += check_execveat_fail(AT_FDCWD, fullname_symlink,
+                                    AT_SYMLINK_NOFOLLOW, ELOOP);
+
+        /* Shell script wrapping executable file: */
+        /*   dfd + path */
+        fail += check_execveat(subdir_dfd, "../script", 0);
+        fail += check_execveat(dot_dfd, "script", 0);
+        fail += check_execveat(dot_dfd_path, "script", 0);
+        /*   absolute path */
+        fail += check_execveat(AT_FDCWD, fullname_script, 0);
+        /*   fd + no path */
+        fail += check_execveat(fd_script, "", AT_EMPTY_PATH);
+        fail += check_execveat(fd_script, "",
+                               AT_EMPTY_PATH|AT_SYMLINK_NOFOLLOW);
+        /*   O_CLOEXEC fd fails for a script (as script file inaccessible) */
+        fail += check_execveat_fail(fd_script_cloexec, "", AT_EMPTY_PATH,
+                                    ENOENT);
+        fail += check_execveat_fail(dot_dfd_cloexec, "script", 0, ENOENT);
+
+        /* Mess with script file that's already open: */
+        /*   fd + no path to a file that's been renamed */
+        rename("script.ephemeral", "script.moved");
+        fail += check_execveat(fd_script_ephemeral, "", AT_EMPTY_PATH);
+        /*   fd + no path to a file that's been deleted */
+        unlink("script.moved"); /* remove the file while fd open */
+        fail += check_execveat(fd_script_ephemeral, "", AT_EMPTY_PATH);
+
+        /* Rename a subdirectory in the path: */
+        rename("subdir.ephemeral", "subdir.moved");
+        fail += check_execveat(subdir_dfd_ephemeral, "../script", 0);
+        fail += check_execveat(subdir_dfd_ephemeral, "script", 0);
+        /* Remove the subdir and its contents */
+        unlink("subdir.moved/script");
+        unlink("subdir.moved");
+        /* Shell loads via deleted subdir OK because name starts with .. */
+        fail += check_execveat(subdir_dfd_ephemeral, "../script", 0);
+        fail += check_execveat_fail(subdir_dfd_ephemeral, "script", 0, ENOENT);
+
+        /* Flag values other than AT_SYMLINK_NOFOLLOW => EINVAL */
+        fail += check_execveat_fail(dot_dfd, "execveat", 0xFFFF, EINVAL);
+        /* Invalid path => ENOENT */
+        fail += check_execveat_fail(dot_dfd, "no-such-file", 0, ENOENT);
+        fail += check_execveat_fail(dot_dfd_path, "no-such-file", 0, ENOENT);
+        fail += check_execveat_fail(AT_FDCWD, "no-such-file", 0, ENOENT);
+        /* Attempt to execute directory => EACCES */
+        fail += check_execveat_fail(dot_dfd, "", AT_EMPTY_PATH, EACCES);
+        /* Attempt to execute non-executable => EACCES */
+        fail += check_execveat_fail(dot_dfd, "Makefile", 0, EACCES);
+        fail += check_execveat_fail(fd_denatured, "", AT_EMPTY_PATH, EACCES);
+        fail += check_execveat_fail(fd_denatured_path, "", AT_EMPTY_PATH,
+                                    EACCES);
+        /* Attempt to execute nonsense FD => EBADF */
+        fail += check_execveat_fail(99, "", AT_EMPTY_PATH, EBADF);
+        fail += check_execveat_fail(99, "execveat", 0, EBADF);
+        /* Attempt to execute relative to non-directory => ENOTDIR */
+        fail += check_execveat_fail(fd, "execveat", 0, ENOTDIR);
+
+        fail += check_execveat_pathmax(dot_dfd, "execveat", 0);
+        fail += check_execveat_pathmax(dot_dfd, "script", 1);
+        return fail;
+}
+
+static void prerequisites(void)
+{
+        int fd;
+        const char *script = "#!/bin/sh\nexit $*\n";
+
+        /* Create ephemeral copies of files */
+        exe_cp("execveat", "execveat.ephemeral");
+        exe_cp("execveat", "execveat.path.ephemeral");
+        exe_cp("script", "script.ephemeral");
+        mkdir("subdir.ephemeral", 0755);
+
+        fd = open("subdir.ephemeral/script", O_RDWR|O_CREAT|O_TRUNC, 0755);
+        write(fd, script, strlen(script));
+        close(fd);
+}
+
+int main(int argc, char **argv)
+{
+        int ii;
+        int rc;
+        const char *verbose = getenv("VERBOSE");
+
+        if (argc >= 2) {
+                /* If we are invoked with an argument, don't run tests. */
+                const char *in_test = getenv("IN_TEST");
+
+                if (verbose) {
+                        printf("  invoked with:");
+                        for (ii = 0; ii < argc; ii++)
+                                printf(" [%d]='%s'", ii, argv[ii]);
+                        printf("\n");
+                }
+
+                /* Check expected environment transferred. */
+                if (!in_test || strcmp(in_test, "yes") != 0) {
+                        printf("[FAIL] (no IN_TEST=yes in env)\n");
+                        return 1;
+                }
+
+                /* Use the final argument as an exit code. */
+                rc = atoi(argv[argc - 1]);
+                fflush(stdout);
+        } else {
+                prerequisites();
+                if (verbose)
+                        envp[1] = "VERBOSE=1";
+                rc = run_tests();
+                if (rc > 0)
+                        printf("%d tests failed\n", rc);
+        }
+        return rc;
+}
diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index 515247601df4..da48812ab95e 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -13,6 +13,7 @@ echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]"
 echo " Options:"
 echo "          -h|--help  Show help message"
 echo "          -k|--keep  Keep passed test logs"
+echo "          -v|--verbose Show all stdout messages in testcases"
 echo "          -d|--debug Debug mode (trace all shell commands)"
 exit $1
 }
@@ -37,7 +38,7 @@ abspath() {
 }
 
 find_testcases() { #directory
-  echo `find $1 -name \*.tc`
+  echo `find $1 -name \*.tc | sort`
 }
 
 parse_opts() { # opts
@@ -53,6 +54,10 @@ parse_opts() { # opts
       KEEP_LOG=1
       shift 1
     ;;
+    --verbose|-v)
+      VERBOSE=1
+      shift 1
+    ;;
     --debug|-d)
       DEBUG=1
       shift 1
@@ -90,6 +95,7 @@ TEST_CASES=`find_testcases $TEST_DIR`
 LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`/
 KEEP_LOG=0
 DEBUG=0
+VERBOSE=0
 # Parse command-line options
 parse_opts $*
 
@@ -135,15 +141,12 @@ TOTAL_RESULT=0
 CASENO=0
 testcase() { # testfile
   CASENO=$((CASENO+1))
-  prlog -n "[$CASENO]"`grep "^#[ \t]*description:" $1 | cut -f2 -d:`
+  desc=`grep "^#[ \t]*description:" $1 | cut -f2 -d:`
+  prlog -n "[$CASENO]$desc"
 }
 
-eval_result() { # retval sigval
-  local retval=$2
-  if [ $2 -eq 0 ]; then
-    test $1 -ne 0 && retval=$FAIL
-  fi
-  case $retval in
+eval_result() { # sigval
+  case $1 in
     $PASS)
       prlog "   [PASS]"
       PASSED_CASES="$PASSED_CASES $CASENO"
@@ -187,6 +190,9 @@ SIG_RESULT=
 SIG_BASE=36     # Use realtime signals
 SIG_PID=$$
 
+SIG_FAIL=$((SIG_BASE + FAIL))
+trap 'SIG_RESULT=$FAIL' $SIG_FAIL
+
 SIG_UNRESOLVED=$((SIG_BASE + UNRESOLVED))
 exit_unresolved () {
   kill -s $SIG_UNRESOLVED $SIG_PID
@@ -215,17 +221,25 @@ exit_xfail () {
 }
 trap 'SIG_RESULT=$XFAIL' $SIG_XFAIL
 
+__run_test() { # testfile
+  # setup PID and PPID, $$ is not updated.
+  (cd $TRACING_DIR; read PID _ < /proc/self/stat ; set -e; set -x; . $1)
+  [ $? -ne 0 ] && kill -s $SIG_FAIL $SIG_PID
+}
+
 # Run one test case
 run_test() { # testfile
   local testname=`basename $1`
-  local testlog=`mktemp --tmpdir=$LOG_DIR ${testname}-XXXXXX.log`
+  local testlog=`mktemp $LOG_DIR/${testname}-log.XXXXXX`
   testcase $1
   echo "execute: "$1 > $testlog
   SIG_RESULT=0
-  # setup PID and PPID, $$ is not updated.
-  (cd $TRACING_DIR; read PID _ < /proc/self/stat ;
-   set -e; set -x; . $1) >> $testlog 2>&1
-  eval_result $? $SIG_RESULT
+  if [ $VERBOSE -ne 0 ]; then
+    __run_test $1 2>> $testlog | tee -a $testlog
+  else
+    __run_test $1 >> $testlog 2>&1
+  fi
+  eval_result $SIG_RESULT
   if [ $? -eq 0 ]; then
     # Remove test log if the test was done as it was expected.
     [ $KEEP_LOG -eq 0 ] && rm $testlog
@@ -235,6 +249,9 @@ run_test() { # testfile
   fi
 }
 
+# load in the helper functions
+. $TEST_DIR/functions
+
 # Main loop
 for t in $TEST_CASES; do
   run_test $t
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc
new file mode 100644
index 000000000000..fd9c49a13612
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc
@@ -0,0 +1,5 @@
+#!/bin/sh
+# description: Basic event tracing check
+test -f available_events -a -f set_event -a -d events
+# check scheduler events are available
+grep -q sched available_events && exit 0 || exit -1
\ No newline at end of file
diff --git a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
new file mode 100644
index 000000000000..668616d9bb03
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
@@ -0,0 +1,53 @@
+#!/bin/sh
+# description: event tracing - enable/disable with event level files
+
+do_reset() {
+    echo > set_event
+    clear_trace
+}
+
+fail() { #msg
+    do_reset
+    echo $1
+    exit -1
+}
+
+if [ ! -f set_event -o ! -d events/sched ]; then
+    echo "event tracing is not supported"
+    exit_unsupported
+fi
+
+reset_tracer
+do_reset
+
+echo 'sched:sched_switch' > set_event
+usleep 1
+
+count=`cat trace | grep sched_switch | wc -l`
+if [ $count -eq 0 ]; then
+    fail "sched_switch events are not recorded"
+fi
+
+do_reset
+
+echo 1 > events/sched/sched_switch/enable
+usleep 1
+
+count=`cat trace | grep sched_switch | wc -l`
+if [ $count -eq 0 ]; then
+    fail "sched_switch events are not recorded"
+fi
+
+do_reset
+
+echo 0 > events/sched/sched_switch/enable
+usleep 1
+
+count=`cat trace | grep sched_switch | wc -l`
+if [ $count -ne 0 ]; then
+    fail "sched_switch events should not be recorded"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
new file mode 100644
index 000000000000..655c415b6e7f
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
@@ -0,0 +1,53 @@
+#!/bin/sh
+# description: event tracing - enable/disable with subsystem level files
+
+do_reset() {
+    echo > set_event
+    clear_trace
+}
+
+fail() { #msg
+    do_reset
+    echo $1
+    exit -1
+}
+
+if [ ! -f set_event -o ! -d events/sched ]; then
+    echo "event tracing is not supported"
+    exit_unsupported
+fi
+
+reset_tracer
+do_reset
+
+echo 'sched:*' > set_event
+usleep 1
+
+count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
+if [ $count -lt 3 ]; then
+    fail "at least fork, exec and exit events should be recorded"
+fi
+
+do_reset
+
+echo 1 > events/sched/enable
+usleep 1
+
+count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
+if [ $count -lt 3 ]; then
+    fail "at least fork, exec and exit events should be recorded"
+fi
+
+do_reset
+
+echo 0 > events/sched/enable
+usleep 1
+
+count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
+if [ $count -ne 0 ]; then
+    fail "any of scheduler events should not be recorded"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
new file mode 100644
index 000000000000..480845774007
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
@@ -0,0 +1,47 @@
+#!/bin/sh
+# description: event tracing - enable/disable with top level files
+
+do_reset() {
+    echo > set_event
+    clear_trace
+}
+
+fail() { #msg
+    do_reset
+    echo $1
+    exit -1
+}
+
+if [ ! -f available_events -o ! -f set_event -o ! -d events ]; then
+    echo "event tracing is not supported"
+    exit_unsupported
+fi
+
+reset_tracer
+do_reset
+
+echo '*:*' > set_event
+count=`cat trace | grep -v ^# | wc -l`
+if [ $count -eq 0 ]; then
+    fail "none of events are recorded"
+fi
+
+do_reset
+
+echo 1 > events/enable
+count=`cat trace | grep -v ^# | wc -l`
+if [ $count -eq 0 ]; then
+    fail "none of events are recorded"
+fi
+
+do_reset
+
+echo 0 > events/enable
+count=`cat trace | grep -v ^# | wc -l`
+if [ $count -ne 0 ]; then
+    fail "any of events should not be recorded"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
new file mode 100644
index 000000000000..c15e018e0220
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
@@ -0,0 +1,89 @@
+#!/bin/sh
+# description: ftrace - function graph filters with stack tracer
+
+# Make sure that function graph filtering works, and is not
+# affected by other tracers enabled (like stack tracer)
+
+if ! grep -q function_graph available_tracers; then
+    echo "no function graph tracer configured"
+    exit_unsupported
+fi
+
+if [ ! -f set_ftrace_filter ]; then
+    echo "set_ftrace_filter not found? Is dynamic ftrace not set?"
+    exit_unsupported
+fi
+
+do_reset() {
+    reset_tracer
+    echo 0 > /proc/sys/kernel/stack_tracer_enabled
+    enable_tracing
+    clear_trace
+    echo > set_ftrace_filter
+}
+
+fail() { # msg
+    do_reset
+    echo $1
+    exit -1
+}
+
+disable_tracing
+clear_trace;
+
+# filter something, schedule is always good
+if ! echo "schedule" > set_ftrace_filter; then
+    # test for powerpc 64
+    if ! echo ".schedule" > set_ftrace_filter; then
+        fail "can not enable schedule filter"
+    fi
+fi
+
+echo function_graph > current_tracer
+
+if [ ! -f stack_trace ]; then
+    echo "Stack tracer not configured"
+    do_reset
+    exit_unsupported;
+fi
+
+echo "Now testing with stack tracer"
+
+echo 1 > /proc/sys/kernel/stack_tracer_enabled
+
+disable_tracing
+clear_trace
+enable_tracing
+sleep 1
+
+count=`cat trace | grep '()' | grep -v schedule | wc -l`
+
+if [ $count -ne 0 ]; then
+    fail "Graph filtering not working with stack tracer?"
+fi
+
+# Make sure we did find something
+count=`cat trace | grep 'schedule()' | wc -l` 
+if [ $count -eq 0 ]; then
+    fail "No schedule traces found?"
+fi
+
+echo 0 > /proc/sys/kernel/stack_tracer_enabled
+clear_trace
+sleep 1
+
+
+count=`cat trace | grep '()' | grep -v schedule | wc -l`
+
+if [ $count -ne 0 ]; then
+    fail "Graph filtering not working after stack tracer disabled?"
+fi
+
+count=`cat trace | grep 'schedule()' | wc -l` 
+if [ $count -eq 0 ]; then
+    fail "No schedule traces found?"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
new file mode 100644
index 000000000000..6af5f6360b18
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
@@ -0,0 +1,52 @@
+#!/bin/sh
+# description: ftrace - function graph filters
+
+# Make sure that function graph filtering works
+
+if ! grep -q function_graph available_tracers; then
+    echo "no function graph tracer configured"
+    exit_unsupported
+fi
+
+do_reset() {
+    reset_tracer
+    enable_tracing
+    clear_trace
+}
+
+fail() { # msg
+    do_reset
+    echo $1
+    exit -1
+}
+
+disable_tracing
+clear_trace
+
+# filter something, schedule is always good
+if ! echo "schedule" > set_ftrace_filter; then
+    # test for powerpc 64
+    if ! echo ".schedule" > set_ftrace_filter; then
+        fail "can not enable schedule filter"
+    fi
+fi
+
+echo function_graph > current_tracer
+enable_tracing
+sleep 1
+# search for functions (has "()" on the line), and make sure
+# that only the schedule function was found
+count=`cat trace | grep '()' | grep -v schedule | wc -l`
+if [ $count -ne 0 ]; then
+    fail "Graph filtering not working by itself?"
+fi
+
+# Make sure we did find something
+count=`cat trace | grep 'schedule()' | wc -l` 
+if [ $count -eq 0 ]; then
+    fail "No schedule traces found?"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
new file mode 100644
index 000000000000..2e719cb1fc4d
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
@@ -0,0 +1,80 @@
+#!/bin/sh
+# description: ftrace - function profiler with function tracing
+
+# There was a bug after a rewrite of the ftrace infrastructure that
+# caused the function_profiler not to be able to run with the function
+# tracer, because the function_profiler used the function_graph tracer
+# and it was assumed the two could not run simultaneously.
+#
+# There was another related bug where the solution to the first bug
+# broke the way filtering of the function tracer worked.
+#
+# This test triggers those bugs on those kernels.
+#
+# We need function_graph and profiling to to run this test
+if ! grep -q function_graph available_tracers; then
+    echo "no function graph tracer configured"
+    exit_unsupported;
+fi
+
+if [ ! -f set_ftrace_filter ]; then
+    echo "set_ftrace_filter not found? Is dynamic ftrace not set?"
+    exit_unsupported
+fi
+
+if [ ! -f function_profile_enabled ]; then
+    echo "function_profile_enabled not found, function profiling enabled?"
+    exit_unsupported
+fi
+
+fail() { # mesg
+    reset_tracer
+    echo > set_ftrace_filter
+    echo $1
+    exit -1
+}
+
+echo "Testing function tracer with profiler:"
+echo "enable function tracer"
+echo function > current_tracer
+echo "enable profiler"
+echo 1 > function_profile_enabled
+
+sleep 1
+
+echo "Now filter on just schedule"
+echo '*schedule' > set_ftrace_filter
+clear_trace
+
+echo "Now disable function profiler"
+echo 0 > function_profile_enabled
+
+sleep 1
+
+# make sure only schedule functions exist
+
+echo "testing if only schedule is being traced"
+if grep -v -e '^#' -e 'schedule' trace; then
+        fail "more than schedule was found"
+fi
+
+echo "Make sure schedule was traced"
+if ! grep -e 'schedule' trace > /dev/null; then
+        cat trace
+        fail "can not find schedule in trace"
+fi
+
+echo > set_ftrace_filter
+clear_trace
+
+sleep 1
+
+echo "make sure something other than scheduler is being traced"
+if ! grep -v -e '^#' -e 'schedule' trace > /dev/null; then
+        cat trace
+        fail "no other functions besides schedule was found"
+fi
+
+reset_tracer
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions
new file mode 100644
index 000000000000..5d8cd06d920f
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/functions
@@ -0,0 +1,16 @@
+
+clear_trace() { # reset trace output
+    echo > trace
+}
+
+disable_tracing() { # stop trace recording
+    echo 0 > tracing_on
+}
+
+enable_tracing() { # start trace recording
+    echo 1 > tracing_on
+}
+
+reset_tracer() { # reset the current tracer
+    echo nop > current_tracer
+}
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
index 1b8b665ab2b3..a5a426211129 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
@@ -9,3 +9,4 @@ echo p:myevent do_fork > kprobe_events
 grep myevent kprobe_events
 test -d events/kprobes/myevent
 echo > kprobe_events
+clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
index b55c84003587..d8c7bb6581fe 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
@@ -11,3 +11,4 @@ echo 1 > events/kprobes/myevent/enable
 echo > kprobe_events && exit 1 # this must fail
 echo 0 > events/kprobes/myevent/enable
 echo > kprobe_events # this must succeed
+clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
index a603d3f8db7b..c45ee2761354 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
@@ -12,5 +12,6 @@ echo 1 > events/kprobes/testprobe/enable
 ( echo "forked")
 echo 0 > events/kprobes/testprobe/enable
 echo "-:testprobe" >> kprobe_events
+clear_trace
 test -d events/kprobes/testprobe && exit 1 || exit 0
 
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
new file mode 100644
index 000000000000..ab41d2b29841
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
@@ -0,0 +1,55 @@
+#!/bin/sh
+# description: Kprobe dynamic event with function tracer
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+grep function available_tracers || exit_unsupported # this is configurable
+
+# prepare
+echo nop > current_tracer
+echo do_fork > set_ftrace_filter
+echo 0 > events/enable
+echo > kprobe_events
+echo 'p:testprobe do_fork' > kprobe_events
+
+# kprobe on / ftrace off
+echo 1 > events/kprobes/testprobe/enable
+echo > trace
+( echo "forked")
+grep testprobe trace
+! grep 'do_fork <-' trace
+
+# kprobe on / ftrace on
+echo function > current_tracer
+echo > trace
+( echo "forked")
+grep testprobe trace
+grep 'do_fork <-' trace
+
+# kprobe off / ftrace on
+echo 0 > events/kprobes/testprobe/enable
+echo > trace
+( echo "forked")
+! grep testprobe trace
+grep 'do_fork <-' trace
+
+# kprobe on / ftrace on
+echo 1 > events/kprobes/testprobe/enable
+echo function > current_tracer
+echo > trace
+( echo "forked")
+grep testprobe trace
+grep 'do_fork <-' trace
+
+# kprobe on / ftrace off
+echo nop > current_tracer
+echo > trace
+( echo "forked")
+grep testprobe trace
+! grep 'do_fork <-' trace
+
+# cleanup
+echo nop > current_tracer
+echo > set_ftrace_filter
+echo 0 > events/kprobes/testprobe/enable
+echo > kprobe_events
+echo > trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
index 283c29e7f7c4..31717985acc7 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
@@ -12,4 +12,5 @@ echo 1 > events/kprobes/testprobe2/enable
 ( echo "forked")
 echo 0 > events/kprobes/testprobe2/enable
 echo '-:testprobe2' >> kprobe_events
+clear_trace
 test -d events/kprobes/testprobe2 && exit 1 || exit 0
diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c
index 552f0810bffb..1b2ce334bb3f 100644
--- a/tools/testing/selftests/ipc/msgque.c
+++ b/tools/testing/selftests/ipc/msgque.c
@@ -5,6 +5,8 @@
 #include <linux/msg.h>
 #include <fcntl.h>
 
+#include "../kselftest.h"
+
 #define MAX_MSG_SIZE            32
 
 struct msg1 {
@@ -195,58 +197,58 @@ int main(int argc, char **argv)
 
         if (getuid() != 0) {
                 printf("Please run the test as root - Exiting.\n");
-                exit(1);
+                return ksft_exit_fail();
         }
 
         msgque.key = ftok(argv[0], 822155650);
         if (msgque.key == -1) {
-                printf("Can't make key\n");
-                return -errno;
+                printf("Can't make key: %d\n", -errno);
+                return ksft_exit_fail();
         }
 
         msgque.msq_id = msgget(msgque.key, IPC_CREAT | IPC_EXCL | 0666);
         if (msgque.msq_id == -1) {
                 err = -errno;
-                printf("Can't create queue\n");
+                printf("Can't create queue: %d\n", err);
                 goto err_out;
         }
 
         err = fill_msgque(&msgque);
         if (err) {
-                printf("Failed to fill queue\n");
+                printf("Failed to fill queue: %d\n", err);
                 goto err_destroy;
         }
 
         err = dump_queue(&msgque);
         if (err) {
-                printf("Failed to dump queue\n");
+                printf("Failed to dump queue: %d\n", err);
                 goto err_destroy;
         }
 
         err = check_and_destroy_queue(&msgque);
         if (err) {
-                printf("Failed to check and destroy queue\n");
+                printf("Failed to check and destroy queue: %d\n", err);
                 goto err_out;
         }
 
         err = restore_queue(&msgque);
         if (err) {
-                printf("Failed to restore queue\n");
+                printf("Failed to restore queue: %d\n", err);
                 goto err_destroy;
         }
 
         err = check_and_destroy_queue(&msgque);
         if (err) {
-                printf("Failed to test queue\n");
+                printf("Failed to test queue: %d\n", err);
                 goto err_out;
         }
-        return 0;
+        return ksft_exit_pass();
 
 err_destroy:
         if (msgctl(msgque.msq_id, IPC_RMID, 0)) {
                 printf("Failed to destroy queue: %d\n", -errno);
-                return -errno;
+                return ksft_exit_fail();
         }
 err_out:
-        return err;
+        return ksft_exit_fail();
 }
diff --git a/tools/testing/selftests/kcmp/Makefile b/tools/testing/selftests/kcmp/Makefile
index 8aabd82db9e4..ff0eefdc6ceb 100644
--- a/tools/testing/selftests/kcmp/Makefile
+++ b/tools/testing/selftests/kcmp/Makefile
@@ -1,25 +1,7 @@
-uname_M := $(shell uname -m 2>/dev/null || echo not)
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/)
-ifeq ($(ARCH),i386)
-        ARCH := x86
-        CFLAGS := -DCONFIG_X86_32 -D__i386__
-endif
-ifeq ($(ARCH),x86_64)
-        ARCH := x86
-        CFLAGS := -DCONFIG_X86_64 -D__x86_64__
-endif
-
-CFLAGS += -I../../../../arch/x86/include/generated/
-CFLAGS += -I../../../../include/
+CC := $(CROSS_COMPILE)$(CC)
 CFLAGS += -I../../../../usr/include/
-CFLAGS += -I../../../../arch/x86/include/
 
-all:
-ifeq ($(ARCH),x86)
-        gcc $(CFLAGS) kcmp_test.c -o kcmp_test
-else
-        echo "Not an x86 target, can't build kcmp selftest"
-endif
+all: kcmp_test
 
 run_tests: all
         @./kcmp_test || echo "kcmp_test: [FAIL]"
diff --git a/tools/testing/selftests/kcmp/kcmp_test.c b/tools/testing/selftests/kcmp/kcmp_test.c
index dbba4084869c..a5a4da856dfe 100644
--- a/tools/testing/selftests/kcmp/kcmp_test.c
+++ b/tools/testing/selftests/kcmp/kcmp_test.c
@@ -17,6 +17,8 @@
 #include <sys/stat.h>
 #include <sys/wait.h>
 
+#include "../kselftest.h"
+
 static long sys_kcmp(int pid1, int pid2, int type, int fd1, int fd2)
 {
         return syscall(__NR_kcmp, pid1, pid2, type, fd1, fd2);
@@ -34,13 +36,13 @@ int main(int argc, char **argv)
 
         if (fd1 < 0) {
                 perror("Can't create file");
-                exit(1);
+                ksft_exit_fail();
         }
 
         pid2 = fork();
         if (pid2 < 0) {
                 perror("fork failed");
-                exit(1);
+                ksft_exit_fail();
         }
 
         if (!pid2) {
@@ -50,7 +52,7 @@ int main(int argc, char **argv)
                 fd2 = open(kpath, O_RDWR, 0644);
                 if (fd2 < 0) {
                         perror("Can't open file");
-                        exit(1);
+                        ksft_exit_fail();
                 }
 
                 /* An example of output and arguments */
@@ -74,23 +76,34 @@ int main(int argc, char **argv)
                 if (ret) {
                         printf("FAIL: 0 expected but %d returned (%s)\n",
                                 ret, strerror(errno));
+                        ksft_inc_fail_cnt();
                         ret = -1;
-                } else
+                } else {
                         printf("PASS: 0 returned as expected\n");
+                        ksft_inc_pass_cnt();
+                }
 
                 /* Compare with self */
                 ret = sys_kcmp(pid1, pid1, KCMP_VM, 0, 0);
                 if (ret) {
                         printf("FAIL: 0 expected but %d returned (%s)\n",
                                 ret, strerror(errno));
+                        ksft_inc_fail_cnt();
                         ret = -1;
-                } else
+                } else {
                         printf("PASS: 0 returned as expected\n");
+                        ksft_inc_pass_cnt();
+                }
+
+                ksft_print_cnts();
 
-                exit(ret);
+                if (ret)
+                        ksft_exit_fail();
+                else
+                        ksft_exit_pass();
         }
 
         waitpid(pid2, &status, P_ALL);
 
-        return 0;
+        return ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h
new file mode 100644
index 000000000000..572c8888167a
--- /dev/null
+++ b/tools/testing/selftests/kselftest.h
@@ -0,0 +1,62 @@
+/*
+ * kselftest.h: kselftest framework return codes to include from
+ *              selftests.
+ *
+ * Copyright (c) 2014 Shuah Khan <shuahkh@osg.samsung.com>
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ *
+ * This file is released under the GPLv2.
+ */
+#ifndef __KSELFTEST_H
+#define __KSELFTEST_H
+
+#include <stdlib.h>
+#include <unistd.h>
+
+/* counters */
+struct ksft_count {
+        unsigned int ksft_pass;
+        unsigned int ksft_fail;
+        unsigned int ksft_xfail;
+        unsigned int ksft_xpass;
+        unsigned int ksft_xskip;
+};
+
+static struct ksft_count ksft_cnt;
+
+static inline void ksft_inc_pass_cnt(void) { ksft_cnt.ksft_pass++; }
+static inline void ksft_inc_fail_cnt(void) { ksft_cnt.ksft_fail++; }
+static inline void ksft_inc_xfail_cnt(void) { ksft_cnt.ksft_xfail++; }
+static inline void ksft_inc_xpass_cnt(void) { ksft_cnt.ksft_xpass++; }
+static inline void ksft_inc_xskip_cnt(void) { ksft_cnt.ksft_xskip++; }
+
+static inline void ksft_print_cnts(void)
+{
+        printf("Pass: %d Fail: %d Xfail: %d Xpass: %d, Xskip: %d\n",
+                ksft_cnt.ksft_pass, ksft_cnt.ksft_fail,
+                ksft_cnt.ksft_xfail, ksft_cnt.ksft_xpass,
+                ksft_cnt.ksft_xskip);
+}
+
+static inline int ksft_exit_pass(void)
+{
+        exit(0);
+}
+static inline int ksft_exit_fail(void)
+{
+        exit(1);
+}
+static inline int ksft_exit_xfail(void)
+{
+        exit(2);
+}
+static inline int ksft_exit_xpass(void)
+{
+        exit(3);
+}
+static inline int ksft_exit_skip(void)
+{
+        exit(4);
+}
+
+#endif /* __KSELFTEST_H */
diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c
index 1b3ff2fda4d0..517785052f1c 100644
--- a/tools/testing/selftests/mount/unprivileged-remount-test.c
+++ b/tools/testing/selftests/mount/unprivileged-remount-test.c
@@ -6,6 +6,8 @@
 #include <sys/types.h>
 #include <sys/mount.h>
 #include <sys/wait.h>
+#include <sys/vfs.h>
+#include <sys/statvfs.h>
 #include <stdlib.h>
 #include <unistd.h>
 #include <fcntl.h>
@@ -32,11 +34,14 @@
 # define CLONE_NEWPID 0x20000000
 #endif
 
+#ifndef MS_REC
+# define MS_REC 16384
+#endif
 #ifndef MS_RELATIME
-#define MS_RELATIME (1 << 21)
+# define MS_RELATIME (1 << 21)
 #endif
 #ifndef MS_STRICTATIME
-#define MS_STRICTATIME (1 << 24)
+# define MS_STRICTATIME (1 << 24)
 #endif
 
 static void die(char *fmt, ...)
@@ -48,17 +53,14 @@ static void die(char *fmt, ...)
         exit(EXIT_FAILURE);
 }
 
-static void write_file(char *filename, char *fmt, ...)
+static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap)
 {
         char buf[4096];
         int fd;
         ssize_t written;
         int buf_len;
-        va_list ap;
 
-        va_start(ap, fmt);
         buf_len = vsnprintf(buf, sizeof(buf), fmt, ap);
-        va_end(ap);
         if (buf_len < 0) {
                 die("vsnprintf failed: %s\n",
                     strerror(errno));
@@ -69,6 +71,8 @@ static void write_file(char *filename, char *fmt, ...)
 
         fd = open(filename, O_WRONLY);
         if (fd < 0) {
+                if ((errno == ENOENT) && enoent_ok)
+                        return;
                 die("open of %s failed: %s\n",
                     filename, strerror(errno));
         }
@@ -87,6 +91,65 @@ static void write_file(char *filename, char *fmt, ...)
         }
 }
 
+static void maybe_write_file(char *filename, char *fmt, ...)
+{
+        va_list ap;
+
+        va_start(ap, fmt);
+        vmaybe_write_file(true, filename, fmt, ap);
+        va_end(ap);
+
+}
+
+static void write_file(char *filename, char *fmt, ...)
+{
+        va_list ap;
+
+        va_start(ap, fmt);
+        vmaybe_write_file(false, filename, fmt, ap);
+        va_end(ap);
+
+}
+
+static int read_mnt_flags(const char *path)
+{
+        int ret;
+        struct statvfs stat;
+        int mnt_flags;
+
+        ret = statvfs(path, &stat);
+        if (ret != 0) {
+                die("statvfs of %s failed: %s\n",
+                        path, strerror(errno));
+        }
+        if (stat.f_flag & ~(ST_RDONLY | ST_NOSUID | ST_NODEV | \
+                        ST_NOEXEC | ST_NOATIME | ST_NODIRATIME | ST_RELATIME | \
+                        ST_SYNCHRONOUS | ST_MANDLOCK)) {
+                die("Unrecognized mount flags\n");
+        }
+        mnt_flags = 0;
+        if (stat.f_flag & ST_RDONLY)
+                mnt_flags |= MS_RDONLY;
+        if (stat.f_flag & ST_NOSUID)
+                mnt_flags |= MS_NOSUID;
+        if (stat.f_flag & ST_NODEV)
+                mnt_flags |= MS_NODEV;
+        if (stat.f_flag & ST_NOEXEC)
+                mnt_flags |= MS_NOEXEC;
+        if (stat.f_flag & ST_NOATIME)
+                mnt_flags |= MS_NOATIME;
+        if (stat.f_flag & ST_NODIRATIME)
+                mnt_flags |= MS_NODIRATIME;
+        if (stat.f_flag & ST_RELATIME)
+                mnt_flags |= MS_RELATIME;
+        if (stat.f_flag & ST_SYNCHRONOUS)
+                mnt_flags |= MS_SYNCHRONOUS;
+        if (stat.f_flag & ST_MANDLOCK)
+                mnt_flags |= ST_MANDLOCK;
+
+        return mnt_flags;
+}
+
 static void create_and_enter_userns(void)
 {
         uid_t uid;
@@ -100,13 +163,10 @@ static void create_and_enter_userns(void)
                         strerror(errno));
         }
 
+        maybe_write_file("/proc/self/setgroups", "deny");
         write_file("/proc/self/uid_map", "0 %d 1", uid);
         write_file("/proc/self/gid_map", "0 %d 1", gid);
 
-        if (setgroups(0, NULL) != 0) {
-                die("setgroups failed: %s\n",
-                        strerror(errno));
-        }
         if (setgid(0) != 0) {
                 die ("setgid(0) failed %s\n",
                         strerror(errno));
@@ -118,7 +178,8 @@ static void create_and_enter_userns(void)
 }
 
 static
-bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags)
+bool test_unpriv_remount(const char *fstype, const char *mount_options,
+                         int mount_flags, int remount_flags, int invalid_flags)
 {
         pid_t child;
 
@@ -151,9 +212,11 @@ bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags)
                         strerror(errno));
         }
 
-        if (mount("testing", "/tmp", "ramfs", mount_flags, NULL) != 0) {
-                die("mount of /tmp failed: %s\n",
-                        strerror(errno));
+        if (mount("testing", "/tmp", fstype, mount_flags, mount_options) != 0) {
+                die("mount of %s with options '%s' on /tmp failed: %s\n",
+                    fstype,
+                    mount_options? mount_options : "",
+                    strerror(errno));
         }
 
         create_and_enter_userns();
@@ -181,62 +244,127 @@ bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags)
 
 static bool test_unpriv_remount_simple(int mount_flags)
 {
-        return test_unpriv_remount(mount_flags, mount_flags, 0);
+        return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags, 0);
 }
 
 static bool test_unpriv_remount_atime(int mount_flags, int invalid_flags)
 {
-        return test_unpriv_remount(mount_flags, mount_flags, invalid_flags);
+        return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags,
+                                   invalid_flags);
+}
+
+static bool test_priv_mount_unpriv_remount(void)
+{
+        pid_t child;
+        int ret;
+        const char *orig_path = "/dev";
+        const char *dest_path = "/tmp";
+        int orig_mnt_flags, remount_mnt_flags;
+
+        child = fork();
+        if (child == -1) {
+                die("fork failed: %s\n",
+                        strerror(errno));
+        }
+        if (child != 0) { /* parent */
+                pid_t pid;
+                int status;
+                pid = waitpid(child, &status, 0);
+                if (pid == -1) {
+                        die("waitpid failed: %s\n",
+                                strerror(errno));
+                }
+                if (pid != child) {
+                        die("waited for %d got %d\n",
+                                child, pid);
+                }
+                if (!WIFEXITED(status)) {
+                        die("child did not terminate cleanly\n");
+                }
+                return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false;
+        }
+
+        orig_mnt_flags = read_mnt_flags(orig_path);
+
+        create_and_enter_userns();
+        ret = unshare(CLONE_NEWNS);
+        if (ret != 0) {
+                die("unshare(CLONE_NEWNS) failed: %s\n",
+                        strerror(errno));
+        }
+
+        ret = mount(orig_path, dest_path, "bind", MS_BIND | MS_REC, NULL);
+        if (ret != 0) {
+                die("recursive bind mount of %s onto %s failed: %s\n",
+                        orig_path, dest_path, strerror(errno));
+        }
+
+        ret = mount(dest_path, dest_path, "none",
+                    MS_REMOUNT | MS_BIND | orig_mnt_flags , NULL);
+        if (ret != 0) {
+                /* system("cat /proc/self/mounts"); */
+                die("remount of /tmp failed: %s\n",
+                    strerror(errno));
+        }
+
+        remount_mnt_flags = read_mnt_flags(dest_path);
+        if (orig_mnt_flags != remount_mnt_flags) {
+                die("Mount flags unexpectedly changed during remount of %s originally mounted on %s\n",
+                        dest_path, orig_path);
+        }
+        exit(EXIT_SUCCESS);
 }
 
 int main(int argc, char **argv)
 {
-        if (!test_unpriv_remount_simple(MS_RDONLY|MS_NODEV)) {
+        if (!test_unpriv_remount_simple(MS_RDONLY)) {
                 die("MS_RDONLY malfunctions\n");
         }
-        if (!test_unpriv_remount_simple(MS_NODEV)) {
+        if (!test_unpriv_remount("devpts", "newinstance", MS_NODEV, MS_NODEV, 0)) {
                 die("MS_NODEV malfunctions\n");
         }
-        if (!test_unpriv_remount_simple(MS_NOSUID|MS_NODEV)) {
+        if (!test_unpriv_remount_simple(MS_NOSUID)) {
                 die("MS_NOSUID malfunctions\n");
         }
-        if (!test_unpriv_remount_simple(MS_NOEXEC|MS_NODEV)) {
+        if (!test_unpriv_remount_simple(MS_NOEXEC)) {
                 die("MS_NOEXEC malfunctions\n");
         }
-        if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODEV,
-                                       MS_NOATIME|MS_NODEV))
+        if (!test_unpriv_remount_atime(MS_RELATIME,
+                                       MS_NOATIME))
         {
                 die("MS_RELATIME malfunctions\n");
         }
-        if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODEV,
-                                       MS_NOATIME|MS_NODEV))
+        if (!test_unpriv_remount_atime(MS_STRICTATIME,
+                                       MS_NOATIME))
         {
                 die("MS_STRICTATIME malfunctions\n");
         }
-        if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODEV,
-                                       MS_STRICTATIME|MS_NODEV))
+        if (!test_unpriv_remount_atime(MS_NOATIME,
+                                       MS_STRICTATIME))
         {
-                die("MS_RELATIME malfunctions\n");
+                die("MS_NOATIME malfunctions\n");
         }
-        if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME|MS_NODEV,
-                                       MS_NOATIME|MS_NODEV))
+        if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME,
+                                       MS_NOATIME))
         {
-                die("MS_RELATIME malfunctions\n");
+                die("MS_RELATIME|MS_NODIRATIME malfunctions\n");
         }
-        if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME|MS_NODEV,
-                                       MS_NOATIME|MS_NODEV))
+        if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME,
+                                       MS_NOATIME))
         {
-                die("MS_RELATIME malfunctions\n");
+                die("MS_STRICTATIME|MS_NODIRATIME malfunctions\n");
         }
-        if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME|MS_NODEV,
-                                       MS_STRICTATIME|MS_NODEV))
+        if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME,
+                                       MS_STRICTATIME))
         {
-                die("MS_RELATIME malfunctions\n");
+                die("MS_NOATIME|MS_DIRATIME malfunctions\n");
         }
-        if (!test_unpriv_remount(MS_STRICTATIME|MS_NODEV, MS_NODEV,
-                                 MS_NOATIME|MS_NODEV))
+        if (!test_unpriv_remount("ramfs", NULL, MS_STRICTATIME, 0, MS_NOATIME))
         {
                 die("Default atime malfunctions\n");
         }
+        if (!test_priv_mount_unpriv_remount()) {
+                die("Mount flags unexpectedly changed after remount\n");
+        }
         return EXIT_SUCCESS;
 }
diff --git a/tools/testing/selftests/mqueue/mq_perf_tests.c b/tools/testing/selftests/mqueue/mq_perf_tests.c
index 94dae65eea41..8519e9ee97e3 100644
--- a/tools/testing/selftests/mqueue/mq_perf_tests.c
+++ b/tools/testing/selftests/mqueue/mq_perf_tests.c
@@ -536,10 +536,9 @@ int main(int argc, char *argv[])
 {
         struct mq_attr attr;
         char *option, *next_option;
-        int i, cpu;
+        int i, cpu, rc;
         struct sigaction sa;
         poptContext popt_context;
-        char rc;
         void *retval;
 
         main_thread = pthread_self();
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index c7493b8f9b0e..62f22cc9941c 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -14,12 +14,6 @@ all: $(NET_PROGS)
 run_tests: all
         @/bin/sh ./run_netsocktests || echo "sockettests: [FAIL]"
         @/bin/sh ./run_afpackettests || echo "afpackettests: [FAIL]"
-        @if /sbin/modprobe test_bpf ; then \
-                /sbin/rmmod test_bpf; \
-                echo "test_bpf: ok"; \
-        else \
-                echo "test_bpf: [FAIL]"; \
-                exit 1; \
-        fi
+        ./test_bpf.sh
 clean:
         $(RM) $(NET_PROGS)
diff --git a/tools/testing/selftests/net/test_bpf.sh b/tools/testing/selftests/net/test_bpf.sh
new file mode 100755
index 000000000000..8b29796d46aa
--- /dev/null
+++ b/tools/testing/selftests/net/test_bpf.sh
@@ -0,0 +1,10 @@
+#!/bin/sh
+# Runs bpf test using test_bpf kernel module
+
+if /sbin/modprobe -q test_bpf ; then
+        /sbin/modprobe -q -r test_bpf;
+        echo "test_bpf: ok";
+else
+        echo "test_bpf: [FAIL]";
+        exit 1;
+fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index f6b2b4771b78..8ca9f21f2efc 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -45,7 +45,7 @@ trap 'rm -rf $T' 0
 touch $T
 
 . $KVM/bin/functions.sh
-. $KVPATH/ver_functions.sh
+. $CONFIGFRAG/ver_functions.sh
 
 config_template=${1}
 config_dir=`echo $config_template | sed -e 's,/[^/]*$,,'`
@@ -168,8 +168,8 @@ then
         touch $resdir/buildonly
         exit 0
 fi
-echo $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
-( $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) &
+echo $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
+( $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) &
 qemu_pid=$!
 commandcompleted=0
 echo Monitoring qemu job at pid $qemu_pid
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index e527dc952eb0..368d64ac779e 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -47,7 +47,6 @@ resdir=""
 configs=""
 cpus=0
 ds=`date +%Y.%m.%d-%H:%M:%S`
-kversion=""
 
 . functions.sh
 
@@ -64,7 +63,6 @@ usage () {
         echo "       --duration minutes"
         echo "       --interactive"
         echo "       --kmake-arg kernel-make-arguments"
-        echo "       --kversion vN.NN"
         echo "       --mac nn:nn:nn:nn:nn:nn"
         echo "       --no-initrd"
         echo "       --qemu-args qemu-system-..."
@@ -128,11 +126,6 @@ do
                 TORTURE_KMAKE_ARG="$2"
                 shift
                 ;;
-        --kversion)
-                checkarg --kversion "(kernel version)" $# "$2" '^v[0-9.]*$' '^error'
-                kversion=$2
-                shift
-                ;;
         --mac)
                 checkarg --mac "(MAC address)" $# "$2" '^\([0-9a-fA-F]\{2\}:\)\{5\}[0-9a-fA-F]\{2\}$' error
                 TORTURE_QEMU_MAC=$2
@@ -170,11 +163,10 @@ do
 done
 
 CONFIGFRAG=${KVM}/configs/${TORTURE_SUITE}; export CONFIGFRAG
-KVPATH=${CONFIGFRAG}/$kversion; export KVPATH
 
 if test -z "$configs"
 then
-        configs="`cat $CONFIGFRAG/$kversion/CFLIST`"
+        configs="`cat $CONFIGFRAG/CFLIST`"
 fi
 
 if test -z "$resdir"
@@ -186,10 +178,10 @@ fi
 touch $T/cfgcpu
 for CF in $configs
 do
-        if test -f "$CONFIGFRAG/$kversion/$CF"
+        if test -f "$CONFIGFRAG/$CF"
         then
-                cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$kversion/$CF`
-                cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$kversion/$CF" "$cpu_count"`
+                cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$CF`
+                cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF" "$cpu_count"`
                 echo $CF $cpu_count >> $T/cfgcpu
         else
                 echo "The --configs file $CF does not exist, terminating."
@@ -252,7 +244,6 @@ END {
 cat << ___EOF___ > $T/script
 CONFIGFRAG="$CONFIGFRAG"; export CONFIGFRAG
 KVM="$KVM"; export KVM
-KVPATH="$KVPATH"; export KVPATH
 PATH="$PATH"; export PATH
 TORTURE_BOOT_IMAGE="$TORTURE_BOOT_IMAGE"; export TORTURE_BOOT_IMAGE
 TORTURE_BUILDONLY="$TORTURE_BUILDONLY"; export TORTURE_BUILDONLY
@@ -285,7 +276,7 @@ then
 fi
 ___EOF___
 awk < $T/cfgcpu.pack \
-        -v CONFIGDIR="$CONFIGFRAG/$kversion/" \
+        -v CONFIGDIR="$CONFIGFRAG/" \
         -v KVM="$KVM" \
         -v ncpus=$cpus \
         -v rd=$resdir/$ds/ \
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
index f4feaee40776..36e41df3d27a 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
@@ -7,6 +7,8 @@ CONFIG_HZ_PERIODIC=y
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=n
 CONFIG_RCU_TRACE=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_PREEMPT_COUNT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot
new file mode 100644
index 000000000000..0f0802730014
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot
@@ -0,0 +1,2 @@
+rcupdate.rcu_self_test=1
+rcupdate.rcu_self_test_bh=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
index 38e3895759dd..f8a10a7500c6 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
@@ -2,7 +2,7 @@ CONFIG_SMP=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
@@ -14,6 +14,5 @@ CONFIG_RCU_NOCB_CPU=y
 CONFIG_RCU_NOCB_CPU_ZERO=y
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_RCU_CPU_STALL_INFO=n
-CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
index ea119ba2f7d4..629122fb8b4a 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
@@ -3,7 +3,7 @@ CONFIG_NR_CPUS=8
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
@@ -19,6 +19,5 @@ CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=n
 CONFIG_RCU_CPU_STALL_INFO=n
-CONFIG_RCU_CPU_STALL_VERBOSE=y
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
index 19cf9485f48a..a25de47888a4 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
@@ -3,7 +3,7 @@ CONFIG_NR_CPUS=8
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
@@ -19,6 +19,5 @@ CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=n
 CONFIG_RCU_CPU_STALL_INFO=n
-CONFIG_RCU_CPU_STALL_VERBOSE=y
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
index f4567fb3e332..53f24e0a0ab6 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
@@ -3,7 +3,7 @@ CONFIG_NR_CPUS=8
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_HZ_PERIODIC=y
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=n
@@ -15,7 +15,6 @@ CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_RCU_CPU_STALL_INFO=n
-CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_KTHREAD_PRIO=2
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
index 0a262fbb0c12..0f84db35b36d 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
@@ -19,5 +19,4 @@ CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_RCU_CPU_STALL_VERBOSE=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
index 3a06b97e9a73..212e3bfd2b2a 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
@@ -19,5 +19,4 @@ CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_PROVE_RCU=y
 CONFIG_RCU_CPU_STALL_INFO=n
-CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
index 3b42b8b033cd..15b3e1a86f74 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
@@ -1 +1,2 @@
 rcutorture.torture_type=sched
+rcupdate.rcu_self_test_sched=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
index 8f084cca91bf..7eee63b44218 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
@@ -20,5 +20,4 @@ CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_PROVE_RCU=y
 CONFIG_RCU_CPU_STALL_INFO=n
-CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot
new file mode 100644
index 000000000000..da9a03a398db
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot
@@ -0,0 +1,3 @@
+rcupdate.rcu_self_test=1
+rcupdate.rcu_self_test_bh=1
+rcupdate.rcu_self_test_sched=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
index 8f1017666aa7..92a97fa97dec 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
@@ -19,5 +19,4 @@ CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
index 69a2e255bf98..5812027d6f9f 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
@@ -3,7 +3,7 @@ CONFIG_NR_CPUS=16
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
@@ -18,7 +18,8 @@ CONFIG_RCU_FANOUT_LEAF=2
 CONFIG_RCU_NOCB_CPU=y
 CONFIG_RCU_NOCB_CPU_ALL=y
 CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
 CONFIG_RCU_CPU_STALL_INFO=n
-CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
index a0f32fb8f17e..3eaeccacb083 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
@@ -3,7 +3,7 @@ CONFIG_NR_CPUS=16
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
@@ -19,6 +19,5 @@ CONFIG_RCU_NOCB_CPU=y
 CONFIG_RCU_NOCB_CPU_ALL=y
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_RCU_CPU_STALL_INFO=n
-CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
index 3b42b8b033cd..2561daf605ad 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
@@ -1 +1,3 @@
 rcutorture.torture_type=sched
+rcupdate.rcu_self_test=1
+rcupdate.rcu_self_test_sched=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
index b7a62a540ad1..6076b36f6c0b 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE09
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
@@ -3,7 +3,7 @@ CONFIG_NR_CPUS=1
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
@@ -14,6 +14,5 @@ CONFIG_HIBERNATION=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_RCU_CPU_STALL_INFO=n
-CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/CFLIST
deleted file mode 100644
index 18223947bbcb..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/CFLIST
+++ /dev/null
@@ -1,14 +0,0 @@
-P1-S-T-NH-SD-SMP-HP
-P2-2-t-nh-sd-SMP-hp
-P3-3-T-nh-SD-SMP-hp
-P4-A-t-NH-sd-SMP-HP
-P5-U-T-NH-sd-SMP-hp
-N1-S-T-NH-SD-SMP-HP
-N2-2-t-nh-sd-SMP-hp
-N3-3-T-nh-SD-SMP-hp
-N4-A-t-NH-sd-SMP-HP
-N5-U-T-NH-sd-SMP-hp
-PT1-nh
-PT2-NH
-NT1-nh
-NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N1-S-T-NH-SD-SMP-HP
deleted file mode 100644
index d3ef873eb6e7..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N1-S-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,18 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=8
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N2-2-t-nh-sd-SMP-hp
deleted file mode 100644
index 02e418572b1b..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N2-2-t-nh-sd-SMP-hp
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=4
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N3-3-T-nh-SD-SMP-hp
deleted file mode 100644
index b3100f69c8cf..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N3-3-T-nh-SD-SMP-hp
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N4-A-t-NH-sd-SMP-HP
deleted file mode 100644
index c56b44530725..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N4-A-t-NH-sd-SMP-HP
+++ /dev/null
@@ -1,18 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N5-U-T-NH-sd-SMP-hp
deleted file mode 100644
index 90d924fea9e9..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N5-U-T-NH-sd-SMP-hp
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=y
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT1-nh
deleted file mode 100644
index 023f312a931c..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT1-nh
+++ /dev/null
@@ -1,23 +0,0 @@
-#CHECK#CONFIG_TINY_RCU=y
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=n
-#
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT3-NH
deleted file mode 100644
index 6fd0235dae73..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT3-NH
+++ /dev/null
@@ -1,20 +0,0 @@
-#CHECK#CONFIG_TINY_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=y
-#
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P1-S-T-NH-SD-SMP-HP
deleted file mode 100644
index f72402d7c13d..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P1-S-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,19 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=8
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P2-2-t-nh-sd-SMP-hp
deleted file mode 100644
index 0f3b667d2a9f..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P2-2-t-nh-sd-SMP-hp
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=4
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P3-3-T-nh-SD-SMP-hp
deleted file mode 100644
index b035e141bf2a..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P3-3-T-nh-SD-SMP-hp
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P4-A-t-NH-sd-SMP-HP
deleted file mode 100644
index 3ccf6a9447f5..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P4-A-t-NH-sd-SMP-HP
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_RT_MUTEXES=y
-CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp
deleted file mode 100644
index a55c00877fe4..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp
+++ /dev/null
@@ -1,27 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=y
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_OBJECTS=y
-CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
-CONFIG_RT_MUTEXES=y
-CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT1-nh
deleted file mode 100644
index e3361c3894a1..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT1-nh
+++ /dev/null
@@ -1,23 +0,0 @@
-CONFIG_TINY_PREEMPT_RCU=y
-CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=n
-#
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT2-NH
deleted file mode 100644
index 64abfc3b4d94..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT2-NH
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_TINY_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=y
-#
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/ver_functions.sh
deleted file mode 100644
index 5ace37a89780..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/ver_functions.sh
+++ /dev/null
@@ -1,33 +0,0 @@
-#!/bin/bash
-#
-# Kernel-version-dependent shell functions for the rest of the scripts.
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
-# Copyright (C) IBM Corporation, 2013
-#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
-
-# per_version_boot_params bootparam-string config-file seconds
-#
-# Adds per-version torture-module parameters to kernels supporting them.
-# Which old kernels do not.
-per_version_boot_params () {
-        echo    rcutorture.stat_interval=15 \
-                rcutorture.shutdown_secs=$3 \
-                rcutorture.rcutorture_runnable=1 \
-                rcutorture.test_no_idle_hz=1 \
-                rcutorture.verbose=1
-}
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/CFLIST
deleted file mode 100644
index da4cbc668f2a..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/CFLIST
+++ /dev/null
@@ -1,17 +0,0 @@
-sysidleY.2013.06.19a
-sysidleN.2013.06.19a
-P1-S-T-NH-SD-SMP-HP
-P2-2-t-nh-sd-SMP-hp
-P3-3-T-nh-SD-SMP-hp
-P4-A-t-NH-sd-SMP-HP
-P5-U-T-NH-sd-SMP-hp
-P6---t-nh-SD-smp-hp
-N1-S-T-NH-SD-SMP-HP
-N2-2-t-nh-sd-SMP-hp
-N3-3-T-nh-SD-SMP-hp
-N4-A-t-NH-sd-SMP-HP
-N5-U-T-NH-sd-SMP-hp
-PT1-nh
-PT2-NH
-NT1-nh
-NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N1-S-T-NH-SD-SMP-HP
deleted file mode 100644
index d81e11d280aa..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N1-S-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,19 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_FAST_NO_HZ=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=8
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N2-2-t-nh-sd-SMP-hp
deleted file mode 100644
index 02e418572b1b..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N2-2-t-nh-sd-SMP-hp
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=4
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N3-3-T-nh-SD-SMP-hp
deleted file mode 100644
index b3100f69c8cf..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N3-3-T-nh-SD-SMP-hp
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N4-A-t-NH-sd-SMP-HP
deleted file mode 100644
index c56b44530725..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N4-A-t-NH-sd-SMP-HP
+++ /dev/null
@@ -1,18 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N5-U-T-NH-sd-SMP-hp
deleted file mode 100644
index 90d924fea9e9..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N5-U-T-NH-sd-SMP-hp
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=y
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N6---t-nh-SD-smp-hp
deleted file mode 100644
index 0ccc36d72738..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N6---t-nh-SD-smp-hp
+++ /dev/null
@@ -1,19 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_NR_CPUS=1
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N7-4-T-NH-SD-SMP-HP
deleted file mode 100644
index 3f640cf84973..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N7-4-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,26 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=16
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_RCU_NOCB_CPU=y
-CONFIG_RCU_NOCB_CPU_NONE=y
-CONFIG_RCU_NOCB_CPU_ZERO=n
-CONFIG_RCU_NOCB_CPU_ALL=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N8-2-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N8-2-T-NH-SD-SMP-HP
deleted file mode 100644
index 285da2dd8ac3..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N8-2-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=14
-CONFIG_NR_CPUS=16
-CONFIG_RCU_FANOUT_EXACT=y
-CONFIG_HOTPLUG_CPU=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT1-nh
deleted file mode 100644
index 023f312a931c..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT1-nh
+++ /dev/null
@@ -1,23 +0,0 @@
-#CHECK#CONFIG_TINY_RCU=y
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=n
-#
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT3-NH
deleted file mode 100644
index 6fd0235dae73..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT3-NH
+++ /dev/null
@@ -1,20 +0,0 @@
-#CHECK#CONFIG_TINY_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=y
-#
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P1-S-T-NH-SD-SMP-HP
deleted file mode 100644
index 9647c44cf4b7..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P1-S-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_RCU_FAST_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=8
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P2-2-t-nh-sd-SMP-hp
deleted file mode 100644
index 0f3b667d2a9f..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P2-2-t-nh-sd-SMP-hp
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=4
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P3-3-T-nh-SD-SMP-hp
deleted file mode 100644
index b035e141bf2a..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P3-3-T-nh-SD-SMP-hp
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P4-A-t-NH-sd-SMP-HP
deleted file mode 100644
index 3ccf6a9447f5..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P4-A-t-NH-sd-SMP-HP
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_RT_MUTEXES=y
-CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp
deleted file mode 100644
index a55c00877fe4..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp
+++ /dev/null
@@ -1,27 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=y
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_OBJECTS=y
-CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
-CONFIG_RT_MUTEXES=y
-CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P6---t-nh-SD-smp-hp
deleted file mode 100644
index f4c9175828bf..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P6---t-nh-SD-smp-hp
+++ /dev/null
@@ -1,18 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=n
-CONFIG_SMP=n
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP
deleted file mode 100644
index 77a8c5b75763..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,30 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=16
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_RCU_NOCB_CPU=y
-CONFIG_RCU_NOCB_CPU_NONE=n
-CONFIG_RCU_NOCB_CPU_ZERO=n
-CONFIG_RCU_NOCB_CPU_ALL=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_OBJECTS=y
-CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_SLUB=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-all b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-all
deleted file mode 100644
index 0eecebc6e95f..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-all
+++ /dev/null
@@ -1,30 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=16
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_RCU_NOCB_CPU=y
-CONFIG_RCU_NOCB_CPU_NONE=y
-CONFIG_RCU_NOCB_CPU_ZERO=n
-CONFIG_RCU_NOCB_CPU_ALL=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_OBJECTS=y
-CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_SLUB=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-none b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-none
deleted file mode 100644
index 0eecebc6e95f..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-none
+++ /dev/null
@@ -1,30 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=16
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_RCU_NOCB_CPU=y
-CONFIG_RCU_NOCB_CPU_NONE=y
-CONFIG_RCU_NOCB_CPU_ZERO=n
-CONFIG_RCU_NOCB_CPU_ALL=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_OBJECTS=y
-CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_SLUB=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-hp
deleted file mode 100644
index 588bc70420cd..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-hp
+++ /dev/null
@@ -1,30 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=16
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_RCU_NOCB_CPU=y
-CONFIG_RCU_NOCB_CPU_NONE=n
-CONFIG_RCU_NOCB_CPU_ZERO=y
-CONFIG_RCU_NOCB_CPU_ALL=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_OBJECTS=y
-CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_SLUB=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT1-nh
deleted file mode 100644
index e3361c3894a1..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT1-nh
+++ /dev/null
@@ -1,23 +0,0 @@
-CONFIG_TINY_PREEMPT_RCU=y
-CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=n
-#
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT2-NH
deleted file mode 100644
index 64abfc3b4d94..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT2-NH
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_TINY_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=y
-#
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/CFLIST
deleted file mode 100644
index 18223947bbcb..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/CFLIST
+++ /dev/null
@@ -1,14 +0,0 @@
-P1-S-T-NH-SD-SMP-HP
-P2-2-t-nh-sd-SMP-hp
-P3-3-T-nh-SD-SMP-hp
-P4-A-t-NH-sd-SMP-HP
-P5-U-T-NH-sd-SMP-hp
-N1-S-T-NH-SD-SMP-HP
-N2-2-t-nh-sd-SMP-hp
-N3-3-T-nh-SD-SMP-hp
-N4-A-t-NH-sd-SMP-HP
-N5-U-T-NH-sd-SMP-hp
-PT1-nh
-PT2-NH
-NT1-nh
-NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N1-S-T-NH-SD-SMP-HP
deleted file mode 100644
index d81e11d280aa..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N1-S-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,19 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_FAST_NO_HZ=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=8
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N2-2-t-nh-sd-SMP-hp
deleted file mode 100644
index 02e418572b1b..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N2-2-t-nh-sd-SMP-hp
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=4
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N3-3-T-nh-SD-SMP-hp
deleted file mode 100644
index b3100f69c8cf..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N3-3-T-nh-SD-SMP-hp
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N4-A-t-NH-sd-SMP-HP
deleted file mode 100644
index c56b44530725..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N4-A-t-NH-sd-SMP-HP
+++ /dev/null
@@ -1,18 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N5-U-T-NH-sd-SMP-hp
deleted file mode 100644
index 90d924fea9e9..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N5-U-T-NH-sd-SMP-hp
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=y
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT1-nh
deleted file mode 100644
index 023f312a931c..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT1-nh
+++ /dev/null
@@ -1,23 +0,0 @@
-#CHECK#CONFIG_TINY_RCU=y
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=n
-#
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT3-NH
deleted file mode 100644
index 6fd0235dae73..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT3-NH
+++ /dev/null
@@ -1,20 +0,0 @@
-#CHECK#CONFIG_TINY_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=y
-#
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P1-S-T-NH-SD-SMP-HP
deleted file mode 100644
index 9647c44cf4b7..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P1-S-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_RCU_FAST_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=8
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P2-2-t-nh-sd-SMP-hp
deleted file mode 100644
index 0f3b667d2a9f..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P2-2-t-nh-sd-SMP-hp
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=4
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P3-3-T-nh-SD-SMP-hp
deleted file mode 100644
index b035e141bf2a..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P3-3-T-nh-SD-SMP-hp
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P4-A-t-NH-sd-SMP-HP
deleted file mode 100644
index 3ccf6a9447f5..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P4-A-t-NH-sd-SMP-HP
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_RT_MUTEXES=y
-CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp
deleted file mode 100644
index a55c00877fe4..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp
+++ /dev/null
@@ -1,27 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=y
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_OBJECTS=y
-CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
-CONFIG_RT_MUTEXES=y
-CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT1-nh
deleted file mode 100644
index e3361c3894a1..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT1-nh
+++ /dev/null
@@ -1,23 +0,0 @@
-CONFIG_TINY_PREEMPT_RCU=y
-CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=n
-#
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT2-NH
deleted file mode 100644
index 64abfc3b4d94..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT2-NH
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_TINY_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=y
-#
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/ver_functions.sh
deleted file mode 100644
index bae55692ce6e..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/ver_functions.sh
+++ /dev/null
@@ -1,44 +0,0 @@
-#!/bin/bash
-#
-# Kernel-version-dependent shell functions for the rest of the scripts.
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
-# Copyright (C) IBM Corporation, 2013
-#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
-
-# rcutorture_param_onoff bootparam-string config-file
-#
-# Adds onoff rcutorture module parameters to kernels having it.
-rcutorture_param_onoff () {
-        if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
-        then
-                echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2
-                echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
-        fi
-}
-
-# per_version_boot_params bootparam-string config-file seconds
-#
-# Adds per-version torture-module parameters to kernels supporting them.
-per_version_boot_params () {
-        echo $1 `rcutorture_param_onoff "$1" "$2"` \
-                rcutorture.stat_interval=15 \
-                rcutorture.shutdown_secs=$3 \
-                rcutorture.rcutorture_runnable=1 \
-                rcutorture.test_no_idle_hz=1 \
-                rcutorture.verbose=1
-}
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/CFLIST
deleted file mode 100644
index 18223947bbcb..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/CFLIST
+++ /dev/null
@@ -1,14 +0,0 @@
-P1-S-T-NH-SD-SMP-HP
-P2-2-t-nh-sd-SMP-hp
-P3-3-T-nh-SD-SMP-hp
-P4-A-t-NH-sd-SMP-HP
-P5-U-T-NH-sd-SMP-hp
-N1-S-T-NH-SD-SMP-HP
-N2-2-t-nh-sd-SMP-hp
-N3-3-T-nh-SD-SMP-hp
-N4-A-t-NH-sd-SMP-HP
-N5-U-T-NH-sd-SMP-hp
-PT1-nh
-PT2-NH
-NT1-nh
-NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N1-S-T-NH-SD-SMP-HP
deleted file mode 100644
index d81e11d280aa..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N1-S-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,19 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_FAST_NO_HZ=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=8
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N2-2-t-nh-sd-SMP-hp
deleted file mode 100644
index 02e418572b1b..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N2-2-t-nh-sd-SMP-hp
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=4
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N3-3-T-nh-SD-SMP-hp
deleted file mode 100644
index b3100f69c8cf..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N3-3-T-nh-SD-SMP-hp
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N4-A-t-NH-sd-SMP-HP
deleted file mode 100644
index c56b44530725..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N4-A-t-NH-sd-SMP-HP
+++ /dev/null
@@ -1,18 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N5-U-T-NH-sd-SMP-hp
deleted file mode 100644
index 90d924fea9e9..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N5-U-T-NH-sd-SMP-hp
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=y
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT1-nh
deleted file mode 100644
index 023f312a931c..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT1-nh
+++ /dev/null
@@ -1,23 +0,0 @@
-#CHECK#CONFIG_TINY_RCU=y
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=n
-#
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT3-NH
deleted file mode 100644
index 6fd0235dae73..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT3-NH
+++ /dev/null
@@ -1,20 +0,0 @@
-#CHECK#CONFIG_TINY_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=y
-#
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P1-S-T-NH-SD-SMP-HP
deleted file mode 100644
index 9647c44cf4b7..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P1-S-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_RCU_FAST_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=8
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P2-2-t-nh-sd-SMP-hp
deleted file mode 100644
index 0f3b667d2a9f..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P2-2-t-nh-sd-SMP-hp
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=4
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P3-3-T-nh-SD-SMP-hp
deleted file mode 100644
index b035e141bf2a..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P3-3-T-nh-SD-SMP-hp
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P4-A-t-NH-sd-SMP-HP
deleted file mode 100644
index 3ccf6a9447f5..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P4-A-t-NH-sd-SMP-HP
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_RT_MUTEXES=y
-CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp
deleted file mode 100644
index a55c00877fe4..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp
+++ /dev/null
@@ -1,27 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=y
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_OBJECTS=y
-CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
-CONFIG_RT_MUTEXES=y
-CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT1-nh
deleted file mode 100644
index e3361c3894a1..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT1-nh
+++ /dev/null
@@ -1,23 +0,0 @@
-CONFIG_TINY_PREEMPT_RCU=y
-CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=n
-#
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT2-NH
deleted file mode 100644
index 64abfc3b4d94..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT2-NH
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_TINY_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=y
-#
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/ver_functions.sh
deleted file mode 100644
index 8977d8d31b19..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/ver_functions.sh
+++ /dev/null
@@ -1,57 +0,0 @@
-#!/bin/bash
-#
-# Kernel-version-dependent shell functions for the rest of the scripts.
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
-# Copyright (C) IBM Corporation, 2013
-#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
-
-# rcutorture_param_n_barrier_cbs bootparam-string
-#
-# Adds n_barrier_cbs rcutorture module parameter to kernels having it.
-rcutorture_param_n_barrier_cbs () {
-        if echo $1 | grep -q "rcutorture\.n_barrier_cbs"
-        then
-                :
-        else
-                echo rcutorture.n_barrier_cbs=4
-        fi
-}
-
-# rcutorture_param_onoff bootparam-string config-file
-#
-# Adds onoff rcutorture module parameters to kernels having it.
-rcutorture_param_onoff () {
-        if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
-        then
-                echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2
-                echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
-        fi
-}
-
-# per_version_boot_params bootparam-string config-file seconds
-#
-# Adds per-version torture-module parameters to kernels supporting them.
-per_version_boot_params () {
-        echo $1 `rcutorture_param_onoff "$1" "$2"` \
-                `rcutorture_param_n_barrier_cbs "$1"` \
-                rcutorture.stat_interval=15 \
-                rcutorture.shutdown_secs=$3 \
-                rcutorture.rcutorture_runnable=1 \
-                rcutorture.test_no_idle_hz=1 \
-                rcutorture.verbose=1
-}
diff --git a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt
index 28db67b54e55..9ef33a743b73 100644
--- a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt
+++ b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt
@@ -34,7 +34,7 @@ CONFIG_PREEMPT
 CONFIG_PREEMPT_RCU
 CONFIG_SMP
 CONFIG_TINY_RCU
-CONFIG_TREE_PREEMPT_RCU
+CONFIG_PREEMPT_RCU
 CONFIG_TREE_RCU
 
         All forced by CONFIG_TINY_RCU.
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
index 3e588db86a17..ec03c883db00 100644
--- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
+++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
@@ -1,5 +1,5 @@
 This document gives a brief rationale for the TREE_RCU-related test
-cases, a group that includes TREE_PREEMPT_RCU.
+cases, a group that includes PREEMPT_RCU.
 
 
 Kconfig Parameters:
@@ -14,10 +14,9 @@ CONFIG_NO_HZ_FULL_SYSIDLE -- Do one.
 CONFIG_PREEMPT -- Do half.  (First three and #8.)
 CONFIG_PROVE_LOCKING -- Do all but two, covering CONFIG_PROVE_RCU and not.
 CONFIG_PROVE_RCU -- Do all but one under CONFIG_PROVE_LOCKING.
-CONFIG_RCU_BOOST -- one of TREE_PREEMPT_RCU.
-CONFIG_RCU_BOOST_PRIO -- set to 2 for _BOOST testing.
-CONFIG_RCU_CPU_STALL_INFO -- do one with and without _VERBOSE.
-CONFIG_RCU_CPU_STALL_VERBOSE -- do one with and without _INFO.
+CONFIG_RCU_BOOST -- one of PREEMPT_RCU.
+CONFIG_RCU_KTHREAD_PRIO -- set to 2 for _BOOST testing.
+CONFIG_RCU_CPU_STALL_INFO -- Do one.
 CONFIG_RCU_FANOUT -- Cover hierarchy as currently, but overlap with others.
 CONFIG_RCU_FANOUT_EXACT -- Do one.
 CONFIG_RCU_FANOUT_LEAF -- Do one non-default.
@@ -27,7 +26,7 @@ CONFIG_RCU_NOCB_CPU_ALL -- Do one.
 CONFIG_RCU_NOCB_CPU_NONE -- Do one.
 CONFIG_RCU_NOCB_CPU_ZERO -- Do one.
 CONFIG_RCU_TRACE -- Do half.
-CONFIG_SMP -- Need one !SMP for TREE_PREEMPT_RCU.
+CONFIG_SMP -- Need one !SMP for PREEMPT_RCU.
 RCU-bh: Do one with PREEMPT and one with !PREEMPT.
 RCU-sched: Do one with PREEMPT but not BOOST.
 
@@ -77,7 +76,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT
 
 CONFIG_RCU_STALL_COMMON
 
-        Implied by TREE_RCU and TREE_PREEMPT_RCU.
+        Implied by TREE_RCU and PREEMPT_RCU.
 
 CONFIG_RCU_TORTURE_TEST
 CONFIG_RCU_TORTURE_TEST_RUNNABLE
@@ -88,7 +87,7 @@ CONFIG_RCU_USER_QS
 
         Redundant with CONFIG_NO_HZ_FULL.
 
-CONFIG_TREE_PREEMPT_RCU
+CONFIG_PREEMPT_RCU
 CONFIG_TREE_RCU
 
         These are controlled by CONFIG_PREEMPT.
diff --git a/tools/testing/selftests/size/.gitignore b/tools/testing/selftests/size/.gitignore
new file mode 100644
index 000000000000..189b7818de34
--- /dev/null
+++ b/tools/testing/selftests/size/.gitignore
@@ -0,0 +1 @@
+get_size
diff --git a/tools/testing/selftests/size/Makefile b/tools/testing/selftests/size/Makefile
new file mode 100644
index 000000000000..04dc25e4fa92
--- /dev/null
+++ b/tools/testing/selftests/size/Makefile
@@ -0,0 +1,12 @@
+CC = $(CROSS_COMPILE)gcc
+
+all: get_size
+
+get_size: get_size.c
+        $(CC) -static -ffreestanding -nostartfiles -s $< -o $@
+
+run_tests: all
+        ./get_size
+
+clean:
+        $(RM) get_size
diff --git a/tools/testing/selftests/size/get_size.c b/tools/testing/selftests/size/get_size.c
new file mode 100644
index 000000000000..2d1af7cca463
--- /dev/null
+++ b/tools/testing/selftests/size/get_size.c
@@ -0,0 +1,100 @@
+/*
+ * Copyright 2014 Sony Mobile Communications Inc.
+ *
+ * Licensed under the terms of the GNU GPL License version 2
+ *
+ * Selftest for runtime system size
+ *
+ * Prints the amount of RAM that the currently running system is using.
+ *
+ * This program tries to be as small as possible itself, to
+ * avoid perturbing the system memory utilization with its
+ * own execution.  It also attempts to have as few dependencies
+ * on kernel features as possible.
+ *
+ * It should be statically linked, with startup libs avoided.
+ * It uses no library calls, and only the following 3 syscalls:
+ *   sysinfo(), write(), and _exit()
+ *
+ * For output, it avoids printf (which in some C libraries
+ * has large external dependencies) by  implementing it's own
+ * number output and print routines, and using __builtin_strlen()
+ */
+
+#include <sys/sysinfo.h>
+#include <unistd.h>
+
+#define STDOUT_FILENO 1
+
+static int print(const char *s)
+{
+        return write(STDOUT_FILENO, s, __builtin_strlen(s));
+}
+
+static inline char *num_to_str(unsigned long num, char *buf, int len)
+{
+        unsigned int digit;
+
+        /* put digits in buffer from back to front */
+        buf += len - 1;
+        *buf = 0;
+        do {
+                digit = num % 10;
+                *(--buf) = digit + '0';
+                num /= 10;
+        } while (num > 0);
+
+        return buf;
+}
+
+static int print_num(unsigned long num)
+{
+        char num_buf[30];
+
+        return print(num_to_str(num, num_buf, sizeof(num_buf)));
+}
+
+static int print_k_value(const char *s, unsigned long num, unsigned long units)
+{
+        unsigned long long temp;
+        int ccode;
+
+        print(s);
+
+        temp = num;
+        temp = (temp * units)/1024;
+        num = temp;
+        ccode = print_num(num);
+        print("\n");
+        return ccode;
+}
+
+/* this program has no main(), as startup libraries are not used */
+void _start(void)
+{
+        int ccode;
+        struct sysinfo info;
+        unsigned long used;
+
+        print("Testing system size.\n");
+        print("1..1\n");
+
+        ccode = sysinfo(&info);
+        if (ccode < 0) {
+                print("not ok 1 get runtime memory use\n");
+                print("# could not get sysinfo\n");
+                _exit(ccode);
+        }
+        /* ignore cache complexities for now */
+        used = info.totalram - info.freeram - info.bufferram;
+        print_k_value("ok 1 get runtime memory use # size = ", used,
+                info.mem_unit);
+
+        print("# System runtime memory report (units in Kilobytes):\n");
+        print_k_value("#   Total:  ", info.totalram, info.mem_unit);
+        print_k_value("#   Free:   ", info.freeram, info.mem_unit);
+        print_k_value("#   Buffer: ", info.bufferram, info.mem_unit);
+        print_k_value("#   In use: ", used, info.mem_unit);
+
+        _exit(0);
+}
diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c
index 41bd85559d4b..f87d970a485c 100644
--- a/tools/testing/selftests/timers/posix_timers.c
+++ b/tools/testing/selftests/timers/posix_timers.c
@@ -15,6 +15,8 @@
 #include <time.h>
 #include <pthread.h>
 
+#include "../kselftest.h"
+
 #define DELAY 2
 #define USECS_PER_SEC 1000000
 
@@ -194,16 +196,16 @@ int main(int argc, char **argv)
         printf("based timers if other threads run on the CPU...\n");
 
         if (check_itimer(ITIMER_VIRTUAL) < 0)
-                return -1;
+                return ksft_exit_fail();
 
         if (check_itimer(ITIMER_PROF) < 0)
-                return -1;
+                return ksft_exit_fail();
 
         if (check_itimer(ITIMER_REAL) < 0)
-                return -1;
+                return ksft_exit_fail();
 
         if (check_timer_create(CLOCK_THREAD_CPUTIME_ID) < 0)
-                return -1;
+                return ksft_exit_fail();
 
         /*
          * It's unfortunately hard to reliably test a timer expiration
@@ -215,7 +217,7 @@ int main(int argc, char **argv)
          * find a better solution.
          */
         if (check_timer_create(CLOCK_PROCESS_CPUTIME_ID) < 0)
-                return -1;
+                return ksft_exit_fail();
 
-        return 0;
+        return ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/user/Makefile b/tools/testing/selftests/user/Makefile
index 396255bd720e..12c9d15bab07 100644
--- a/tools/testing/selftests/user/Makefile
+++ b/tools/testing/selftests/user/Makefile
@@ -4,10 +4,4 @@
 all:
 
 run_tests: all
-        @if /sbin/modprobe test_user_copy ; then \
-                rmmod test_user_copy; \
-                echo "user_copy: ok"; \
-        else \
-                echo "user_copy: [FAIL]"; \
-                exit 1; \
-        fi
+        ./test_user_copy.sh
diff --git a/tools/testing/selftests/user/test_user_copy.sh b/tools/testing/selftests/user/test_user_copy.sh
new file mode 100755
index 000000000000..350107f40c1d
--- /dev/null
+++ b/tools/testing/selftests/user/test_user_copy.sh
@@ -0,0 +1,10 @@
+#!/bin/sh
+# Runs copy_to/from_user infrastructure using test_user_copy kernel module
+
+if /sbin/modprobe -q test_user_copy; then
+        /sbin/modprobe -q -r test_user_copy
+        echo "user_copy: ok"
+else
+        echo "user_copy: [FAIL]"
+        exit 1
+fi
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 4c4b1f631ecf..077828c889f1 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -7,7 +7,7 @@ BINARIES += transhuge-stress
 
 all: $(BINARIES)
 %: %.c
-        $(CC) $(CFLAGS) -o $@ $^
+        $(CC) $(CFLAGS) -o $@ $^ -lrt
 
 run_tests: all
         @/bin/sh ./run_vmtests || (echo "vmtests: [FAIL]"; exit 1)
diff --git a/tools/thermal/tmon/sysfs.c b/tools/thermal/tmon/sysfs.c
index dfe454855cd2..1c12536f2081 100644
--- a/tools/thermal/tmon/sysfs.c
+++ b/tools/thermal/tmon/sysfs.c
@@ -446,7 +446,7 @@ int probe_thermal_sysfs(void)
                 return -1;
         }
 
-        ptdata.tzi = calloc(sizeof(struct tz_info), ptdata.max_tz_instance+1);
+        ptdata.tzi = calloc(ptdata.max_tz_instance+1, sizeof(struct tz_info));
         if (!ptdata.tzi) {
                 fprintf(stderr, "Err: allocate tz_info\n");
                 return -1;
@@ -454,8 +454,8 @@ int probe_thermal_sysfs(void)
 
         /* we still show thermal zone information if there is no cdev */
         if (ptdata.nr_cooling_dev) {
-                ptdata.cdi = calloc(sizeof(struct cdev_info),
-                                ptdata.max_cdev_instance + 1);
+                ptdata.cdi = calloc(ptdata.max_cdev_instance + 1,
+                                sizeof(struct cdev_info));
                 if (!ptdata.cdi) {
                         free(ptdata.tzi);
                         fprintf(stderr, "Err: allocate cdev_info\n");
diff --git a/tools/usb/ffs-aio-example/multibuff/device_app/aio_multibuff.c b/tools/usb/ffs-aio-example/multibuff/device_app/aio_multibuff.c
index af4b0508be77..aaca1f44e788 100644
--- a/tools/usb/ffs-aio-example/multibuff/device_app/aio_multibuff.c
+++ b/tools/usb/ffs-aio-example/multibuff/device_app/aio_multibuff.c
@@ -342,7 +342,7 @@ int main(int argc, char *argv[])
                                 iobuf[i].requested = ret;
                                 printf("submit: %d requests buf: %d\n", ret, i);
                         } else
-                                perror("unable to submit reqests");
+                                perror("unable to submit requests");
                 }
 
                 /* if event is ready to read */
diff --git a/tools/usb/usbip/libsrc/list.h b/tools/usb/usbip/libsrc/list.h
index 8d0c936e184f..5eaaa78e2c6a 100644
--- a/tools/usb/usbip/libsrc/list.h
+++ b/tools/usb/usbip/libsrc/list.h
@@ -98,7 +98,7 @@ static inline void list_del(struct list_head *entry)
  * list_entry - get the struct for this entry
  * @ptr:        the &struct list_head pointer.
  * @type:       the type of the struct this is embedded in.
- * @member:     the name of the list_struct within the struct.
+ * @member:     the name of the list_head within the struct.
  */
 #define list_entry(ptr, type, member) \
         container_of(ptr, type, member)
diff --git a/tools/usb/usbip/src/usbipd.c b/tools/usb/usbip/src/usbipd.c
index 2f87f2d348ba..2a7cd2b8d966 100644
--- a/tools/usb/usbip/src/usbipd.c
+++ b/tools/usb/usbip/src/usbipd.c
@@ -91,7 +91,6 @@ static void usbipd_help(void)
 static int recv_request_import(int sockfd)
 {
         struct op_import_request req;
-        struct op_common reply;
         struct usbip_exported_device *edev;
         struct usbip_usb_device pdu_udev;
         struct list_head *i;
@@ -100,7 +99,6 @@ static int recv_request_import(int sockfd)
         int rc;
 
         memset(&req, 0, sizeof(req));
-        memset(&reply, 0, sizeof(reply));
 
         rc = usbip_net_recv(sockfd, &req, sizeof(req));
         if (rc < 0) {
diff --git a/tools/virtio/Makefile b/tools/virtio/Makefile
index 9325f4693821..505ad51b3b51 100644
--- a/tools/virtio/Makefile
+++ b/tools/virtio/Makefile
@@ -3,7 +3,7 @@ test: virtio_test vringh_test
 virtio_test: virtio_ring.o virtio_test.o
 vringh_test: vringh_test.o vringh.o virtio_ring.o
 
-CFLAGS += -g -O2 -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE
+CFLAGS += -g -O2 -Werror -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE
 vpath %.c ../../drivers/virtio ../../drivers/vhost
 mod:
         ${MAKE} -C `pwd`/../.. M=`pwd`/vhost_test
diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h
index 5a2d1f0f6bc7..a3e07016a440 100644
--- a/tools/virtio/linux/virtio.h
+++ b/tools/virtio/linux/virtio.h
@@ -6,31 +6,12 @@
 /* TODO: empty stubs for now. Broken but enough for virtio_ring.c */
 #define list_add_tail(a, b) do {} while (0)
 #define list_del(a) do {} while (0)
-
-#define BIT_WORD(nr)            ((nr) / BITS_PER_LONG)
-#define BITS_PER_BYTE           8
-#define BITS_PER_LONG (sizeof(long) * BITS_PER_BYTE)
-#define BIT_MASK(nr)            (1UL << ((nr) % BITS_PER_LONG))
-
-/* TODO: Not atomic as it should be:
- * we don't use this for anything important. */
-static inline void clear_bit(int nr, volatile unsigned long *addr)
-{
-        unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-
-        *p &= ~mask;
-}
-
-static inline int test_bit(int nr, const volatile unsigned long *addr)
-{
-        return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
-}
+#define list_for_each_entry(a, b, c) while (0)
 /* end of stubs */
 
 struct virtio_device {
         void *dev;
-        unsigned long features[1];
+        u64 features;
 };
 
 struct virtqueue {
diff --git a/tools/virtio/linux/virtio_byteorder.h b/tools/virtio/linux/virtio_byteorder.h
new file mode 100644
index 000000000000..9de9e6ac1d10
--- /dev/null
+++ b/tools/virtio/linux/virtio_byteorder.h
@@ -0,0 +1,8 @@
+#ifndef _LINUX_VIRTIO_BYTEORDER_STUB_H
+#define _LINUX_VIRTIO_BYTEORDER_STUB_H
+
+#include <asm/byteorder.h>
+#include "../../include/linux/byteorder/generic.h"
+#include "../../include/linux/virtio_byteorder.h"
+
+#endif
diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h
index 5049967f99f7..806d683ab107 100644
--- a/tools/virtio/linux/virtio_config.h
+++ b/tools/virtio/linux/virtio_config.h
@@ -1,6 +1,72 @@
-#define VIRTIO_TRANSPORT_F_START        28
-#define VIRTIO_TRANSPORT_F_END          32
+#include <linux/virtio_byteorder.h>
+#include <linux/virtio.h>
+#include <uapi/linux/virtio_config.h>
+
+/*
+ * __virtio_test_bit - helper to test feature bits. For use by transports.
+ *                     Devices should normally use virtio_has_feature,
+ *                     which includes more checks.
+ * @vdev: the device
+ * @fbit: the feature bit
+ */
+static inline bool __virtio_test_bit(const struct virtio_device *vdev,
+                                     unsigned int fbit)
+{
+        return vdev->features & (1ULL << fbit);
+}
+
+/**
+ * __virtio_set_bit - helper to set feature bits. For use by transports.
+ * @vdev: the device
+ * @fbit: the feature bit
+ */
+static inline void __virtio_set_bit(struct virtio_device *vdev,
+                                    unsigned int fbit)
+{
+        vdev->features |= (1ULL << fbit);
+}
+
+/**
+ * __virtio_clear_bit - helper to clear feature bits. For use by transports.
+ * @vdev: the device
+ * @fbit: the feature bit
+ */
+static inline void __virtio_clear_bit(struct virtio_device *vdev,
+                                      unsigned int fbit)
+{
+        vdev->features &= ~(1ULL << fbit);
+}
 
 #define virtio_has_feature(dev, feature) \
-        test_bit((feature), (dev)->features)
+        (__virtio_test_bit((dev), feature))
+
+static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val)
+{
+        return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val)
+{
+        return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val)
+{
+        return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val)
+{
+        return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val)
+{
+        return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
+{
+        return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
 
diff --git a/tools/virtio/uapi/linux/virtio_types.h b/tools/virtio/uapi/linux/virtio_types.h
new file mode 100644
index 000000000000..e7a1096e7c97
--- /dev/null
+++ b/tools/virtio/uapi/linux/virtio_types.h
@@ -0,0 +1 @@
+#include "../../include/uapi/linux/virtio_types.h"
diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c
index 00ea679b3826..e0445898f08f 100644
--- a/tools/virtio/virtio_test.c
+++ b/tools/virtio/virtio_test.c
@@ -11,6 +11,7 @@
 #include <sys/types.h>
 #include <fcntl.h>
 #include <stdbool.h>
+#include <linux/virtio_types.h>
 #include <linux/vhost.h>
 #include <linux/virtio.h>
 #include <linux/virtio_ring.h>
@@ -60,7 +61,7 @@ void vhost_vq_setup(struct vdev_info *dev, struct vq_info *info)
 {
         struct vhost_vring_state state = { .index = info->idx };
         struct vhost_vring_file file = { .index = info->idx };
-        unsigned long long features = dev->vdev.features[0];
+        unsigned long long features = dev->vdev.features;
         struct vhost_vring_addr addr = {
                 .index = info->idx,
                 .desc_user_addr = (uint64_t)(unsigned long)info->vring.desc,
@@ -113,8 +114,7 @@ static void vdev_info_init(struct vdev_info* dev, unsigned long long features)
 {
         int r;
         memset(dev, 0, sizeof *dev);
-        dev->vdev.features[0] = features;
-        dev->vdev.features[1] = features >> 32;
+        dev->vdev.features = features;
         dev->buf_size = 1024;
         dev->buf = malloc(dev->buf_size);
         assert(dev->buf);
@@ -228,6 +228,14 @@ const struct option longopts[] = {
                 .val = 'i',
         },
         {
+                .name = "virtio-1",
+                .val = '1',
+        },
+        {
+                .name = "no-virtio-1",
+                .val = '0',
+        },
+        {
                 .name = "delayed-interrupt",
                 .val = 'D',
         },
@@ -244,6 +252,7 @@ static void help(void)
         fprintf(stderr, "Usage: virtio_test [--help]"
                 " [--no-indirect]"
                 " [--no-event-idx]"
+                " [--no-virtio-1]"
                 " [--delayed-interrupt]"
                 "\n");
 }
@@ -252,7 +261,7 @@ int main(int argc, char **argv)
 {
         struct vdev_info dev;
         unsigned long long features = (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
-                (1ULL << VIRTIO_RING_F_EVENT_IDX);
+                (1ULL << VIRTIO_RING_F_EVENT_IDX) | (1ULL << VIRTIO_F_VERSION_1);
         int o;
         bool delayed = false;
 
@@ -273,6 +282,9 @@ int main(int argc, char **argv)
                 case 'i':
                         features &= ~(1ULL << VIRTIO_RING_F_INDIRECT_DESC);
                         break;
+                case '0':
+                        features &= ~(1ULL << VIRTIO_F_VERSION_1);
+                        break;
                 case 'D':
                         delayed = true;
                         break;
diff --git a/tools/virtio/vringh_test.c b/tools/virtio/vringh_test.c
index 14a4f4cab5b9..5f94f5105678 100644
--- a/tools/virtio/vringh_test.c
+++ b/tools/virtio/vringh_test.c
@@ -7,6 +7,7 @@
 #include <linux/virtio.h>
 #include <linux/vringh.h>
 #include <linux/virtio_ring.h>
+#include <linux/virtio_config.h>
 #include <linux/uaccess.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -131,7 +132,7 @@ static inline int vringh_get_head(struct vringh *vrh, u16 *head)
         return 1;
 }
 
-static int parallel_test(unsigned long features,
+static int parallel_test(u64 features,
                          bool (*getrange)(struct vringh *vrh,
                                           u64 addr, struct vringh_range *r),
                          bool fast_vringh)
@@ -304,7 +305,7 @@ static int parallel_test(unsigned long features,
                 close(to_guest[1]);
                 close(to_host[0]);
 
-                gvdev.vdev.features[0] = features;
+                gvdev.vdev.features = features;
                 gvdev.to_host_fd = to_host[1];
                 gvdev.notifies = 0;
 
@@ -449,13 +450,15 @@ int main(int argc, char *argv[])
         bool fast_vringh = false, parallel = false;
 
         getrange = getrange_iov;
-        vdev.features[0] = 0;
+        vdev.features = 0;
 
         while (argv[1]) {
                 if (strcmp(argv[1], "--indirect") == 0)
-                        vdev.features[0] |= (1 << VIRTIO_RING_F_INDIRECT_DESC);
+                        __virtio_set_bit(&vdev, VIRTIO_RING_F_INDIRECT_DESC);
                 else if (strcmp(argv[1], "--eventidx") == 0)
-                        vdev.features[0] |= (1 << VIRTIO_RING_F_EVENT_IDX);
+                        __virtio_set_bit(&vdev, VIRTIO_RING_F_EVENT_IDX);
+                else if (strcmp(argv[1], "--virtio-1") == 0)
+                        __virtio_set_bit(&vdev, VIRTIO_F_VERSION_1);
                 else if (strcmp(argv[1], "--slow-range") == 0)
                         getrange = getrange_slow;
                 else if (strcmp(argv[1], "--fast-vringh") == 0)
@@ -468,7 +471,7 @@ int main(int argc, char *argv[])
         }
 
         if (parallel)
-                return parallel_test(vdev.features[0], getrange, fast_vringh);
+                return parallel_test(vdev.features, getrange, fast_vringh);
 
         if (posix_memalign(&__user_addr_min, PAGE_SIZE, USER_MEM) != 0)
                 abort();
@@ -483,7 +486,7 @@ int main(int argc, char *argv[])
 
         /* Set up host side. */
         vring_init(&vrh.vring, RINGSIZE, __user_addr_min, ALIGN);
-        vringh_init_user(&vrh, vdev.features[0], RINGSIZE, true,
+        vringh_init_user(&vrh, vdev.features, RINGSIZE, true,
                          vrh.vring.desc, vrh.vring.avail, vrh.vring.used);
 
         /* No descriptor to get yet... */
@@ -652,13 +655,13 @@ int main(int argc, char *argv[])
         }
 
         /* Test weird (but legal!) indirect. */
-        if (vdev.features[0] & (1 << VIRTIO_RING_F_INDIRECT_DESC)) {
+        if (__virtio_test_bit(&vdev, VIRTIO_RING_F_INDIRECT_DESC)) {
                 char *data = __user_addr_max - USER_MEM/4;
                 struct vring_desc *d = __user_addr_max - USER_MEM/2;
                 struct vring vring;
 
                 /* Force creation of direct, which we modify. */
-                vdev.features[0] &= ~(1 << VIRTIO_RING_F_INDIRECT_DESC);
+                __virtio_clear_bit(&vdev, VIRTIO_RING_F_INDIRECT_DESC);
                 vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &vdev, true,
                                          __user_addr_min,
                                          never_notify_host,
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
index 3d907dacf2ac..ac884b65a072 100644
--- a/tools/vm/Makefile
+++ b/tools/vm/Makefile
@@ -1,6 +1,6 @@
 # Makefile for vm tools
 #
-TARGETS=page-types slabinfo
+TARGETS=page-types slabinfo page_owner_sort
 
 LIB_DIR = ../lib/api
 LIBS = $(LIB_DIR)/libapikfs.a
@@ -18,5 +18,5 @@ $(LIBS):
         $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS)
 
 clean:
-        $(RM) page-types slabinfo
+        $(RM) page-types slabinfo page_owner_sort
         make -C $(LIB_DIR) clean
diff --git a/tools/vm/page_owner_sort.c b/tools/vm/page_owner_sort.c
new file mode 100644
index 000000000000..77147b42d598
--- /dev/null
+++ b/tools/vm/page_owner_sort.c
@@ -0,0 +1,144 @@
+/*
+ * User-space helper to sort the output of /sys/kernel/debug/page_owner
+ *
+ * Example use:
+ * cat /sys/kernel/debug/page_owner > page_owner_full.txt
+ * grep -v ^PFN page_owner_full.txt > page_owner.txt
+ * ./sort page_owner.txt sorted_page_owner.txt
+*/
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <string.h>
+
+struct block_list {
+        char *txt;
+        int len;
+        int num;
+};
+
+
+static struct block_list *list;
+static int list_size;
+static int max_size;
+
+struct block_list *block_head;
+
+int read_block(char *buf, int buf_size, FILE *fin)
+{
+        char *curr = buf, *const buf_end = buf + buf_size;
+
+        while (buf_end - curr > 1 && fgets(curr, buf_end - curr, fin)) {
+                if (*curr == '\n') /* empty line */
+                        return curr - buf;
+                curr += strlen(curr);
+        }
+
+        return -1; /* EOF or no space left in buf. */
+}
+
+static int compare_txt(const void *p1, const void *p2)
+{
+        const struct block_list *l1 = p1, *l2 = p2;
+
+        return strcmp(l1->txt, l2->txt);
+}
+
+static int compare_num(const void *p1, const void *p2)
+{
+        const struct block_list *l1 = p1, *l2 = p2;
+
+        return l2->num - l1->num;
+}
+
+static void add_list(char *buf, int len)
+{
+        if (list_size != 0 &&
+            len == list[list_size-1].len &&
+            memcmp(buf, list[list_size-1].txt, len) == 0) {
+                list[list_size-1].num++;
+                return;
+        }
+        if (list_size == max_size) {
+                printf("max_size too small??\n");
+                exit(1);
+        }
+        list[list_size].txt = malloc(len+1);
+        list[list_size].len = len;
+        list[list_size].num = 1;
+        memcpy(list[list_size].txt, buf, len);
+        list[list_size].txt[len] = 0;
+        list_size++;
+        if (list_size % 1000 == 0) {
+                printf("loaded %d\r", list_size);
+                fflush(stdout);
+        }
+}
+
+#define BUF_SIZE        1024
+
+int main(int argc, char **argv)
+{
+        FILE *fin, *fout;
+        char buf[BUF_SIZE];
+        int ret, i, count;
+        struct block_list *list2;
+        struct stat st;
+
+        if (argc < 3) {
+                printf("Usage: ./program <input> <output>\n");
+                perror("open: ");
+                exit(1);
+        }
+
+        fin = fopen(argv[1], "r");
+        fout = fopen(argv[2], "w");
+        if (!fin || !fout) {
+                printf("Usage: ./program <input> <output>\n");
+                perror("open: ");
+                exit(1);
+        }
+
+        fstat(fileno(fin), &st);
+        max_size = st.st_size / 100; /* hack ... */
+
+        list = malloc(max_size * sizeof(*list));
+
+        for ( ; ; ) {
+                ret = read_block(buf, BUF_SIZE, fin);
+                if (ret < 0)
+                        break;
+
+                add_list(buf, ret);
+        }
+
+        printf("loaded %d\n", list_size);
+
+        printf("sorting ....\n");
+
+        qsort(list, list_size, sizeof(list[0]), compare_txt);
+
+        list2 = malloc(sizeof(*list) * list_size);
+
+        printf("culling\n");
+
+        for (i = count = 0; i < list_size; i++) {
+                if (count == 0 ||
+                    strcmp(list2[count-1].txt, list[i].txt) != 0) {
+                        list2[count++] = list[i];
+                } else {
+                        list2[count-1].num += list[i].num;
+                }
+        }
+
+        qsort(list2, count, sizeof(list[0]), compare_num);
+
+        for (i = 0; i < count; i++)
+                fprintf(fout, "%d times:\n%s\n", list2[i].num, list2[i].txt);
+
+        return 0;
+}