88 files changed, 2223 insertions, 1056 deletions
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 5a1f6489d185..07819bfa7dba 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -127,7 +127,8 @@ static void kvp_acquire_lock(int pool)
        fl.l_pid = getpid();
        if (fcntl(kvp_file_info[pool].fd, F_SETLKW, &fl) == -1) {
-                syslog(LOG_ERR, "Failed to acquire the lock pool: %d", pool);
+                syslog(LOG_ERR, "Failed to acquire the lock pool: %d; error: %d %s", pool,
+                                errno, strerror(errno));
                exit(EXIT_FAILURE);
        }
 }
@@ -138,8 +139,8 @@ static void kvp_release_lock(int pool)
        fl.l_pid = getpid();
        if (fcntl(kvp_file_info[pool].fd, F_SETLK, &fl) == -1) {
-                perror("fcntl");
+                syslog(LOG_ERR, "Failed to release the lock pool: %d; error: %d %s", pool,
-                syslog(LOG_ERR, "Failed to release the lock pool: %d", pool);
+                                errno, strerror(errno));
                exit(EXIT_FAILURE);
        }
 }
@@ -157,8 +158,9 @@ static void kvp_update_file(int pool)
        filep = fopen(kvp_file_info[pool].fname, "we");
        if (!filep) {
+                syslog(LOG_ERR, "Failed to open file, pool: %d; error: %d %s", pool,
+                                errno, strerror(errno));
                kvp_release_lock(pool);
-                syslog(LOG_ERR, "Failed to open file, pool: %d", pool);
                exit(EXIT_FAILURE);
        }
@@ -188,8 +190,9 @@ static void kvp_update_mem_state(int pool)
        filep = fopen(kvp_file_info[pool].fname, "re");
        if (!filep) {
+                syslog(LOG_ERR, "Failed to open file, pool: %d; error: %d %s", pool,
+                                errno, strerror(errno));
                kvp_release_lock(pool);
-                syslog(LOG_ERR, "Failed to open file, pool: %d", pool);
                exit(EXIT_FAILURE);
        }
        for (;;) {
@@ -240,7 +243,8 @@ static int kvp_file_init(void)
        if (access(KVP_CONFIG_LOC, F_OK)) {
                if (mkdir(KVP_CONFIG_LOC, 0755 /* rwxr-xr-x */)) {
-                        syslog(LOG_ERR, " Failed to create %s", KVP_CONFIG_LOC);
+                        syslog(LOG_ERR, "Failed to create '%s'; error: %d %s", KVP_CONFIG_LOC,
+                                        errno, strerror(errno));
                        exit(EXIT_FAILURE);
                }
        }
@@ -257,12 +261,15 @@ static int kvp_file_init(void)
                filep = fopen(fname, "re");
-                if (!filep)
+                if (!filep) {
+                        close(fd);
                        return 1;
+                }
                record = malloc(alloc_unit * num_blocks);
                if (record == NULL) {
                        fclose(filep);
+                        close(fd);
                        return 1;
                }
                for (;;) {
@@ -286,6 +293,7 @@ static int kvp_file_init(void)
                                                num_blocks);
                                if (record == NULL) {
                                        fclose(filep);
+                                        close(fd);
                                        return 1;
                                }
                                continue;
@@ -765,7 +773,9 @@ static void kvp_process_ipconfig_file(char *cmd,
                        break;
                x = strchr(p, '\n');
-                *x = '\0';
+                if (x)
+                        *x = '\0';
                strcat(config_buf, p);
                strcat(config_buf, ";");
        }
@@ -1016,9 +1026,10 @@ kvp_get_ip_info(int family, char *if_name, int op,
                                if (sn_offset == 0)
                                        strcpy(sn_str, cidr_mask);
-                                else
+                                else {
+                                        strcat((char *)ip_buffer->sub_net, ";");
                                        strcat(sn_str, cidr_mask);
-                                strcat((char *)ip_buffer->sub_net, ";");
+                                }
                                sn_offset += strlen(sn_str) + 1;
                        }
@@ -1274,7 +1285,8 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val)
        file = fopen(if_file, "w");
        if (file == NULL) {
-                syslog(LOG_ERR, "Failed to open config file");
+                syslog(LOG_ERR, "Failed to open config file; error: %d %s",
+                                errno, strerror(errno));
                return HV_E_FAIL;
        }
@@ -1441,7 +1453,8 @@ int main(void)
        fd = socket(AF_NETLINK, SOCK_DGRAM, NETLINK_CONNECTOR);
        if (fd < 0) {
-                syslog(LOG_ERR, "netlink socket creation failed; error:%d", fd);
+                syslog(LOG_ERR, "netlink socket creation failed; error: %d %s", errno,
+                                strerror(errno));
                exit(EXIT_FAILURE);
        }
        addr.nl_family = AF_NETLINK;
@@ -1452,12 +1465,18 @@ int main(void)
        error = bind(fd, (struct sockaddr *)&addr, sizeof(addr));
        if (error < 0) {
-                syslog(LOG_ERR, "bind failed; error:%d", error);
+                syslog(LOG_ERR, "bind failed; error: %d %s", errno, strerror(errno));
                close(fd);
                exit(EXIT_FAILURE);
        }
        nl_group = CN_KVP_IDX;
-        setsockopt(fd, SOL_NETLINK, NETLINK_ADD_MEMBERSHIP, &nl_group, sizeof(nl_group));
+        if (setsockopt(fd, SOL_NETLINK, NETLINK_ADD_MEMBERSHIP, &nl_group, sizeof(nl_group)) < 0) {
+                syslog(LOG_ERR, "setsockopt failed; error: %d %s", errno, strerror(errno));
+                close(fd);
+                exit(EXIT_FAILURE);
+        }
        /*
         * Register ourselves with the kernel.
         */
@@ -1472,7 +1491,7 @@ int main(void)
        len = netlink_send(fd, message);
        if (len < 0) {
-                syslog(LOG_ERR, "netlink_send failed; error:%d", len);
+                syslog(LOG_ERR, "netlink_send failed; error: %d %s", errno, strerror(errno));
                close(fd);
                exit(EXIT_FAILURE);
        }
@@ -1484,7 +1503,16 @@ int main(void)
                socklen_t addr_l = sizeof(addr);
                pfd.events = POLLIN;
                pfd.revents = 0;
-                poll(&pfd, 1, -1);
+                if (poll(&pfd, 1, -1) < 0) {
+                        syslog(LOG_ERR, "poll failed; error: %d %s", errno, strerror(errno));
+                        if (errno == EINVAL) {
+                                close(fd);
+                                exit(EXIT_FAILURE);
+                        }
+                        else
+                                continue;
+                }
                len = recvfrom(fd, kvp_recv_buffer, sizeof(kvp_recv_buffer), 0,
                                addr_p, &addr_l);
@@ -1695,7 +1723,8 @@ kvp_done:
                len = netlink_send(fd, incoming_cn_msg);
                if (len < 0) {
-                        syslog(LOG_ERR, "net_link send failed; error:%d", len);
+                        syslog(LOG_ERR, "net_link send failed; error: %d %s", errno,
+                                        strerror(errno));
                        exit(EXIT_FAILURE);
                }
        }
diff --git a/tools/include/tools/be_byteshift.h b/tools/include/tools/be_byteshift.h
index f4912e2668ba..84c17d836578 100644
--- a/tools/include/tools/be_byteshift.h
+++ b/tools/include/tools/be_byteshift.h
@@ -1,68 +1,68 @@
 #ifndef _TOOLS_BE_BYTESHIFT_H
 #define _TOOLS_BE_BYTESHIFT_H
-#include <linux/types.h>
+#include <stdint.h>
-static inline __u16 __get_unaligned_be16(const __u8 *p)
+static inline uint16_t __get_unaligned_be16(const uint8_t *p)
 {
        return p[0] << 8 | p[1];
 }
-static inline __u32 __get_unaligned_be32(const __u8 *p)
+static inline uint32_t __get_unaligned_be32(const uint8_t *p)
 {
        return p[0] << 24 | p[1] << 16 | p[2] << 8 | p[3];
 }
-static inline __u64 __get_unaligned_be64(const __u8 *p)
+static inline uint64_t __get_unaligned_be64(const uint8_t *p)
 {
-        return (__u64)__get_unaligned_be32(p) << 32 |
+        return (uint64_t)__get_unaligned_be32(p) << 32 |
               __get_unaligned_be32(p + 4);
 }
-static inline void __put_unaligned_be16(__u16 val, __u8 *p)
+static inline void __put_unaligned_be16(uint16_t val, uint8_t *p)
 {
        *p++ = val >> 8;
        *p++ = val;
 }
-static inline void __put_unaligned_be32(__u32 val, __u8 *p)
+static inline void __put_unaligned_be32(uint32_t val, uint8_t *p)
 {
        __put_unaligned_be16(val >> 16, p);
        __put_unaligned_be16(val, p + 2);
 }
-static inline void __put_unaligned_be64(__u64 val, __u8 *p)
+static inline void __put_unaligned_be64(uint64_t val, uint8_t *p)
 {
        __put_unaligned_be32(val >> 32, p);
        __put_unaligned_be32(val, p + 4);
 }
-static inline __u16 get_unaligned_be16(const void *p)
+static inline uint16_t get_unaligned_be16(const void *p)
 {
-        return __get_unaligned_be16((const __u8 *)p);
+        return __get_unaligned_be16((const uint8_t *)p);
 }
-static inline __u32 get_unaligned_be32(const void *p)
+static inline uint32_t get_unaligned_be32(const void *p)
 {
-        return __get_unaligned_be32((const __u8 *)p);
+        return __get_unaligned_be32((const uint8_t *)p);
 }
-static inline __u64 get_unaligned_be64(const void *p)
+static inline uint64_t get_unaligned_be64(const void *p)
 {
-        return __get_unaligned_be64((const __u8 *)p);
+        return __get_unaligned_be64((const uint8_t *)p);
 }
-static inline void put_unaligned_be16(__u16 val, void *p)
+static inline void put_unaligned_be16(uint16_t val, void *p)
 {
        __put_unaligned_be16(val, p);
 }
-static inline void put_unaligned_be32(__u32 val, void *p)
+static inline void put_unaligned_be32(uint32_t val, void *p)
 {
        __put_unaligned_be32(val, p);
 }
-static inline void put_unaligned_be64(__u64 val, void *p)
+static inline void put_unaligned_be64(uint64_t val, void *p)
 {
        __put_unaligned_be64(val, p);
 }
diff --git a/tools/include/tools/le_byteshift.h b/tools/include/tools/le_byteshift.h
index c99d45a68bda..8fe9f2488ec7 100644
--- a/tools/include/tools/le_byteshift.h
+++ b/tools/include/tools/le_byteshift.h
@@ -1,68 +1,68 @@
 #ifndef _TOOLS_LE_BYTESHIFT_H
 #define _TOOLS_LE_BYTESHIFT_H
-#include <linux/types.h>
+#include <stdint.h>
-static inline __u16 __get_unaligned_le16(const __u8 *p)
+static inline uint16_t __get_unaligned_le16(const uint8_t *p)
 {
        return p[0] | p[1] << 8;
 }
-static inline __u32 __get_unaligned_le32(const __u8 *p)
+static inline uint32_t __get_unaligned_le32(const uint8_t *p)
 {
        return p[0] | p[1] << 8 | p[2] << 16 | p[3] << 24;
 }
-static inline __u64 __get_unaligned_le64(const __u8 *p)
+static inline uint64_t __get_unaligned_le64(const uint8_t *p)
 {
-        return (__u64)__get_unaligned_le32(p + 4) << 32 |
+        return (uint64_t)__get_unaligned_le32(p + 4) << 32 |
               __get_unaligned_le32(p);
 }
-static inline void __put_unaligned_le16(__u16 val, __u8 *p)
+static inline void __put_unaligned_le16(uint16_t val, uint8_t *p)
 {
        *p++ = val;
        *p++ = val >> 8;
 }
-static inline void __put_unaligned_le32(__u32 val, __u8 *p)
+static inline void __put_unaligned_le32(uint32_t val, uint8_t *p)
 {
        __put_unaligned_le16(val >> 16, p + 2);
        __put_unaligned_le16(val, p);
 }
-static inline void __put_unaligned_le64(__u64 val, __u8 *p)
+static inline void __put_unaligned_le64(uint64_t val, uint8_t *p)
 {
        __put_unaligned_le32(val >> 32, p + 4);
        __put_unaligned_le32(val, p);
 }
-static inline __u16 get_unaligned_le16(const void *p)
+static inline uint16_t get_unaligned_le16(const void *p)
 {
-        return __get_unaligned_le16((const __u8 *)p);
+        return __get_unaligned_le16((const uint8_t *)p);
 }
-static inline __u32 get_unaligned_le32(const void *p)
+static inline uint32_t get_unaligned_le32(const void *p)
 {
-        return __get_unaligned_le32((const __u8 *)p);
+        return __get_unaligned_le32((const uint8_t *)p);
 }
-static inline __u64 get_unaligned_le64(const void *p)
+static inline uint64_t get_unaligned_le64(const void *p)
 {
-        return __get_unaligned_le64((const __u8 *)p);
+        return __get_unaligned_le64((const uint8_t *)p);
 }
-static inline void put_unaligned_le16(__u16 val, void *p)
+static inline void put_unaligned_le16(uint16_t val, void *p)
 {
        __put_unaligned_le16(val, p);
 }
-static inline void put_unaligned_le32(__u32 val, void *p)
+static inline void put_unaligned_le32(uint32_t val, void *p)
 {
        __put_unaligned_le32(val, p);
 }
-static inline void put_unaligned_le64(__u64 val, void *p)
+static inline void put_unaligned_le64(uint64_t val, void *p)
 {
        __put_unaligned_le64(val, p);
 }
diff --git a/tools/lguest/Makefile b/tools/lguest/Makefile
index 0ac34206f7a7..97bca4871ea3 100644
--- a/tools/lguest/Makefile
+++ b/tools/lguest/Makefile
@@ -1,5 +1,4 @@
 # This creates the demonstration utility "lguest" which runs a Linux guest.
-# Missing headers?  Add "-I../../../include -I../../../arch/x86/include"
 CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE
 all: lguest
diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c
index 07a03452c227..68f67cf3d318 100644
--- a/tools/lguest/lguest.c
+++ b/tools/lguest/lguest.c
@@ -42,14 +42,6 @@
 #include <pwd.h>
 #include <grp.h>
-#include <linux/virtio_config.h>
-#include <linux/virtio_net.h>
-#include <linux/virtio_blk.h>
-#include <linux/virtio_console.h>
-#include <linux/virtio_rng.h>
-#include <linux/virtio_ring.h>
-#include <asm/bootparam.h>
-#include "../../include/linux/lguest_launcher.h"
 /*L:110
 * We can ignore the 43 include files we need for this program, but I do want
 * to draw attention to the use of kernel-style types.
@@ -65,6 +57,15 @@ typedef uint16_t u16;
 typedef uint8_t u8;
 /*:*/
+#include <linux/virtio_config.h>
+#include <linux/virtio_net.h>
+#include <linux/virtio_blk.h>
+#include <linux/virtio_console.h>
+#include <linux/virtio_rng.h>
+#include <linux/virtio_ring.h>
+#include <asm/bootparam.h>
+#include "../../include/linux/lguest_launcher.h"
 #define BRIDGE_PFX "bridge:"
 #ifndef SIOCBRADDIF
 #define SIOCBRADDIF     0x89a2          /* add interface to bridge      */
@@ -177,7 +178,8 @@ static struct termios orig_term;
 * in precise order.
 */
 #define wmb() __asm__ __volatile__("" : : : "memory")
-#define mb() __asm__ __volatile__("" : : : "memory")
+#define rmb() __asm__ __volatile__("lock; addl $0,0(%%esp)" : : : "memory")
+#define mb() __asm__ __volatile__("lock; addl $0,0(%%esp)" : : : "memory")
 /* Wrapper for the last available index.  Makes it easier to change. */
 #define lg_last_avail(vq)       ((vq)->last_avail_idx)
@@ -676,6 +678,12 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
                errx(1, "Guest moved used index from %u to %u",
                     last_avail, vq->vring.avail->idx);
+        /* 
+         * Make sure we read the descriptor number *after* we read the ring
+         * update; don't let the cpu or compiler change the order.
+         */
+        rmb();
        /*
         * Grab the next descriptor number they're advertising, and increment
         * the index we've seen.
@@ -695,6 +703,12 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
        i = head;
        /*
+         * We have to read the descriptor after we read the descriptor number,
+         * but there's a data dependency there so the CPU shouldn't reorder
+         * that: no rmb() required.
+         */
+        /*
         * If this is an indirect entry, then this buffer contains a descriptor
         * table which we handle as if it's any normal descriptor chain.
         */
diff --git a/tools/lib/lk/Makefile b/tools/lib/lk/Makefile
index 926cbf3efc7f..280dd8205430 100644
--- a/tools/lib/lk/Makefile
+++ b/tools/lib/lk/Makefile
@@ -1,5 +1,23 @@
 include ../../scripts/Makefile.include
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
 # guard against environment variables
 LIB_H=
 LIB_OBJS=
@@ -11,7 +29,7 @@ LIB_OBJS += $(OUTPUT)debugfs.o
 LIBFILE = liblk.a
 CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -fPIC
-EXTLIBS = -lpthread -lrt -lelf -lm
+EXTLIBS = -lelf -lpthread -lrt -lm
 ALL_CFLAGS = $(CFLAGS) $(BASIC_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 ALL_LDFLAGS = $(LDFLAGS)
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index eb30044a922a..5a37a7c84e69 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -1,12 +1,6 @@
+include ../../scripts/Makefile.include
 include ../config/utilities.mak
-OUTPUT := ./
-ifeq ("$(origin O)", "command line")
-  ifneq ($(O),)
-        OUTPUT := $(O)/
-  endif
-endif
 MAN1_TXT= \
        $(filter-out $(addsuffix .txt, $(ARTICLES) $(SP_ARTICLES)), \
                $(wildcard perf-*.txt)) \
@@ -150,7 +144,7 @@ NO_SUBDIR = :
 endif
 ifneq ($(findstring $(MAKEFLAGS),s),s)
-ifndef V
+ifneq ($(V),1)
        QUIET_ASCIIDOC  = @echo '   ' ASCIIDOC $@;
        QUIET_XMLTO     = @echo '   ' XMLTO $@;
        QUIET_DB2TEXI   = @echo '   ' DB2TEXI $@;
@@ -277,7 +271,7 @@ $(MAN_HTML): $(OUTPUT)%.html : %.txt
 $(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml
        $(QUIET_XMLTO)$(RM) $@ && \
-        $(XMLTO) -o $(OUTPUT) -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
+        $(XMLTO) -o $(OUTPUT). -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
 $(OUTPUT)%.xml : %.txt
        $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
diff --git a/tools/perf/Documentation/examples.txt b/tools/perf/Documentation/examples.txt
index 77f952762426..a4e392156488 100644
--- a/tools/perf/Documentation/examples.txt
+++ b/tools/perf/Documentation/examples.txt
@@ -66,7 +66,7 @@ Furthermore, these tracepoints can be used to sample the workload as
 well. For example the page allocations done by a 'git gc' can be
 captured the following way:
- titan:~/git> perf record -f -e kmem:mm_page_alloc -c 1 ./git gc
+ titan:~/git> perf record -e kmem:mm_page_alloc -c 1 ./git gc
 Counting objects: 1148, done.
 Delta compression using up to 2 threads.
 Compressing objects: 100% (450/450), done.
@@ -120,7 +120,7 @@ Furthermore, call-graph sampling can be done too, of page
 allocations - to see precisely what kind of page allocations there
 are:
- titan:~/git> perf record -f -g -e kmem:mm_page_alloc -c 1 ./git gc
+ titan:~/git> perf record -g -e kmem:mm_page_alloc -c 1 ./git gc
 Counting objects: 1148, done.
 Delta compression using up to 2 threads.
 Compressing objects: 100% (450/450), done.
diff --git a/tools/perf/Documentation/perf-archive.txt b/tools/perf/Documentation/perf-archive.txt
index fae174dc7d01..5032a142853e 100644
--- a/tools/perf/Documentation/perf-archive.txt
+++ b/tools/perf/Documentation/perf-archive.txt
@@ -13,7 +13,7 @@ SYNOPSIS
 DESCRIPTION
 -----------
 This command runs runs perf-buildid-list --with-hits, and collects the files
-with the buildids found so that analisys of perf.data contents can be possible
+with the buildids found so that analysis of perf.data contents can be possible
 on another machine.
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index d4da111ef53d..e297b74471b8 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -65,16 +65,10 @@ OPTIONS
 -r::
 --realtime=::
        Collect data with this RT SCHED_FIFO priority.
 -D::
 --no-delay::
        Collect data without buffering.
-A::
--append::
-        Append to the output file to do incremental profiling.
-f::
--force::
-        Overwrite existing data file. (deprecated)
 -c::
 --count=::
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 7d5f4f38aa52..66dab7410c1d 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -210,6 +210,10 @@ OPTIONS
        Demangle symbol names to human readable form. It's enabled by default,
        disable with --no-demangle.
+--percent-limit::
+        Do not show entries which have an overhead under that percent.
+        (Default: 0).
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 9f1a2fe54757..7fdd1909e376 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -155,6 +155,10 @@ Default is to monitor all CPUS.
        Default: fractal,0.5,callee.
+--percent-limit::
+        Do not show entries which have an overhead under that percent.
+        (Default: 0).
 INTERACTIVE PROMPTING KEYS
 --------------------------
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index b0f164b133d9..641fccddb249 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -51,189 +51,63 @@ include config/utilities.mak
 # Define NO_BACKTRACE if you do not want stack backtrace debug feature
 #
 # Define NO_LIBNUMA if you do not want numa perf benchmark
+#
+# Define NO_LIBAUDIT if you do not want libaudit support
+#
+# Define NO_LIBBIONIC if you do not want bionic support
-$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
+ifeq ($(srctree),)
-        @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
-uname_M := $(shell uname -m 2>/dev/null || echo not)
+#$(info Determined 'srctree' to be $(srctree))
-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/ \
-                                  -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ )
-NO_PERF_REGS := 1
-CC = $(CROSS_COMPILE)gcc
-AR = $(CROSS_COMPILE)ar
-# Additional ARCH settings for x86
-ifeq ($(ARCH),i386)
-        override ARCH := x86
-        NO_PERF_REGS := 0
-        LIBUNWIND_LIBS = -lunwind -lunwind-x86
-endif
-ifeq ($(ARCH),x86_64)
-        override ARCH := x86
-        IS_X86_64 := 0
-        ifeq (, $(findstring m32,$(EXTRA_CFLAGS)))
-                IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
-        endif
-        ifeq (${IS_X86_64}, 1)
-                RAW_ARCH := x86_64
-                ARCH_CFLAGS := -DARCH_X86_64
-                ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
-        endif
-        NO_PERF_REGS := 0
-        LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
-endif
-# Treat warnings as errors unless directed not to
-ifneq ($(WERROR),0)
-        CFLAGS_WERROR := -Werror
-endif
-ifeq ("$(origin DEBUG)", "command line")
-  PERF_DEBUG = $(DEBUG)
-endif
-ifndef PERF_DEBUG
-  CFLAGS_OPTIMIZE = -O6
 endif
-ifdef PARSER_DEBUG
+ifneq ($(objtree),)
-        PARSER_DEBUG_BISON  := -t
+#$(info Determined 'objtree' to be $(objtree))
-        PARSER_DEBUG_FLEX   := -d
-        PARSER_DEBUG_CFLAGS := -DPARSER_DEBUG
 endif
-ifdef NO_NEWT
+ifneq ($(OUTPUT),)
-        NO_SLANG=1
+#$(info Determined 'OUTPUT' to be $(OUTPUT))
 endif
-CFLAGS = -fno-omit-frame-pointer -ggdb3 -funwind-tables -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) $(PARSER_DEBUG_CFLAGS)
+$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
-EXTLIBS = -lpthread -lrt -lelf -lm
+        @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
-ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
-ALL_LDFLAGS = $(LDFLAGS)
-STRIP ?= strip
-# Among the variables below, these:
-#   perfexecdir
-#   template_dir
-#   mandir
-#   infodir
-#   htmldir
-#   ETC_PERFCONFIG (but not sysconfdir)
-# can be specified as a relative path some/where/else;
-# this is interpreted as relative to $(prefix) and "perf" at
-# runtime figures out where they are based on the path to the executable.
-# This can help installing the suite in a relocatable way.
-# Make the path relative to DESTDIR, not to prefix
-ifndef DESTDIR
-prefix = $(HOME)
-endif
-bindir_relative = bin
-bindir = $(prefix)/$(bindir_relative)
-mandir = share/man
-infodir = share/info
-perfexecdir = libexec/perf-core
-sharedir = $(prefix)/share
-template_dir = share/perf-core/templates
-htmldir = share/doc/perf-doc
-ifeq ($(prefix),/usr)
-sysconfdir = /etc
-ETC_PERFCONFIG = $(sysconfdir)/perfconfig
-else
-sysconfdir = $(prefix)/etc
-ETC_PERFCONFIG = etc/perfconfig
-endif
-lib = lib
-export prefix bindir sharedir sysconfdir
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
-RM = rm -f
+RM      = rm -f
-MKDIR = mkdir
+MKDIR   = mkdir
-FIND = find
+FIND    = find
 INSTALL = install
-FLEX = flex
+FLEX    = flex
-BISON= bison
+BISON   = bison
+STRIP   = strip
-# sparse is architecture-neutral, which means that we need to tell it
-# explicitly what architecture to check for. Fix this up for yours..
-SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
-ifneq ($(MAKECMDGOALS),clean)
+LK_DIR          = $(srctree)/tools/lib/lk/
-ifneq ($(MAKECMDGOALS),tags)
+TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
-include config/feature-tests.mak
-ifeq ($(call get-executable,$(FLEX)),)
+# include config/Makefile by default and rule out
-        dummy := $(error Error: $(FLEX) is missing on this system, please install it)
+# non-config cases
-endif
+config := 1
-ifeq ($(call get-executable,$(BISON)),)
+NON_CONFIG_TARGETS := clean TAGS tags cscope help
-        dummy := $(error Error: $(BISON) is missing on this system, please install it)
-endif
-ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y)
+ifdef MAKECMDGOALS
-        CFLAGS := $(CFLAGS) -fstack-protector-all
+ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
+  config := 0
 endif
-ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wstack-protector,-Wstack-protector),y)
-       CFLAGS := $(CFLAGS) -Wstack-protector
-endif
-ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wvolatile-register-var,-Wvolatile-register-var),y)
-       CFLAGS := $(CFLAGS) -Wvolatile-register-var
 endif
-ifndef PERF_DEBUG
+ifeq ($(config),1)
-        ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -D_FORTIFY_SOURCE=2,-D_FORTIFY_SOURCE=2),y)
+include config/Makefile
-                CFLAGS := $(CFLAGS) -D_FORTIFY_SOURCE=2
-        endif
 endif
-### --- END CONFIGURATION SECTION ---
+export prefix bindir sharedir sysconfdir
-ifeq ($(srctree),)
-srctree := $(patsubst %/,%,$(dir $(shell pwd)))
-srctree := $(patsubst %/,%,$(dir $(srctree)))
-#$(info Determined 'srctree' to be $(srctree))
-endif
-ifneq ($(objtree),)
-#$(info Determined 'objtree' to be $(objtree))
-endif
-ifneq ($(OUTPUT),)
-#$(info Determined 'OUTPUT' to be $(OUTPUT))
-endif
-BASIC_CFLAGS = \
+# sparse is architecture-neutral, which means that we need to tell it
-        -Iutil/include \
+# explicitly what architecture to check for. Fix this up for yours..
-        -Iarch/$(ARCH)/include \
+SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
-        $(if $(objtree),-I$(objtree)/arch/$(ARCH)/include/generated/uapi) \
-        -I$(srctree)/arch/$(ARCH)/include/uapi \
-        -I$(srctree)/arch/$(ARCH)/include \
-        $(if $(objtree),-I$(objtree)/include/generated/uapi) \
-        -I$(srctree)/include/uapi \
-        -I$(srctree)/include \
-        -I$(OUTPUT)util \
-        -Iutil \
-        -I. \
-        -I$(TRACE_EVENT_DIR) \
-        -I../lib/ \
-        -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
-BASIC_LDFLAGS =
-ifeq ($(call try-cc,$(SOURCE_BIONIC),$(CFLAGS),bionic),y)
-        BIONIC := 1
-        EXTLIBS := $(filter-out -lrt,$(EXTLIBS))
-        EXTLIBS := $(filter-out -lpthread,$(EXTLIBS))
-        BASIC_CFLAGS += -I.
-endif
-endif # MAKECMDGOALS != tags
-endif # MAKECMDGOALS != clean
 # Guard against environment variables
 BUILTIN_OBJS =
@@ -247,20 +121,16 @@ SCRIPT_SH += perf-archive.sh
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
-LK_DIR = ../lib/lk/
-TRACE_EVENT_DIR = ../lib/traceevent/
-LK_PATH=$(LK_DIR)
 ifneq ($(OUTPUT),)
-        TE_PATH=$(OUTPUT)
+  TE_PATH=$(OUTPUT)
 ifneq ($(subdir),)
-        LK_PATH=$(OUTPUT)$(LK_DIR)
+  LK_PATH=$(objtree)/lib/lk/
 else
-        LK_PATH=$(OUTPUT)
+  LK_PATH=$(OUTPUT)
 endif
 else
-        TE_PATH=$(TRACE_EVENT_DIR)
+  TE_PATH=$(TRACE_EVENT_DIR)
+  LK_PATH=$(LK_DIR)
 endif
 LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
@@ -278,10 +148,10 @@ export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP
 python-clean := rm -rf $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so
 PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
-PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT)
+PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBLK)
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
-        $(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
+        $(QUIET_GEN)CFLAGS='$(CFLAGS)' $(PYTHON_WORD) util/setup.py \
          --quiet build_ext; \
        mkdir -p $(OUTPUT)python && \
        cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/
@@ -296,8 +166,6 @@ SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
 #
 PROGRAMS += $(OUTPUT)perf
-LANG_BINDINGS =
 # what 'all' will build and 'install' will install, in perfexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
@@ -306,10 +174,10 @@ OTHER_PROGRAMS = $(OUTPUT)perf
 # Set paths to tools early so that they can be used for version tests.
 ifndef SHELL_PATH
-        SHELL_PATH = /bin/sh
+  SHELL_PATH = /bin/sh
 endif
 ifndef PERL_PATH
-        PERL_PATH = /usr/bin/perl
+  PERL_PATH = /usr/bin/perl
 endif
 export PERL_PATH
@@ -557,79 +425,14 @@ BUILTIN_OBJS += $(OUTPUT)builtin-mem.o
 PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT)
-#
-# Platform specific tweaks
-#
-ifneq ($(MAKECMDGOALS),clean)
-ifneq ($(MAKECMDGOALS),tags)
 # We choose to avoid "if .. else if .. else .. endif endif"
 # because maintaining the nesting to match is a pain.  If
 # we had "elif" things would have been much nicer...
-ifdef NO_LIBELF
-        NO_DWARF := 1
-        NO_DEMANGLE := 1
-        NO_LIBUNWIND := 1
-else
-FLAGS_LIBELF=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS)
-ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF),libelf),y)
-        FLAGS_GLIBC=$(ALL_CFLAGS) $(ALL_LDFLAGS)
-        ifeq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC),glibc),y)
-                LIBC_SUPPORT := 1
-        endif
-        ifeq ($(BIONIC),1)
-                LIBC_SUPPORT := 1
-        endif
-        ifeq ($(LIBC_SUPPORT),1)
-                msg := $(warning No libelf found, disables 'probe' tool, please install elfutils-libelf-devel/libelf-dev);
-                NO_LIBELF := 1
-                NO_DWARF := 1
-                NO_DEMANGLE := 1
-        else
-                msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
-        endif
-else
-        # for linking with debug library, run like:
-        # make DEBUG=1 LIBDW_DIR=/opt/libdw/
-        ifdef LIBDW_DIR
-                LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
-                LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
-        endif
-        FLAGS_DWARF=$(ALL_CFLAGS) $(LIBDW_CFLAGS) -ldw -lelf $(LIBDW_LDFLAGS) $(ALL_LDFLAGS) $(EXTLIBS)
-        ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF),libdw),y)
-                msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
-                NO_DWARF := 1
-        endif # Dwarf support
-endif # SOURCE_LIBELF
-endif # NO_LIBELF
-# There's only x86 (both 32 and 64) support for CFI unwind so far
-ifneq ($(ARCH),x86)
-        NO_LIBUNWIND := 1
-endif
-ifndef NO_LIBUNWIND
-# for linking with debug library, run like:
-# make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
-ifdef LIBUNWIND_DIR
-        LIBUNWIND_CFLAGS  := -I$(LIBUNWIND_DIR)/include
-        LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib
-endif
-FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(ALL_CFLAGS) $(LIBUNWIND_LDFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS)
-ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND),libunwind),y)
-        msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 0.99);
-        NO_LIBUNWIND := 1
-endif # Libunwind support
-endif # NO_LIBUNWIND
 -include arch/$(ARCH)/Makefile
 ifneq ($(OUTPUT),)
-        BASIC_CFLAGS += -I$(OUTPUT)
+  CFLAGS += -I$(OUTPUT)
 endif
 ifdef NO_LIBELF
@@ -647,281 +450,74 @@ BUILTIN_OBJS := $(filter-out $(OUTPUT)builtin-probe.o,$(BUILTIN_OBJS))
 LIB_OBJS += $(OUTPUT)util/symbol-minimal.o
 else # NO_LIBELF
-BASIC_CFLAGS += -DLIBELF_SUPPORT
-FLAGS_LIBELF=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS)
-ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y)
-        BASIC_CFLAGS += -DLIBELF_MMAP
-endif
 ifndef NO_DWARF
-ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
+  LIB_OBJS += $(OUTPUT)util/probe-finder.o
-        msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
+  LIB_OBJS += $(OUTPUT)util/dwarf-aux.o
-else
-        BASIC_CFLAGS := -DDWARF_SUPPORT $(LIBDW_CFLAGS) $(BASIC_CFLAGS)
-        BASIC_LDFLAGS := $(LIBDW_LDFLAGS) $(BASIC_LDFLAGS)
-        EXTLIBS += -lelf -ldw
-        LIB_OBJS += $(OUTPUT)util/probe-finder.o
-        LIB_OBJS += $(OUTPUT)util/dwarf-aux.o
-endif # PERF_HAVE_DWARF_REGS
 endif # NO_DWARF
 endif # NO_LIBELF
 ifndef NO_LIBUNWIND
-        BASIC_CFLAGS += -DLIBUNWIND_SUPPORT
+  LIB_OBJS += $(OUTPUT)util/unwind.o
-        EXTLIBS += $(LIBUNWIND_LIBS)
-        BASIC_CFLAGS := $(LIBUNWIND_CFLAGS) $(BASIC_CFLAGS)
-        BASIC_LDFLAGS := $(LIBUNWIND_LDFLAGS) $(BASIC_LDFLAGS)
-        LIB_OBJS += $(OUTPUT)util/unwind.o
 endif
 ifndef NO_LIBAUDIT
-        FLAGS_LIBAUDIT = $(ALL_CFLAGS) $(ALL_LDFLAGS) -laudit
+  BUILTIN_OBJS += $(OUTPUT)builtin-trace.o
-        ifneq ($(call try-cc,$(SOURCE_LIBAUDIT),$(FLAGS_LIBAUDIT),libaudit),y)
-                msg := $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev);
-        else
-                BASIC_CFLAGS += -DLIBAUDIT_SUPPORT
-                BUILTIN_OBJS += $(OUTPUT)builtin-trace.o
-                EXTLIBS += -laudit
-        endif
 endif
 ifndef NO_SLANG
-        FLAGS_SLANG=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -I/usr/include/slang -lslang
+  LIB_OBJS += $(OUTPUT)ui/browser.o
-        ifneq ($(call try-cc,$(SOURCE_SLANG),$(FLAGS_SLANG),libslang),y)
+  LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o
-                msg := $(warning slang not found, disables TUI support. Please install slang-devel or libslang-dev);
+  LIB_OBJS += $(OUTPUT)ui/browsers/hists.o
-        else
+  LIB_OBJS += $(OUTPUT)ui/browsers/map.o
-                # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
+  LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o
-                BASIC_CFLAGS += -I/usr/include/slang
+  LIB_OBJS += $(OUTPUT)ui/tui/setup.o
-                BASIC_CFLAGS += -DSLANG_SUPPORT
+  LIB_OBJS += $(OUTPUT)ui/tui/util.o
-                EXTLIBS += -lslang
+  LIB_OBJS += $(OUTPUT)ui/tui/helpline.o
-                LIB_OBJS += $(OUTPUT)ui/browser.o
+  LIB_OBJS += $(OUTPUT)ui/tui/progress.o
-                LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o
+  LIB_H += ui/browser.h
-                LIB_OBJS += $(OUTPUT)ui/browsers/hists.o
+  LIB_H += ui/browsers/map.h
-                LIB_OBJS += $(OUTPUT)ui/browsers/map.o
+  LIB_H += ui/keysyms.h
-                LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o
+  LIB_H += ui/libslang.h
-                LIB_OBJS += $(OUTPUT)ui/tui/setup.o
-                LIB_OBJS += $(OUTPUT)ui/tui/util.o
-                LIB_OBJS += $(OUTPUT)ui/tui/helpline.o
-                LIB_OBJS += $(OUTPUT)ui/tui/progress.o
-                LIB_H += ui/browser.h
-                LIB_H += ui/browsers/map.h
-                LIB_H += ui/keysyms.h
-                LIB_H += ui/libslang.h
-        endif
 endif
 ifndef NO_GTK2
-        FLAGS_GTK2=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
+  LIB_OBJS += $(OUTPUT)ui/gtk/browser.o
-        ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2),gtk2),y)
+  LIB_OBJS += $(OUTPUT)ui/gtk/hists.o
-                msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev);
+  LIB_OBJS += $(OUTPUT)ui/gtk/setup.o
-        else
+  LIB_OBJS += $(OUTPUT)ui/gtk/util.o
-                ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2),-DHAVE_GTK_INFO_BAR),y)
+  LIB_OBJS += $(OUTPUT)ui/gtk/helpline.o
-                        BASIC_CFLAGS += -DHAVE_GTK_INFO_BAR
+  LIB_OBJS += $(OUTPUT)ui/gtk/progress.o
-                endif
+  LIB_OBJS += $(OUTPUT)ui/gtk/annotate.o
-                BASIC_CFLAGS += -DGTK2_SUPPORT
-                BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null)
-                EXTLIBS += $(shell pkg-config --libs gtk+-2.0 2>/dev/null)
-                LIB_OBJS += $(OUTPUT)ui/gtk/browser.o
-                LIB_OBJS += $(OUTPUT)ui/gtk/hists.o
-                LIB_OBJS += $(OUTPUT)ui/gtk/setup.o
-                LIB_OBJS += $(OUTPUT)ui/gtk/util.o
-                LIB_OBJS += $(OUTPUT)ui/gtk/helpline.o
-                LIB_OBJS += $(OUTPUT)ui/gtk/progress.o
-                LIB_OBJS += $(OUTPUT)ui/gtk/annotate.o
-        endif
 endif
-ifdef NO_LIBPERL
+ifndef NO_LIBPERL
-        BASIC_CFLAGS += -DNO_LIBPERL
+  LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o
-else
+  LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o
-       PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null)
-       PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
-       PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
-        PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
-        FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
-        ifneq ($(call try-cc,$(SOURCE_PERL_EMBED),$(FLAGS_PERL_EMBED),perl),y)
-                BASIC_CFLAGS += -DNO_LIBPERL
-        else
-               ALL_LDFLAGS += $(PERL_EMBED_LDFLAGS)
-               EXTLIBS += $(PERL_EMBED_LIBADD)
-                LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o
-                LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o
-        endif
 endif
-disable-python = $(eval $(disable-python_code))
+ifndef NO_LIBPYTHON
-define disable-python_code
+  LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
-  BASIC_CFLAGS += -DNO_LIBPYTHON
+  LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
-  $(if $(1),$(warning No $(1) was found))
-  $(warning Python support will not be built)
-endef
-override PYTHON := \
-  $(call get-executable-or-default,PYTHON,python)
-ifndef PYTHON
-  $(call disable-python,python interpreter)
-else
-  PYTHON_WORD := $(call shell-wordify,$(PYTHON))
-  ifdef NO_LIBPYTHON
-    $(call disable-python)
-  else
-    override PYTHON_CONFIG := \
-      $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON)-config)
-    ifndef PYTHON_CONFIG
-      $(call disable-python,python-config tool)
-    else
-      PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
-      PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
-      PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
-      PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
-      PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-      FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
-      ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED),python),y)
-        $(call disable-python,Python.h (for Python 2.x))
-      else
-        ifneq ($(call try-cc,$(SOURCE_PYTHON_VERSION),$(FLAGS_PYTHON_EMBED),python version),y)
-          $(warning Python 3 is not yet supported; please set)
-          $(warning PYTHON and/or PYTHON_CONFIG appropriately.)
-          $(warning If you also have Python 2 installed, then)
-          $(warning try something like:)
-          $(warning $(and ,))
-          $(warning $(and ,)  make PYTHON=python2)
-          $(warning $(and ,))
-          $(warning Otherwise, disable Python support entirely:)
-          $(warning $(and ,))
-          $(warning $(and ,)  make NO_LIBPYTHON=1)
-          $(warning $(and ,))
-          $(error   $(and ,))
-        else
-          ALL_LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
-          EXTLIBS += $(PYTHON_EMBED_LIBADD)
-          LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
-          LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
-          LANG_BINDINGS += $(OUTPUT)python/perf.so
-        endif
-      endif
-    endif
-  endif
-endif
-ifdef NO_DEMANGLE
-        BASIC_CFLAGS += -DNO_DEMANGLE
-else
-        ifdef HAVE_CPLUS_DEMANGLE
-                EXTLIBS += -liberty
-                BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
-        else
-                FLAGS_BFD=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -DPACKAGE='perf' -lbfd
-                has_bfd := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD),libbfd)
-                ifeq ($(has_bfd),y)
-                        EXTLIBS += -lbfd
-                else
-                        FLAGS_BFD_IBERTY=$(FLAGS_BFD) -liberty
-                        has_bfd_iberty := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY),liberty)
-                        ifeq ($(has_bfd_iberty),y)
-                                EXTLIBS += -lbfd -liberty
-                        else
-                                FLAGS_BFD_IBERTY_Z=$(FLAGS_BFD_IBERTY) -lz
-                                has_bfd_iberty_z := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY_Z),libz)
-                                ifeq ($(has_bfd_iberty_z),y)
-                                        EXTLIBS += -lbfd -liberty -lz
-                                else
-                                        FLAGS_CPLUS_DEMANGLE=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -liberty
-                                        has_cplus_demangle := $(call try-cc,$(SOURCE_CPLUS_DEMANGLE),$(FLAGS_CPLUS_DEMANGLE),demangle)
-                                        ifeq ($(has_cplus_demangle),y)
-                                                EXTLIBS += -liberty
-                                                BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
-                                        else
-                                                msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling)
-                                                BASIC_CFLAGS += -DNO_DEMANGLE
-                                        endif
-                                endif
-                        endif
-                endif
-        endif
 endif
 ifeq ($(NO_PERF_REGS),0)
-        ifeq ($(ARCH),x86)
+  ifeq ($(ARCH),x86)
-                LIB_H += arch/x86/include/perf_regs.h
+    LIB_H += arch/x86/include/perf_regs.h
-        endif
+  endif
-        BASIC_CFLAGS += -DHAVE_PERF_REGS
-endif
-ifndef NO_STRLCPY
-        ifeq ($(call try-cc,$(SOURCE_STRLCPY),,-DHAVE_STRLCPY),y)
-                BASIC_CFLAGS += -DHAVE_STRLCPY
-        endif
-endif
-ifndef NO_ON_EXIT
-        ifeq ($(call try-cc,$(SOURCE_ON_EXIT),,-DHAVE_ON_EXIT),y)
-                BASIC_CFLAGS += -DHAVE_ON_EXIT
-        endif
-endif
-ifndef NO_BACKTRACE
-       ifeq ($(call try-cc,$(SOURCE_BACKTRACE),,-DBACKTRACE_SUPPORT),y)
-               BASIC_CFLAGS += -DBACKTRACE_SUPPORT
-       endif
 endif
 ifndef NO_LIBNUMA
-        FLAGS_LIBNUMA = $(ALL_CFLAGS) $(ALL_LDFLAGS) -lnuma
+  BUILTIN_OBJS += $(OUTPUT)bench/numa.o
-        ifneq ($(call try-cc,$(SOURCE_LIBNUMA),$(FLAGS_LIBNUMA),libnuma),y)
-                msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numa-libs-devel or libnuma-dev);
-        else
-                BASIC_CFLAGS += -DLIBNUMA_SUPPORT
-                BUILTIN_OBJS += $(OUTPUT)bench/numa.o
-                EXTLIBS += -lnuma
-        endif
 endif
 ifdef ASCIIDOC8
-        export ASCIIDOC8
+  export ASCIIDOC8
 endif
-endif # MAKECMDGOALS != tags
-endif # MAKECMDGOALS != clean
-# Shell quote (do not use $(call) to accommodate ancient setups);
-ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG))
-DESTDIR_SQ = $(subst ','\'',$(DESTDIR))
-bindir_SQ = $(subst ','\'',$(bindir))
-bindir_relative_SQ = $(subst ','\'',$(bindir_relative))
-mandir_SQ = $(subst ','\'',$(mandir))
-infodir_SQ = $(subst ','\'',$(infodir))
-perfexecdir_SQ = $(subst ','\'',$(perfexecdir))
-template_dir_SQ = $(subst ','\'',$(template_dir))
-htmldir_SQ = $(subst ','\'',$(htmldir))
-prefix_SQ = $(subst ','\'',$(prefix))
-sysconfdir_SQ = $(subst ','\'',$(sysconfdir))
-SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
 LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
-ALL_CFLAGS += $(BASIC_CFLAGS)
-ALL_CFLAGS += $(ARCH_CFLAGS)
-ALL_LDFLAGS += $(BASIC_LDFLAGS)
 export INSTALL SHELL_PATH
 ### Build rules
 SHELL = $(SHELL_PATH)
@@ -939,20 +535,20 @@ strip: $(PROGRAMS) $(OUTPUT)perf
 $(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
        $(QUIET_CC)$(CC) -include $(OUTPUT)PERF-VERSION-FILE \
                '-DPERF_HTML_PATH="$(htmldir_SQ)"' \
-                $(ALL_CFLAGS) -c $(filter %.c,$^) -o $@
+                $(CFLAGS) -c $(filter %.c,$^) -o $@
 $(OUTPUT)perf: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
-        $(QUIET_LINK)$(CC) $(ALL_CFLAGS) $(ALL_LDFLAGS) $(OUTPUT)perf.o \
+        $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OUTPUT)perf.o \
               $(BUILTIN_OBJS) $(LIBS) -o $@
 $(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
                '-DPERF_HTML_PATH="$(htmldir_SQ)"' \
                '-DPERF_MAN_PATH="$(mandir_SQ)"' \
                '-DPERF_INFO_PATH="$(infodir_SQ)"' $<
 $(OUTPUT)builtin-timechart.o: builtin-timechart.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
                '-DPERF_HTML_PATH="$(htmldir_SQ)"' \
                '-DPERF_MAN_PATH="$(mandir_SQ)"' \
                '-DPERF_INFO_PATH="$(infodir_SQ)"' $<
@@ -977,77 +573,77 @@ $(OUTPUT)perf.o perf.spec \
 # over the general rule for .o
 $(OUTPUT)util/%-flex.o: $(OUTPUT)util/%-flex.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(ALL_CFLAGS) -w $<
+        $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -w $<
 $(OUTPUT)util/%-bison.o: $(OUTPUT)util/%-bison.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(ALL_CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $<
+        $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $<
 $(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $<
 $(OUTPUT)%.i: %.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -E $(ALL_CFLAGS) $<
+        $(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $<
 $(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -S $(ALL_CFLAGS) $<
+        $(QUIET_CC)$(CC) -o $@ -S $(CFLAGS) $<
 $(OUTPUT)%.o: %.S
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $<
 $(OUTPUT)%.s: %.S
-        $(QUIET_CC)$(CC) -o $@ -E $(ALL_CFLAGS) $<
+        $(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $<
 $(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
                '-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \
                '-DPREFIX="$(prefix_SQ)"' \
                $<
 $(OUTPUT)tests/attr.o: tests/attr.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
                '-DBINDIR="$(bindir_SQ)"' -DPYTHON='"$(PYTHON_WORD)"' \
                $<
 $(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
                -DPYTHONPATH='"$(OUTPUT)python"' \
                -DPYTHON='"$(PYTHON_WORD)"' \
                $<
 $(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 $(OUTPUT)ui/browser.o: ui/browser.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
 $(OUTPUT)ui/browsers/annotate.o: ui/browsers/annotate.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
 $(OUTPUT)ui/browsers/hists.o: ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
 $(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
 $(OUTPUT)ui/browsers/scripts.o: ui/browsers/scripts.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
 $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+        $(QUIET_CC)$(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 $(ALL_CFLAGS) -Wno-redundant-decls $<
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $<
 $(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
 $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
 $(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
 $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
 $(OUTPUT)perf-%: %.o $(PERFLIBS)
-        $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
+        $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS)
 $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
 $(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
@@ -1134,7 +730,7 @@ cscope:
        $(FIND) . -name '*.[hcS]' -print | xargs cscope -b
 ### Detect prefix changes
-TRACK_CFLAGS = $(subst ','\'',$(ALL_CFLAGS)):\
+TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\
             $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ)
 $(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS
@@ -1155,7 +751,7 @@ check: $(OUTPUT)common-cmds.h
        then \
                for i in *.c */*.c; \
                do \
-                        sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; \
+                        sparse $(CFLAGS) $(SPARSE_FLAGS) $$i || exit; \
                done; \
        else \
                exit 1; \
@@ -1163,13 +759,6 @@ check: $(OUTPUT)common-cmds.h
 ### Installation rules
-ifneq ($(filter /%,$(firstword $(perfexecdir))),)
-perfexec_instdir = $(perfexecdir)
-else
-perfexec_instdir = $(prefix)/$(perfexecdir)
-endif
-perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
 install-bin: all
        $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
        $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 93c83e3cb4a7..25fd3f1966f1 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -111,11 +111,11 @@ static double timeval2double(struct timeval *ts)
 static void alloc_mem(void **dst, void **src, size_t length)
 {
        *dst = zalloc(length);
-        if (!dst)
+        if (!*dst)
                die("memory allocation failed - maybe length is too large?\n");
        *src = zalloc(length);
-        if (!src)
+        if (!*src)
                die("memory allocation failed - maybe length is too large?\n");
 }
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
index c6e4bc523492..4a2f12081964 100644
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -111,7 +111,7 @@ static double timeval2double(struct timeval *ts)
 static void alloc_mem(void **dst, size_t length)
 {
        *dst = zalloc(length);
-        if (!dst)
+        if (!*dst)
                die("memory allocation failed - maybe length is too large?\n");
 }
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 2d0462d89a97..0aac5f3e594d 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -323,13 +323,20 @@ static void hists__baseline_only(struct hists *hists)
 static void hists__precompute(struct hists *hists)
 {
-        struct rb_node *next = rb_first(&hists->entries);
+        struct rb_root *root;
+        struct rb_node *next;
+        if (sort__need_collapse)
+                root = &hists->entries_collapsed;
+        else
+                root = hists->entries_in;
+        next = rb_first(root);
        while (next != NULL) {
-                struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node);
+                struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node_in);
                struct hist_entry *pair = hist_entry__next_pair(he);
-                next = rb_next(&he->rb_node);
+                next = rb_next(&he->rb_node_in);
                if (!pair)
                        continue;
@@ -457,7 +464,7 @@ static void hists__process(struct hists *old, struct hists *new)
                hists__output_resort(new);
        }
-        hists__fprintf(new, true, 0, 0, stdout);
+        hists__fprintf(new, true, 0, 0, 0, stdout);
 }
 static int __cmd_diff(void)
@@ -600,7 +607,6 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
                input_new = "perf.data.guest";
        }
-        symbol_conf.exclude_other = false;
        if (symbol__init() < 0)
                return -1;
@@ -611,9 +617,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
        setup_pager();
-        sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", NULL);
+        sort__setup_elide(NULL);
-        sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", NULL);
-        sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", NULL);
        return __cmd_diff();
 }
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 46878daca5cc..0259502638b4 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -708,7 +708,7 @@ static int parse_line_opt(const struct option *opt __maybe_unused,
 static int __cmd_record(int argc, const char **argv)
 {
        const char * const record_args[] = {
-        "record", "-a", "-R", "-f", "-c", "1",
+        "record", "-a", "-R", "-c", "1",
        "-e", "kmem:kmalloc",
        "-e", "kmem:kmalloc_node",
        "-e", "kmem:kfree",
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 533501e2b07c..24b78aecc928 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -328,6 +328,7 @@ static int kvm_events_hash_fn(u64 key)
 static bool kvm_event_expand(struct kvm_event *event, int vcpu_id)
 {
        int old_max_vcpu = event->max_vcpu;
+        void *prev;
        if (vcpu_id < event->max_vcpu)
                return true;
@@ -335,9 +336,11 @@ static bool kvm_event_expand(struct kvm_event *event, int vcpu_id)
        while (event->max_vcpu <= vcpu_id)
                event->max_vcpu += DEFAULT_VCPU_NUM;
+        prev = event->vcpu;
        event->vcpu = realloc(event->vcpu,
                              event->max_vcpu * sizeof(*event->vcpu));
        if (!event->vcpu) {
+                free(prev);
                pr_err("Not enough memory\n");
                return false;
        }
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 425830069749..76543a4a7a30 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -878,7 +878,7 @@ static int __cmd_report(void)
 static int __cmd_record(int argc, const char **argv)
 {
        const char *record_args[] = {
-                "record", "-R", "-f", "-m", "1024", "-c", "1",
+                "record", "-R", "-m", "1024", "-c", "1",
        };
        unsigned int rec_argc, i, j;
        const char **rec_argv;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index cdf58ecc04b1..ecca62e27b28 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -61,11 +61,6 @@ static void __handle_on_exit_funcs(void)
 }
 #endif
-enum write_mode_t {
-        WRITE_FORCE,
-        WRITE_APPEND
-};
 struct perf_record {
        struct perf_tool        tool;
        struct perf_record_opts opts;
@@ -77,12 +72,8 @@ struct perf_record {
        int                     output;
        unsigned int            page_size;
        int                     realtime_prio;
-        enum write_mode_t       write_mode;
        bool                    no_buildid;
        bool                    no_buildid_cache;
-        bool                    force;
-        bool                    file_new;
-        bool                    append_file;
        long                    samples;
        off_t                   post_processing_offset;
 };
@@ -198,26 +189,6 @@ static void perf_record__sig_exit(int exit_status __maybe_unused, void *arg)
                return;
        signal(signr, SIG_DFL);
-        kill(getpid(), signr);
-}
-static bool perf_evlist__equal(struct perf_evlist *evlist,
-                               struct perf_evlist *other)
-{
-        struct perf_evsel *pos, *pair;
-        if (evlist->nr_entries != other->nr_entries)
-                return false;
-        pair = perf_evlist__first(other);
-        list_for_each_entry(pos, &evlist->entries, node) {
-                if (memcmp(&pos->attr, &pair->attr, sizeof(pos->attr) != 0))
-                        return false;
-                pair = perf_evsel__next(pair);
-        }
-        return true;
 }
 static int perf_record__open(struct perf_record *rec)
@@ -274,16 +245,7 @@ try_again:
                goto out;
        }
-        if (rec->file_new)
+        session->evlist = evlist;
-                session->evlist = evlist;
-        else {
-                if (!perf_evlist__equal(session->evlist, evlist)) {
-                        fprintf(stderr, "incompatible append\n");
-                        rc = -1;
-                        goto out;
-                }
-        }
        perf_session__set_id_hdr_size(session);
 out:
        return rc;
@@ -404,6 +366,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
        signal(SIGCHLD, sig_handler);
        signal(SIGINT, sig_handler);
        signal(SIGUSR1, sig_handler);
+        signal(SIGTERM, sig_handler);
        if (!output_name) {
                if (!fstat(STDOUT_FILENO, &st) && S_ISFIFO(st.st_mode))
@@ -415,23 +378,15 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
                if (!strcmp(output_name, "-"))
                        opts->pipe_output = true;
                else if (!stat(output_name, &st) && st.st_size) {
-                        if (rec->write_mode == WRITE_FORCE) {
+                        char oldname[PATH_MAX];
-                                char oldname[PATH_MAX];
+                        snprintf(oldname, sizeof(oldname), "%s.old",
-                                snprintf(oldname, sizeof(oldname), "%s.old",
+                                 output_name);
-                                         output_name);
+                        unlink(oldname);
-                                unlink(oldname);
+                        rename(output_name, oldname);
-                                rename(output_name, oldname);
-                        }
-                } else if (rec->write_mode == WRITE_APPEND) {
-                        rec->write_mode = WRITE_FORCE;
                }
        }
-        flags = O_CREAT|O_RDWR;
+        flags = O_CREAT|O_RDWR|O_TRUNC;
-        if (rec->write_mode == WRITE_APPEND)
-                rec->file_new = 0;
-        else
-                flags |= O_TRUNC;
        if (opts->pipe_output)
                output = STDOUT_FILENO;
@@ -445,7 +400,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
        rec->output = output;
        session = perf_session__new(output_name, O_WRONLY,
-                                    rec->write_mode == WRITE_FORCE, false, NULL);
+                                    true, false, NULL);
        if (session == NULL) {
                pr_err("Not enough memory for reading perf file header\n");
                return -1;
@@ -465,12 +420,6 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
        if (!rec->opts.branch_stack)
                perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
-        if (!rec->file_new) {
-                err = perf_session__read_header(session, output);
-                if (err < 0)
-                        goto out_delete_session;
-        }
        if (forks) {
                err = perf_evlist__prepare_workload(evsel_list, &opts->target,
                                                    argv, opts->pipe_output,
@@ -498,7 +447,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
                err = perf_header__write_pipe(output);
                if (err < 0)
                        goto out_delete_session;
-        } else if (rec->file_new) {
+        } else {
                err = perf_session__write_header(session, evsel_list,
                                                 output, false);
                if (err < 0)
@@ -869,8 +818,6 @@ static struct perf_record record = {
                        .uses_mmap   = true,
                },
        },
-        .write_mode = WRITE_FORCE,
-        .file_new   = true,
 };
 #define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: "
@@ -906,12 +853,8 @@ const struct option record_options[] = {
                    "collect raw sample records from all opened counters"),
        OPT_BOOLEAN('a', "all-cpus", &record.opts.target.system_wide,
                            "system-wide collection from all CPUs"),
-        OPT_BOOLEAN('A', "append", &record.append_file,
-                            "append to the output file to do incremental profiling"),
        OPT_STRING('C', "cpu", &record.opts.target.cpu_list, "cpu",
                    "list of cpus to monitor"),
-        OPT_BOOLEAN('f', "force", &record.force,
-                        "overwrite existing data file (deprecated)"),
        OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
        OPT_STRING('o', "output", &record.output_name, "file",
                    "output file name"),
@@ -977,16 +920,6 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
        if (!argc && perf_target__none(&rec->opts.target))
                usage_with_options(record_usage, record_options);
-        if (rec->force && rec->append_file) {
-                ui__error("Can't overwrite and append at the same time."
-                          " You need to choose between -f and -A");
-                usage_with_options(record_usage, record_options);
-        } else if (rec->append_file) {
-                rec->write_mode = WRITE_APPEND;
-        } else {
-                rec->write_mode = WRITE_FORCE;
-        }
        if (nr_cgroups && !rec->opts.target.system_wide) {
                ui__error("cgroup monitoring only available in"
                          " system-wide mode\n");
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index bd0ca81eeaca..3662047cc6b1 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -52,6 +52,7 @@ struct perf_report {
        symbol_filter_t         annotate_init;
        const char              *cpu_list;
        const char              *symbol_filter_str;
+        float                   min_percent;
        DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
@@ -61,6 +62,11 @@ static int perf_report_config(const char *var, const char *value, void *cb)
                symbol_conf.event_group = perf_config_bool(var, value);
                return 0;
        }
+        if (!strcmp(var, "report.percent-limit")) {
+                struct perf_report *rep = cb;
+                rep->min_percent = strtof(value, NULL);
+                return 0;
+        }
        return perf_default_config(var, value, cb);
 }
@@ -187,6 +193,9 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
        for (i = 0; i < sample->branch_stack->nr; i++) {
                if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
                        continue;
+                err = -ENOMEM;
                /*
                 * The report shows the percentage of total branches captured
                 * and not events sampled. Thus we use a pseudo period of 1.
@@ -195,7 +204,6 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
                                &bi[i], 1, 1);
                if (he) {
                        struct annotation *notes;
-                        err = -ENOMEM;
                        bx = he->branch_info;
                        if (bx->from.sym && use_browser == 1 && sort__has_sym) {
                                notes = symbol__annotation(bx->from.sym);
@@ -226,11 +234,12 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
                        }
                        evsel->hists.stats.total_period += 1;
                        hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
-                        err = 0;
                } else
-                        return -ENOMEM;
+                        goto out;
        }
+        err = 0;
 out:
+        free(bi);
        return err;
 }
@@ -294,6 +303,7 @@ static int process_sample_event(struct perf_tool *tool,
 {
        struct perf_report *rep = container_of(tool, struct perf_report, tool);
        struct addr_location al;
+        int ret;
        if (perf_event__preprocess_sample(event, machine, &al, sample,
                                          rep->annotate_init) < 0) {
@@ -308,28 +318,25 @@ static int process_sample_event(struct perf_tool *tool,
        if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
                return 0;
-        if (sort__branch_mode == 1) {
+        if (sort__mode == SORT_MODE__BRANCH) {
-                if (perf_report__add_branch_hist_entry(tool, &al, sample,
+                ret = perf_report__add_branch_hist_entry(tool, &al, sample,
-                                                       evsel, machine)) {
+                                                         evsel, machine);
+                if (ret < 0)
                        pr_debug("problem adding lbr entry, skipping event\n");
-                        return -1;
-                }
        } else if (rep->mem_mode == 1) {
-                if (perf_report__add_mem_hist_entry(tool, &al, sample,
+                ret = perf_report__add_mem_hist_entry(tool, &al, sample,
-                                                    evsel, machine, event)) {
+                                                      evsel, machine, event);
+                if (ret < 0)
                        pr_debug("problem adding mem entry, skipping event\n");
-                        return -1;
-                }
        } else {
                if (al.map != NULL)
                        al.map->dso->hit = 1;
-                if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) {
+                ret = perf_evsel__add_hist_entry(evsel, &al, sample, machine);
+                if (ret < 0)
                        pr_debug("problem incrementing symbol period, skipping event\n");
-                        return -1;
-                }
        }
-        return 0;
+        return ret;
 }
 static int process_read_event(struct perf_tool *tool,
@@ -384,7 +391,7 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
                        }
        }
-        if (sort__branch_mode == 1) {
+        if (sort__mode == SORT_MODE__BRANCH) {
                if (!self->fd_pipe &&
                    !(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
                        ui__error("Selected -b but no branch data. "
@@ -455,7 +462,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
                        continue;
                hists__fprintf_nr_sample_events(rep, hists, evname, stdout);
-                hists__fprintf(hists, true, 0, 0, stdout);
+                hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout);
                fprintf(stdout, "\n\n");
        }
@@ -574,8 +581,8 @@ static int __cmd_report(struct perf_report *rep)
        if (use_browser > 0) {
                if (use_browser == 1) {
                        ret = perf_evlist__tui_browse_hists(session->evlist,
-                                                        help,
+                                                        help, NULL,
-                                                        NULL,
+                                                        rep->min_percent,
                                                        &session->header.env);
                        /*
                         * Usually "ret" is the last pressed key, and we only
@@ -586,7 +593,7 @@ static int __cmd_report(struct perf_report *rep)
                } else if (use_browser == 2) {
                        perf_evlist__gtk_browse_hists(session->evlist, help,
-                                                      NULL);
+                                                      NULL, rep->min_percent);
                }
        } else
                perf_evlist__tty_browse_hists(session->evlist, rep, help);
@@ -691,7 +698,19 @@ static int
 parse_branch_mode(const struct option *opt __maybe_unused,
                  const char *str __maybe_unused, int unset)
 {
-        sort__branch_mode = !unset;
+        int *branch_mode = opt->value;
+        *branch_mode = !unset;
+        return 0;
+}
+static int
+parse_percent_limit(const struct option *opt, const char *str,
+                    int unset __maybe_unused)
+{
+        struct perf_report *rep = opt->value;
+        rep->min_percent = strtof(str, NULL);
        return 0;
 }
@@ -700,6 +719,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
        struct perf_session *session;
        struct stat st;
        bool has_br_stack = false;
+        int branch_mode = -1;
        int ret = -1;
        char callchain_default_opt[] = "fractal,0.5,callee";
        const char * const report_usage[] = {
@@ -796,17 +816,19 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                    "Show a column with the sum of periods"),
        OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
                    "Show event group information together"),
-        OPT_CALLBACK_NOOPT('b', "branch-stack", &sort__branch_mode, "",
+        OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "",
                    "use branch records for histogram filling", parse_branch_mode),
        OPT_STRING(0, "objdump", &objdump_path, "path",
                   "objdump binary to use for disassembly and annotations"),
        OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
                    "Disable symbol demangling"),
        OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
+        OPT_CALLBACK(0, "percent-limit", &report, "percent",
+                     "Don't show entries under that percent", parse_percent_limit),
        OPT_END()
        };
-        perf_config(perf_report_config, NULL);
+        perf_config(perf_report_config, &report);
        argc = parse_options(argc, argv, options, report_usage, 0);
@@ -846,11 +868,11 @@ repeat:
        has_br_stack = perf_header__has_feat(&session->header,
                                             HEADER_BRANCH_STACK);
-        if (sort__branch_mode == -1 && has_br_stack)
+        if (branch_mode == -1 && has_br_stack)
-                sort__branch_mode = 1;
+                sort__mode = SORT_MODE__BRANCH;
-        /* sort__branch_mode could be 0 if --no-branch-stack */
+        /* sort__mode could be NORMAL if --no-branch-stack */
-        if (sort__branch_mode == 1) {
+        if (sort__mode == SORT_MODE__BRANCH) {
                /*
                 * if no sort_order is provided, then specify
                 * branch-mode specific order
@@ -861,10 +883,12 @@ repeat:
        }
        if (report.mem_mode) {
-                if (sort__branch_mode == 1) {
+                if (sort__mode == SORT_MODE__BRANCH) {
                        fprintf(stderr, "branch and mem mode incompatible\n");
                        goto error;
                }
+                sort__mode = SORT_MODE__MEMORY;
                /*
                 * if no sort_order is provided, then specify
                 * branch-mode specific order
@@ -915,8 +939,7 @@ repeat:
                 */
                if (!strstr(sort_order, "parent"))
                        sort_parent.elide = 1;
-        } else
+        }
-                symbol_conf.exclude_other = false;
        if (argc) {
                /*
@@ -929,25 +952,7 @@ repeat:
                report.symbol_filter_str = argv[0];
        }
-        sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout);
+        sort__setup_elide(stdout);
-        if (sort__branch_mode == 1) {
-                sort_entry__setup_elide(&sort_dso_from, symbol_conf.dso_from_list, "dso_from", stdout);
-                sort_entry__setup_elide(&sort_dso_to, symbol_conf.dso_to_list, "dso_to", stdout);
-                sort_entry__setup_elide(&sort_sym_from, symbol_conf.sym_from_list, "sym_from", stdout);
-                sort_entry__setup_elide(&sort_sym_to, symbol_conf.sym_to_list, "sym_to", stdout);
-        } else {
-                if (report.mem_mode) {
-                        sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "symbol_daddr", stdout);
-                        sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso_daddr", stdout);
-                        sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "mem", stdout);
-                        sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "local_weight", stdout);
-                        sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "tlb", stdout);
-                        sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "snoop", stdout);
-                }
-                sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
-                sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
-        }
        ret = __cmd_report(&report);
        if (ret == K_SWITCH_INPUT_DATA) {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 2da2a6ca22bf..fed9ae432c16 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1632,7 +1632,6 @@ static int __cmd_record(int argc, const char **argv)
                "record",
                "-a",
                "-R",
-                "-f",
                "-m", "1024",
                "-c", "1",
                "-e", "sched:sched_switch",
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7e910bab1097..352fbd7ff4a1 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -87,7 +87,7 @@ static int			run_count			=  1;
 static bool                     no_inherit                      = false;
 static bool                     scale                           =  true;
 static enum aggr_mode           aggr_mode                       = AGGR_GLOBAL;
-static pid_t                    child_pid                       = -1;
+static volatile pid_t           child_pid                       = -1;
 static bool                     null_run                        =  false;
 static int                      detailed_run                    =  0;
 static bool                     big_num                         =  true;
@@ -924,7 +924,7 @@ static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 static void print_aggr(char *prefix)
 {
        struct perf_evsel *counter;
-        int cpu, s, s2, id, nr;
+        int cpu, cpu2, s, s2, id, nr;
        u64 ena, run, val;
        if (!(aggr_map || aggr_get_id))
@@ -936,7 +936,8 @@ static void print_aggr(char *prefix)
                        val = ena = run = 0;
                        nr = 0;
                        for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-                                s2 = aggr_get_id(evsel_list->cpus, cpu);
+                                cpu2 = perf_evsel__cpus(counter)->map[cpu];
+                                s2 = aggr_get_id(evsel_list->cpus, cpu2);
                                if (s2 != id)
                                        continue;
                                val += counter->counts->cpu[cpu].val;
@@ -948,7 +949,7 @@ static void print_aggr(char *prefix)
                                fprintf(output, "%s", prefix);
                        if (run == 0 || ena == 0) {
-                                aggr_printout(counter, cpu, nr);
+                                aggr_printout(counter, id, nr);
                                fprintf(output, "%*s%s%*s",
                                        csv_output ? 0 : 18,
@@ -1148,13 +1149,34 @@ static void skip_signal(int signo)
                done = 1;
        signr = signo;
+        /*
+         * render child_pid harmless
+         * won't send SIGTERM to a random
+         * process in case of race condition
+         * and fast PID recycling
+         */
+        child_pid = -1;
 }
 static void sig_atexit(void)
 {
+        sigset_t set, oset;
+        /*
+         * avoid race condition with SIGCHLD handler
+         * in skip_signal() which is modifying child_pid
+         * goal is to avoid send SIGTERM to a random
+         * process
+         */
+        sigemptyset(&set);
+        sigaddset(&set, SIGCHLD);
+        sigprocmask(SIG_BLOCK, &set, &oset);
        if (child_pid != -1)
                kill(child_pid, SIGTERM);
+        sigprocmask(SIG_SETMASK, &oset, NULL);
        if (signr == -1)
                return;
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index ab4cf232b852..4536a92b18f3 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1005,7 +1005,7 @@ static int __cmd_record(int argc, const char **argv)
 {
 #ifdef SUPPORT_OLD_POWER_EVENTS
        const char * const record_old_args[] = {
-                "record", "-a", "-R", "-f", "-c", "1",
+                "record", "-a", "-R", "-c", "1",
                "-e", "power:power_start",
                "-e", "power:power_end",
                "-e", "power:power_frequency",
@@ -1014,7 +1014,7 @@ static int __cmd_record(int argc, const char **argv)
        };
 #endif
        const char * const record_new_args[] = {
-                "record", "-a", "-R", "-f", "-c", "1",
+                "record", "-a", "-R", "-c", "1",
                "-e", "power:cpu_frequency",
                "-e", "power:cpu_idle",
                "-e", "sched:sched_wakeup",
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 67bdb9f14ad6..e06c4f869330 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -70,10 +70,11 @@
 static volatile int done;
+#define HEADER_LINE_NR  5
 static void perf_top__update_print_entries(struct perf_top *top)
 {
-        if (top->print_entries > 9)
+        top->print_entries = top->winsize.ws_row - HEADER_LINE_NR;
-                top->print_entries -= 9;
 }
 static void perf_top__sig_winch(int sig __maybe_unused,
@@ -82,13 +83,6 @@ static void perf_top__sig_winch(int sig __maybe_unused,
        struct perf_top *top = arg;
        get_term_dimensions(&top->winsize);
-        if (!top->print_entries
-            || (top->print_entries+4) > top->winsize.ws_row) {
-                top->print_entries = top->winsize.ws_row;
-        } else {
-                top->print_entries += 4;
-                top->winsize.ws_row = top->print_entries;
-        }
        perf_top__update_print_entries(top);
 }
@@ -251,8 +245,11 @@ static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 {
        struct hist_entry *he;
+        pthread_mutex_lock(&evsel->hists.lock);
        he = __hists__add_entry(&evsel->hists, al, NULL, sample->period,
                                sample->weight);
+        pthread_mutex_unlock(&evsel->hists.lock);
        if (he == NULL)
                return NULL;
@@ -290,16 +287,17 @@ static void perf_top__print_sym_table(struct perf_top *top)
                return;
        }
-        hists__collapse_resort_threaded(&top->sym_evsel->hists);
+        hists__collapse_resort(&top->sym_evsel->hists);
-        hists__output_resort_threaded(&top->sym_evsel->hists);
+        hists__output_resort(&top->sym_evsel->hists);
-        hists__decay_entries_threaded(&top->sym_evsel->hists,
+        hists__decay_entries(&top->sym_evsel->hists,
-                                      top->hide_user_symbols,
+                             top->hide_user_symbols,
-                                      top->hide_kernel_symbols);
+                             top->hide_kernel_symbols);
        hists__output_recalc_col_len(&top->sym_evsel->hists,
-                                     top->winsize.ws_row - 3);
+                                     top->print_entries - printed);
        putchar('\n');
        hists__fprintf(&top->sym_evsel->hists, false,
-                       top->winsize.ws_row - 4 - printed, win_width, stdout);
+                       top->print_entries - printed, win_width,
+                       top->min_percent, stdout);
 }
 static void prompt_integer(int *target, const char *msg)
@@ -477,7 +475,6 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
                                perf_top__sig_winch(SIGWINCH, NULL, top);
                                sigaction(SIGWINCH, &act, NULL);
                        } else {
-                                perf_top__sig_winch(SIGWINCH, NULL, top);
                                signal(SIGWINCH, SIG_DFL);
                        }
                        break;
@@ -556,11 +553,11 @@ static void perf_top__sort_new_samples(void *arg)
        if (t->evlist->selected != NULL)
                t->sym_evsel = t->evlist->selected;
-        hists__collapse_resort_threaded(&t->sym_evsel->hists);
+        hists__collapse_resort(&t->sym_evsel->hists);
-        hists__output_resort_threaded(&t->sym_evsel->hists);
+        hists__output_resort(&t->sym_evsel->hists);
-        hists__decay_entries_threaded(&t->sym_evsel->hists,
+        hists__decay_entries(&t->sym_evsel->hists,
-                                      t->hide_user_symbols,
+                             t->hide_user_symbols,
-                                      t->hide_kernel_symbols);
+                             t->hide_kernel_symbols);
 }
 static void *display_thread_tui(void *arg)
@@ -584,7 +581,7 @@ static void *display_thread_tui(void *arg)
        list_for_each_entry(pos, &top->evlist->entries, node)
                pos->hists.uid_filter_str = top->record_opts.target.uid_str;
-        perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+        perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent,
                                      &top->session->header.env);
        done = 1;
@@ -794,7 +791,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
                                return;
                }
-                if (top->sort_has_symbols)
+                if (sort__has_sym)
                        perf_top__record_precise_ip(top, he, evsel->idx, ip);
        }
@@ -912,9 +909,9 @@ out_err:
        return -1;
 }
-static int perf_top__setup_sample_type(struct perf_top *top)
+static int perf_top__setup_sample_type(struct perf_top *top __maybe_unused)
 {
-        if (!top->sort_has_symbols) {
+        if (!sort__has_sym) {
                if (symbol_conf.use_callchain) {
                        ui__error("Selected -g but \"sym\" not present in --sort/-s.");
                        return -EINVAL;
@@ -1025,6 +1022,16 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
        return record_parse_callchain_opt(opt, arg, unset);
 }
+static int
+parse_percent_limit(const struct option *opt, const char *arg,
+                    int unset __maybe_unused)
+{
+        struct perf_top *top = opt->value;
+        top->min_percent = strtof(arg, NULL);
+        return 0;
+}
 int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 {
        int status;
@@ -1110,6 +1117,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
        OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
                   "Specify disassembler style (e.g. -M intel for intel syntax)"),
        OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"),
+        OPT_CALLBACK(0, "percent-limit", &top, "percent",
+                     "Don't show entries under that percent", parse_percent_limit),
        OPT_END()
        };
        const char * const top_usage[] = {
@@ -1121,8 +1130,6 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
        if (top.evlist == NULL)
                return -ENOMEM;
-        symbol_conf.exclude_other = false;
        argc = parse_options(argc, argv, options, top_usage, 0);
        if (argc)
                usage_with_options(top_usage, options);
@@ -1133,6 +1140,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
        if (setup_sorting() < 0)
                usage_with_options(top_usage, options);
+        /* display thread wants entries to be collapsed in a different tree */
+        sort__need_collapse = 1;
        if (top.use_stdio)
                use_browser = 0;
        else if (top.use_tui)
@@ -1200,15 +1210,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
        if (symbol__init() < 0)
                return -1;
-        sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
+        sort__setup_elide(stdout);
-        sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout);
-        sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
-        /*
-         * Avoid annotation data structures overhead when symbols aren't on the
-         * sort list.
-         */
-        top.sort_has_symbols = sort_sym.list.next != NULL;
        get_term_dimensions(&top.winsize);
        if (top.print_entries == 0) {
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
new file mode 100644
index 000000000000..b5d9238cb181
--- /dev/null
+++ b/tools/perf/config/Makefile
@@ -0,0 +1,477 @@
+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/ \
+                                  -e s/arm.*/arm/ -e s/sa110/arm/ \
+                                  -e s/s390x/s390/ -e s/parisc64/parisc/ \
+                                  -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
+                                  -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ )
+NO_PERF_REGS := 1
+CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
+# Additional ARCH settings for x86
+ifeq ($(ARCH),i386)
+  override ARCH := x86
+  NO_PERF_REGS := 0
+  LIBUNWIND_LIBS = -lunwind -lunwind-x86
+endif
+ifeq ($(ARCH),x86_64)
+  override ARCH := x86
+  IS_X86_64 := 0
+  ifeq (, $(findstring m32,$(CFLAGS)))
+    IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
+  endif
+  ifeq (${IS_X86_64}, 1)
+    RAW_ARCH := x86_64
+    CFLAGS += -DARCH_X86_64
+    ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
+  endif
+  NO_PERF_REGS := 0
+  LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
+endif
+ifeq ($(NO_PERF_REGS),0)
+  CFLAGS += -DHAVE_PERF_REGS
+endif
+ifeq ($(src-perf),)
+src-perf := $(srctree)/tools/perf
+endif
+ifeq ($(obj-perf),)
+obj-perf := $(OUTPUT)
+endif
+ifneq ($(obj-perf),)
+obj-perf := $(abspath $(obj-perf))/
+endif
+# include ARCH specific config
+-include $(src-perf)/arch/$(ARCH)/Makefile
+include $(src-perf)/config/feature-tests.mak
+include $(src-perf)/config/utilities.mak
+ifeq ($(call get-executable,$(FLEX)),)
+  dummy := $(error Error: $(FLEX) is missing on this system, please install it)
+endif
+ifeq ($(call get-executable,$(BISON)),)
+  dummy := $(error Error: $(BISON) is missing on this system, please install it)
+endif
+# Treat warnings as errors unless directed not to
+ifneq ($(WERROR),0)
+  CFLAGS += -Werror
+endif
+ifeq ("$(origin DEBUG)", "command line")
+  PERF_DEBUG = $(DEBUG)
+endif
+ifndef PERF_DEBUG
+  CFLAGS += -O6
+endif
+ifdef PARSER_DEBUG
+  PARSER_DEBUG_BISON := -t
+  PARSER_DEBUG_FLEX  := -d
+  CFLAGS             += -DPARSER_DEBUG
+endif
+CFLAGS += -fno-omit-frame-pointer
+CFLAGS += -ggdb3
+CFLAGS += -funwind-tables
+CFLAGS += -Wall
+CFLAGS += -Wextra
+CFLAGS += -std=gnu99
+EXTLIBS = -lelf -lpthread -lrt -lm
+ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y)
+  CFLAGS += -fstack-protector-all
+endif
+ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wstack-protector,-Wstack-protector),y)
+  CFLAGS += -Wstack-protector
+endif
+ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wvolatile-register-var,-Wvolatile-register-var),y)
+  CFLAGS += -Wvolatile-register-var
+endif
+ifndef PERF_DEBUG
+  ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -D_FORTIFY_SOURCE=2,-D_FORTIFY_SOURCE=2),y)
+    CFLAGS += -D_FORTIFY_SOURCE=2
+  endif
+endif
+CFLAGS += -I$(src-perf)/util/include
+CFLAGS += -I$(src-perf)/arch/$(ARCH)/include
+CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi
+CFLAGS += -I$(srctree)/arch/$(ARCH)/include
+CFLAGS += -I$(srctree)/include/uapi
+CFLAGS += -I$(srctree)/include
+# $(obj-perf)      for generated common-cmds.h
+# $(obj-perf)/util for generated bison/flex headers
+ifneq ($(OUTPUT),)
+CFLAGS += -I$(obj-perf)/util
+CFLAGS += -I$(obj-perf)
+endif
+CFLAGS += -I$(src-perf)/util
+CFLAGS += -I$(src-perf)
+CFLAGS += -I$(TRACE_EVENT_DIR)
+CFLAGS += -I$(srctree)/tools/lib/
+CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+ifndef NO_BIONIC
+ifeq ($(call try-cc,$(SOURCE_BIONIC),$(CFLAGS),bionic),y)
+  BIONIC := 1
+  EXTLIBS := $(filter-out -lrt,$(EXTLIBS))
+  EXTLIBS := $(filter-out -lpthread,$(EXTLIBS))
+endif
+endif # NO_BIONIC
+ifdef NO_LIBELF
+  NO_DWARF := 1
+  NO_DEMANGLE := 1
+  NO_LIBUNWIND := 1
+else
+FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS)
+ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF),libelf),y)
+  FLAGS_GLIBC=$(CFLAGS) $(LDFLAGS)
+  ifeq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC),glibc),y)
+    LIBC_SUPPORT := 1
+  endif
+  ifeq ($(BIONIC),1)
+    LIBC_SUPPORT := 1
+  endif
+  ifeq ($(LIBC_SUPPORT),1)
+    msg := $(warning No libelf found, disables 'probe' tool, please install elfutils-libelf-devel/libelf-dev);
+    NO_LIBELF := 1
+    NO_DWARF := 1
+    NO_DEMANGLE := 1
+  else
+    msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
+  endif
+else
+  # for linking with debug library, run like:
+  # make DEBUG=1 LIBDW_DIR=/opt/libdw/
+  ifdef LIBDW_DIR
+    LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
+    LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
+  endif
+  FLAGS_DWARF=$(CFLAGS) $(LIBDW_CFLAGS) -ldw -lz -lelf $(LIBDW_LDFLAGS) $(LDFLAGS) $(EXTLIBS)
+  ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF),libdw),y)
+    msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
+    NO_DWARF := 1
+  endif # Dwarf support
+endif # SOURCE_LIBELF
+endif # NO_LIBELF
+ifndef NO_LIBELF
+CFLAGS += -DLIBELF_SUPPORT
+FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS)
+ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y)
+  CFLAGS += -DLIBELF_MMAP
+endif
+# include ARCH specific config
+-include $(src-perf)/arch/$(ARCH)/Makefile
+ifndef NO_DWARF
+ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
+  msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
+  NO_DWARF := 1
+else
+  CFLAGS += -DDWARF_SUPPORT $(LIBDW_CFLAGS)
+  LDFLAGS += $(LIBDW_LDFLAGS)
+  EXTLIBS += -lelf -ldw
+endif # PERF_HAVE_DWARF_REGS
+endif # NO_DWARF
+endif # NO_LIBELF
+ifndef NO_LIBELF
+CFLAGS += -DLIBELF_SUPPORT
+FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS)
+ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y)
+  CFLAGS += -DLIBELF_MMAP
+endif # try-cc
+endif # NO_LIBELF
+# There's only x86 (both 32 and 64) support for CFI unwind so far
+ifneq ($(ARCH),x86)
+  NO_LIBUNWIND := 1
+endif
+ifndef NO_LIBUNWIND
+# for linking with debug library, run like:
+# make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
+ifdef LIBUNWIND_DIR
+  LIBUNWIND_CFLAGS  := -I$(LIBUNWIND_DIR)/include
+  LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib
+endif
+FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(CFLAGS) $(LIBUNWIND_LDFLAGS) $(LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS)
+ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND),libunwind),y)
+  msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 0.99);
+  NO_LIBUNWIND := 1
+endif # Libunwind support
+endif # NO_LIBUNWIND
+ifndef NO_LIBUNWIND
+  CFLAGS += -DLIBUNWIND_SUPPORT
+  EXTLIBS += $(LIBUNWIND_LIBS)
+  CFLAGS += $(LIBUNWIND_CFLAGS)
+  LDFLAGS += $(LIBUNWIND_LDFLAGS)
+endif # NO_LIBUNWIND
+ifndef NO_LIBAUDIT
+  FLAGS_LIBAUDIT = $(CFLAGS) $(LDFLAGS) -laudit
+  ifneq ($(call try-cc,$(SOURCE_LIBAUDIT),$(FLAGS_LIBAUDIT),libaudit),y)
+    msg := $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev);
+    NO_LIBAUDIT := 1
+  else
+    CFLAGS += -DLIBAUDIT_SUPPORT
+    EXTLIBS += -laudit
+  endif
+endif
+ifdef NO_NEWT
+  NO_SLANG=1
+endif
+ifndef NO_SLANG
+  FLAGS_SLANG=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -I/usr/include/slang -lslang
+  ifneq ($(call try-cc,$(SOURCE_SLANG),$(FLAGS_SLANG),libslang),y)
+    msg := $(warning slang not found, disables TUI support. Please install slang-devel or libslang-dev);
+    NO_SLANG := 1
+  else
+    # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
+    CFLAGS += -I/usr/include/slang
+    CFLAGS += -DSLANG_SUPPORT
+    EXTLIBS += -lslang
+  endif
+endif
+ifndef NO_GTK2
+  FLAGS_GTK2=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
+  ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2),gtk2),y)
+    msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev);
+    NO_GTK2 := 1
+  else
+    ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2),-DHAVE_GTK_INFO_BAR),y)
+      CFLAGS += -DHAVE_GTK_INFO_BAR
+    endif
+    CFLAGS += -DGTK2_SUPPORT
+    CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null)
+    EXTLIBS += $(shell pkg-config --libs gtk+-2.0 2>/dev/null)
+  endif
+endif
+grep-libs  = $(filter -l%,$(1))
+strip-libs = $(filter-out -l%,$(1))
+ifdef NO_LIBPERL
+  CFLAGS += -DNO_LIBPERL
+else
+  PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null)
+  PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
+  PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
+  PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
+  FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
+  ifneq ($(call try-cc,$(SOURCE_PERL_EMBED),$(FLAGS_PERL_EMBED),perl),y)
+    CFLAGS += -DNO_LIBPERL
+    NO_LIBPERL := 1
+  else
+    LDFLAGS += $(PERL_EMBED_LDFLAGS)
+    EXTLIBS += $(PERL_EMBED_LIBADD)
+  endif
+endif
+disable-python = $(eval $(disable-python_code))
+define disable-python_code
+  CFLAGS += -DNO_LIBPYTHON
+  $(if $(1),$(warning No $(1) was found))
+  $(warning Python support will not be built)
+  NO_LIBPYTHON := 1
+endef
+override PYTHON := \
+  $(call get-executable-or-default,PYTHON,python)
+ifndef PYTHON
+  $(call disable-python,python interpreter)
+else
+  PYTHON_WORD := $(call shell-wordify,$(PYTHON))
+  ifdef NO_LIBPYTHON
+    $(call disable-python)
+  else
+    override PYTHON_CONFIG := \
+      $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON)-config)
+    ifndef PYTHON_CONFIG
+      $(call disable-python,python-config tool)
+    else
+      PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+      PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+      PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
+      PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
+      PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+      FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
+      ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED),python),y)
+        $(call disable-python,Python.h (for Python 2.x))
+      else
+        ifneq ($(call try-cc,$(SOURCE_PYTHON_VERSION),$(FLAGS_PYTHON_EMBED),python version),y)
+          $(warning Python 3 is not yet supported; please set)
+          $(warning PYTHON and/or PYTHON_CONFIG appropriately.)
+          $(warning If you also have Python 2 installed, then)
+          $(warning try something like:)
+          $(warning $(and ,))
+          $(warning $(and ,)  make PYTHON=python2)
+          $(warning $(and ,))
+          $(warning Otherwise, disable Python support entirely:)
+          $(warning $(and ,))
+          $(warning $(and ,)  make NO_LIBPYTHON=1)
+          $(warning $(and ,))
+          $(error   $(and ,))
+        else
+          LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
+          EXTLIBS += $(PYTHON_EMBED_LIBADD)
+          LANG_BINDINGS += $(obj-perf)python/perf.so
+        endif
+      endif
+    endif
+  endif
+endif
+ifdef NO_DEMANGLE
+  CFLAGS += -DNO_DEMANGLE
+else
+  ifdef HAVE_CPLUS_DEMANGLE
+    EXTLIBS += -liberty
+    CFLAGS += -DHAVE_CPLUS_DEMANGLE
+  else
+    FLAGS_BFD=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -DPACKAGE='perf' -lbfd
+    has_bfd := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD),libbfd)
+    ifeq ($(has_bfd),y)
+      EXTLIBS += -lbfd
+    else
+      FLAGS_BFD_IBERTY=$(FLAGS_BFD) -liberty
+      has_bfd_iberty := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY),liberty)
+      ifeq ($(has_bfd_iberty),y)
+        EXTLIBS += -lbfd -liberty
+      else
+        FLAGS_BFD_IBERTY_Z=$(FLAGS_BFD_IBERTY) -lz
+        has_bfd_iberty_z := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY_Z),libz)
+        ifeq ($(has_bfd_iberty_z),y)
+          EXTLIBS += -lbfd -liberty -lz
+        else
+          FLAGS_CPLUS_DEMANGLE=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -liberty
+          has_cplus_demangle := $(call try-cc,$(SOURCE_CPLUS_DEMANGLE),$(FLAGS_CPLUS_DEMANGLE),demangle)
+          ifeq ($(has_cplus_demangle),y)
+            EXTLIBS += -liberty
+            CFLAGS += -DHAVE_CPLUS_DEMANGLE
+          else
+            msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling)
+            CFLAGS += -DNO_DEMANGLE
+          endif
+        endif
+      endif
+    endif
+  endif
+endif
+ifndef NO_STRLCPY
+  ifeq ($(call try-cc,$(SOURCE_STRLCPY),,-DHAVE_STRLCPY),y)
+    CFLAGS += -DHAVE_STRLCPY
+  endif
+endif
+ifndef NO_ON_EXIT
+  ifeq ($(call try-cc,$(SOURCE_ON_EXIT),,-DHAVE_ON_EXIT),y)
+    CFLAGS += -DHAVE_ON_EXIT
+  endif
+endif
+ifndef NO_BACKTRACE
+  ifeq ($(call try-cc,$(SOURCE_BACKTRACE),,-DBACKTRACE_SUPPORT),y)
+    CFLAGS += -DBACKTRACE_SUPPORT
+  endif
+endif
+ifndef NO_LIBNUMA
+  FLAGS_LIBNUMA = $(CFLAGS) $(LDFLAGS) -lnuma
+  ifneq ($(call try-cc,$(SOURCE_LIBNUMA),$(FLAGS_LIBNUMA),libnuma),y)
+    msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numa-libs-devel or libnuma-dev);
+    NO_LIBNUMA := 1
+  else
+    CFLAGS += -DLIBNUMA_SUPPORT
+    EXTLIBS += -lnuma
+  endif
+endif
+# Among the variables below, these:
+#   perfexecdir
+#   template_dir
+#   mandir
+#   infodir
+#   htmldir
+#   ETC_PERFCONFIG (but not sysconfdir)
+# can be specified as a relative path some/where/else;
+# this is interpreted as relative to $(prefix) and "perf" at
+# runtime figures out where they are based on the path to the executable.
+# This can help installing the suite in a relocatable way.
+# Make the path relative to DESTDIR, not to prefix
+ifndef DESTDIR
+prefix = $(HOME)
+endif
+bindir_relative = bin
+bindir = $(prefix)/$(bindir_relative)
+mandir = share/man
+infodir = share/info
+perfexecdir = libexec/perf-core
+sharedir = $(prefix)/share
+template_dir = share/perf-core/templates
+htmldir = share/doc/perf-doc
+ifeq ($(prefix),/usr)
+sysconfdir = /etc
+ETC_PERFCONFIG = $(sysconfdir)/perfconfig
+else
+sysconfdir = $(prefix)/etc
+ETC_PERFCONFIG = etc/perfconfig
+endif
+lib = lib
+# Shell quote (do not use $(call) to accommodate ancient setups);
+ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG))
+DESTDIR_SQ = $(subst ','\'',$(DESTDIR))
+bindir_SQ = $(subst ','\'',$(bindir))
+mandir_SQ = $(subst ','\'',$(mandir))
+infodir_SQ = $(subst ','\'',$(infodir))
+perfexecdir_SQ = $(subst ','\'',$(perfexecdir))
+template_dir_SQ = $(subst ','\'',$(template_dir))
+htmldir_SQ = $(subst ','\'',$(htmldir))
+prefix_SQ = $(subst ','\'',$(prefix))
+sysconfdir_SQ = $(subst ','\'',$(sysconfdir))
+ifneq ($(filter /%,$(firstword $(perfexecdir))),)
+perfexec_instdir = $(perfexecdir)
+else
+perfexec_instdir = $(prefix)/$(perfexecdir)
+endif
+perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
index 8ef3bd30a549..94d2d4f9c35d 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/perf/config/utilities.mak
@@ -173,7 +173,7 @@ _ge-abspath = $(if $(is-executable),$(1))
 # Usage: absolute-executable-path-or-empty = $(call get-executable-or-default,variable,default)
 #
 define get-executable-or-default
-$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2),$(1)))
+$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2)))
 endef
 _ge_attempt = $(if $(get-executable),$(get-executable),$(_gea_warn)$(call _gea_err,$(2)))
 _gea_warn = $(warning The path '$(1)' is not executable.)
@@ -181,7 +181,7 @@ _gea_err  = $(if $(1),$(error Please set '$(1)' appropriately))
 # try-cc
 # Usage: option = $(call try-cc, source-to-build, cc-options, msg)
-ifndef V
+ifneq ($(V),1)
 TRY_CC_OUTPUT= > /dev/null 2>&1
 endif
 TRY_CC_MSG=echo "    CHK $(3)" 1>&2;
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs b/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs
index c1e2ed1ed34e..8c7ea42444d1 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs
@@ -23,7 +23,7 @@
 #include "perl.h"
 #include "XSUB.h"
 #include "../../../perf.h"
-#include "../../../util/script-event.h"
+#include "../../../util/trace-event.h"
 MODULE = Perf::Trace::Context           PACKAGE = Perf::Trace::Context
 PROTOTYPES: ENABLE
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index b4fc835de607..e9bd6391f2ae 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -27,8 +27,8 @@ watermark=0
 precise_ip=0
 mmap_data=0
 sample_id_all=1
-exclude_host=0
+exclude_host=0|1
-exclude_guest=1
+exclude_guest=0|1
 exclude_callchain_kernel=0
 exclude_callchain_user=0
 wakeup_events=0
diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat
index 748ee949a204..91cd48b399f3 100644
--- a/tools/perf/tests/attr/base-stat
+++ b/tools/perf/tests/attr/base-stat
@@ -27,8 +27,8 @@ watermark=0
 precise_ip=0
 mmap_data=0
 sample_id_all=0
-exclude_host=0
+exclude_host=0|1
-exclude_guest=1
+exclude_guest=0|1
 exclude_callchain_kernel=0
 exclude_callchain_user=0
 wakeup_events=0
diff --git a/tools/perf/tests/attr/test-record-data b/tools/perf/tests/attr/test-record-data
index 6627c3e7534a..716e143b5291 100644
--- a/tools/perf/tests/attr/test-record-data
+++ b/tools/perf/tests/attr/test-record-data
@@ -4,5 +4,8 @@ args    = -d kill >/dev/null 2>&1
 [event:base-record]
 sample_period=4000
-sample_type=271
+# sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_TIME |
+# PERF_SAMPLE_ADDR | PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC
+sample_type=33039
 mmap_data=1
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index 68daa289e94c..aba095489193 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -4,6 +4,12 @@
 * (git://github.com/deater/perf_event_tests)
 */
+/*
+ * Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select
+ * 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu.
+ */
+#define __SANE_USERSPACE_TYPES__
 #include <stdlib.h>
 #include <stdio.h>
 #include <unistd.h>
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
index fe7ed28815f8..44ac82179708 100644
--- a/tools/perf/tests/bp_signal_overflow.c
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -3,6 +3,12 @@
 * perf_event_tests (git://github.com/deater/perf_event_tests)
 */
+/*
+ * Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select
+ * 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu.
+ */
+#define __SANE_USERSPACE_TYPES__
 #include <stdlib.h>
 #include <stdio.h>
 #include <unistd.h>
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 0918ada4cc41..35b45f1466b5 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -70,7 +70,7 @@ static struct test {
                .func = test__attr,
        },
        {
-                .desc = "Test matching and linking mutliple hists",
+                .desc = "Test matching and linking multiple hists",
                .func = test__hists_link,
        },
        {
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
new file mode 100644
index 000000000000..c441a2875128
--- /dev/null
+++ b/tools/perf/tests/make
@@ -0,0 +1,138 @@
+PERF := .
+MK   := Makefile
+# standard single make variable specified
+make_clean_all      := clean all
+make_python_perf_so := python/perf.so
+make_debug          := DEBUG=1
+make_no_libperl     := NO_LIBPERL=1
+make_no_libpython   := NO_LIBPYTHON=1
+make_no_scripts     := NO_LIBPYTHON=1 NO_LIBPERL=1
+make_no_newt        := NO_NEWT=1
+make_no_slang       := NO_SLANG=1
+make_no_gtk2        := NO_GTK2=1
+make_no_ui          := NO_NEWT=1 NO_SLANG=1 NO_GTK2=1
+make_no_demangle    := NO_DEMANGLE=1
+make_no_libelf      := NO_LIBELF=1
+make_no_libunwind   := NO_LIBUNWIND=1
+make_no_backtrace   := NO_BACKTRACE=1
+make_no_libnuma     := NO_LIBNUMA=1
+make_no_libaudit    := NO_LIBAUDIT=1
+make_no_libbionic   := NO_LIBBIONIC=1
+make_tags           := tags
+make_cscope         := cscope
+make_help           := help
+make_doc            := doc
+make_perf_o         := perf.o
+make_util_map_o     := util/map.o
+# all the NO_* variable combined
+make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
+make_minimal        += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1
+make_minimal        += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1
+# $(run) contains all available tests
+run := make_pure
+run += make_clean_all
+run += make_python_perf_so
+run += make_debug
+run += make_no_libperl
+run += make_no_libpython
+run += make_no_scripts
+run += make_no_newt
+run += make_no_slang
+run += make_no_gtk2
+run += make_no_ui
+run += make_no_demangle
+run += make_no_libelf
+run += make_no_libunwind
+run += make_no_backtrace
+run += make_no_libnuma
+run += make_no_libaudit
+run += make_no_libbionic
+run += make_tags
+run += make_cscope
+run += make_help
+run += make_doc
+run += make_perf_o
+run += make_util_map_o
+run += make_minimal
+# $(run_O) contains same portion of $(run) tests with '_O' attached
+# to distinguish O=... tests
+run_O := $(addsuffix _O,$(run))
+# disable some tests for O=...
+run_O := $(filter-out make_python_perf_so_O,$(run_O))
+# define test for each compile as 'test_NAME' variable
+# with the test itself as a value
+test_make_tags   = test -f tags
+test_make_cscope = test -f cscope.out
+test_make_tags_O   := $(test_make_tags)
+test_make_cscope_O := $(test_make_cscope)
+test_ok          := true
+test_make_help   := $(test_ok)
+test_make_doc    := $(test_ok)
+test_make_help_O := $(test_ok)
+test_make_doc_O  := $(test_ok)
+test_make_python_perf_so := test -f $(PERF)/python/perf.so
+test_make_perf_o     := test -f $(PERF)/perf.o
+test_make_util_map_o := test -f $(PERF)/util/map.o
+# Kbuild tests only
+#test_make_python_perf_so_O := test -f $$TMP/tools/perf/python/perf.so
+#test_make_perf_o_O         := test -f $$TMP/tools/perf/perf.o
+#test_make_util_map_o_O     := test -f $$TMP/tools/perf/util/map.o
+test_make_perf_o_O     := true
+test_make_util_map_o_O := true
+test_default = test -x $(PERF)/perf
+test = $(if $(test_$1),$(test_$1),$(test_default))
+test_default_O = test -x $$TMP/perf
+test_O = $(if $(test_$1),$(test_$1),$(test_default_O))
+all:
+ifdef DEBUG
+d := $(info run   $(run))
+d := $(info run_O $(run_O))
+endif
+MAKEFLAGS := --no-print-directory
+clean := @(cd $(PERF); make -s -f $(MK) clean >/dev/null)
+$(run):
+        $(call clean)
+        @cmd="cd $(PERF) && make -f $(MK) $($@)"; \
+        echo "- $@: $$cmd" && echo $$cmd > $@ && \
+        ( eval $$cmd ) >> $@ 2>&1; \
+        echo "  test: $(call test,$@)"; \
+        $(call test,$@) && \
+        rm -f $@
+$(run_O):
+        $(call clean)
+        @TMP=$$(mktemp -d); \
+        cmd="cd $(PERF) && make -f $(MK) $($(patsubst %_O,%,$@)) O=$$TMP"; \
+        echo "- $@: $$cmd" && echo $$cmd > $@ && \
+        ( eval $$cmd ) >> $@ 2>&1 && \
+        echo "  test: $(call test_O,$@)"; \
+        $(call test_O,$@) && \
+        rm -f $@ && \
+        rm -rf $$TMP
+all: $(run) $(run_O)
+        @echo OK
+out: $(run_O)
+        @echo OK
+.PHONY: all $(run) $(run_O) clean
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index d88a2d0acb6d..fc0bd3843d34 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -25,7 +25,8 @@ struct hist_browser {
        struct map_symbol   *selection;
        int                  print_seq;
        bool                 show_dso;
-        bool                 has_symbols;
+        float                min_pcnt;
+        u64                  nr_pcnt_entries;
 };
 extern void hist_browser__init_hpp(void);
@@ -309,6 +310,8 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser)
                "Or reduce the sampling frequency.");
 }
+static void hist_browser__update_pcnt_entries(struct hist_browser *hb);
 static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
                             struct hist_browser_timer *hbt)
 {
@@ -318,6 +321,8 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
        browser->b.entries = &browser->hists->entries;
        browser->b.nr_entries = browser->hists->nr_entries;
+        if (browser->min_pcnt)
+                browser->b.nr_entries = browser->nr_pcnt_entries;
        hist_browser__refresh_dimensions(browser);
        hists__browser_title(browser->hists, title, sizeof(title), ev_name);
@@ -330,9 +335,18 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
                key = ui_browser__run(&browser->b, delay_secs);
                switch (key) {
-                case K_TIMER:
+                case K_TIMER: {
+                        u64 nr_entries;
                        hbt->timer(hbt->arg);
-                        ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
+                        if (browser->min_pcnt) {
+                                hist_browser__update_pcnt_entries(browser);
+                                nr_entries = browser->nr_pcnt_entries;
+                        } else {
+                                nr_entries = browser->hists->nr_entries;
+                        }
+                        ui_browser__update_nr_entries(&browser->b, nr_entries);
                        if (browser->hists->stats.nr_lost_warned !=
                            browser->hists->stats.nr_events[PERF_RECORD_LOST]) {
@@ -344,6 +358,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
                        hists__browser_title(browser->hists, title, sizeof(title), ev_name);
                        ui_browser__show_title(&browser->b, title);
                        continue;
+                }
                case 'D': { /* Debug */
                        static int seq;
                        struct hist_entry *h = rb_entry(browser->b.top,
@@ -796,10 +811,15 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
        for (nd = browser->top; nd; nd = rb_next(nd)) {
                struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+                float percent = h->stat.period * 100.0 /
+                                        hb->hists->stats.total_period;
                if (h->filtered)
                        continue;
+                if (percent < hb->min_pcnt)
+                        continue;
                row += hist_browser__show_entry(hb, h, row);
                if (row == browser->height)
                        break;
@@ -808,10 +828,18 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
        return row;
 }
-static struct rb_node *hists__filter_entries(struct rb_node *nd)
+static struct rb_node *hists__filter_entries(struct rb_node *nd,
+                                             struct hists *hists,
+                                             float min_pcnt)
 {
        while (nd != NULL) {
                struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+                float percent = h->stat.period * 100.0 /
+                                        hists->stats.total_period;
+                if (percent < min_pcnt)
+                        return NULL;
                if (!h->filtered)
                        return nd;
@@ -821,11 +849,16 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd)
        return NULL;
 }
-static struct rb_node *hists__filter_prev_entries(struct rb_node *nd)
+static struct rb_node *hists__filter_prev_entries(struct rb_node *nd,
+                                                  struct hists *hists,
+                                                  float min_pcnt)
 {
        while (nd != NULL) {
                struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-                if (!h->filtered)
+                float percent = h->stat.period * 100.0 /
+                                        hists->stats.total_period;
+                if (!h->filtered && percent >= min_pcnt)
                        return nd;
                nd = rb_prev(nd);
@@ -840,6 +873,9 @@ static void ui_browser__hists_seek(struct ui_browser *browser,
        struct hist_entry *h;
        struct rb_node *nd;
        bool first = true;
+        struct hist_browser *hb;
+        hb = container_of(browser, struct hist_browser, b);
        if (browser->nr_entries == 0)
                return;
@@ -848,13 +884,15 @@ static void ui_browser__hists_seek(struct ui_browser *browser,
        switch (whence) {
        case SEEK_SET:
-                nd = hists__filter_entries(rb_first(browser->entries));
+                nd = hists__filter_entries(rb_first(browser->entries),
+                                           hb->hists, hb->min_pcnt);
                break;
        case SEEK_CUR:
                nd = browser->top;
                goto do_offset;
        case SEEK_END:
-                nd = hists__filter_prev_entries(rb_last(browser->entries));
+                nd = hists__filter_prev_entries(rb_last(browser->entries),
+                                                hb->hists, hb->min_pcnt);
                first = false;
                break;
        default:
@@ -897,7 +935,8 @@ do_offset:
                                        break;
                                }
                        }
-                        nd = hists__filter_entries(rb_next(nd));
+                        nd = hists__filter_entries(rb_next(nd), hb->hists,
+                                                   hb->min_pcnt);
                        if (nd == NULL)
                                break;
                        --offset;
@@ -930,7 +969,8 @@ do_offset:
                                }
                        }
-                        nd = hists__filter_prev_entries(rb_prev(nd));
+                        nd = hists__filter_prev_entries(rb_prev(nd), hb->hists,
+                                                        hb->min_pcnt);
                        if (nd == NULL)
                                break;
                        ++offset;
@@ -1099,14 +1139,17 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
 static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp)
 {
-        struct rb_node *nd = hists__filter_entries(rb_first(browser->b.entries));
+        struct rb_node *nd = hists__filter_entries(rb_first(browser->b.entries),
+                                                   browser->hists,
+                                                   browser->min_pcnt);
        int printed = 0;
        while (nd) {
                struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
                printed += hist_browser__fprintf_entry(browser, h, fp);
-                nd = hists__filter_entries(rb_next(nd));
+                nd = hists__filter_entries(rb_next(nd), browser->hists,
+                                           browser->min_pcnt);
        }
        return printed;
@@ -1155,10 +1198,6 @@ static struct hist_browser *hist_browser__new(struct hists *hists)
                browser->b.refresh = hist_browser__refresh;
                browser->b.seek = ui_browser__hists_seek;
                browser->b.use_navkeypressed = true;
-                if (sort__branch_mode == 1)
-                        browser->has_symbols = sort_sym_from.list.next != NULL;
-                else
-                        browser->has_symbols = sort_sym.list.next != NULL;
        }
        return browser;
@@ -1329,11 +1368,25 @@ close_file_and_continue:
        return ret;
 }
+static void hist_browser__update_pcnt_entries(struct hist_browser *hb)
+{
+        u64 nr_entries = 0;
+        struct rb_node *nd = rb_first(&hb->hists->entries);
+        while (nd) {
+                nr_entries++;
+                nd = hists__filter_entries(rb_next(nd), hb->hists,
+                                           hb->min_pcnt);
+        }
+        hb->nr_pcnt_entries = nr_entries;
+}
 static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                                    const char *helpline, const char *ev_name,
                                    bool left_exits,
                                    struct hist_browser_timer *hbt,
+                                    float min_pcnt,
                                    struct perf_session_env *env)
 {
        struct hists *hists = &evsel->hists;
@@ -1350,6 +1403,11 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
        if (browser == NULL)
                return -1;
+        if (min_pcnt) {
+                browser->min_pcnt = min_pcnt;
+                hist_browser__update_pcnt_entries(browser);
+        }
        fstack = pstack__new(2);
        if (fstack == NULL)
                goto out;
@@ -1386,7 +1444,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                         */
                        goto out_free_stack;
                case 'a':
-                        if (!browser->has_symbols) {
+                        if (!sort__has_sym) {
                                ui_browser__warning(&browser->b, delay_secs * 2,
                        "Annotation is only available for symbolic views, "
                        "include \"sym*\" in --sort to use it.");
@@ -1485,10 +1543,10 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                        continue;
                }
-                if (!browser->has_symbols)
+                if (!sort__has_sym)
                        goto add_exit_option;
-                if (sort__branch_mode == 1) {
+                if (sort__mode == SORT_MODE__BRANCH) {
                        bi = browser->he_selection->branch_info;
                        if (browser->selection != NULL &&
                            bi &&
@@ -1689,6 +1747,7 @@ struct perf_evsel_menu {
        struct ui_browser b;
        struct perf_evsel *selection;
        bool lost_events, lost_events_warned;
+        float min_pcnt;
        struct perf_session_env *env;
 };
@@ -1782,6 +1841,7 @@ browse_hists:
                        ev_name = perf_evsel__name(pos);
                        key = perf_evsel__hists_browse(pos, nr_events, help,
                                                       ev_name, true, hbt,
+                                                       menu->min_pcnt,
                                                       menu->env);
                        ui_browser__show_title(&menu->b, title);
                        switch (key) {
@@ -1843,6 +1903,7 @@ static bool filter_group_entries(struct ui_browser *self __maybe_unused,
 static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
                                           int nr_entries, const char *help,
                                           struct hist_browser_timer *hbt,
+                                           float min_pcnt,
                                           struct perf_session_env *env)
 {
        struct perf_evsel *pos;
@@ -1856,6 +1917,7 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
                        .nr_entries = nr_entries,
                        .priv       = evlist,
                },
+                .min_pcnt = min_pcnt,
                .env = env,
        };
@@ -1874,6 +1936,7 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
                                  struct hist_browser_timer *hbt,
+                                  float min_pcnt,
                                  struct perf_session_env *env)
 {
        int nr_entries = evlist->nr_entries;
@@ -1885,7 +1948,8 @@ single_entry:
                const char *ev_name = perf_evsel__name(first);
                return perf_evsel__hists_browse(first, nr_entries, help,
-                                                ev_name, false, hbt, env);
+                                                ev_name, false, hbt, min_pcnt,
+                                                env);
        }
        if (symbol_conf.event_group) {
@@ -1901,5 +1965,5 @@ single_entry:
        }
        return __perf_evlist__tui_browse_hists(evlist, nr_entries, help,
-                                               hbt, env);
+                                               hbt, min_pcnt, env);
 }
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 6f259b3d14e2..9708dd5fb8f3 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -124,7 +124,8 @@ void perf_gtk__init_hpp(void)
                                perf_gtk__hpp_color_overhead_guest_us;
 }
-static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
+static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
+                                 float min_pcnt)
 {
        struct perf_hpp_fmt *fmt;
        GType col_types[MAX_COLUMNS];
@@ -189,10 +190,15 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
        for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
                struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
                GtkTreeIter iter;
+                float percent = h->stat.period * 100.0 /
+                                        hists->stats.total_period;
                if (h->filtered)
                        continue;
+                if (percent < min_pcnt)
+                        continue;
                gtk_list_store_append(store, &iter);
                col_idx = 0;
@@ -222,7 +228,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
 int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
                                  const char *help,
-                                  struct hist_browser_timer *hbt __maybe_unused)
+                                  struct hist_browser_timer *hbt __maybe_unused,
+                                  float min_pcnt)
 {
        struct perf_evsel *pos;
        GtkWidget *vbox;
@@ -286,7 +293,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
                                                        GTK_POLICY_AUTOMATIC,
                                                        GTK_POLICY_AUTOMATIC);
-                perf_gtk__show_hists(scrolled_window, hists);
+                perf_gtk__show_hists(scrolled_window, hists, min_pcnt);
                tab_label = gtk_label_new(evname);
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index ff1f60cf442e..ae7a75432249 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -334,7 +334,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 }
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
-                      int max_cols, FILE *fp)
+                      int max_cols, float min_pcnt, FILE *fp)
 {
        struct perf_hpp_fmt *fmt;
        struct sort_entry *se;
@@ -440,10 +440,15 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 print_entries:
        for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
                struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+                float percent = h->stat.period * 100.0 /
+                                        hists->stats.total_period;
                if (h->filtered)
                        continue;
+                if (percent < min_pcnt)
+                        continue;
                ret += hist_entry__fprintf(h, max_cols, hists, fp);
                if (max_rows && ++nr_rows >= max_rows)
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 055fef34b6f6..15a77b7c0e36 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -13,13 +13,22 @@ LF='
 # First check if there is a .git to get the version from git describe
 # otherwise try to get the version from the kernel Makefile
 #
-if test -d ../../.git -o -f ../../.git &&
+CID=
-        VN=$(git tag 2>/dev/null | tail -1 | grep -E "v[0-9].[0-9]*")
+TAG=
+if test -d ../../.git -o -f ../../.git
 then
-        VN=$(echo $VN"-g"$(git log -1 --abbrev=4 --pretty=format:"%h" HEAD))
+        TAG=$(git describe --abbrev=0 --match "v[0-9].[0-9]*" 2>/dev/null )
-        VN=$(echo "$VN" | sed -e 's/-/./g');
+        CID=$(git log -1 --abbrev=4 --pretty=format:"%h" 2>/dev/null) && CID="-g$CID"
-else
+fi
-        VN=$(MAKEFLAGS= make -sC ../.. kernelversion)
+if test -z "$TAG"
+then
+        TAG=$(MAKEFLAGS= make -sC ../.. kernelversion)
+fi
+VN="$TAG$CID"
+if test -n "$CID"
+then
+        # format version string, strip trailing zero of sublevel:
+        VN=$(echo "$VN" | sed -e 's/-/./g;s/\([0-9]*[.][0-9]*\)[.]0/\1/')
 fi
 VN=$(expr "$VN" : v*'\(.*\)')
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 6f7d5a9d6b05..c4374f07603c 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -513,10 +513,16 @@ void dsos__add(struct list_head *head, struct dso *dso)
        list_add_tail(&dso->node, head);
 }
-struct dso *dsos__find(struct list_head *head, const char *name)
+struct dso *dsos__find(struct list_head *head, const char *name, bool cmp_short)
 {
        struct dso *pos;
+        if (cmp_short) {
+                list_for_each_entry(pos, head, node)
+                        if (strcmp(pos->short_name, name) == 0)
+                                return pos;
+                return NULL;
+        }
        list_for_each_entry(pos, head, node)
                if (strcmp(pos->long_name, name) == 0)
                        return pos;
@@ -525,7 +531,7 @@ struct dso *dsos__find(struct list_head *head, const char *name)
 struct dso *__dsos__findnew(struct list_head *head, const char *name)
 {
-        struct dso *dso = dsos__find(head, name);
+        struct dso *dso = dsos__find(head, name, false);
        if (!dso) {
                dso = dso__new(name);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 450199ab51b5..d51aaf272c68 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -133,7 +133,8 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
                                const char *short_name, int dso_type);
 void dsos__add(struct list_head *head, struct dso *dso);
-struct dso *dsos__find(struct list_head *head, const char *name);
+struct dso *dsos__find(struct list_head *head, const char *name,
+                       bool cmp_short);
 struct dso *__dsos__findnew(struct list_head *head, const char *name);
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index f7c727801aab..8065ce8fa9a5 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -776,6 +776,8 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
                if (pipe_output)
                        dup2(2, 1);
+                signal(SIGTERM, SIG_DFL);
                close(child_ready_pipe[0]);
                close(go_pipe[1]);
                fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
@@ -819,6 +821,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
                goto out_close_pipes;
        }
+        fcntl(go_pipe[1], F_SETFD, FD_CLOEXEC);
        evlist->workload.cork_fd = go_pipe[1];
        close(child_ready_pipe[0]);
        return 0;
@@ -835,10 +838,17 @@ out_close_ready_pipe:
 int perf_evlist__start_workload(struct perf_evlist *evlist)
 {
        if (evlist->workload.cork_fd > 0) {
+                char bf;
+                int ret;
                /*
                 * Remove the cork, let it rip!
                 */
-                return close(evlist->workload.cork_fd);
+                ret = write(evlist->workload.cork_fd, &bf, 1);
+                if (ret < 0)
+                        perror("enable to write to pipe");
+                close(evlist->workload.cork_fd);
+                return ret;
        }
        return 0;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 07b1a3ad3e24..c9c7494506a1 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -124,7 +124,7 @@ struct event_format *event_format__new(const char *sys, const char *name)
                        bf = nbf;
                }
-                n = read(fd, bf + size, BUFSIZ);
+                n = read(fd, bf + size, alloc_size - size);
                if (n < 0)
                        goto out_free_bf;
                size += n;
@@ -1170,7 +1170,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                } else {
                        data->user_stack.data = (char *)array;
                        array += size / sizeof(*array);
-                        data->user_stack.size = *array;
+                        data->user_stack.size = *array++;
                }
        }
@@ -1514,7 +1514,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel,
        switch (err) {
        case EPERM:
        case EACCES:
-                return scnprintf(msg, size, "%s",
+                return scnprintf(msg, size,
                 "You may not have permission to collect %sstats.\n"
                 "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
                 " -1 - Not paranoid at all\n"
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 326068a593a5..a4dafbee2511 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2303,29 +2303,18 @@ int perf_session__write_header(struct perf_session *session,
        struct perf_file_header f_header;
        struct perf_file_attr   f_attr;
        struct perf_header *header = &session->header;
-        struct perf_evsel *evsel, *pair = NULL;
+        struct perf_evsel *evsel;
        int err;
        lseek(fd, sizeof(f_header), SEEK_SET);
-        if (session->evlist != evlist)
-                pair = perf_evlist__first(session->evlist);
        list_for_each_entry(evsel, &evlist->entries, node) {
                evsel->id_offset = lseek(fd, 0, SEEK_CUR);
                err = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
                if (err < 0) {
-out_err_write:
                        pr_debug("failed to write perf header\n");
                        return err;
                }
-                if (session->evlist != evlist) {
-                        err = do_write(fd, pair->id, pair->ids * sizeof(u64));
-                        if (err < 0)
-                                goto out_err_write;
-                        evsel->ids += pair->ids;
-                        pair = perf_evsel__next(pair);
-                }
        }
        header->attr_offset = lseek(fd, 0, SEEK_CUR);
@@ -2391,7 +2380,6 @@ out_err_write:
        }
        lseek(fd, header->data_offset + header->data_size, SEEK_SET);
-        header->frozen = 1;
        return 0;
 }
@@ -2871,7 +2859,6 @@ int perf_session__read_header(struct perf_session *session, int fd)
                                                   session->pevent))
                goto out_delete_evlist;
-        header->frozen = 1;
        return 0;
 out_errno:
        return -errno;
@@ -2969,6 +2956,8 @@ int perf_event__process_attr(union perf_event *event,
                perf_evlist__id_add(evlist, evsel, 0, i, event->attr.id[i]);
        }
+        symbol_conf.nr_events = evlist->nr_entries;
        return 0;
 }
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index c9fc55cada6d..16a3e83c584e 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -84,7 +84,6 @@ struct perf_session_env {
 };
 struct perf_header {
-        int                     frozen;
        bool                    needs_swap;
        s64                     attr_offset;
        u64                     data_offset;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6b32721f829a..b11a6cfdb414 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -70,9 +70,17 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
        int symlen;
        u16 len;
-        if (h->ms.sym)
+        /*
-                hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen + 4);
+         * +4 accounts for '[x] ' priv level info
-        else {
+         * +2 accounts for 0x prefix on raw addresses
+         * +3 accounts for ' y ' symtab origin info
+         */
+        if (h->ms.sym) {
+                symlen = h->ms.sym->namelen + 4;
+                if (verbose)
+                        symlen += BITS_PER_LONG / 4 + 2 + 3;
+                hists__new_col_len(hists, HISTC_SYMBOL, symlen);
+        } else {
                symlen = unresolved_col_width + 4 + 2;
                hists__new_col_len(hists, HISTC_SYMBOL, symlen);
                hists__set_unres_dso_col_len(hists, HISTC_DSO);
@@ -91,12 +99,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
                hists__new_col_len(hists, HISTC_PARENT, h->parent->namelen);
        if (h->branch_info) {
-                /*
-                 * +4 accounts for '[x] ' priv level info
-                 * +2 account of 0x prefix on raw addresses
-                 */
                if (h->branch_info->from.sym) {
                        symlen = (int)h->branch_info->from.sym->namelen + 4;
+                        if (verbose)
+                                symlen += BITS_PER_LONG / 4 + 2 + 3;
                        hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
                        symlen = dso__name_len(h->branch_info->from.map->dso);
@@ -109,6 +115,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
                if (h->branch_info->to.sym) {
                        symlen = (int)h->branch_info->to.sym->namelen + 4;
+                        if (verbose)
+                                symlen += BITS_PER_LONG / 4 + 2 + 3;
                        hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
                        symlen = dso__name_len(h->branch_info->to.map->dso);
@@ -121,10 +129,6 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
        }
        if (h->mem_info) {
-                /*
-                 * +4 accounts for '[x] ' priv level info
-                 * +2 account of 0x prefix on raw addresses
-                 */
                if (h->mem_info->daddr.sym) {
                        symlen = (int)h->mem_info->daddr.sym->namelen + 4
                               + unresolved_col_width + 2;
@@ -236,8 +240,7 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
        return he->stat.period == 0;
 }
-static void __hists__decay_entries(struct hists *hists, bool zap_user,
+void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
-                                   bool zap_kernel, bool threaded)
 {
        struct rb_node *next = rb_first(&hists->entries);
        struct hist_entry *n;
@@ -256,7 +259,7 @@ static void __hists__decay_entries(struct hists *hists, bool zap_user,
                    !n->used) {
                        rb_erase(&n->rb_node, &hists->entries);
-                        if (sort__need_collapse || threaded)
+                        if (sort__need_collapse)
                                rb_erase(&n->rb_node_in, &hists->entries_collapsed);
                        hist_entry__free(n);
@@ -265,17 +268,6 @@ static void __hists__decay_entries(struct hists *hists, bool zap_user,
        }
 }
-void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
-{
-        return __hists__decay_entries(hists, zap_user, zap_kernel, false);
-}
-void hists__decay_entries_threaded(struct hists *hists,
-                                   bool zap_user, bool zap_kernel)
-{
-        return __hists__decay_entries(hists, zap_user, zap_kernel, true);
-}
 /*
 * histogram, sorted on item, collects periods
 */
@@ -292,6 +284,20 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template)
                        he->ms.map->referenced = true;
                if (he->branch_info) {
+                        /*
+                         * This branch info is (a part of) allocated from
+                         * machine__resolve_bstack() and will be freed after
+                         * adding new entries.  So we need to save a copy.
+                         */
+                        he->branch_info = malloc(sizeof(*he->branch_info));
+                        if (he->branch_info == NULL) {
+                                free(he);
+                                return NULL;
+                        }
+                        memcpy(he->branch_info, template->branch_info,
+                               sizeof(*he->branch_info));
                        if (he->branch_info->from.map)
                                he->branch_info->from.map->referenced = true;
                        if (he->branch_info->to.map)
@@ -341,8 +347,6 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
        struct hist_entry *he;
        int cmp;
-        pthread_mutex_lock(&hists->lock);
        p = &hists->entries_in->rb_node;
        while (*p != NULL) {
@@ -360,6 +364,12 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
                if (!cmp) {
                        he_stat__add_period(&he->stat, period, weight);
+                        /*
+                         * This mem info was allocated from machine__resolve_mem
+                         * and will not be used anymore.
+                         */
+                        free(entry->mem_info);
                        /* If the map of an existing hist_entry has
                         * become out-of-date due to an exec() or
                         * similar, update it.  Otherwise we will
@@ -382,14 +392,12 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
        he = hist_entry__new(entry);
        if (!he)
-                goto out_unlock;
+                return NULL;
        rb_link_node(&he->rb_node_in, parent, p);
        rb_insert_color(&he->rb_node_in, hists->entries_in);
 out:
        hist_entry__add_cpumode_period(he, al->cpumode, period);
-out_unlock:
-        pthread_mutex_unlock(&hists->lock);
        return he;
 }
@@ -589,13 +597,13 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he)
        hists__filter_entry_by_symbol(hists, he);
 }
-static void __hists__collapse_resort(struct hists *hists, bool threaded)
+void hists__collapse_resort(struct hists *hists)
 {
        struct rb_root *root;
        struct rb_node *next;
        struct hist_entry *n;
-        if (!sort__need_collapse && !threaded)
+        if (!sort__need_collapse)
                return;
        root = hists__get_rotate_entries_in(hists);
@@ -617,16 +625,6 @@ static void __hists__collapse_resort(struct hists *hists, bool threaded)
        }
 }
-void hists__collapse_resort(struct hists *hists)
-{
-        return __hists__collapse_resort(hists, false);
-}
-void hists__collapse_resort_threaded(struct hists *hists)
-{
-        return __hists__collapse_resort(hists, true);
-}
 /*
 * reverse the map, sort on period.
 */
@@ -713,7 +711,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
        rb_insert_color(&he->rb_node, entries);
 }
-static void __hists__output_resort(struct hists *hists, bool threaded)
+void hists__output_resort(struct hists *hists)
 {
        struct rb_root *root;
        struct rb_node *next;
@@ -722,7 +720,7 @@ static void __hists__output_resort(struct hists *hists, bool threaded)
        min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100);
-        if (sort__need_collapse || threaded)
+        if (sort__need_collapse)
                root = &hists->entries_collapsed;
        else
                root = hists->entries_in;
@@ -743,16 +741,6 @@ static void __hists__output_resort(struct hists *hists, bool threaded)
        }
 }
-void hists__output_resort(struct hists *hists)
-{
-        return __hists__output_resort(hists, false);
-}
-void hists__output_resort_threaded(struct hists *hists)
-{
-        return __hists__output_resort(hists, true);
-}
 static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h,
                                       enum hist_filter filter)
 {
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 14c2fe20aa62..2d3790fd99bb 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -43,12 +43,12 @@ enum hist_column {
        HISTC_COMM,
        HISTC_PARENT,
        HISTC_CPU,
+        HISTC_SRCLINE,
        HISTC_MISPREDICT,
        HISTC_SYMBOL_FROM,
        HISTC_SYMBOL_TO,
        HISTC_DSO_FROM,
        HISTC_DSO_TO,
-        HISTC_SRCLINE,
        HISTC_LOCAL_WEIGHT,
        HISTC_GLOBAL_WEIGHT,
        HISTC_MEM_DADDR_SYMBOL,
@@ -104,13 +104,9 @@ struct hist_entry *__hists__add_mem_entry(struct hists *self,
                                          u64 weight);
 void hists__output_resort(struct hists *self);
-void hists__output_resort_threaded(struct hists *hists);
 void hists__collapse_resort(struct hists *self);
-void hists__collapse_resort_threaded(struct hists *hists);
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
-void hists__decay_entries_threaded(struct hists *hists, bool zap_user,
-                                   bool zap_kernel);
 void hists__output_recalc_col_len(struct hists *hists, int max_rows);
 void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h);
@@ -119,7 +115,7 @@ void events_stats__inc(struct events_stats *stats, u32 type);
 size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 size_t hists__fprintf(struct hists *self, bool show_header, int max_rows,
-                      int max_cols, FILE *fp);
+                      int max_cols, float min_pcnt, FILE *fp);
 int hist_entry__inc_addr_samples(struct hist_entry *self, int evidx, u64 addr);
 int hist_entry__annotate(struct hist_entry *self, size_t privsize);
@@ -199,6 +195,7 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
                                  struct hist_browser_timer *hbt,
+                                  float min_pcnt,
                                  struct perf_session_env *env);
 int script_browse(const char *script_opt);
 #else
@@ -206,6 +203,7 @@ static inline
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
                                  const char *help __maybe_unused,
                                  struct hist_browser_timer *hbt __maybe_unused,
+                                  float min_pcnt __maybe_unused,
                                  struct perf_session_env *env __maybe_unused)
 {
        return 0;
@@ -233,12 +231,14 @@ static inline int script_browse(const char *script_opt __maybe_unused)
 #ifdef GTK2_SUPPORT
 int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help,
-                                  struct hist_browser_timer *hbt __maybe_unused);
+                                  struct hist_browser_timer *hbt __maybe_unused,
+                                  float min_pcnt);
 #else
 static inline
 int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused,
                                  const char *help __maybe_unused,
-                                  struct hist_browser_timer *hbt __maybe_unused)
+                                  struct hist_browser_timer *hbt __maybe_unused,
+                                  float min_pcnt __maybe_unused)
 {
        return 0;
 }
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 6fcb9de62340..8bcdf9e54089 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -21,6 +21,7 @@ const char *map_type__name[MAP__NR_TYPES] = {
 static inline int is_anon_memory(const char *filename)
 {
        return !strcmp(filename, "//anon") ||
+               !strcmp(filename, "/dev/zero (deleted)") ||
               !strcmp(filename, "/anon_hugepage (deleted)");
 }
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 6c8bb0fb189b..995fc25db8c6 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -860,7 +860,8 @@ int parse_events_terms(struct list_head *terms, const char *str)
                return 0;
        }
-        parse_events__free_terms(data.terms);
+        if (data.terms)
+                parse_events__free_terms(data.terms);
        return ret;
 }
@@ -1183,6 +1184,7 @@ static int new_term(struct parse_events_term **_term, int type_val,
                term->val.str = str;
                break;
        default:
+                free(term);
                return -EINVAL;
        }
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 6b51d47acdba..f3b235ec7bf4 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -37,7 +37,6 @@ struct perf_session {
        int                     fd;
        bool                    fd_pipe;
        bool                    repipe;
-        int                     cwdlen;
        char                    *cwd;
        struct ordered_samples  ordered_samples;
        char                    filename[1];
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 6b0ed322907e..58ea5ca6c255 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -18,8 +18,9 @@ class install_lib(_install_lib):
        self.build_dir = build_lib
-cflags = ['-fno-strict-aliasing', '-Wno-write-strings']
+cflags = getenv('CFLAGS', '').split()
-cflags += getenv('CFLAGS', '').split()
+# switch off several checks (need to be at the end of cflags list)
+cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ]
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 5f52d492590c..313a5a730112 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1,5 +1,6 @@
 #include "sort.h"
 #include "hist.h"
+#include "symbol.h"
 regex_t         parent_regex;
 const char      default_parent_pattern[] = "^sys_|^do_page_fault";
@@ -9,7 +10,7 @@ const char	*sort_order = default_sort_order;
 int             sort__need_collapse = 0;
 int             sort__has_parent = 0;
 int             sort__has_sym = 0;
-int             sort__branch_mode = -1; /* -1 = means not set */
+enum sort_mode  sort__mode = SORT_MODE__NORMAL;
 enum sort_type  sort__first_dimension;
@@ -194,7 +195,7 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
        if (verbose) {
                char o = map ? dso__symtab_origin(map->dso) : '!';
                ret += repsep_snprintf(bf, size, "%-#*llx %c ",
-                                       BITS_PER_LONG / 4, ip, o);
+                                       BITS_PER_LONG / 4 + 2, ip, o);
        }
        ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
@@ -871,14 +872,6 @@ static struct sort_dimension common_sort_dimensions[] = {
        DIM(SORT_PARENT, "parent", sort_parent),
        DIM(SORT_CPU, "cpu", sort_cpu),
        DIM(SORT_SRCLINE, "srcline", sort_srcline),
-        DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
-        DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
-        DIM(SORT_MEM_DADDR_SYMBOL, "symbol_daddr", sort_mem_daddr_sym),
-        DIM(SORT_MEM_DADDR_DSO, "dso_daddr", sort_mem_daddr_dso),
-        DIM(SORT_MEM_LOCKED, "locked", sort_mem_locked),
-        DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb),
-        DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
-        DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
 };
 #undef DIM
@@ -895,6 +888,36 @@ static struct sort_dimension bstack_sort_dimensions[] = {
 #undef DIM
+#define DIM(d, n, func) [d - __SORT_MEMORY_MODE] = { .name = n, .entry = &(func) }
+static struct sort_dimension memory_sort_dimensions[] = {
+        DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
+        DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
+        DIM(SORT_MEM_DADDR_SYMBOL, "symbol_daddr", sort_mem_daddr_sym),
+        DIM(SORT_MEM_DADDR_DSO, "dso_daddr", sort_mem_daddr_dso),
+        DIM(SORT_MEM_LOCKED, "locked", sort_mem_locked),
+        DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb),
+        DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
+        DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
+};
+#undef DIM
+static void __sort_dimension__add(struct sort_dimension *sd, enum sort_type idx)
+{
+        if (sd->taken)
+                return;
+        if (sd->entry->se_collapse)
+                sort__need_collapse = 1;
+        if (list_empty(&hist_entry__sort_list))
+                sort__first_dimension = idx;
+        list_add_tail(&sd->entry->list, &hist_entry__sort_list);
+        sd->taken = 1;
+}
 int sort_dimension__add(const char *tok)
 {
        unsigned int i;
@@ -915,25 +938,11 @@ int sort_dimension__add(const char *tok)
                                return -EINVAL;
                        }
                        sort__has_parent = 1;
-                } else if (sd->entry == &sort_sym ||
+                } else if (sd->entry == &sort_sym) {
-                           sd->entry == &sort_sym_from ||
-                           sd->entry == &sort_sym_to ||
-                           sd->entry == &sort_mem_daddr_sym) {
                        sort__has_sym = 1;
                }
-                if (sd->taken)
+                __sort_dimension__add(sd, i);
-                        return 0;
-                if (sd->entry->se_collapse)
-                        sort__need_collapse = 1;
-                if (list_empty(&hist_entry__sort_list))
-                        sort__first_dimension = i;
-                list_add_tail(&sd->entry->list, &hist_entry__sort_list);
-                sd->taken = 1;
                return 0;
        }
@@ -943,24 +952,29 @@ int sort_dimension__add(const char *tok)
                if (strncasecmp(tok, sd->name, strlen(tok)))
                        continue;
-                if (sort__branch_mode != 1)
+                if (sort__mode != SORT_MODE__BRANCH)
                        return -EINVAL;
                if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to)
                        sort__has_sym = 1;
-                if (sd->taken)
+                __sort_dimension__add(sd, i + __SORT_BRANCH_STACK);
-                        return 0;
+                return 0;
+        }
-                if (sd->entry->se_collapse)
+        for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) {
-                        sort__need_collapse = 1;
+                struct sort_dimension *sd = &memory_sort_dimensions[i];
-                if (list_empty(&hist_entry__sort_list))
+                if (strncasecmp(tok, sd->name, strlen(tok)))
-                        sort__first_dimension = i + __SORT_BRANCH_STACK;
+                        continue;
-                list_add_tail(&sd->entry->list, &hist_entry__sort_list);
+                if (sort__mode != SORT_MODE__MEMORY)
-                sd->taken = 1;
+                        return -EINVAL;
+                if (sd->entry == &sort_mem_daddr_sym)
+                        sort__has_sym = 1;
+                __sort_dimension__add(sd, i + __SORT_MEMORY_MODE);
                return 0;
        }
@@ -993,8 +1007,9 @@ int setup_sorting(void)
        return ret;
 }
-void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
+static void sort_entry__setup_elide(struct sort_entry *self,
-                             const char *list_name, FILE *fp)
+                                    struct strlist *list,
+                                    const char *list_name, FILE *fp)
 {
        if (list && strlist__nr_entries(list) == 1) {
                if (fp != NULL)
@@ -1003,3 +1018,42 @@ void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
                self->elide = true;
        }
 }
+void sort__setup_elide(FILE *output)
+{
+        sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
+                                "dso", output);
+        sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list,
+                                "comm", output);
+        sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list,
+                                "symbol", output);
+        if (sort__mode == SORT_MODE__BRANCH) {
+                sort_entry__setup_elide(&sort_dso_from,
+                                        symbol_conf.dso_from_list,
+                                        "dso_from", output);
+                sort_entry__setup_elide(&sort_dso_to,
+                                        symbol_conf.dso_to_list,
+                                        "dso_to", output);
+                sort_entry__setup_elide(&sort_sym_from,
+                                        symbol_conf.sym_from_list,
+                                        "sym_from", output);
+                sort_entry__setup_elide(&sort_sym_to,
+                                        symbol_conf.sym_to_list,
+                                        "sym_to", output);
+        } else if (sort__mode == SORT_MODE__MEMORY) {
+                sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
+                                        "symbol_daddr", output);
+                sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
+                                        "dso_daddr", output);
+                sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
+                                        "mem", output);
+                sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
+                                        "local_weight", output);
+                sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
+                                        "tlb", output);
+                sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
+                                        "snoop", output);
+        }
+}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index f24bdf64238c..45ac84c1e037 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -32,7 +32,7 @@ extern const char default_sort_order[];
 extern int sort__need_collapse;
 extern int sort__has_parent;
 extern int sort__has_sym;
-extern int sort__branch_mode;
+extern enum sort_mode sort__mode;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;
 extern struct sort_entry sort_sym;
@@ -117,12 +117,18 @@ static inline struct hist_entry *hist_entry__next_pair(struct hist_entry *he)
        return NULL;
 }
-static inline void hist_entry__add_pair(struct hist_entry *he,
+static inline void hist_entry__add_pair(struct hist_entry *pair,
-                                        struct hist_entry *pair)
+                                        struct hist_entry *he)
 {
-        list_add_tail(&he->pairs.head, &pair->pairs.node);
+        list_add_tail(&pair->pairs.node, &he->pairs.head);
 }
+enum sort_mode {
+        SORT_MODE__NORMAL,
+        SORT_MODE__BRANCH,
+        SORT_MODE__MEMORY,
+};
 enum sort_type {
        /* common sort keys */
        SORT_PID,
@@ -132,14 +138,6 @@ enum sort_type {
        SORT_PARENT,
        SORT_CPU,
        SORT_SRCLINE,
-        SORT_LOCAL_WEIGHT,
-        SORT_GLOBAL_WEIGHT,
-        SORT_MEM_DADDR_SYMBOL,
-        SORT_MEM_DADDR_DSO,
-        SORT_MEM_LOCKED,
-        SORT_MEM_TLB,
-        SORT_MEM_LVL,
-        SORT_MEM_SNOOP,
        /* branch stack specific sort keys */
        __SORT_BRANCH_STACK,
@@ -148,6 +146,17 @@ enum sort_type {
        SORT_SYM_FROM,
        SORT_SYM_TO,
        SORT_MISPREDICT,
+        /* memory mode specific sort keys */
+        __SORT_MEMORY_MODE,
+        SORT_LOCAL_WEIGHT = __SORT_MEMORY_MODE,
+        SORT_GLOBAL_WEIGHT,
+        SORT_MEM_DADDR_SYMBOL,
+        SORT_MEM_DADDR_DSO,
+        SORT_MEM_LOCKED,
+        SORT_MEM_TLB,
+        SORT_MEM_LVL,
+        SORT_MEM_SNOOP,
 };
 /*
@@ -172,7 +181,6 @@ extern struct list_head hist_entry__sort_list;
 int setup_sorting(void);
 extern int sort_dimension__add(const char *);
-void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
+void sort__setup_elide(FILE *fp);
-                             const char *list_name, FILE *fp);
 #endif  /* __PERF_SORT_H */
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 23742126f47c..7c59c28afcc5 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -37,7 +37,7 @@ double stddev_stats(struct stats *stats)
 {
        double variance, variance_mean;
-        if (!stats->n)
+        if (stats->n < 2)
                return 0.0;
        variance = stats->M2 / (stats->n - 1);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 8cf3b5426a9a..d5528e1cc03a 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -32,7 +32,6 @@ int vmlinux_path__nr_entries;
 char **vmlinux_path;
 struct symbol_conf symbol_conf = {
-        .exclude_other    = true,
        .use_modules      = true,
        .try_vmlinux_path = true,
        .annotate_src     = true,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 632e40e5ceca..40399cbcca77 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -14,6 +14,7 @@ struct thread *thread__new(pid_t pid)
        if (self != NULL) {
                map_groups__init(&self->mg);
                self->pid = pid;
+                self->ppid = -1;
                self->comm = malloc(32);
                if (self->comm)
                        snprintf(self->comm, 32, ":%d", self->pid);
@@ -82,5 +83,8 @@ int thread__fork(struct thread *self, struct thread *parent)
        for (i = 0; i < MAP__NR_TYPES; ++i)
                if (map_groups__clone(&self->mg, &parent->mg, i) < 0)
                        return -ENOMEM;
+        self->ppid = parent->pid;
        return 0;
 }
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 5ad266403098..eeb7ac62b9e3 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -13,6 +13,7 @@ struct thread {
        };
        struct map_groups       mg;
        pid_t                   pid;
+        pid_t                   ppid;
        char                    shortname[3];
        bool                    comm_set;
        char                    *comm;
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index 54d37a4753c5..f857b51b6bde 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -23,20 +23,31 @@
 size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 {
-        float samples_per_sec = top->samples / top->delay_secs;
+        float samples_per_sec;
-        float ksamples_per_sec = top->kernel_samples / top->delay_secs;
+        float ksamples_per_sec;
-        float esamples_percent = (100.0 * top->exact_samples) / top->samples;
+        float esamples_percent;
        struct perf_record_opts *opts = &top->record_opts;
        struct perf_target *target = &opts->target;
        size_t ret = 0;
+        if (top->samples) {
+                samples_per_sec = top->samples / top->delay_secs;
+                ksamples_per_sec = top->kernel_samples / top->delay_secs;
+                esamples_percent = (100.0 * top->exact_samples) / top->samples;
+        } else {
+                samples_per_sec = ksamples_per_sec = esamples_percent = 0.0;
+        }
        if (!perf_guest) {
+                float ksamples_percent = 0.0;
+                if (samples_per_sec)
+                        ksamples_percent = (100.0 * ksamples_per_sec) /
+                                                        samples_per_sec;
                ret = SNPRINTF(bf, size,
                               "   PerfTop:%8.0f irqs/sec  kernel:%4.1f%%"
                               "  exact: %4.1f%% [", samples_per_sec,
-                               100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) /
+                               ksamples_percent, esamples_percent);
-                                        samples_per_sec)),
-                                esamples_percent);
        } else {
                float us_samples_per_sec = top->us_samples / top->delay_secs;
                float guest_kernel_samples_per_sec = top->guest_kernel_samples / top->delay_secs;
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 7ebf357dc9e1..df46be93d902 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -26,7 +26,6 @@ struct perf_top {
        int                print_entries, count_filter, delay_secs;
        bool               hide_kernel_symbols, hide_user_symbols, zero;
        bool               use_tui, use_stdio;
-        bool               sort_has_symbols;
        bool               kptr_restrict_warned;
        bool               vmlinux_warned;
        bool               dump_symtab;
@@ -37,6 +36,7 @@ struct perf_top {
        int                realtime_prio;
        int                sym_pcnt_filter;
        const char         *sym_filter;
+        float              min_percent;
 };
 size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size);
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index a45710b70a55..2732fad03908 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -72,6 +72,7 @@
 #include "types.h"
 #include <sys/ttydefaults.h>
 #include <lk/debugfs.h>
+#include <termios.h>
 extern const char *graph_line;
 extern const char *graph_dotted_line;
@@ -221,8 +222,8 @@ extern unsigned char sane_ctype[256];
 #define isalpha(x) sane_istest(x,GIT_ALPHA)
 #define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT)
 #define isprint(x) sane_istest(x,GIT_PRINT)
-#define islower(x) (sane_istest(x,GIT_ALPHA) && sane_istest(x,0x20))
+#define islower(x) (sane_istest(x,GIT_ALPHA) && (x & 0x20))
-#define isupper(x) (sane_istest(x,GIT_ALPHA) && !sane_istest(x,0x20))
+#define isupper(x) (sane_istest(x,GIT_ALPHA) && !(x & 0x20))
 #define tolower(x) sane_case((unsigned char)(x), 0x20)
 #define toupper(x) sane_case((unsigned char)(x), 0)
@@ -274,6 +275,5 @@ void dump_stack(void);
 extern unsigned int page_size;
-struct winsize;
 void get_term_dimensions(struct winsize *ws);
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index e60951fcdb12..39159822d58f 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -91,7 +91,7 @@ void vdso__exit(void)
 struct dso *vdso__dso_findnew(struct list_head *head)
 {
-        struct dso *dso = dsos__find(head, VDSO__MAP_NAME);
+        struct dso *dso = dsos__find(head, VDSO__MAP_NAME, true);
        if (!dso) {
                char *file;
diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index d875a74a3bdf..cbfec92af327 100644
--- a/tools/power/cpupower/Makefile
+++ b/tools/power/cpupower/Makefile
@@ -128,10 +128,12 @@ UTIL_OBJS =  utils/helpers/amd.o utils/helpers/topology.o utils/helpers/msr.o \
        utils/helpers/sysfs.o utils/helpers/misc.o utils/helpers/cpuid.o \
        utils/helpers/pci.o utils/helpers/bitmask.o \
        utils/idle_monitor/nhm_idle.o utils/idle_monitor/snb_idle.o \
+        utils/idle_monitor/hsw_ext_idle.o \
        utils/idle_monitor/amd_fam14h_idle.o utils/idle_monitor/cpuidle_sysfs.o \
        utils/idle_monitor/mperf_monitor.o utils/idle_monitor/cpupower-monitor.o \
        utils/cpupower.o utils/cpufreq-info.o utils/cpufreq-set.o \
-        utils/cpupower-set.o utils/cpupower-info.o utils/cpuidle-info.o
+        utils/cpupower-set.o utils/cpupower-info.o utils/cpuidle-info.o \
+        utils/cpuidle-set.o
 UTIL_SRC := $(UTIL_OBJS:.o=.c)
diff --git a/tools/power/cpupower/man/cpupower-monitor.1 b/tools/power/cpupower/man/cpupower-monitor.1
index e01c35d13b6e..914cbb9d9cd0 100644
--- a/tools/power/cpupower/man/cpupower-monitor.1
+++ b/tools/power/cpupower/man/cpupower-monitor.1
@@ -110,13 +110,21 @@ May work poorly on Linux-2.6.20 through 2.6.29, as the \fBacpi-cpufreq \fP
 kernel frequency driver periodically cleared aperf/mperf registers in those
 kernels.
-.SS "Nehalem" "SandyBridge"
+.SS "Nehalem" "SandyBridge" "HaswellExtended"
 Intel Core and Package sleep state counters.
 Threads (hyperthreaded cores) may not be able to enter deeper core states if
 its sibling is utilized.
 Deepest package sleep states may in reality show up as machine/platform wide
 sleep states and can only be entered if all cores are idle. Look up Intel
 manuals (some are provided in the References section) for further details.
+The monitors are named after the CPU family where the sleep state capabilities
+got introduced and may not match exactly the CPU name of the platform.
+For example an IvyBridge processor has sleep state capabilities which got
+introduced in Nehalem and SandyBridge processor families.
+Thus on an IvyBridge processor one will get Nehalem and SandyBridge sleep
+state monitors.
+HaswellExtended extra package sleep state capabilities are available only in a
+specific Haswell (family 0x45) and probably also other future processors.
 .SS "Fam_12h" "Fam_14h"
 AMD laptop and desktop processor (family 12h and 14h) sleep state counters.
diff --git a/tools/power/cpupower/utils/builtin.h b/tools/power/cpupower/utils/builtin.h
index c10496fbe3c6..2284c8ea4e2a 100644
--- a/tools/power/cpupower/utils/builtin.h
+++ b/tools/power/cpupower/utils/builtin.h
@@ -5,6 +5,7 @@ extern int cmd_set(int argc, const char **argv);
 extern int cmd_info(int argc, const char **argv);
 extern int cmd_freq_set(int argc, const char **argv);
 extern int cmd_freq_info(int argc, const char **argv);
+extern int cmd_idle_set(int argc, const char **argv);
 extern int cmd_idle_info(int argc, const char **argv);
 extern int cmd_monitor(int argc, const char **argv);
diff --git a/tools/power/cpupower/utils/cpuidle-info.c b/tools/power/cpupower/utils/cpuidle-info.c
index 8145af5f93a6..75e66de7e7a7 100644
--- a/tools/power/cpupower/utils/cpuidle-info.c
+++ b/tools/power/cpupower/utils/cpuidle-info.c
@@ -22,7 +22,7 @@
 static void cpuidle_cpu_output(unsigned int cpu, int verbose)
 {
-        int idlestates, idlestate;
+        unsigned int idlestates, idlestate;
        char *tmp;
        printf(_ ("Analyzing CPU %d:\n"), cpu);
@@ -31,10 +31,8 @@ static void cpuidle_cpu_output(unsigned int cpu, int verbose)
        if (idlestates == 0) {
                printf(_("CPU %u: No idle states\n"), cpu);
                return;
-        } else if (idlestates <= 0) {
-                printf(_("CPU %u: Can't read idle state info\n"), cpu);
-                return;
        }
        printf(_("Number of idle states: %d\n"), idlestates);
        printf(_("Available idle states:"));
        for (idlestate = 0; idlestate < idlestates; idlestate++) {
@@ -50,10 +48,14 @@ static void cpuidle_cpu_output(unsigned int cpu, int verbose)
                return;
        for (idlestate = 0; idlestate < idlestates; idlestate++) {
+                int disabled = sysfs_is_idlestate_disabled(cpu, idlestate);
+                /* Disabled interface not supported on older kernels */
+                if (disabled < 0)
+                        disabled = 0;
                tmp = sysfs_get_idlestate_name(cpu, idlestate);
                if (!tmp)
                        continue;
-                printf("%s:\n", tmp);
+                printf("%s%s:\n", tmp, (disabled) ? " (DISABLED) " : "");
                free(tmp);
                tmp = sysfs_get_idlestate_desc(cpu, idlestate);
@@ -98,21 +100,13 @@ static void cpuidle_general_output(void)
 static void proc_cpuidle_cpu_output(unsigned int cpu)
 {
        long max_allowed_cstate = 2000000000;
-        int cstates, cstate;
+        unsigned int cstate, cstates;
        cstates = sysfs_get_idlestate_count(cpu);
        if (cstates == 0) {
-                /*
+                printf(_("CPU %u: No C-states info\n"), cpu);
-                 * Go on and print same useless info as you'd see with
-                 * cat /proc/acpi/processor/../power
-                 *      printf(_("CPU %u: No C-states available\n"), cpu);
-                 *      return;
-                 */
-        } else if (cstates <= 0) {
-                printf(_("CPU %u: Can't read C-state info\n"), cpu);
                return;
        }
-        /* printf("Cstates: %d\n", cstates); */
        printf(_("active state:            C0\n"));
        printf(_("max_cstate:              C%u\n"), cstates-1);
diff --git a/tools/power/cpupower/utils/cpuidle-set.c b/tools/power/cpupower/utils/cpuidle-set.c
new file mode 100644
index 000000000000..c78141c5dfac
--- /dev/null
+++ b/tools/power/cpupower/utils/cpuidle-set.c
@@ -0,0 +1,118 @@
+#include <unistd.h>
+#include <stdio.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <limits.h>
+#include <string.h>
+#include <ctype.h>
+#include <getopt.h>
+#include "cpufreq.h"
+#include "helpers/helpers.h"
+#include "helpers/sysfs.h"
+static struct option info_opts[] = {
+        { .name = "disable",    .has_arg = required_argument,   .flag = NULL,   .val = 'd'},
+        { .name = "enable",     .has_arg = required_argument,   .flag = NULL,   .val = 'e'},
+        { },
+};
+int cmd_idle_set(int argc, char **argv)
+{
+        extern char *optarg;
+        extern int optind, opterr, optopt;
+        int ret = 0, cont = 1, param = 0, idlestate = 0;
+        unsigned int cpu = 0;
+        do {
+                ret = getopt_long(argc, argv, "d:e:", info_opts, NULL);
+                if (ret == -1)
+                        break;
+                switch (ret) {
+                case '?':
+                        param = '?';
+                        cont = 0;
+                        break;
+                case 'd':
+                        if (param) {
+                                param = -1;
+                                cont = 0;
+                                break;
+                        }
+                        param = ret;
+                        idlestate = atoi(optarg);
+                        break;
+                case 'e':
+                        if (param) {
+                                param = -1;
+                                cont = 0;
+                                break;
+                        }
+                        param = ret;
+                        idlestate = atoi(optarg);
+                        break;
+                case -1:
+                        cont = 0;
+                        break;
+                }
+        } while (cont);
+        switch (param) {
+        case -1:
+                printf(_("You can't specify more than one "
+                         "output-specific argument\n"));
+                exit(EXIT_FAILURE);
+        case '?':
+                printf(_("invalid or unknown argument\n"));
+                exit(EXIT_FAILURE);
+        }
+        /* Default is: set all CPUs */
+        if (bitmask_isallclear(cpus_chosen))
+                bitmask_setall(cpus_chosen);
+        for (cpu = bitmask_first(cpus_chosen);
+             cpu <= bitmask_last(cpus_chosen); cpu++) {
+                if (!bitmask_isbitset(cpus_chosen, cpu))
+                        continue;
+                switch (param) {
+                case 'd':
+                        ret = sysfs_idlestate_disable(cpu, idlestate, 1);
+                        if (ret == 0)
+                printf(_("Idlestate %u disabled on CPU %u\n"),  idlestate, cpu);
+                        else if (ret == -1)
+                printf(_("Idlestate %u not available on CPU %u\n"),
+                       idlestate, cpu);
+                        else if (ret == -2)
+                printf(_("Idlestate disabling not supported by kernel\n"));
+                        else
+                printf(_("Idlestate %u not disabled on CPU %u\n"),
+                       idlestate, cpu);
+                        break;
+                case 'e':
+                        ret = sysfs_idlestate_disable(cpu, idlestate, 0);
+                        if (ret == 0)
+                printf(_("Idlestate %u enabled on CPU %u\n"),  idlestate, cpu);
+                        else if (ret == -1)
+                printf(_("Idlestate %u not available on CPU %u\n"),
+                       idlestate, cpu);
+                        else if (ret == -2)
+                printf(_("Idlestate enabling not supported by kernel\n"));
+                        else
+                printf(_("Idlestate %u not enabled on CPU %u\n"),
+                       idlestate, cpu);
+                        break;
+                default:
+                        /* Not reachable with proper args checking */
+                        printf(_("Invalid or unknown argument\n"));
+                        exit(EXIT_FAILURE);
+                        break;
+                }
+        }
+        return EXIT_SUCCESS;
+}
diff --git a/tools/power/cpupower/utils/cpupower.c b/tools/power/cpupower/utils/cpupower.c
index 52bee591c1c5..7efc570ffbaa 100644
--- a/tools/power/cpupower/utils/cpupower.c
+++ b/tools/power/cpupower/utils/cpupower.c
@@ -17,12 +17,6 @@
 #include "helpers/helpers.h"
 #include "helpers/bitmask.h"
-struct cmd_struct {
-        const char *cmd;
-        int (*main)(int, const char **);
-        int needs_root;
-};
 #define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0]))
 static int cmd_help(int argc, const char **argv);
@@ -43,10 +37,17 @@ int be_verbose;
 static void print_help(void);
+struct cmd_struct {
+        const char *cmd;
+        int (*main)(int, const char **);
+        int needs_root;
+};
 static struct cmd_struct commands[] = {
        { "frequency-info",     cmd_freq_info,  0       },
        { "frequency-set",      cmd_freq_set,   1       },
        { "idle-info",          cmd_idle_info,  0       },
+        { "idle-set",           cmd_idle_set,   1       },
        { "set",                cmd_set,        1       },
        { "info",               cmd_info,       0       },
        { "monitor",            cmd_monitor,    0       },
diff --git a/tools/power/cpupower/utils/helpers/sysfs.c b/tools/power/cpupower/utils/helpers/sysfs.c
index 38ab91629463..5cdc600e8152 100644
--- a/tools/power/cpupower/utils/helpers/sysfs.c
+++ b/tools/power/cpupower/utils/helpers/sysfs.c
@@ -89,6 +89,33 @@ int sysfs_is_cpu_online(unsigned int cpu)
 /* CPUidle idlestate specific /sys/devices/system/cpu/cpuX/cpuidle/ access */
+/* CPUidle idlestate specific /sys/devices/system/cpu/cpuX/cpuidle/ access */
+/*
+ * helper function to check whether a file under "../cpuX/cpuidle/stateX/" dir
+ * exists.
+ * For example the functionality to disable c-states was introduced in later
+ * kernel versions, this function can be used to explicitly check for this
+ * feature.
+ *
+ * returns 1 if the file exists, 0 otherwise.
+ */
+unsigned int sysfs_idlestate_file_exists(unsigned int cpu,
+                                         unsigned int idlestate,
+                                         const char *fname)
+{
+        char path[SYSFS_PATH_MAX];
+        struct stat statbuf;
+        snprintf(path, sizeof(path), PATH_TO_CPU "cpu%u/cpuidle/state%u/%s",
+                 cpu, idlestate, fname);
+        if (stat(path, &statbuf) != 0)
+                return 0;
+        return 1;
+}
 /*
 * helper function to read file from /sys into given buffer
 * fname is a relative path under "cpuX/cpuidle/stateX/" dir
@@ -121,6 +148,40 @@ unsigned int sysfs_idlestate_read_file(unsigned int cpu, unsigned int idlestate,
        return (unsigned int) numread;
 }
+/* 
+ * helper function to write a new value to a /sys file
+ * fname is a relative path under "../cpuX/cpuidle/cstateY/" dir
+ *
+ * Returns the number of bytes written or 0 on error
+ */
+static
+unsigned int sysfs_idlestate_write_file(unsigned int cpu,
+                                        unsigned int idlestate,
+                                        const char *fname,
+                                        const char *value, size_t len)
+{
+        char path[SYSFS_PATH_MAX];
+        int fd;
+        ssize_t numwrite;
+        snprintf(path, sizeof(path), PATH_TO_CPU "cpu%u/cpuidle/state%u/%s",
+                 cpu, idlestate, fname);
+        fd = open(path, O_WRONLY);
+        if (fd == -1)
+                return 0;
+        numwrite = write(fd, value, len);
+        if (numwrite < 1) {
+                close(fd);
+                return 0;
+        }
+        close(fd);
+        return (unsigned int) numwrite;
+}
 /* read access to files which contain one numeric value */
 enum idlestate_value {
@@ -128,6 +189,7 @@ enum idlestate_value {
        IDLESTATE_POWER,
        IDLESTATE_LATENCY,
        IDLESTATE_TIME,
+        IDLESTATE_DISABLE,
        MAX_IDLESTATE_VALUE_FILES
 };
@@ -136,6 +198,7 @@ static const char *idlestate_value_files[MAX_IDLESTATE_VALUE_FILES] = {
        [IDLESTATE_POWER] = "power",
        [IDLESTATE_LATENCY] = "latency",
        [IDLESTATE_TIME]  = "time",
+        [IDLESTATE_DISABLE]  = "disable",
 };
 static unsigned long long sysfs_idlestate_get_one_value(unsigned int cpu,
@@ -205,8 +268,59 @@ static char *sysfs_idlestate_get_one_string(unsigned int cpu,
        return result;
 }
+/*
+ * Returns:
+ *    1  if disabled
+ *    0  if enabled
+ *    -1 if idlestate is not available
+ *    -2 if disabling is not supported by the kernel
+ */
+int sysfs_is_idlestate_disabled(unsigned int cpu,
+                                unsigned int idlestate)
+{
+        if (sysfs_get_idlestate_count(cpu) < idlestate)
+                return -1;
+        if (!sysfs_idlestate_file_exists(cpu, idlestate,
+                                 idlestate_value_files[IDLESTATE_DISABLE]))
+                return -2;
+        return sysfs_idlestate_get_one_value(cpu, idlestate, IDLESTATE_DISABLE);
+}
+/*
+ * Pass 1 as last argument to disable or 0 to enable the state
+ * Returns:
+ *    0  on success
+ *    negative values on error, for example:
+ *      -1 if idlestate is not available
+ *      -2 if disabling is not supported by the kernel
+ *      -3 No write access to disable/enable C-states
+ */
+int sysfs_idlestate_disable(unsigned int cpu,
+                            unsigned int idlestate,
+                            unsigned int disable)
+{
+        char value[SYSFS_PATH_MAX];
+        int bytes_written;
+        if (sysfs_get_idlestate_count(cpu) < idlestate)
+                return -1;
+        if (!sysfs_idlestate_file_exists(cpu, idlestate,
+                                 idlestate_value_files[IDLESTATE_DISABLE]))
+                return -2;
+        snprintf(value, SYSFS_PATH_MAX, "%u", disable);
+        bytes_written = sysfs_idlestate_write_file(cpu, idlestate, "disable",
+                                                   value, sizeof(disable));
+        if (bytes_written)
+                return 0;
+        return -3;
+}
 unsigned long sysfs_get_idlestate_latency(unsigned int cpu,
-                                        unsigned int idlestate)
+                                          unsigned int idlestate)
 {
        return sysfs_idlestate_get_one_value(cpu, idlestate, IDLESTATE_LATENCY);
 }
@@ -238,7 +352,7 @@ char *sysfs_get_idlestate_desc(unsigned int cpu, unsigned int idlestate)
 * Negativ in error case
 * Zero if cpuidle does not export any C-states
 */
-int sysfs_get_idlestate_count(unsigned int cpu)
+unsigned int sysfs_get_idlestate_count(unsigned int cpu)
 {
        char file[SYSFS_PATH_MAX];
        struct stat statbuf;
diff --git a/tools/power/cpupower/utils/helpers/sysfs.h b/tools/power/cpupower/utils/helpers/sysfs.h
index 8cb797bbceb0..d28f11fedbda 100644
--- a/tools/power/cpupower/utils/helpers/sysfs.h
+++ b/tools/power/cpupower/utils/helpers/sysfs.h
@@ -7,8 +7,16 @@
 extern unsigned int sysfs_read_file(const char *path, char *buf, size_t buflen);
+extern unsigned int sysfs_idlestate_file_exists(unsigned int cpu,
+                                                unsigned int idlestate,
+                                                const char *fname);
 extern int sysfs_is_cpu_online(unsigned int cpu);
+extern int sysfs_is_idlestate_disabled(unsigned int cpu,
+                                       unsigned int idlestate);
+extern int sysfs_idlestate_disable(unsigned int cpu, unsigned int idlestate,
+                                   unsigned int disable);
 extern unsigned long sysfs_get_idlestate_latency(unsigned int cpu,
                                                unsigned int idlestate);
 extern unsigned long sysfs_get_idlestate_usage(unsigned int cpu,
@@ -19,7 +27,7 @@ extern char *sysfs_get_idlestate_name(unsigned int cpu,
                                unsigned int idlestate);
 extern char *sysfs_get_idlestate_desc(unsigned int cpu,
                                unsigned int idlestate);
-extern int sysfs_get_idlestate_count(unsigned int cpu);
+extern unsigned int sysfs_get_idlestate_count(unsigned int cpu);
 extern char *sysfs_get_cpuidle_governor(void);
 extern char *sysfs_get_cpuidle_driver(void);
diff --git a/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c b/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c
new file mode 100644
index 000000000000..ebeaba6571a3
--- /dev/null
+++ b/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c
@@ -0,0 +1,196 @@
+/*
+ *  (C) 2010,2011       Thomas Renninger <trenn@suse.de>, Novell Inc.
+ *
+ *  Licensed under the terms of the GNU GPL License version 2.
+ *
+ *  Based on SandyBridge monitor. Implements the new package C-states
+ *  (PC8, PC9, PC10) coming with a specific Haswell (family 0x45) CPU.
+ */
+#if defined(__i386__) || defined(__x86_64__)
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+#include "helpers/helpers.h"
+#include "idle_monitor/cpupower-monitor.h"
+#define MSR_PKG_C8_RESIDENCY           0x00000630
+#define MSR_PKG_C9_RESIDENCY           0x00000631
+#define MSR_PKG_C10_RESIDENCY          0x00000632
+#define MSR_TSC 0x10
+enum intel_hsw_ext_id { PC8 = 0, PC9, PC10, HSW_EXT_CSTATE_COUNT,
+                        TSC = 0xFFFF };
+static int hsw_ext_get_count_percent(unsigned int self_id, double *percent,
+                                 unsigned int cpu);
+static cstate_t hsw_ext_cstates[HSW_EXT_CSTATE_COUNT] = {
+        {
+                .name                   = "PC8",
+                .desc                   = N_("Processor Package C8"),
+                .id                     = PC8,
+                .range                  = RANGE_PACKAGE,
+                .get_count_percent      = hsw_ext_get_count_percent,
+        },
+        {
+                .name                   = "PC9",
+                .desc                   = N_("Processor Package C9"),
+                .desc                   = N_("Processor Package C2"),
+                .id                     = PC9,
+                .range                  = RANGE_PACKAGE,
+                .get_count_percent      = hsw_ext_get_count_percent,
+        },
+        {
+                .name                   = "PC10",
+                .desc                   = N_("Processor Package C10"),
+                .id                     = PC10,
+                .range                  = RANGE_PACKAGE,
+                .get_count_percent      = hsw_ext_get_count_percent,
+        },
+};
+static unsigned long long tsc_at_measure_start;
+static unsigned long long tsc_at_measure_end;
+static unsigned long long *previous_count[HSW_EXT_CSTATE_COUNT];
+static unsigned long long *current_count[HSW_EXT_CSTATE_COUNT];
+/* valid flag for all CPUs. If a MSR read failed it will be zero */
+static int *is_valid;
+static int hsw_ext_get_count(enum intel_hsw_ext_id id, unsigned long long *val,
+                        unsigned int cpu)
+{
+        int msr;
+        switch (id) {
+        case PC8:
+                msr = MSR_PKG_C8_RESIDENCY;
+                break;
+        case PC9:
+                msr = MSR_PKG_C9_RESIDENCY;
+                break;
+        case PC10:
+                msr = MSR_PKG_C10_RESIDENCY;
+                break;
+        case TSC:
+                msr = MSR_TSC;
+                break;
+        default:
+                return -1;
+        };
+        if (read_msr(cpu, msr, val))
+                return -1;
+        return 0;
+}
+static int hsw_ext_get_count_percent(unsigned int id, double *percent,
+                                 unsigned int cpu)
+{
+        *percent = 0.0;
+        if (!is_valid[cpu])
+                return -1;
+        *percent = (100.0 *
+                (current_count[id][cpu] - previous_count[id][cpu])) /
+                (tsc_at_measure_end - tsc_at_measure_start);
+        dprint("%s: previous: %llu - current: %llu - (%u)\n",
+                hsw_ext_cstates[id].name, previous_count[id][cpu],
+                current_count[id][cpu], cpu);
+        dprint("%s: tsc_diff: %llu - count_diff: %llu - percent: %2.f (%u)\n",
+               hsw_ext_cstates[id].name,
+               (unsigned long long) tsc_at_measure_end - tsc_at_measure_start,
+               current_count[id][cpu] - previous_count[id][cpu],
+               *percent, cpu);
+        return 0;
+}
+static int hsw_ext_start(void)
+{
+        int num, cpu;
+        unsigned long long val;
+        for (num = 0; num < HSW_EXT_CSTATE_COUNT; num++) {
+                for (cpu = 0; cpu < cpu_count; cpu++) {
+                        hsw_ext_get_count(num, &val, cpu);
+                        previous_count[num][cpu] = val;
+                }
+        }
+        hsw_ext_get_count(TSC, &tsc_at_measure_start, 0);
+        return 0;
+}
+static int hsw_ext_stop(void)
+{
+        unsigned long long val;
+        int num, cpu;
+        hsw_ext_get_count(TSC, &tsc_at_measure_end, 0);
+        for (num = 0; num < HSW_EXT_CSTATE_COUNT; num++) {
+                for (cpu = 0; cpu < cpu_count; cpu++) {
+                        is_valid[cpu] = !hsw_ext_get_count(num, &val, cpu);
+                        current_count[num][cpu] = val;
+                }
+        }
+        return 0;
+}
+struct cpuidle_monitor intel_hsw_ext_monitor;
+static struct cpuidle_monitor *hsw_ext_register(void)
+{
+        int num;
+        if (cpupower_cpu_info.vendor != X86_VENDOR_INTEL
+            || cpupower_cpu_info.family != 6)
+                return NULL;
+        switch (cpupower_cpu_info.model) {
+        case 0x45: /* HSW */
+                break;
+        default:
+                return NULL;
+        }
+        is_valid = calloc(cpu_count, sizeof(int));
+        for (num = 0; num < HSW_EXT_CSTATE_COUNT; num++) {
+                previous_count[num] = calloc(cpu_count,
+                                        sizeof(unsigned long long));
+                current_count[num]  = calloc(cpu_count,
+                                        sizeof(unsigned long long));
+        }
+        intel_hsw_ext_monitor.name_len = strlen(intel_hsw_ext_monitor.name);
+        return &intel_hsw_ext_monitor;
+}
+void hsw_ext_unregister(void)
+{
+        int num;
+        free(is_valid);
+        for (num = 0; num < HSW_EXT_CSTATE_COUNT; num++) {
+                free(previous_count[num]);
+                free(current_count[num]);
+        }
+}
+struct cpuidle_monitor intel_hsw_ext_monitor = {
+        .name                   = "HaswellExtended",
+        .hw_states              = hsw_ext_cstates,
+        .hw_states_num          = HSW_EXT_CSTATE_COUNT,
+        .start                  = hsw_ext_start,
+        .stop                   = hsw_ext_stop,
+        .do_register            = hsw_ext_register,
+        .unregister             = hsw_ext_unregister,
+        .needs_root             = 1,
+        .overflow_s             = 922000000 /* 922337203 seconds TSC overflow
+                                               at 20GHz */
+};
+#endif /* defined(__i386__) || defined(__x86_64__) */
diff --git a/tools/power/cpupower/utils/idle_monitor/idle_monitors.def b/tools/power/cpupower/utils/idle_monitor/idle_monitors.def
index e3f8d9b2b18f..0d6ba4dbb9c7 100644
--- a/tools/power/cpupower/utils/idle_monitor/idle_monitors.def
+++ b/tools/power/cpupower/utils/idle_monitor/idle_monitors.def
@@ -2,6 +2,7 @@
 DEF(amd_fam14h)
 DEF(intel_nhm)
 DEF(intel_snb)
+DEF(intel_hsw_ext)
 DEF(mperf)
 #endif
 DEF(cpuidle_sysfs)
diff --git a/tools/power/cpupower/utils/idle_monitor/snb_idle.c b/tools/power/cpupower/utils/idle_monitor/snb_idle.c
index a99b43b97d6d..efc8a69c9aba 100644
--- a/tools/power/cpupower/utils/idle_monitor/snb_idle.c
+++ b/tools/power/cpupower/utils/idle_monitor/snb_idle.c
@@ -155,6 +155,10 @@ static struct cpuidle_monitor *snb_register(void)
        case 0x2D: /* SNB Xeon */
        case 0x3A: /* IVB */
        case 0x3E: /* IVB Xeon */
+        case 0x3C: /* HSW */
+        case 0x3F: /* HSW */
+        case 0x45: /* HSW */
+        case 0x46: /* HSW */
                break;
        default:
                return NULL;
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index f03e681f8891..0d0506d55c71 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -59,7 +59,7 @@ QUIET_SUBDIR0  = +$(MAKE) $(COMMAND_O) -C # space to separate -C and subdir
 QUIET_SUBDIR1  =
 ifneq ($(findstring $(MAKEFLAGS),s),s)
-ifndef V
+ifneq ($(V),1)
        QUIET_CC       = @echo '   ' CC $@;
        QUIET_AR       = @echo '   ' AR $@;
        QUIET_LINK     = @echo '   ' LINK $@;
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 0d7fd8b51544..999eab1bc64f 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -1796,7 +1796,7 @@ sub monitor {
                # We already booted into the kernel we are testing,
                # but now we booted into another kernel?
                # Consider this a triple fault.
-                doprint "Aleady booted in Linux kernel $version, but now\n";
+                doprint "Already booted in Linux kernel $version, but now\n";
                doprint "we booted into Linux kernel $1.\n";
                doprint "Assuming that this is a triple fault.\n";
                doprint "To disable this: set DETECT_TRIPLE_FAULT to 0\n";
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 0a63658065f0..4cb14cae3791 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -6,6 +6,7 @@ TARGETS += memory-hotplug
 TARGETS += mqueue
 TARGETS += net
 TARGETS += ptrace
+TARGETS += timers
 TARGETS += vm
 all:
diff --git a/tools/testing/selftests/cpu-hotplug/Makefile b/tools/testing/selftests/cpu-hotplug/Makefile
index 12657a5e4bf9..ae5faf9aade2 100644
--- a/tools/testing/selftests/cpu-hotplug/Makefile
+++ b/tools/testing/selftests/cpu-hotplug/Makefile
@@ -1,6 +1,6 @@
 all:
 run_tests:
-        @./on-off-test.sh || echo "cpu-hotplug selftests: [FAIL]"
+        @/bin/sh ./on-off-test.sh || echo "cpu-hotplug selftests: [FAIL]"
 clean:
diff --git a/tools/testing/selftests/kcmp/.gitignore b/tools/testing/selftests/kcmp/.gitignore
new file mode 100644
index 000000000000..5a9b3732b2de
--- /dev/null
+++ b/tools/testing/selftests/kcmp/.gitignore
@@ -0,0 +1,2 @@
+kcmp_test
+kcmp-test-file
diff --git a/tools/testing/selftests/kcmp/Makefile b/tools/testing/selftests/kcmp/Makefile
index 56eb5523dbb8..d7d6bbeeff2f 100644
--- a/tools/testing/selftests/kcmp/Makefile
+++ b/tools/testing/selftests/kcmp/Makefile
@@ -25,5 +25,4 @@ run_tests: all
        @./kcmp_test || echo "kcmp_test: [FAIL]"
 clean:
-        rm -fr ./run_test
+        $(RM) kcmp_test kcmp-test-file
-        rm -fr ./test-file
diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile
index 0f49c3f5f58d..350bfeda3aa8 100644
--- a/tools/testing/selftests/memory-hotplug/Makefile
+++ b/tools/testing/selftests/memory-hotplug/Makefile
@@ -1,6 +1,6 @@
 all:
 run_tests:
-        @./on-off-test.sh || echo "memory-hotplug selftests: [FAIL]"
+        @/bin/sh ./on-off-test.sh || echo "memory-hotplug selftests: [FAIL]"
 clean:
diff --git a/tools/testing/selftests/net/psock_tpacket.c b/tools/testing/selftests/net/psock_tpacket.c
index c41b58640a05..24adf709bd9d 100644
--- a/tools/testing/selftests/net/psock_tpacket.c
+++ b/tools/testing/selftests/net/psock_tpacket.c
@@ -1,6 +1,7 @@
 /*
 * Copyright 2013 Red Hat, Inc.
 * Author: Daniel Borkmann <dborkman@redhat.com>
+ *         Chetan Loke <loke.chetan@gmail.com> (TPACKET_V3 usage example)
 *
 * A basic test of packet socket's TPACKET_V1/TPACKET_V2/TPACKET_V3 behavior.
 *
@@ -71,18 +72,8 @@
 # define __align_tpacket(x)     __attribute__((aligned(TPACKET_ALIGN(x))))
 #endif
-#define BLOCK_STATUS(x)         ((x)->h1.block_status)
-#define BLOCK_NUM_PKTS(x)       ((x)->h1.num_pkts)
-#define BLOCK_O2FP(x)           ((x)->h1.offset_to_first_pkt)
-#define BLOCK_LEN(x)            ((x)->h1.blk_len)
-#define BLOCK_SNUM(x)           ((x)->h1.seq_num)
-#define BLOCK_O2PRIV(x)         ((x)->offset_to_priv)
-#define BLOCK_PRIV(x)           ((void *) ((uint8_t *) (x) + BLOCK_O2PRIV(x)))
-#define BLOCK_HDR_LEN           (ALIGN_8(sizeof(struct block_desc)))
-#define ALIGN_8(x)              (((x) + 8 - 1) & ~(8 - 1))
-#define BLOCK_PLUS_PRIV(sz_pri) (BLOCK_HDR_LEN + ALIGN_8((sz_pri)))
 #define NUM_PACKETS             100
+#define ALIGN_8(x)              (((x) + 8 - 1) & ~(8 - 1))
 struct ring {
        struct iovec *rd;
@@ -476,41 +467,30 @@ static uint64_t __v3_prev_block_seq_num = 0;
 void __v3_test_block_seq_num(struct block_desc *pbd)
 {
-        if (__v3_prev_block_seq_num + 1 != BLOCK_SNUM(pbd)) {
+        if (__v3_prev_block_seq_num + 1 != pbd->h1.seq_num) {
                fprintf(stderr, "\nprev_block_seq_num:%"PRIu64", expected "
                        "seq:%"PRIu64" != actual seq:%"PRIu64"\n",
                        __v3_prev_block_seq_num, __v3_prev_block_seq_num + 1,
-                        (uint64_t) BLOCK_SNUM(pbd));
+                        (uint64_t) pbd->h1.seq_num);
                exit(1);
        }
-        __v3_prev_block_seq_num = BLOCK_SNUM(pbd);
+        __v3_prev_block_seq_num = pbd->h1.seq_num;
 }
 static void __v3_test_block_len(struct block_desc *pbd, uint32_t bytes, int block_num)
 {
-        if (BLOCK_NUM_PKTS(pbd)) {
+        if (pbd->h1.num_pkts && bytes != pbd->h1.blk_len) {
-                if (bytes != BLOCK_LEN(pbd)) {
+                fprintf(stderr, "\nblock:%u with %upackets, expected "
-                        fprintf(stderr, "\nblock:%u with %upackets, expected "
+                        "len:%u != actual len:%u\n", block_num,
-                                "len:%u != actual len:%u\n", block_num,
+                        pbd->h1.num_pkts, bytes, pbd->h1.blk_len);
-                                BLOCK_NUM_PKTS(pbd), bytes, BLOCK_LEN(pbd));
+                exit(1);
-                        exit(1);
-                }
-        } else {
-                if (BLOCK_LEN(pbd) != BLOCK_PLUS_PRIV(13)) {
-                        fprintf(stderr, "\nblock:%u, expected len:%lu != "
-                                "actual len:%u\n", block_num, BLOCK_HDR_LEN,
-                                BLOCK_LEN(pbd));
-                        exit(1);
-                }
        }
 }
 static void __v3_test_block_header(struct block_desc *pbd, const int block_num)
 {
-        uint32_t block_status = BLOCK_STATUS(pbd);
+        if ((pbd->h1.block_status & TP_STATUS_USER) == 0) {
-        if ((block_status & TP_STATUS_USER) == 0) {
                fprintf(stderr, "\nblock %u: not in TP_STATUS_USER\n", block_num);
                exit(1);
        }
@@ -520,14 +500,15 @@ static void __v3_test_block_header(struct block_desc *pbd, const int block_num)
 static void __v3_walk_block(struct block_desc *pbd, const int block_num)
 {
-        int num_pkts = BLOCK_NUM_PKTS(pbd), i;
+        int num_pkts = pbd->h1.num_pkts, i;
-        unsigned long bytes = 0;
+        unsigned long bytes = 0, bytes_with_padding = ALIGN_8(sizeof(*pbd));
-        unsigned long bytes_with_padding = BLOCK_PLUS_PRIV(13);
        struct tpacket3_hdr *ppd;
        __v3_test_block_header(pbd, block_num);
-        ppd = (struct tpacket3_hdr *) ((uint8_t *) pbd + BLOCK_O2FP(pbd));
+        ppd = (struct tpacket3_hdr *) ((uint8_t *) pbd +
+                                       pbd->h1.offset_to_first_pkt);
        for (i = 0; i < num_pkts; ++i) {
                bytes += ppd->tp_snaplen;
@@ -551,7 +532,7 @@ static void __v3_walk_block(struct block_desc *pbd, const int block_num)
 void __v3_flush_block(struct block_desc *pbd)
 {
-        BLOCK_STATUS(pbd) = TP_STATUS_KERNEL;
+        pbd->h1.block_status = TP_STATUS_KERNEL;
        __sync_synchronize();
 }
@@ -577,7 +558,7 @@ static void walk_v3_rx(int sock, struct ring *ring)
        while (total_packets < NUM_PACKETS * 2) {
                pbd = (struct block_desc *) ring->rd[block_num].iov_base;
-                while ((BLOCK_STATUS(pbd) & TP_STATUS_USER) == 0)
+                while ((pbd->h1.block_status & TP_STATUS_USER) == 0)
                        poll(&pfd, 1, 1);
                __v3_walk_block(pbd, block_num);
@@ -624,8 +605,8 @@ static void __v1_v2_fill(struct ring *ring, unsigned int blocks)
 static void __v3_fill(struct ring *ring, unsigned int blocks)
 {
        ring->req3.tp_retire_blk_tov = 64;
-        ring->req3.tp_sizeof_priv = 13;
+        ring->req3.tp_sizeof_priv = 0;
-        ring->req3.tp_feature_req_word |= TP_FT_REQ_FILL_RXHASH;
+        ring->req3.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH;
        ring->req3.tp_block_size = getpagesize() << 2;
        ring->req3.tp_frame_size = TPACKET_ALIGNMENT << 7;
diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile
new file mode 100644
index 000000000000..eb2859f4ad21
--- /dev/null
+++ b/tools/testing/selftests/timers/Makefile
@@ -0,0 +1,8 @@
+all:
+        gcc posix_timers.c -o posix_timers -lrt
+run_tests: all
+        ./posix_timers
+clean:
+        rm -f ./posix_timers
diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c
new file mode 100644
index 000000000000..4fa655d68a81
--- /dev/null
+++ b/tools/testing/selftests/timers/posix_timers.c
@@ -0,0 +1,221 @@
+/*
+ * Copyright (C) 2013 Red Hat, Inc., Frederic Weisbecker <fweisbec@redhat.com>
+ *
+ * Licensed under the terms of the GNU GPL License version 2
+ *
+ * Selftests for a few posix timers interface.
+ *
+ * Kernel loop code stolen from Steven Rostedt <srostedt@redhat.com>
+ */
+#include <sys/time.h>
+#include <stdio.h>
+#include <signal.h>
+#include <unistd.h>
+#include <time.h>
+#include <pthread.h>
+#define DELAY 2
+#define USECS_PER_SEC 1000000
+static volatile int done;
+/* Busy loop in userspace to elapse ITIMER_VIRTUAL */
+static void user_loop(void)
+{
+        while (!done);
+}
+/*
+ * Try to spend as much time as possible in kernelspace
+ * to elapse ITIMER_PROF.
+ */
+static void kernel_loop(void)
+{
+        void *addr = sbrk(0);
+        while (!done) {
+                brk(addr + 4096);
+                brk(addr);
+        }
+}
+/*
+ * Sleep until ITIMER_REAL expiration.
+ */
+static void idle_loop(void)
+{
+        pause();
+}
+static void sig_handler(int nr)
+{
+        done = 1;
+}
+/*
+ * Check the expected timer expiration matches the GTOD elapsed delta since
+ * we armed the timer. Keep a 0.5 sec error margin due to various jitter.
+ */
+static int check_diff(struct timeval start, struct timeval end)
+{
+        long long diff;
+        diff = end.tv_usec - start.tv_usec;
+        diff += (end.tv_sec - start.tv_sec) * USECS_PER_SEC;
+        if (abs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) {
+                printf("Diff too high: %lld..", diff);
+                return -1;
+        }
+        return 0;
+}
+static int check_itimer(int which)
+{
+        int err;
+        struct timeval start, end;
+        struct itimerval val = {
+                .it_value.tv_sec = DELAY,
+        };
+        printf("Check itimer ");
+        if (which == ITIMER_VIRTUAL)
+                printf("virtual... ");
+        else if (which == ITIMER_PROF)
+                printf("prof... ");
+        else if (which == ITIMER_REAL)
+                printf("real... ");
+        fflush(stdout);
+        done = 0;
+        if (which == ITIMER_VIRTUAL)
+                signal(SIGVTALRM, sig_handler);
+        else if (which == ITIMER_PROF)
+                signal(SIGPROF, sig_handler);
+        else if (which == ITIMER_REAL)
+                signal(SIGALRM, sig_handler);
+        err = gettimeofday(&start, NULL);
+        if (err < 0) {
+                perror("Can't call gettimeofday()\n");
+                return -1;
+        }
+        err = setitimer(which, &val, NULL);
+        if (err < 0) {
+                perror("Can't set timer\n");
+                return -1;
+        }
+        if (which == ITIMER_VIRTUAL)
+                user_loop();
+        else if (which == ITIMER_PROF)
+                kernel_loop();
+        else if (which == ITIMER_REAL)
+                idle_loop();
+        gettimeofday(&end, NULL);
+        if (err < 0) {
+                perror("Can't call gettimeofday()\n");
+                return -1;
+        }
+        if (!check_diff(start, end))
+                printf("[OK]\n");
+        else
+                printf("[FAIL]\n");
+        return 0;
+}
+static int check_timer_create(int which)
+{
+        int err;
+        timer_t id;
+        struct timeval start, end;
+        struct itimerspec val = {
+                .it_value.tv_sec = DELAY,
+        };
+        printf("Check timer_create() ");
+        if (which == CLOCK_THREAD_CPUTIME_ID) {
+                printf("per thread... ");
+        } else if (which == CLOCK_PROCESS_CPUTIME_ID) {
+                printf("per process... ");
+        }
+        fflush(stdout);
+        done = 0;
+        timer_create(which, NULL, &id);
+        if (err < 0) {
+                perror("Can't create timer\n");
+                return -1;
+        }
+        signal(SIGALRM, sig_handler);
+        err = gettimeofday(&start, NULL);
+        if (err < 0) {
+                perror("Can't call gettimeofday()\n");
+                return -1;
+        }
+        err = timer_settime(id, 0, &val, NULL);
+        if (err < 0) {
+                perror("Can't set timer\n");
+                return -1;
+        }
+        user_loop();
+        gettimeofday(&end, NULL);
+        if (err < 0) {
+                perror("Can't call gettimeofday()\n");
+                return -1;
+        }
+        if (!check_diff(start, end))
+                printf("[OK]\n");
+        else
+                printf("[FAIL]\n");
+        return 0;
+}
+int main(int argc, char **argv)
+{
+        int err;
+        printf("Testing posix timers. False negative may happen on CPU execution \n");
+        printf("based timers if other threads run on the CPU...\n");
+        if (check_itimer(ITIMER_VIRTUAL) < 0)
+                return -1;
+        if (check_itimer(ITIMER_PROF) < 0)
+                return -1;
+        if (check_itimer(ITIMER_REAL) < 0)
+                return -1;
+        if (check_timer_create(CLOCK_THREAD_CPUTIME_ID) < 0)
+                return -1;
+        /*
+         * It's unfortunately hard to reliably test a timer expiration
+         * on parallel multithread cputime. We could arm it to expire
+         * on DELAY * nr_threads, with nr_threads busy looping, then wait
+         * the normal DELAY since the time is elapsing nr_threads faster.
+         * But for that we need to ensure we have real physical free CPUs
+         * to ensure true parallelism. So test only one thread until we
+         * find a better solution.
+         */
+        if (check_timer_create(CLOCK_PROCESS_CPUTIME_ID) < 0)
+                return -1;
+        return 0;
+}
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
new file mode 100644
index 000000000000..ff1bb16cec4f
--- /dev/null
+++ b/tools/testing/selftests/vm/.gitignore
@@ -0,0 +1,4 @@
+hugepage-mmap
+hugepage-shm
+map_hugetlb
+thuge-gen
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 436d2e81868b..3f94e1afd6cf 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -2,13 +2,14 @@
 CC = $(CROSS_COMPILE)gcc
 CFLAGS = -Wall
+BINARIES = hugepage-mmap hugepage-shm map_hugetlb thuge-gen hugetlbfstest
-all: hugepage-mmap hugepage-shm  map_hugetlb thuge-gen
+all: $(BINARIES)
 %: %.c
        $(CC) $(CFLAGS) -o $@ $^
 run_tests: all
-        @/bin/sh ./run_vmtests || echo "vmtests: [FAIL]"
+        @/bin/sh ./run_vmtests || (echo "vmtests: [FAIL]"; exit 1)
 clean:
-        $(RM) hugepage-mmap hugepage-shm  map_hugetlb
+        $(RM) $(BINARIES)
diff --git a/tools/testing/selftests/vm/hugetlbfstest.c b/tools/testing/selftests/vm/hugetlbfstest.c
new file mode 100644
index 000000000000..ea40ff8c2391
--- /dev/null
+++ b/tools/testing/selftests/vm/hugetlbfstest.c
@@ -0,0 +1,84 @@
+#define _GNU_SOURCE
+#include <assert.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+typedef unsigned long long u64;
+static size_t length = 1 << 24;
+static u64 read_rss(void)
+{
+        char buf[4096], *s = buf;
+        int i, fd;
+        u64 rss;
+        fd = open("/proc/self/statm", O_RDONLY);
+        assert(fd > 2);
+        memset(buf, 0, sizeof(buf));
+        read(fd, buf, sizeof(buf) - 1);
+        for (i = 0; i < 1; i++)
+                s = strchr(s, ' ') + 1;
+        rss = strtoull(s, NULL, 10);
+        return rss << 12; /* assumes 4k pagesize */
+}
+static void do_mmap(int fd, int extra_flags, int unmap)
+{
+        int *p;
+        int flags = MAP_PRIVATE | MAP_POPULATE | extra_flags;
+        u64 before, after;
+        before = read_rss();
+        p = mmap(NULL, length, PROT_READ | PROT_WRITE, flags, fd, 0);
+        assert(p != MAP_FAILED ||
+                        !"mmap returned an unexpected error");
+        after = read_rss();
+        assert(llabs(after - before - length) < 0x40000 ||
+                        !"rss didn't grow as expected");
+        if (!unmap)
+                return;
+        munmap(p, length);
+        after = read_rss();
+        assert(llabs(after - before) < 0x40000 ||
+                        !"rss didn't shrink as expected");
+}
+static int open_file(const char *path)
+{
+        int fd, err;
+        unlink(path);
+        fd = open(path, O_CREAT | O_RDWR | O_TRUNC | O_EXCL
+                        | O_LARGEFILE | O_CLOEXEC, 0600);
+        assert(fd > 2);
+        unlink(path);
+        err = ftruncate(fd, length);
+        assert(!err);
+        return fd;
+}
+int main(void)
+{
+        int hugefd, fd;
+        fd = open_file("/dev/shm/hugetlbhog");
+        hugefd = open_file("/hugepages/hugetlbhog");
+        system("echo 100 > /proc/sys/vm/nr_hugepages");
+        do_mmap(-1, MAP_ANONYMOUS, 1);
+        do_mmap(fd, 0, 1);
+        do_mmap(-1, MAP_ANONYMOUS | MAP_HUGETLB, 1);
+        do_mmap(hugefd, 0, 1);
+        do_mmap(hugefd, MAP_HUGETLB, 1);
+        /* Leak the last one to test do_exit() */
+        do_mmap(-1, MAP_ANONYMOUS | MAP_HUGETLB, 0);
+        printf("oll korrekt.\n");
+        return 0;
+}
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index 4c53cae6c273..c87b6812300d 100644
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -4,6 +4,7 @@
 #we need 256M, below is the size in kB
 needmem=262144
 mnt=./huge
+exitcode=0
 #get pagesize and freepages from /proc/meminfo
 while read name size unit; do
@@ -41,6 +42,7 @@ echo "--------------------"
 ./hugepage-mmap
 if [ $? -ne 0 ]; then
        echo "[FAIL]"
+        exitcode=1
 else
        echo "[PASS]"
 fi
@@ -55,6 +57,7 @@ echo "--------------------"
 ./hugepage-shm
 if [ $? -ne 0 ]; then
        echo "[FAIL]"
+        exitcode=1
 else
        echo "[PASS]"
 fi
@@ -67,6 +70,18 @@ echo "--------------------"
 ./map_hugetlb
 if [ $? -ne 0 ]; then
        echo "[FAIL]"
+        exitcode=1
+else
+        echo "[PASS]"
+fi
+echo "--------------------"
+echo "running hugetlbfstest"
+echo "--------------------"
+./hugetlbfstest
+if [ $? -ne 0 ]; then
+        echo "[FAIL]"
+        exitcode=1
 else
        echo "[PASS]"
 fi
@@ -75,3 +90,4 @@ fi
 umount $mnt
 rm -rf $mnt
 echo $nr_hugepgs > /proc/sys/vm/nr_hugepages
+exit $exitcode
diff --git a/tools/virtio/linux/module.h b/tools/virtio/linux/module.h
index 3039a7e972b6..28ce95a05997 100644
--- a/tools/virtio/linux/module.h
+++ b/tools/virtio/linux/module.h
@@ -1 +1,6 @@
 #include <linux/export.h>
+#define MODULE_LICENSE(__MODULE_LICENSE_value) \
+        static __attribute__((unused)) const char *__MODULE_LICENSE_name = \
+                __MODULE_LICENSE_value
diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h
index cd801838156f..844783040703 100644
--- a/tools/virtio/linux/virtio.h
+++ b/tools/virtio/linux/virtio.h
@@ -45,9 +45,6 @@ struct virtqueue {
        void *priv;
 };
-#define MODULE_LICENSE(__MODULE_LICENSE_value) \
-        const char *__MODULE_LICENSE_name = __MODULE_LICENSE_value
 /* Interfaces exported by virtio_ring. */
 int virtqueue_add_sgs(struct virtqueue *vq,
                      struct scatterlist *sgs[],