240 files changed, 9147 insertions, 1876 deletions

diff --git a/Documentation/trace/events-msr.txt b/Documentation/trace/events-msr.txt
new file mode 100644
index 000000000000..78c383bf06aa
--- /dev/null
+++ b/Documentation/trace/events-msr.txt
@@ -0,0 +1,37 @@
+
+The x86 kernel supports tracing most MSR (Model Specific Register) accesses.
+To see the definition of the MSRs on Intel systems please see the SDM
+at http://www.intel.com/sdm (Volume 3)
+
+Available trace points:
+
+/sys/kernel/debug/tracing/events/msr/
+
+Trace MSR reads
+
+read_msr
+
+msr: MSR number
+val: Value written
+failed: 1 if the access failed, otherwise 0
+
+
+Trace MSR writes
+
+write_msr
+
+msr: MSR number
+val: Value written
+failed: 1 if the access failed, otherwise 0
+
+
+Trace RDPMC in kernel
+
+rdpmc
+
+The trace data can be post processed with the postprocess/decode_msr.py script
+
+cat /sys/kernel/debug/tracing/trace | decode_msr.py /usr/src/linux/include/asm/msr-index.h
+
+to add symbolic MSR names.
+
diff --git a/Documentation/trace/postprocess/decode_msr.py b/Documentation/trace/postprocess/decode_msr.py
new file mode 100644
index 000000000000..0ab40e0db580
--- /dev/null
+++ b/Documentation/trace/postprocess/decode_msr.py
@@ -0,0 +1,37 @@
+#!/usr/bin/python
+# add symbolic names to read_msr / write_msr in trace
+# decode_msr msr-index.h < trace
+import sys
+import re
+
+msrs = dict()
+
+with open(sys.argv[1] if len(sys.argv) > 1 else "msr-index.h", "r") as f:
+        for j in f:
+                m = re.match(r'#define (MSR_\w+)\s+(0x[0-9a-fA-F]+)', j)
+                if m:
+                        msrs[int(m.group(2), 16)] = m.group(1)
+
+extra_ranges = (
+        ( "MSR_LASTBRANCH_%d_FROM_IP", 0x680, 0x69F ),
+        ( "MSR_LASTBRANCH_%d_TO_IP", 0x6C0, 0x6DF ),
+        ( "LBR_INFO_%d", 0xdc0, 0xddf ),
+)
+
+for j in sys.stdin:
+        m = re.search(r'(read|write)_msr:\s+([0-9a-f]+)', j)
+        if m:
+                r = None
+                num = int(m.group(2), 16)
+                if num in msrs:
+                        r = msrs[num]
+                else:
+                        for er in extra_ranges:
+                                if er[1] <= num <= er[2]:
+                                        r = er[0] % (num - er[1],)
+                                        break
+                if r:
+                        j = j.replace(" " + m.group(2), " " + r + "(" + m.group(2) + ")")
+        print j,
+
+
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index ae5fb83e6d91..3e8674288198 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -3,7 +3,6 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <asm/processor.h>
 #include <asm/alternative.h>
 #include <asm/cmpxchg.h>
 #include <asm/rmwcc.h>
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index a11c30b77fb5..a984111135b1 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -3,7 +3,6 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <asm/processor.h>
 //#include <asm/cmpxchg.h>
 
 /* An 64bit atomic type */
diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h
new file mode 100644
index 000000000000..e1a411786bf5
--- /dev/null
+++ b/arch/x86/include/asm/intel_pt.h
@@ -0,0 +1,10 @@
+#ifndef _ASM_X86_INTEL_PT_H
+#define _ASM_X86_INTEL_PT_H
+
+#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
+void cpu_emergency_stop_pt(void);
+#else
+static inline void cpu_emergency_stop_pt(void) {}
+#endif
+
+#endif /* _ASM_X86_INTEL_PT_H */
diff --git a/arch/x86/include/asm/msr-trace.h b/arch/x86/include/asm/msr-trace.h
new file mode 100644
index 000000000000..7567225747d8
--- /dev/null
+++ b/arch/x86/include/asm/msr-trace.h
@@ -0,0 +1,57 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM msr
+
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE msr-trace
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH asm/
+
+#if !defined(_TRACE_MSR_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MSR_H
+
+#include <linux/tracepoint.h>
+
+/*
+ * Tracing for x86 model specific registers. Directly maps to the
+ * RDMSR/WRMSR instructions.
+ */
+
+DECLARE_EVENT_CLASS(msr_trace_class,
+            TP_PROTO(unsigned msr, u64 val, int failed),
+            TP_ARGS(msr, val, failed),
+            TP_STRUCT__entry(
+                    __field(    unsigned,       msr )
+                    __field(    u64,            val )
+                    __field(    int,            failed )
+            ),
+            TP_fast_assign(
+                    __entry->msr = msr;
+                    __entry->val = val;
+                    __entry->failed = failed;
+            ),
+            TP_printk("%x, value %llx%s",
+                      __entry->msr,
+                      __entry->val,
+                      __entry->failed ? " #GP" : "")
+);
+
+DEFINE_EVENT(msr_trace_class, read_msr,
+             TP_PROTO(unsigned msr, u64 val, int failed),
+             TP_ARGS(msr, val, failed)
+);
+
+DEFINE_EVENT(msr_trace_class, write_msr,
+             TP_PROTO(unsigned msr, u64 val, int failed),
+             TP_ARGS(msr, val, failed)
+);
+
+DEFINE_EVENT(msr_trace_class, rdpmc,
+             TP_PROTO(unsigned msr, u64 val, int failed),
+             TP_ARGS(msr, val, failed)
+);
+
+#endif /* _TRACE_MSR_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 77d8b284e4a7..fedd6e6d1e43 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -57,11 +57,34 @@ static inline unsigned long long native_read_tscp(unsigned int *aux)
 #define EAX_EDX_RET(val, low, high)     "=A" (val)
 #endif
 
+#ifdef CONFIG_TRACEPOINTS
+/*
+ * Be very careful with includes. This header is prone to include loops.
+ */
+#include <asm/atomic.h>
+#include <linux/tracepoint-defs.h>
+
+extern struct tracepoint __tracepoint_read_msr;
+extern struct tracepoint __tracepoint_write_msr;
+extern struct tracepoint __tracepoint_rdpmc;
+#define msr_tracepoint_active(t) static_key_false(&(t).key)
+extern void do_trace_write_msr(unsigned msr, u64 val, int failed);
+extern void do_trace_read_msr(unsigned msr, u64 val, int failed);
+extern void do_trace_rdpmc(unsigned msr, u64 val, int failed);
+#else
+#define msr_tracepoint_active(t) false
+static inline void do_trace_write_msr(unsigned msr, u64 val, int failed) {}
+static inline void do_trace_read_msr(unsigned msr, u64 val, int failed) {}
+static inline void do_trace_rdpmc(unsigned msr, u64 val, int failed) {}
+#endif
+
 static inline unsigned long long native_read_msr(unsigned int msr)
 {
         DECLARE_ARGS(val, low, high);
 
         asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr));
+        if (msr_tracepoint_active(__tracepoint_read_msr))
+                do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0);
         return EAX_EDX_VAL(val, low, high);
 }
 
@@ -78,6 +101,8 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
                      _ASM_EXTABLE(2b, 3b)
                      : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
                      : "c" (msr), [fault] "i" (-EIO));
+        if (msr_tracepoint_active(__tracepoint_read_msr))
+                do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err);
         return EAX_EDX_VAL(val, low, high);
 }
 
@@ -85,6 +110,8 @@ static inline void native_write_msr(unsigned int msr,
                                     unsigned low, unsigned high)
 {
         asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory");
+        if (msr_tracepoint_active(__tracepoint_read_msr))
+                do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
 }
 
 /* Can be uninlined because referenced by paravirt */
@@ -102,6 +129,8 @@ notrace static inline int native_write_msr_safe(unsigned int msr,
                      : "c" (msr), "0" (low), "d" (high),
                        [fault] "i" (-EIO)
                      : "memory");
+        if (msr_tracepoint_active(__tracepoint_read_msr))
+                do_trace_write_msr(msr, ((u64)high << 32 | low), err);
         return err;
 }
 
@@ -160,6 +189,8 @@ static inline unsigned long long native_read_pmc(int counter)
         DECLARE_ARGS(val, low, high);
 
         asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter));
+        if (msr_tracepoint_active(__tracepoint_rdpmc))
+                do_trace_rdpmc(counter, EAX_EDX_VAL(val, low, high), 0);
         return EAX_EDX_VAL(val, low, high);
 }
 
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 09b1b0ab94b7..660458af425d 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -745,5 +745,14 @@ copy_to_user(void __user *to, const void *from, unsigned long n)
 #undef __copy_from_user_overflow
 #undef __copy_to_user_overflow
 
+/*
+ * We rely on the nested NMI work to allow atomic faults from the NMI path; the
+ * nested NMI paths are careful to preserve CR2.
+ *
+ * Caller must use pagefault_enable/disable, or run in interrupt context,
+ * and also do a uaccess_ok() check
+ */
+#define __copy_from_user_nmi __copy_from_user_inatomic
+
 #endif /* _ASM_X86_UACCESS_H */
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 2bf79d7c97df..1b443db2db50 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -482,6 +482,9 @@ int x86_pmu_hw_config(struct perf_event *event)
                         /* Support for IP fixup */
                         if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2)
                                 precise++;
+
+                        if (x86_pmu.pebs_prec_dist)
+                                precise++;
                 }
 
                 if (event->attr.precise_ip > precise)
@@ -1531,6 +1534,7 @@ static void __init filter_events(struct attribute **attrs)
 {
         struct device_attribute *d;
         struct perf_pmu_events_attr *pmu_attr;
+        int offset = 0;
         int i, j;
 
         for (i = 0; attrs[i]; i++) {
@@ -1539,7 +1543,7 @@ static void __init filter_events(struct attribute **attrs)
                 /* str trumps id */
                 if (pmu_attr->event_str)
                         continue;
-                if (x86_pmu.event_map(i))
+                if (x86_pmu.event_map(i + offset))
                         continue;
 
                 for (j = i; attrs[j]; j++)
@@ -1547,6 +1551,14 @@ static void __init filter_events(struct attribute **attrs)
 
                 /* Check the shifted attr. */
                 i--;
+
+                /*
+                 * event_map() is index based, the attrs array is organized
+                 * by increasing event index. If we shift the events, then
+                 * we need to compensate for the event_map(), otherwise
+                 * we are looking up the wrong event in the map
+                 */
+                offset++;
         }
 }
 
@@ -2250,12 +2262,19 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
         ss_base = get_segment_base(regs->ss);
 
         fp = compat_ptr(ss_base + regs->bp);
+        pagefault_disable();
         while (entry->nr < PERF_MAX_STACK_DEPTH) {
                 unsigned long bytes;
                 frame.next_frame     = 0;
                 frame.return_address = 0;
 
-                bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+                if (!access_ok(VERIFY_READ, fp, 8))
+                        break;
+
+                bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4);
+                if (bytes != 0)
+                        break;
+                bytes = __copy_from_user_nmi(&frame.return_address, fp+4, 4);
                 if (bytes != 0)
                         break;
 
@@ -2265,6 +2284,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
                 perf_callchain_store(entry, cs_base + frame.return_address);
                 fp = compat_ptr(ss_base + frame.next_frame);
         }
+        pagefault_enable();
         return 1;
 }
 #else
@@ -2302,12 +2322,19 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
         if (perf_callchain_user32(regs, entry))
                 return;
 
+        pagefault_disable();
         while (entry->nr < PERF_MAX_STACK_DEPTH) {
                 unsigned long bytes;
                 frame.next_frame             = NULL;
                 frame.return_address = 0;
 
-                bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+                if (!access_ok(VERIFY_READ, fp, 16))
+                        break;
+
+                bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8);
+                if (bytes != 0)
+                        break;
+                bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8);
                 if (bytes != 0)
                         break;
 
@@ -2315,8 +2342,9 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
                         break;
 
                 perf_callchain_store(entry, frame.return_address);
-                fp = frame.next_frame;
+                fp = (void __user *)frame.next_frame;
         }
+        pagefault_enable();
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index d0e35ebb2adb..7bb61e32fb29 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -14,17 +14,7 @@
 
 #include <linux/perf_event.h>
 
-#if 0
-#undef wrmsrl
-#define wrmsrl(msr, val)                                                \
-do {                                                                    \
-        unsigned int _msr = (msr);                                      \
-        u64 _val = (val);                                               \
-        trace_printk("wrmsrl(%x, %Lx)\n", (unsigned int)(_msr),         \
-                        (unsigned long long)(_val));                    \
-        native_write_msr((_msr), (u32)(_val), (u32)(_val >> 32));       \
-} while (0)
-#endif
+/* To enable MSR tracing please use the generic trace points. */
 
 /*
  *          |   NHM/WSM    |      SNB     |
@@ -318,6 +308,10 @@ struct cpu_hw_events {
 #define INTEL_UEVENT_CONSTRAINT(c, n)   \
         EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
 
+/* Constraint on specific umask bit only + event */
+#define INTEL_UBIT_EVENT_CONSTRAINT(c, n)       \
+        EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|(c))
+
 /* Like UEVENT_CONSTRAINT, but match flags too */
 #define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n)     \
         EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
@@ -589,7 +583,8 @@ struct x86_pmu {
                         bts_active      :1,
                         pebs            :1,
                         pebs_active     :1,
-                        pebs_broken     :1;
+                        pebs_broken     :1,
+                        pebs_prec_dist  :1;
         int             pebs_record_size;
         void            (*drain_pebs)(struct pt_regs *regs);
         struct event_constraint *pebs_constraints;
@@ -907,6 +902,8 @@ void intel_pmu_lbr_init_hsw(void);
 
 void intel_pmu_lbr_init_skl(void);
 
+void intel_pmu_lbr_init_knl(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 1cee5d2d7ece..05e76bf65781 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -18,7 +18,7 @@ static __initconst const u64 amd_hw_cache_event_ids
                 [ C(RESULT_MISS)   ] = 0x0141, /* Data Cache Misses          */
         },
         [ C(OP_WRITE) ] = {
-                [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
+                [ C(RESULT_ACCESS) ] = 0,
                 [ C(RESULT_MISS)   ] = 0,
         },
         [ C(OP_PREFETCH) ] = {
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index e2a430021e46..a667078a5180 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -185,6 +185,14 @@ struct event_constraint intel_skl_event_constraints[] = {
         EVENT_CONSTRAINT_END
 };
 
+static struct extra_reg intel_knl_extra_regs[] __read_mostly = {
+        INTEL_UEVENT_EXTRA_REG(0x01b7,
+                               MSR_OFFCORE_RSP_0, 0x7f9ffbffffull, RSP_0),
+        INTEL_UEVENT_EXTRA_REG(0x02b7,
+                               MSR_OFFCORE_RSP_1, 0x3f9ffbffffull, RSP_1),
+        EVENT_EXTRA_END
+};
+
 static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
         /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
         INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
@@ -255,7 +263,7 @@ struct event_constraint intel_bdw_event_constraints[] = {
         FIXED_EVENT_CONSTRAINT(0x003c, 1),      /* CPU_CLK_UNHALTED.CORE */
         FIXED_EVENT_CONSTRAINT(0x0300, 2),      /* CPU_CLK_UNHALTED.REF */
         INTEL_UEVENT_CONSTRAINT(0x148, 0x4),    /* L1D_PEND_MISS.PENDING */
-        INTEL_UEVENT_CONSTRAINT(0x8a3, 0x4),    /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
+        INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4),        /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
         EVENT_CONSTRAINT_END
 };
 
@@ -1457,6 +1465,42 @@ static __initconst const u64 slm_hw_cache_event_ids
  },
 };
 
+#define KNL_OT_L2_HITE          BIT_ULL(19) /* Other Tile L2 Hit */
+#define KNL_OT_L2_HITF          BIT_ULL(20) /* Other Tile L2 Hit */
+#define KNL_MCDRAM_LOCAL        BIT_ULL(21)
+#define KNL_MCDRAM_FAR          BIT_ULL(22)
+#define KNL_DDR_LOCAL           BIT_ULL(23)
+#define KNL_DDR_FAR             BIT_ULL(24)
+#define KNL_DRAM_ANY            (KNL_MCDRAM_LOCAL | KNL_MCDRAM_FAR | \
+                                    KNL_DDR_LOCAL | KNL_DDR_FAR)
+#define KNL_L2_READ             SLM_DMND_READ
+#define KNL_L2_WRITE            SLM_DMND_WRITE
+#define KNL_L2_PREFETCH         SLM_DMND_PREFETCH
+#define KNL_L2_ACCESS           SLM_LLC_ACCESS
+#define KNL_L2_MISS             (KNL_OT_L2_HITE | KNL_OT_L2_HITF | \
+                                   KNL_DRAM_ANY | SNB_SNP_ANY | \
+                                                  SNB_NON_DRAM)
+
+static __initconst const u64 knl_hw_cache_extra_regs
+                                [PERF_COUNT_HW_CACHE_MAX]
+                                [PERF_COUNT_HW_CACHE_OP_MAX]
+                                [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+        [C(LL)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)] = KNL_L2_READ | KNL_L2_ACCESS,
+                        [C(RESULT_MISS)]   = 0,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)] = KNL_L2_WRITE | KNL_L2_ACCESS,
+                        [C(RESULT_MISS)]   = KNL_L2_WRITE | KNL_L2_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)] = KNL_L2_PREFETCH | KNL_L2_ACCESS,
+                        [C(RESULT_MISS)]   = KNL_L2_PREFETCH | KNL_L2_MISS,
+                },
+        },
+};
+
 /*
  * Use from PMIs where the LBRs are already disabled.
  */
@@ -2475,6 +2519,44 @@ static void intel_pebs_aliases_snb(struct perf_event *event)
         }
 }
 
+static void intel_pebs_aliases_precdist(struct perf_event *event)
+{
+        if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+                /*
+                 * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
+                 * (0x003c) so that we can use it with PEBS.
+                 *
+                 * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't
+                 * PEBS capable. However we can use INST_RETIRED.PREC_DIST
+                 * (0x01c0), which is a PEBS capable event, to get the same
+                 * count.
+                 *
+                 * The PREC_DIST event has special support to minimize sample
+                 * shadowing effects. One drawback is that it can be
+                 * only programmed on counter 1, but that seems like an
+                 * acceptable trade off.
+                 */
+                u64 alt_config = X86_CONFIG(.event=0xc0, .umask=0x01, .inv=1, .cmask=16);
+
+                alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
+                event->hw.config = alt_config;
+        }
+}
+
+static void intel_pebs_aliases_ivb(struct perf_event *event)
+{
+        if (event->attr.precise_ip < 3)
+                return intel_pebs_aliases_snb(event);
+        return intel_pebs_aliases_precdist(event);
+}
+
+static void intel_pebs_aliases_skl(struct perf_event *event)
+{
+        if (event->attr.precise_ip < 3)
+                return intel_pebs_aliases_core2(event);
+        return intel_pebs_aliases_precdist(event);
+}
+
 static unsigned long intel_pmu_free_running_flags(struct perf_event *event)
 {
         unsigned long flags = x86_pmu.free_running_flags;
@@ -3332,6 +3414,7 @@ __init int intel_pmu_init(void)
 
                 x86_pmu.event_constraints = intel_gen_event_constraints;
                 x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints;
+                x86_pmu.pebs_aliases = intel_pebs_aliases_core2;
                 pr_cont("Atom events, ");
                 break;
 
@@ -3431,7 +3514,8 @@ __init int intel_pmu_init(void)
 
                 x86_pmu.event_constraints = intel_ivb_event_constraints;
                 x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
-                x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+                x86_pmu.pebs_aliases = intel_pebs_aliases_ivb;
+                x86_pmu.pebs_prec_dist = true;
                 if (boot_cpu_data.x86_model == 62)
                         x86_pmu.extra_regs = intel_snbep_extra_regs;
                 else
@@ -3464,7 +3548,8 @@ __init int intel_pmu_init(void)
                 x86_pmu.event_constraints = intel_hsw_event_constraints;
                 x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
                 x86_pmu.extra_regs = intel_snbep_extra_regs;
-                x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+                x86_pmu.pebs_aliases = intel_pebs_aliases_ivb;
+                x86_pmu.pebs_prec_dist = true;
                 /* all extra regs are per-cpu when HT is on */
                 x86_pmu.flags |= PMU_FL_HAS_RSP_1;
                 x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
@@ -3499,7 +3584,8 @@ __init int intel_pmu_init(void)
                 x86_pmu.event_constraints = intel_bdw_event_constraints;
                 x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
                 x86_pmu.extra_regs = intel_snbep_extra_regs;
-                x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+                x86_pmu.pebs_aliases = intel_pebs_aliases_ivb;
+                x86_pmu.pebs_prec_dist = true;
                 /* all extra regs are per-cpu when HT is on */
                 x86_pmu.flags |= PMU_FL_HAS_RSP_1;
                 x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
@@ -3511,6 +3597,24 @@ __init int intel_pmu_init(void)
                 pr_cont("Broadwell events, ");
                 break;
 
+        case 87: /* Knights Landing Xeon Phi */
+                memcpy(hw_cache_event_ids,
+                       slm_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+                memcpy(hw_cache_extra_regs,
+                       knl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+                intel_pmu_lbr_init_knl();
+
+                x86_pmu.event_constraints = intel_slm_event_constraints;
+                x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
+                x86_pmu.extra_regs = intel_knl_extra_regs;
+
+                /* all extra regs are per-cpu when HT is on */
+                x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+                x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
+
+                pr_cont("Knights Landing events, ");
+                break;
+
         case 78: /* 14nm Skylake Mobile */
         case 94: /* 14nm Skylake Desktop */
                 x86_pmu.late_ack = true;
@@ -3521,7 +3625,8 @@ __init int intel_pmu_init(void)
                 x86_pmu.event_constraints = intel_skl_event_constraints;
                 x86_pmu.pebs_constraints = intel_skl_pebs_event_constraints;
                 x86_pmu.extra_regs = intel_skl_extra_regs;
-                x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+                x86_pmu.pebs_aliases = intel_pebs_aliases_skl;
+                x86_pmu.pebs_prec_dist = true;
                 /* all extra regs are per-cpu when HT is on */
                 x86_pmu.flags |= PMU_FL_HAS_RSP_1;
                 x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 5db1c7755548..10602f0a438f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -620,6 +620,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
         INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
         /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
         INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01),
+        /* Allow all events as PEBS with no flags */
+        INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
         EVENT_CONSTRAINT_END
 };
 
@@ -686,6 +688,8 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = {
         INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
         /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
         INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+        /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
         INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
         INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
         INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -700,6 +704,8 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = {
         INTEL_PLD_CONSTRAINT(0x01cd, 0xf),    /* MEM_TRANS_RETIRED.* */
         /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
         INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+        /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
         INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
         INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
         INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
@@ -718,9 +724,10 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = {
 
 struct event_constraint intel_skl_pebs_event_constraints[] = {
         INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2),      /* INST_RETIRED.PREC_DIST */
-        INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
-        /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
-        INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+        /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+        /* INST_RETIRED.TOTAL_CYCLES_PS (inv=1, cmask=16) (cycles:p). */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f),
         INTEL_PLD_CONSTRAINT(0x1cd, 0xf),                     /* MEM_TRANS_RETIRED.* */
         INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */
         INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */
@@ -1101,6 +1108,13 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit)
         void *at;
         u64 pebs_status;
 
+        /*
+         * fmt0 does not have a status bitfield (does not use
+         * perf_record_nhm format)
+         */
+        if (x86_pmu.intel_cap.pebs_format < 1)
+                return base;
+
         if (base == NULL)
                 return NULL;
 
@@ -1186,7 +1200,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
         if (!event->attr.precise_ip)
                 return;
 
-        n = (top - at) / x86_pmu.pebs_record_size;
+        n = top - at;
         if (n <= 0)
                 return;
 
@@ -1230,12 +1244,21 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
                 pebs_status = p->status & cpuc->pebs_enabled;
                 pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
 
+                /*
+                 * On some CPUs the PEBS status can be zero when PEBS is
+                 * racing with clearing of GLOBAL_STATUS.
+                 *
+                 * Normally we would drop that record, but in the
+                 * case when there is only a single active PEBS event
+                 * we can assume it's for that event.
+                 */
+                if (!pebs_status && cpuc->pebs_enabled &&
+                        !(cpuc->pebs_enabled & (cpuc->pebs_enabled-1)))
+                        pebs_status = cpuc->pebs_enabled;
+
                 bit = find_first_bit((unsigned long *)&pebs_status,
                                         x86_pmu.max_pebs_events);
-                if (WARN(bit >= x86_pmu.max_pebs_events,
-                         "PEBS record without PEBS event! status=%Lx pebs_enabled=%Lx active_mask=%Lx",
-                         (unsigned long long)p->status, (unsigned long long)cpuc->pebs_enabled,
-                         *(unsigned long long *)cpuc->active_mask))
+                if (bit >= x86_pmu.max_pebs_events)
                         continue;
 
                 /*
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 659f01e165d5..653f88d25987 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -42,6 +42,13 @@ static enum {
 #define LBR_FAR_BIT             8 /* do not capture far branches */
 #define LBR_CALL_STACK_BIT      9 /* enable call stack */
 
+/*
+ * Following bit only exists in Linux; we mask it out before writing it to
+ * the actual MSR. But it helps the constraint perf code to understand
+ * that this is a separate configuration.
+ */
+#define LBR_NO_INFO_BIT        63 /* don't read LBR_INFO. */
+
 #define LBR_KERNEL      (1 << LBR_KERNEL_BIT)
 #define LBR_USER        (1 << LBR_USER_BIT)
 #define LBR_JCC         (1 << LBR_JCC_BIT)
@@ -52,6 +59,7 @@ static enum {
 #define LBR_IND_JMP     (1 << LBR_IND_JMP_BIT)
 #define LBR_FAR         (1 << LBR_FAR_BIT)
 #define LBR_CALL_STACK  (1 << LBR_CALL_STACK_BIT)
+#define LBR_NO_INFO     (1ULL << LBR_NO_INFO_BIT)
 
 #define LBR_PLM (LBR_KERNEL | LBR_USER)
 
@@ -152,8 +160,8 @@ static void __intel_pmu_lbr_enable(bool pmi)
          * did not change.
          */
         if (cpuc->lbr_sel)
-                lbr_select = cpuc->lbr_sel->config;
-        if (!pmi)
+                lbr_select = cpuc->lbr_sel->config & x86_pmu.lbr_sel_mask;
+        if (!pmi && cpuc->lbr_sel)
                 wrmsrl(MSR_LBR_SELECT, lbr_select);
 
         rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
@@ -422,6 +430,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
  */
 static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 {
+        bool need_info = false;
         unsigned long mask = x86_pmu.lbr_nr - 1;
         int lbr_format = x86_pmu.intel_cap.lbr_format;
         u64 tos = intel_pmu_lbr_tos();
@@ -429,8 +438,11 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
         int out = 0;
         int num = x86_pmu.lbr_nr;
 
-        if (cpuc->lbr_sel->config & LBR_CALL_STACK)
-                num = tos;
+        if (cpuc->lbr_sel) {
+                need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO);
+                if (cpuc->lbr_sel->config & LBR_CALL_STACK)
+                        num = tos;
+        }
 
         for (i = 0; i < num; i++) {
                 unsigned long lbr_idx = (tos - i) & mask;
@@ -442,7 +454,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
                 rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
                 rdmsrl(x86_pmu.lbr_to   + lbr_idx, to);
 
-                if (lbr_format == LBR_FORMAT_INFO) {
+                if (lbr_format == LBR_FORMAT_INFO && need_info) {
                         u64 info;
 
                         rdmsrl(MSR_LBR_INFO_0 + lbr_idx, info);
@@ -590,6 +602,7 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
                 if (v != LBR_IGN)
                         mask |= v;
         }
+
         reg = &event->hw.branch_reg;
         reg->idx = EXTRA_REG_LBR;
 
@@ -600,6 +613,11 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
          */
         reg->config = mask ^ x86_pmu.lbr_sel_mask;
 
+        if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) &&
+            (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) &&
+            (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO))
+                reg->config |= LBR_NO_INFO;
+
         return 0;
 }
 
@@ -1028,3 +1046,17 @@ void __init intel_pmu_lbr_init_atom(void)
          */
         pr_cont("8-deep LBR, ");
 }
+
+/* Knights Landing */
+void intel_pmu_lbr_init_knl(void)
+{
+        x86_pmu.lbr_nr     = 8;
+        x86_pmu.lbr_tos    = MSR_LBR_TOS;
+        x86_pmu.lbr_from   = MSR_LBR_NHM_FROM;
+        x86_pmu.lbr_to     = MSR_LBR_NHM_TO;
+
+        x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
+        x86_pmu.lbr_sel_map  = snb_lbr_sel_map;
+
+        pr_cont("8-deep LBR, ");
+}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
index 868e1194337f..c0bbd1033b7c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -27,6 +27,7 @@
 #include <asm/perf_event.h>
 #include <asm/insn.h>
 #include <asm/io.h>
+#include <asm/intel_pt.h>
 
 #include "perf_event.h"
 #include "intel_pt.h"
@@ -1122,6 +1123,14 @@ static int pt_event_init(struct perf_event *event)
         return 0;
 }
 
+void cpu_emergency_stop_pt(void)
+{
+        struct pt *pt = this_cpu_ptr(&pt_ctx);
+
+        if (pt->handle.event)
+                pt_event_stop(pt->handle.event, PERF_EF_UPDATE);
+}
+
 static __init int pt_init(void)
 {
         int ret, cpu, prior_warn = 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index ed446bdcbf31..24a351ad628d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -63,7 +63,7 @@
 #define INTEL_RAPL_PP1          0x4     /* pseudo-encoding */
 
 #define NR_RAPL_DOMAINS         0x4
-static const char *rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
+static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
         "pp0-core",
         "package",
         "dram",
@@ -109,11 +109,11 @@ static struct kobj_attribute format_attr_##_var =		\
 
 #define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */
 
-#define RAPL_EVENT_ATTR_STR(_name, v, str)                              \
-static struct perf_pmu_events_attr event_attr_##v = {                   \
-        .attr           = __ATTR(_name, 0444, rapl_sysfs_show, NULL),   \
-        .id             = 0,                                            \
-        .event_str      = str,                                          \
+#define RAPL_EVENT_ATTR_STR(_name, v, str)                                      \
+static struct perf_pmu_events_attr event_attr_##v = {                           \
+        .attr           = __ATTR(_name, 0444, perf_event_sysfs_show, NULL),     \
+        .id             = 0,                                                    \
+        .event_str      = str,                                                  \
 };
 
 struct rapl_pmu {
@@ -405,19 +405,6 @@ static struct attribute_group rapl_pmu_attr_group = {
         .attrs = rapl_pmu_attrs,
 };
 
-static ssize_t rapl_sysfs_show(struct device *dev,
-                               struct device_attribute *attr,
-                               char *page)
-{
-        struct perf_pmu_events_attr *pmu_attr = \
-                container_of(attr, struct perf_pmu_events_attr, attr);
-
-        if (pmu_attr->event_str)
-                return sprintf(page, "%s", pmu_attr->event_str);
-
-        return 0;
-}
-
 RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
 RAPL_EVENT_ATTR_STR(energy-pkg  ,   rapl_pkg, "event=0x02");
 RAPL_EVENT_ATTR_STR(energy-ram  ,   rapl_ram, "event=0x03");
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 61215a69b03d..f97f8075bf04 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -884,6 +884,15 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
          * each box has a different function id.
          */
         pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
+        /* Knights Landing uses a common PCI device ID for multiple instances of
+         * an uncore PMU device type. There is only one entry per device type in
+         * the knl_uncore_pci_ids table inspite of multiple devices present for
+         * some device types. Hence PCI device idx would be 0 for all devices.
+         * So increment pmu pointer to point to an unused array element.
+         */
+        if (boot_cpu_data.x86_model == 87)
+                while (pmu->func_id >= 0)
+                        pmu++;
         if (pmu->func_id < 0)
                 pmu->func_id = pdev->devfn;
         else
@@ -966,6 +975,7 @@ static int __init uncore_pci_init(void)
         case 63: /* Haswell-EP */
                 ret = hswep_uncore_pci_init();
                 break;
+        case 79: /* BDX-EP */
         case 86: /* BDX-DE */
                 ret = bdx_uncore_pci_init();
                 break;
@@ -982,6 +992,9 @@ static int __init uncore_pci_init(void)
         case 61: /* Broadwell */
                 ret = bdw_uncore_pci_init();
                 break;
+        case 87: /* Knights Landing */
+                ret = knl_uncore_pci_init();
+                break;
         default:
                 return 0;
         }
@@ -1287,9 +1300,13 @@ static int __init uncore_cpu_init(void)
         case 63: /* Haswell-EP */
                 hswep_uncore_cpu_init();
                 break;
+        case 79: /* BDX-EP */
         case 86: /* BDX-DE */
                 bdx_uncore_cpu_init();
                 break;
+        case 87: /* Knights Landing */
+                knl_uncore_cpu_init();
+                break;
         default:
                 return 0;
         }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 2f0a4a98e16b..07aa2d6bd710 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -338,6 +338,7 @@ int hsw_uncore_pci_init(void);
 int bdw_uncore_pci_init(void);
 void snb_uncore_cpu_init(void);
 void nhm_uncore_cpu_init(void);
+int snb_pci2phy_map_init(int devid);
 
 /* perf_event_intel_uncore_snbep.c */
 int snbep_uncore_pci_init(void);
@@ -348,6 +349,8 @@ int hswep_uncore_pci_init(void);
 void hswep_uncore_cpu_init(void);
 int bdx_uncore_pci_init(void);
 void bdx_uncore_cpu_init(void);
+int knl_uncore_pci_init(void);
+void knl_uncore_cpu_init(void);
 
 /* perf_event_intel_uncore_nhmex.c */
 void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index 845256158a10..0b934820fafd 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -417,7 +417,7 @@ static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
         }
 }
 
-static int snb_pci2phy_map_init(int devid)
+int snb_pci2phy_map_init(int devid)
 {
         struct pci_dev *dev = NULL;
         struct pci2phy_map *map;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index f0f4fcba252e..33acb884ccf1 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -209,31 +209,98 @@
 #define HSWEP_PCU_MSR_PMON_BOX_CTL              0x710
 #define HSWEP_PCU_MSR_PMON_BOX_FILTER           0x715
 
+/* KNL Ubox */
+#define KNL_U_MSR_PMON_RAW_EVENT_MASK \
+                                        (SNBEP_U_MSR_PMON_RAW_EVENT_MASK | \
+                                                SNBEP_CBO_PMON_CTL_TID_EN)
+/* KNL CHA */
+#define KNL_CHA_MSR_OFFSET                      0xc
+#define KNL_CHA_MSR_PMON_CTL_QOR                (1 << 16)
+#define KNL_CHA_MSR_PMON_RAW_EVENT_MASK \
+                                        (SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK | \
+                                         KNL_CHA_MSR_PMON_CTL_QOR)
+#define KNL_CHA_MSR_PMON_BOX_FILTER_TID         0x1ff
+#define KNL_CHA_MSR_PMON_BOX_FILTER_STATE       (7 << 18)
+#define KNL_CHA_MSR_PMON_BOX_FILTER_OP          (0xfffffe2aULL << 32)
+
+/* KNL EDC/MC UCLK */
+#define KNL_UCLK_MSR_PMON_CTR0_LOW              0x400
+#define KNL_UCLK_MSR_PMON_CTL0                  0x420
+#define KNL_UCLK_MSR_PMON_BOX_CTL               0x430
+#define KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW        0x44c
+#define KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL        0x454
+#define KNL_PMON_FIXED_CTL_EN                   0x1
+
+/* KNL EDC */
+#define KNL_EDC0_ECLK_MSR_PMON_CTR0_LOW         0xa00
+#define KNL_EDC0_ECLK_MSR_PMON_CTL0             0xa20
+#define KNL_EDC0_ECLK_MSR_PMON_BOX_CTL          0xa30
+#define KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_LOW   0xa3c
+#define KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_CTL   0xa44
+
+/* KNL MC */
+#define KNL_MC0_CH0_MSR_PMON_CTR0_LOW           0xb00
+#define KNL_MC0_CH0_MSR_PMON_CTL0               0xb20
+#define KNL_MC0_CH0_MSR_PMON_BOX_CTL            0xb30
+#define KNL_MC0_CH0_MSR_PMON_FIXED_LOW          0xb3c
+#define KNL_MC0_CH0_MSR_PMON_FIXED_CTL          0xb44
+
+/* KNL IRP */
+#define KNL_IRP_PCI_PMON_BOX_CTL                0xf0
+#define KNL_IRP_PCI_PMON_RAW_EVENT_MASK         (SNBEP_PMON_RAW_EVENT_MASK | \
+                                                 KNL_CHA_MSR_PMON_CTL_QOR)
+/* KNL PCU */
+#define KNL_PCU_PMON_CTL_EV_SEL_MASK            0x0000007f
+#define KNL_PCU_PMON_CTL_USE_OCC_CTR            (1 << 7)
+#define KNL_PCU_MSR_PMON_CTL_TRESH_MASK         0x3f000000
+#define KNL_PCU_MSR_PMON_RAW_EVENT_MASK \
+                                (KNL_PCU_PMON_CTL_EV_SEL_MASK | \
+                                 KNL_PCU_PMON_CTL_USE_OCC_CTR | \
+                                 SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
+                                 SNBEP_PMON_CTL_EDGE_DET | \
+                                 SNBEP_CBO_PMON_CTL_TID_EN | \
+                                 SNBEP_PMON_CTL_EV_SEL_EXT | \
+                                 SNBEP_PMON_CTL_INVERT | \
+                                 KNL_PCU_MSR_PMON_CTL_TRESH_MASK | \
+                                 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
+                                 SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
 
 DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6");
 DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
+DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7");
 DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16");
 DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
 DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
 DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
 DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(thresh6, thresh, "config:24-29");
 DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28");
 DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15");
 DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30");
 DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
+DEFINE_UNCORE_FORMAT_ATTR(occ_edge_det, occ_edge_det, "config:31");
 DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
 DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0");
 DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5");
+DEFINE_UNCORE_FORMAT_ATTR(filter_tid4, filter_tid, "config1:0-8");
 DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5");
 DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
 DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8");
+DEFINE_UNCORE_FORMAT_ATTR(filter_link3, filter_link, "config1:12");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47");
 DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
 DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22");
 DEFINE_UNCORE_FORMAT_ATTR(filter_state3, filter_state, "config1:17-23");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state4, filter_state, "config1:18-20");
+DEFINE_UNCORE_FORMAT_ATTR(filter_local, filter_local, "config1:33");
+DEFINE_UNCORE_FORMAT_ATTR(filter_all_op, filter_all_op, "config1:35");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nnm, filter_nnm, "config1:37");
 DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
 DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc3, filter_opc, "config1:41-60");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nc, filter_nc, "config1:62");
 DEFINE_UNCORE_FORMAT_ATTR(filter_c6, filter_c6, "config1:61");
 DEFINE_UNCORE_FORMAT_ATTR(filter_isoc, filter_isoc, "config1:63");
@@ -315,8 +382,9 @@ static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct pe
 static void snbep_uncore_pci_init_box(struct intel_uncore_box *box)
 {
         struct pci_dev *pdev = box->pci_dev;
+        int box_ctl = uncore_pci_box_ctl(box);
 
-        pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT);
+        pci_write_config_dword(pdev, box_ctl, SNBEP_PMON_BOX_CTL_INT);
 }
 
 static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
@@ -1728,6 +1796,419 @@ int ivbep_uncore_pci_init(void)
 }
 /* end of IvyTown uncore support */
 
+/* KNL uncore support */
+static struct attribute *knl_uncore_ubox_formats_attr[] = {
+        &format_attr_event.attr,
+        &format_attr_umask.attr,
+        &format_attr_edge.attr,
+        &format_attr_tid_en.attr,
+        &format_attr_inv.attr,
+        &format_attr_thresh5.attr,
+        NULL,
+};
+
+static struct attribute_group knl_uncore_ubox_format_group = {
+        .name = "format",
+        .attrs = knl_uncore_ubox_formats_attr,
+};
+
+static struct intel_uncore_type knl_uncore_ubox = {
+        .name                   = "ubox",
+        .num_counters           = 2,
+        .num_boxes              = 1,
+        .perf_ctr_bits          = 48,
+        .fixed_ctr_bits         = 48,
+        .perf_ctr               = HSWEP_U_MSR_PMON_CTR0,
+        .event_ctl              = HSWEP_U_MSR_PMON_CTL0,
+        .event_mask             = KNL_U_MSR_PMON_RAW_EVENT_MASK,
+        .fixed_ctr              = HSWEP_U_MSR_PMON_UCLK_FIXED_CTR,
+        .fixed_ctl              = HSWEP_U_MSR_PMON_UCLK_FIXED_CTL,
+        .ops                    = &snbep_uncore_msr_ops,
+        .format_group           = &knl_uncore_ubox_format_group,
+};
+
+static struct attribute *knl_uncore_cha_formats_attr[] = {
+        &format_attr_event.attr,
+        &format_attr_umask.attr,
+        &format_attr_qor.attr,
+        &format_attr_edge.attr,
+        &format_attr_tid_en.attr,
+        &format_attr_inv.attr,
+        &format_attr_thresh8.attr,
+        &format_attr_filter_tid4.attr,
+        &format_attr_filter_link3.attr,
+        &format_attr_filter_state4.attr,
+        &format_attr_filter_local.attr,
+        &format_attr_filter_all_op.attr,
+        &format_attr_filter_nnm.attr,
+        &format_attr_filter_opc3.attr,
+        &format_attr_filter_nc.attr,
+        &format_attr_filter_isoc.attr,
+        NULL,
+};
+
+static struct attribute_group knl_uncore_cha_format_group = {
+        .name = "format",
+        .attrs = knl_uncore_cha_formats_attr,
+};
+
+static struct event_constraint knl_uncore_cha_constraints[] = {
+        UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
+        UNCORE_EVENT_CONSTRAINT(0x1f, 0x1),
+        UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
+        EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg knl_uncore_cha_extra_regs[] = {
+        SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
+                                  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x3d, 0xff, 0x2),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x4),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x4),
+        EVENT_EXTRA_END
+};
+
+static u64 knl_cha_filter_mask(int fields)
+{
+        u64 mask = 0;
+
+        if (fields & 0x1)
+                mask |= KNL_CHA_MSR_PMON_BOX_FILTER_TID;
+        if (fields & 0x2)
+                mask |= KNL_CHA_MSR_PMON_BOX_FILTER_STATE;
+        if (fields & 0x4)
+                mask |= KNL_CHA_MSR_PMON_BOX_FILTER_OP;
+        return mask;
+}
+
+static struct event_constraint *
+knl_cha_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+        return __snbep_cbox_get_constraint(box, event, knl_cha_filter_mask);
+}
+
+static int knl_cha_hw_config(struct intel_uncore_box *box,
+                             struct perf_event *event)
+{
+        struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+        struct extra_reg *er;
+        int idx = 0;
+
+        for (er = knl_uncore_cha_extra_regs; er->msr; er++) {
+                if (er->event != (event->hw.config & er->config_mask))
+                        continue;
+                idx |= er->idx;
+        }
+
+        if (idx) {
+                reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 +
+                            KNL_CHA_MSR_OFFSET * box->pmu->pmu_idx;
+                reg1->config = event->attr.config1 & knl_cha_filter_mask(idx);
+                reg1->idx = idx;
+        }
+        return 0;
+}
+
+static void hswep_cbox_enable_event(struct intel_uncore_box *box,
+                                    struct perf_event *event);
+
+static struct intel_uncore_ops knl_uncore_cha_ops = {
+        .init_box               = snbep_uncore_msr_init_box,
+        .disable_box            = snbep_uncore_msr_disable_box,
+        .enable_box             = snbep_uncore_msr_enable_box,
+        .disable_event          = snbep_uncore_msr_disable_event,
+        .enable_event           = hswep_cbox_enable_event,
+        .read_counter           = uncore_msr_read_counter,
+        .hw_config              = knl_cha_hw_config,
+        .get_constraint         = knl_cha_get_constraint,
+        .put_constraint         = snbep_cbox_put_constraint,
+};
+
+static struct intel_uncore_type knl_uncore_cha = {
+        .name                   = "cha",
+        .num_counters           = 4,
+        .num_boxes              = 38,
+        .perf_ctr_bits          = 48,
+        .event_ctl              = HSWEP_C0_MSR_PMON_CTL0,
+        .perf_ctr               = HSWEP_C0_MSR_PMON_CTR0,
+        .event_mask             = KNL_CHA_MSR_PMON_RAW_EVENT_MASK,
+        .box_ctl                = HSWEP_C0_MSR_PMON_BOX_CTL,
+        .msr_offset             = KNL_CHA_MSR_OFFSET,
+        .num_shared_regs        = 1,
+        .constraints            = knl_uncore_cha_constraints,
+        .ops                    = &knl_uncore_cha_ops,
+        .format_group           = &knl_uncore_cha_format_group,
+};
+
+static struct attribute *knl_uncore_pcu_formats_attr[] = {
+        &format_attr_event2.attr,
+        &format_attr_use_occ_ctr.attr,
+        &format_attr_occ_sel.attr,
+        &format_attr_edge.attr,
+        &format_attr_tid_en.attr,
+        &format_attr_inv.attr,
+        &format_attr_thresh6.attr,
+        &format_attr_occ_invert.attr,
+        &format_attr_occ_edge_det.attr,
+        NULL,
+};
+
+static struct attribute_group knl_uncore_pcu_format_group = {
+        .name = "format",
+        .attrs = knl_uncore_pcu_formats_attr,
+};
+
+static struct intel_uncore_type knl_uncore_pcu = {
+        .name                   = "pcu",
+        .num_counters           = 4,
+        .num_boxes              = 1,
+        .perf_ctr_bits          = 48,
+        .perf_ctr               = HSWEP_PCU_MSR_PMON_CTR0,
+        .event_ctl              = HSWEP_PCU_MSR_PMON_CTL0,
+        .event_mask             = KNL_PCU_MSR_PMON_RAW_EVENT_MASK,
+        .box_ctl                = HSWEP_PCU_MSR_PMON_BOX_CTL,
+        .ops                    = &snbep_uncore_msr_ops,
+        .format_group           = &knl_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *knl_msr_uncores[] = {
+        &knl_uncore_ubox,
+        &knl_uncore_cha,
+        &knl_uncore_pcu,
+        NULL,
+};
+
+void knl_uncore_cpu_init(void)
+{
+        uncore_msr_uncores = knl_msr_uncores;
+}
+
+static void knl_uncore_imc_enable_box(struct intel_uncore_box *box)
+{
+        struct pci_dev *pdev = box->pci_dev;
+        int box_ctl = uncore_pci_box_ctl(box);
+
+        pci_write_config_dword(pdev, box_ctl, 0);
+}
+
+static void knl_uncore_imc_enable_event(struct intel_uncore_box *box,
+                                        struct perf_event *event)
+{
+        struct pci_dev *pdev = box->pci_dev;
+        struct hw_perf_event *hwc = &event->hw;
+
+        if ((event->attr.config & SNBEP_PMON_CTL_EV_SEL_MASK)
+                                                        == UNCORE_FIXED_EVENT)
+                pci_write_config_dword(pdev, hwc->config_base,
+                                       hwc->config | KNL_PMON_FIXED_CTL_EN);
+        else
+                pci_write_config_dword(pdev, hwc->config_base,
+                                       hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops knl_uncore_imc_ops = {
+        .init_box       = snbep_uncore_pci_init_box,
+        .disable_box    = snbep_uncore_pci_disable_box,
+        .enable_box     = knl_uncore_imc_enable_box,
+        .read_counter   = snbep_uncore_pci_read_counter,
+        .enable_event   = knl_uncore_imc_enable_event,
+        .disable_event  = snbep_uncore_pci_disable_event,
+};
+
+static struct intel_uncore_type knl_uncore_imc_uclk = {
+        .name                   = "imc_uclk",
+        .num_counters           = 4,
+        .num_boxes              = 2,
+        .perf_ctr_bits          = 48,
+        .fixed_ctr_bits         = 48,
+        .perf_ctr               = KNL_UCLK_MSR_PMON_CTR0_LOW,
+        .event_ctl              = KNL_UCLK_MSR_PMON_CTL0,
+        .event_mask             = SNBEP_PMON_RAW_EVENT_MASK,
+        .fixed_ctr              = KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW,
+        .fixed_ctl              = KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL,
+        .box_ctl                = KNL_UCLK_MSR_PMON_BOX_CTL,
+        .ops                    = &knl_uncore_imc_ops,
+        .format_group           = &snbep_uncore_format_group,
+};
+
+static struct intel_uncore_type knl_uncore_imc_dclk = {
+        .name                   = "imc",
+        .num_counters           = 4,
+        .num_boxes              = 6,
+        .perf_ctr_bits          = 48,
+        .fixed_ctr_bits         = 48,
+        .perf_ctr               = KNL_MC0_CH0_MSR_PMON_CTR0_LOW,
+        .event_ctl              = KNL_MC0_CH0_MSR_PMON_CTL0,
+        .event_mask             = SNBEP_PMON_RAW_EVENT_MASK,
+        .fixed_ctr              = KNL_MC0_CH0_MSR_PMON_FIXED_LOW,
+        .fixed_ctl              = KNL_MC0_CH0_MSR_PMON_FIXED_CTL,
+        .box_ctl                = KNL_MC0_CH0_MSR_PMON_BOX_CTL,
+        .ops                    = &knl_uncore_imc_ops,
+        .format_group           = &snbep_uncore_format_group,
+};
+
+static struct intel_uncore_type knl_uncore_edc_uclk = {
+        .name                   = "edc_uclk",
+        .num_counters           = 4,
+        .num_boxes              = 8,
+        .perf_ctr_bits          = 48,
+        .fixed_ctr_bits         = 48,
+        .perf_ctr               = KNL_UCLK_MSR_PMON_CTR0_LOW,
+        .event_ctl              = KNL_UCLK_MSR_PMON_CTL0,
+        .event_mask             = SNBEP_PMON_RAW_EVENT_MASK,
+        .fixed_ctr              = KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW,
+        .fixed_ctl              = KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL,
+        .box_ctl                = KNL_UCLK_MSR_PMON_BOX_CTL,
+        .ops                    = &knl_uncore_imc_ops,
+        .format_group           = &snbep_uncore_format_group,
+};
+
+static struct intel_uncore_type knl_uncore_edc_eclk = {
+        .name                   = "edc_eclk",
+        .num_counters           = 4,
+        .num_boxes              = 8,
+        .perf_ctr_bits          = 48,
+        .fixed_ctr_bits         = 48,
+        .perf_ctr               = KNL_EDC0_ECLK_MSR_PMON_CTR0_LOW,
+        .event_ctl              = KNL_EDC0_ECLK_MSR_PMON_CTL0,
+        .event_mask             = SNBEP_PMON_RAW_EVENT_MASK,
+        .fixed_ctr              = KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_LOW,
+        .fixed_ctl              = KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_CTL,
+        .box_ctl                = KNL_EDC0_ECLK_MSR_PMON_BOX_CTL,
+        .ops                    = &knl_uncore_imc_ops,
+        .format_group           = &snbep_uncore_format_group,
+};
+
+static struct event_constraint knl_uncore_m2pcie_constraints[] = {
+        UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+        EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type knl_uncore_m2pcie = {
+        .name           = "m2pcie",
+        .num_counters   = 4,
+        .num_boxes      = 1,
+        .perf_ctr_bits  = 48,
+        .constraints    = knl_uncore_m2pcie_constraints,
+        SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct attribute *knl_uncore_irp_formats_attr[] = {
+        &format_attr_event.attr,
+        &format_attr_umask.attr,
+        &format_attr_qor.attr,
+        &format_attr_edge.attr,
+        &format_attr_inv.attr,
+        &format_attr_thresh8.attr,
+        NULL,
+};
+
+static struct attribute_group knl_uncore_irp_format_group = {
+        .name = "format",
+        .attrs = knl_uncore_irp_formats_attr,
+};
+
+static struct intel_uncore_type knl_uncore_irp = {
+        .name                   = "irp",
+        .num_counters           = 2,
+        .num_boxes              = 1,
+        .perf_ctr_bits          = 48,
+        .perf_ctr               = SNBEP_PCI_PMON_CTR0,
+        .event_ctl              = SNBEP_PCI_PMON_CTL0,
+        .event_mask             = KNL_IRP_PCI_PMON_RAW_EVENT_MASK,
+        .box_ctl                = KNL_IRP_PCI_PMON_BOX_CTL,
+        .ops                    = &snbep_uncore_pci_ops,
+        .format_group           = &knl_uncore_irp_format_group,
+};
+
+enum {
+        KNL_PCI_UNCORE_MC_UCLK,
+        KNL_PCI_UNCORE_MC_DCLK,
+        KNL_PCI_UNCORE_EDC_UCLK,
+        KNL_PCI_UNCORE_EDC_ECLK,
+        KNL_PCI_UNCORE_M2PCIE,
+        KNL_PCI_UNCORE_IRP,
+};
+
+static struct intel_uncore_type *knl_pci_uncores[] = {
+        [KNL_PCI_UNCORE_MC_UCLK]        = &knl_uncore_imc_uclk,
+        [KNL_PCI_UNCORE_MC_DCLK]        = &knl_uncore_imc_dclk,
+        [KNL_PCI_UNCORE_EDC_UCLK]       = &knl_uncore_edc_uclk,
+        [KNL_PCI_UNCORE_EDC_ECLK]       = &knl_uncore_edc_eclk,
+        [KNL_PCI_UNCORE_M2PCIE]         = &knl_uncore_m2pcie,
+        [KNL_PCI_UNCORE_IRP]            = &knl_uncore_irp,
+        NULL,
+};
+
+/*
+ * KNL uses a common PCI device ID for multiple instances of an Uncore PMU
+ * device type. prior to KNL, each instance of a PMU device type had a unique
+ * device ID.
+ *
+ *      PCI Device ID   Uncore PMU Devices
+ *      ----------------------------------
+ *      0x7841          MC0 UClk, MC1 UClk
+ *      0x7843          MC0 DClk CH 0, MC0 DClk CH 1, MC0 DClk CH 2,
+ *                      MC1 DClk CH 0, MC1 DClk CH 1, MC1 DClk CH 2
+ *      0x7833          EDC0 UClk, EDC1 UClk, EDC2 UClk, EDC3 UClk,
+ *                      EDC4 UClk, EDC5 UClk, EDC6 UClk, EDC7 UClk
+ *      0x7835          EDC0 EClk, EDC1 EClk, EDC2 EClk, EDC3 EClk,
+ *                      EDC4 EClk, EDC5 EClk, EDC6 EClk, EDC7 EClk
+ *      0x7817          M2PCIe
+ *      0x7814          IRP
+*/
+
+static const struct pci_device_id knl_uncore_pci_ids[] = {
+        { /* MC UClk */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7841),
+                .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_UCLK, 0),
+        },
+        { /* MC DClk Channel */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843),
+                .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_DCLK, 0),
+        },
+        { /* EDC UClk */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+                .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_UCLK, 0),
+        },
+        { /* EDC EClk */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+                .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_ECLK, 0),
+        },
+        { /* M2PCIe */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7817),
+                .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_M2PCIE, 0),
+        },
+        { /* IRP */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7814),
+                .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_IRP, 0),
+        },
+        { /* end: all zeroes */ }
+};
+
+static struct pci_driver knl_uncore_pci_driver = {
+        .name           = "knl_uncore",
+        .id_table       = knl_uncore_pci_ids,
+};
+
+int knl_uncore_pci_init(void)
+{
+        int ret;
+
+        /* All KNL PCI based PMON units are on the same PCI bus except IRP */
+        ret = snb_pci2phy_map_init(0x7814); /* IRP */
+        if (ret)
+                return ret;
+        ret = snb_pci2phy_map_init(0x7817); /* M2PCIe */
+        if (ret)
+                return ret;
+        uncore_pci_uncores = knl_pci_uncores;
+        uncore_pci_driver = &knl_uncore_pci_driver;
+        return 0;
+}
+
+/* end of KNL uncore support */
+
 /* Haswell-EP uncore support */
 static struct attribute *hswep_uncore_ubox_formats_attr[] = {
         &format_attr_event.attr,
@@ -2338,7 +2819,7 @@ int hswep_uncore_pci_init(void)
 }
 /* end of Haswell-EP uncore support */
 
-/* BDX-DE uncore support */
+/* BDX uncore support */
 
 static struct intel_uncore_type bdx_uncore_ubox = {
         .name                   = "ubox",
@@ -2360,13 +2841,14 @@ static struct event_constraint bdx_uncore_cbox_constraints[] = {
         UNCORE_EVENT_CONSTRAINT(0x09, 0x3),
         UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
         UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
+        UNCORE_EVENT_CONSTRAINT(0x3e, 0x1),
         EVENT_CONSTRAINT_END
 };
 
 static struct intel_uncore_type bdx_uncore_cbox = {
         .name                   = "cbox",
         .num_counters           = 4,
-        .num_boxes              = 8,
+        .num_boxes              = 24,
         .perf_ctr_bits          = 48,
         .event_ctl              = HSWEP_C0_MSR_PMON_CTL0,
         .perf_ctr               = HSWEP_C0_MSR_PMON_CTR0,
@@ -2379,9 +2861,24 @@ static struct intel_uncore_type bdx_uncore_cbox = {
         .format_group           = &hswep_uncore_cbox_format_group,
 };
 
+static struct intel_uncore_type bdx_uncore_sbox = {
+        .name                   = "sbox",
+        .num_counters           = 4,
+        .num_boxes              = 4,
+        .perf_ctr_bits          = 48,
+        .event_ctl              = HSWEP_S0_MSR_PMON_CTL0,
+        .perf_ctr               = HSWEP_S0_MSR_PMON_CTR0,
+        .event_mask             = HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
+        .box_ctl                = HSWEP_S0_MSR_PMON_BOX_CTL,
+        .msr_offset             = HSWEP_SBOX_MSR_OFFSET,
+        .ops                    = &hswep_uncore_sbox_msr_ops,
+        .format_group           = &hswep_uncore_sbox_format_group,
+};
+
 static struct intel_uncore_type *bdx_msr_uncores[] = {
         &bdx_uncore_ubox,
         &bdx_uncore_cbox,
+        &bdx_uncore_sbox,
         &hswep_uncore_pcu,
         NULL,
 };
@@ -2396,7 +2893,7 @@ void bdx_uncore_cpu_init(void)
 static struct intel_uncore_type bdx_uncore_ha = {
         .name           = "ha",
         .num_counters   = 4,
-        .num_boxes      = 1,
+        .num_boxes      = 2,
         .perf_ctr_bits  = 48,
         SNBEP_UNCORE_PCI_COMMON_INIT(),
 };
@@ -2404,7 +2901,7 @@ static struct intel_uncore_type bdx_uncore_ha = {
 static struct intel_uncore_type bdx_uncore_imc = {
         .name           = "imc",
         .num_counters   = 5,
-        .num_boxes      = 2,
+        .num_boxes      = 8,
         .perf_ctr_bits  = 48,
         .fixed_ctr_bits = 48,
         .fixed_ctr      = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
@@ -2424,6 +2921,19 @@ static struct intel_uncore_type bdx_uncore_irp = {
         .format_group           = &snbep_uncore_format_group,
 };
 
+static struct intel_uncore_type bdx_uncore_qpi = {
+        .name                   = "qpi",
+        .num_counters           = 4,
+        .num_boxes              = 3,
+        .perf_ctr_bits          = 48,
+        .perf_ctr               = SNBEP_PCI_PMON_CTR0,
+        .event_ctl              = SNBEP_PCI_PMON_CTL0,
+        .event_mask             = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+        .box_ctl                = SNBEP_PCI_PMON_BOX_CTL,
+        .num_shared_regs        = 1,
+        .ops                    = &snbep_uncore_qpi_ops,
+        .format_group           = &snbep_uncore_qpi_format_group,
+};
 
 static struct event_constraint bdx_uncore_r2pcie_constraints[] = {
         UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
@@ -2432,6 +2942,8 @@ static struct event_constraint bdx_uncore_r2pcie_constraints[] = {
         UNCORE_EVENT_CONSTRAINT(0x23, 0x1),
         UNCORE_EVENT_CONSTRAINT(0x25, 0x1),
         UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
         UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
         EVENT_CONSTRAINT_END
 };
@@ -2445,18 +2957,65 @@ static struct intel_uncore_type bdx_uncore_r2pcie = {
         SNBEP_UNCORE_PCI_COMMON_INIT(),
 };
 
+static struct event_constraint bdx_uncore_r3qpi_constraints[] = {
+        UNCORE_EVENT_CONSTRAINT(0x01, 0x7),
+        UNCORE_EVENT_CONSTRAINT(0x07, 0x7),
+        UNCORE_EVENT_CONSTRAINT(0x08, 0x7),
+        UNCORE_EVENT_CONSTRAINT(0x09, 0x7),
+        UNCORE_EVENT_CONSTRAINT(0x0a, 0x7),
+        UNCORE_EVENT_CONSTRAINT(0x0e, 0x7),
+        UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x13, 0x1),
+        UNCORE_EVENT_CONSTRAINT(0x14, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x15, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x1f, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x20, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x22, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x29, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x2e, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x2f, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x36, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
+        EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type bdx_uncore_r3qpi = {
+        .name           = "r3qpi",
+        .num_counters   = 3,
+        .num_boxes      = 3,
+        .perf_ctr_bits  = 48,
+        .constraints    = bdx_uncore_r3qpi_constraints,
+        SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
 enum {
         BDX_PCI_UNCORE_HA,
         BDX_PCI_UNCORE_IMC,
         BDX_PCI_UNCORE_IRP,
+        BDX_PCI_UNCORE_QPI,
         BDX_PCI_UNCORE_R2PCIE,
+        BDX_PCI_UNCORE_R3QPI,
 };
 
 static struct intel_uncore_type *bdx_pci_uncores[] = {
         [BDX_PCI_UNCORE_HA]     = &bdx_uncore_ha,
         [BDX_PCI_UNCORE_IMC]    = &bdx_uncore_imc,
         [BDX_PCI_UNCORE_IRP]    = &bdx_uncore_irp,
+        [BDX_PCI_UNCORE_QPI]    = &bdx_uncore_qpi,
         [BDX_PCI_UNCORE_R2PCIE] = &bdx_uncore_r2pcie,
+        [BDX_PCI_UNCORE_R3QPI]  = &bdx_uncore_r3qpi,
         NULL,
 };
 
@@ -2465,6 +3024,10 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = {
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f30),
                 .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 0),
         },
+        { /* Home Agent 1 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f38),
+                .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 1),
+        },
         { /* MC0 Channel 0 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb0),
                 .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 0),
@@ -2473,14 +3036,74 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = {
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb1),
                 .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 1),
         },
+        { /* MC0 Channel 2 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb4),
+                .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 2),
+        },
+        { /* MC0 Channel 3 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb5),
+                .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 3),
+        },
+        { /* MC1 Channel 0 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd0),
+                .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 4),
+        },
+        { /* MC1 Channel 1 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd1),
+                .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 5),
+        },
+        { /* MC1 Channel 2 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd4),
+                .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 6),
+        },
+        { /* MC1 Channel 3 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd5),
+                .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 7),
+        },
         { /* IRP */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f39),
                 .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IRP, 0),
         },
+        { /* QPI0 Port 0 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f32),
+                .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 0),
+        },
+        { /* QPI0 Port 1 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f33),
+                .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 1),
+        },
+        { /* QPI1 Port 2 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f3a),
+                .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 2),
+        },
         { /* R2PCIe */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f34),
                 .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R2PCIE, 0),
         },
+        { /* R3QPI0 Link 0 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f36),
+                .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 0),
+        },
+        { /* R3QPI0 Link 1 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f37),
+                .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 1),
+        },
+        { /* R3QPI1 Link 2 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f3e),
+                .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 2),
+        },
+        { /* QPI Port 0 filter  */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86),
+                .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0),
+        },
+        { /* QPI Port 1 filter  */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96),
+                .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1),
+        },
+        { /* QPI Port 2 filter  */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46),
+                .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2),
+        },
         { /* end: all zeroes */ }
 };
 
@@ -2500,4 +3123,4 @@ int bdx_uncore_pci_init(void)
         return 0;
 }
 
-/* end of BDX-DE uncore support */
+/* end of BDX uncore support */
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 2c1910f6717e..58f34319b29a 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -35,6 +35,7 @@
 #include <asm/cpu.h>
 #include <asm/reboot.h>
 #include <asm/virtext.h>
+#include <asm/intel_pt.h>
 
 /* Alignment required for elf header segment */
 #define ELF_CORE_HEADER_ALIGN   4096
@@ -125,6 +126,11 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
         cpu_emergency_vmxoff();
         cpu_emergency_svm_disable();
 
+        /*
+         * Disable Intel PT to stop its logging
+         */
+        cpu_emergency_stop_pt();
+
         disable_local_APIC();
 }
 
@@ -169,6 +175,11 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
         cpu_emergency_vmxoff();
         cpu_emergency_svm_disable();
 
+        /*
+         * Disable Intel PT to stop its logging
+         */
+        cpu_emergency_stop_pt();
+
 #ifdef CONFIG_X86_IO_APIC
         /* Prevent crash_kexec() from deadlocking on ioapic_lock. */
         ioapic_zap_locks();
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 43623739c7cf..004c861b1648 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -1,6 +1,8 @@
 #include <linux/module.h>
 #include <linux/preempt.h>
 #include <asm/msr.h>
+#define CREATE_TRACE_POINTS
+#include <asm/msr-trace.h>
 
 struct msr *msrs_alloc(void)
 {
@@ -108,3 +110,27 @@ int msr_clear_bit(u32 msr, u8 bit)
 {
         return __flip_bit(msr, bit, false);
 }
+
+#ifdef CONFIG_TRACEPOINTS
+void do_trace_write_msr(unsigned msr, u64 val, int failed)
+{
+        trace_write_msr(msr, val, failed);
+}
+EXPORT_SYMBOL(do_trace_write_msr);
+EXPORT_TRACEPOINT_SYMBOL(write_msr);
+
+void do_trace_read_msr(unsigned msr, u64 val, int failed)
+{
+        trace_read_msr(msr, val, failed);
+}
+EXPORT_SYMBOL(do_trace_read_msr);
+EXPORT_TRACEPOINT_SYMBOL(read_msr);
+
+void do_trace_rdpmc(unsigned counter, u64 val, int failed)
+{
+        trace_rdpmc(counter, val, failed);
+}
+EXPORT_SYMBOL(do_trace_rdpmc);
+EXPORT_TRACEPOINT_SYMBOL(rdpmc);
+
+#endif
diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h
new file mode 100644
index 000000000000..e1ee97c713bf
--- /dev/null
+++ b/include/linux/tracepoint-defs.h
@@ -0,0 +1,27 @@
+#ifndef TRACEPOINT_DEFS_H
+#define TRACEPOINT_DEFS_H 1
+
+/*
+ * File can be included directly by headers who only want to access
+ * tracepoint->key to guard out of line trace calls. Otherwise
+ * linux/tracepoint.h should be used.
+ */
+
+#include <linux/atomic.h>
+#include <linux/static_key.h>
+
+struct tracepoint_func {
+        void *func;
+        void *data;
+        int prio;
+};
+
+struct tracepoint {
+        const char *name;               /* Tracepoint name */
+        struct static_key key;
+        void (*regfunc)(void);
+        void (*unregfunc)(void);
+        struct tracepoint_func __rcu *funcs;
+};
+
+#endif
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 7834a8a8bf1e..78e8397a1800 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -17,26 +17,12 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/rcupdate.h>
-#include <linux/static_key.h>
+#include <linux/tracepoint-defs.h>
 
 struct module;
 struct tracepoint;
 struct notifier_block;
 
-struct tracepoint_func {
-        void *func;
-        void *data;
-        int prio;
-};
-
-struct tracepoint {
-        const char *name;               /* Tracepoint name */
-        struct static_key key;
-        void (*regfunc)(void);
-        void (*unregfunc)(void);
-        struct tracepoint_func __rcu *funcs;
-};
-
 struct trace_enum_map {
         const char              *system;
         const char              *enum_string;
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index d801bb0d9f6d..1afe9623c1a7 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -171,6 +171,9 @@ enum perf_branch_sample_type_shift {
         PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT       = 12, /* indirect jumps */
         PERF_SAMPLE_BRANCH_CALL_SHIFT           = 13, /* direct call */
 
+        PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT       = 14, /* no flags */
+        PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT      = 15, /* no cycles */
+
         PERF_SAMPLE_BRANCH_MAX_SHIFT            /* non-ABI */
 };
 
@@ -192,6 +195,9 @@ enum perf_branch_sample_type {
         PERF_SAMPLE_BRANCH_IND_JUMP     = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT,
         PERF_SAMPLE_BRANCH_CALL         = 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT,
 
+        PERF_SAMPLE_BRANCH_NO_FLAGS     = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT,
+        PERF_SAMPLE_BRANCH_NO_CYCLES    = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT,
+
         PERF_SAMPLE_BRANCH_MAX          = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index cfc227ccfceb..bf8244190d0f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -126,6 +126,37 @@ static int cpu_function_call(int cpu, remote_function_f func, void *info)
         return data.ret;
 }
 
+static void event_function_call(struct perf_event *event,
+                                int (*active)(void *),
+                                void (*inactive)(void *),
+                                void *data)
+{
+        struct perf_event_context *ctx = event->ctx;
+        struct task_struct *task = ctx->task;
+
+        if (!task) {
+                cpu_function_call(event->cpu, active, data);
+                return;
+        }
+
+again:
+        if (!task_function_call(task, active, data))
+                return;
+
+        raw_spin_lock_irq(&ctx->lock);
+        if (ctx->is_active) {
+                /*
+                 * Reload the task pointer, it might have been changed by
+                 * a concurrent perf_event_context_sched_out().
+                 */
+                task = ctx->task;
+                raw_spin_unlock_irq(&ctx->lock);
+                goto again;
+        }
+        inactive(data);
+        raw_spin_unlock_irq(&ctx->lock);
+}
+
 #define EVENT_OWNER_KERNEL ((void *) -1)
 
 static bool is_kernel_event(struct perf_event *event)
@@ -1629,6 +1660,17 @@ struct remove_event {
         bool detach_group;
 };
 
+static void ___perf_remove_from_context(void *info)
+{
+        struct remove_event *re = info;
+        struct perf_event *event = re->event;
+        struct perf_event_context *ctx = event->ctx;
+
+        if (re->detach_group)
+                perf_group_detach(event);
+        list_del_event(event, ctx);
+}
+
 /*
  * Cross CPU call to remove a performance event
  *
@@ -1656,7 +1698,6 @@ static int __perf_remove_from_context(void *info)
         return 0;
 }
 
-
 /*
  * Remove the event from a task's (or a CPU's) list of events.
  *
@@ -1673,7 +1714,6 @@ static int __perf_remove_from_context(void *info)
 static void perf_remove_from_context(struct perf_event *event, bool detach_group)
 {
         struct perf_event_context *ctx = event->ctx;
-        struct task_struct *task = ctx->task;
         struct remove_event re = {
                 .event = event,
                 .detach_group = detach_group,
@@ -1681,44 +1721,8 @@ static void perf_remove_from_context(struct perf_event *event, bool detach_group
 
         lockdep_assert_held(&ctx->mutex);
 
-        if (!task) {
-                /*
-                 * Per cpu events are removed via an smp call. The removal can
-                 * fail if the CPU is currently offline, but in that case we
-                 * already called __perf_remove_from_context from
-                 * perf_event_exit_cpu.
-                 */
-                cpu_function_call(event->cpu, __perf_remove_from_context, &re);
-                return;
-        }
-
-retry:
-        if (!task_function_call(task, __perf_remove_from_context, &re))
-                return;
-
-        raw_spin_lock_irq(&ctx->lock);
-        /*
-         * If we failed to find a running task, but find the context active now
-         * that we've acquired the ctx->lock, retry.
-         */
-        if (ctx->is_active) {
-                raw_spin_unlock_irq(&ctx->lock);
-                /*
-                 * Reload the task pointer, it might have been changed by
-                 * a concurrent perf_event_context_sched_out().
-                 */
-                task = ctx->task;
-                goto retry;
-        }
-
-        /*
-         * Since the task isn't running, its safe to remove the event, us
-         * holding the ctx->lock ensures the task won't get scheduled in.
-         */
-        if (detach_group)
-                perf_group_detach(event);
-        list_del_event(event, ctx);
-        raw_spin_unlock_irq(&ctx->lock);
+        event_function_call(event, __perf_remove_from_context,
+                            ___perf_remove_from_context, &re);
 }
 
 /*
@@ -1762,6 +1766,20 @@ int __perf_event_disable(void *info)
         return 0;
 }
 
+void ___perf_event_disable(void *info)
+{
+        struct perf_event *event = info;
+
+        /*
+         * Since we have the lock this context can't be scheduled
+         * in, so we can change the state safely.
+         */
+        if (event->state == PERF_EVENT_STATE_INACTIVE) {
+                update_group_times(event);
+                event->state = PERF_EVENT_STATE_OFF;
+        }
+}
+
 /*
  * Disable a event.
  *
@@ -1778,43 +1796,16 @@ int __perf_event_disable(void *info)
 static void _perf_event_disable(struct perf_event *event)
 {
         struct perf_event_context *ctx = event->ctx;
-        struct task_struct *task = ctx->task;
-
-        if (!task) {
-                /*
-                 * Disable the event on the cpu that it's on
-                 */
-                cpu_function_call(event->cpu, __perf_event_disable, event);
-                return;
-        }
-
-retry:
-        if (!task_function_call(task, __perf_event_disable, event))
-                return;
 
         raw_spin_lock_irq(&ctx->lock);
-        /*
-         * If the event is still active, we need to retry the cross-call.
-         */
-        if (event->state == PERF_EVENT_STATE_ACTIVE) {
+        if (event->state <= PERF_EVENT_STATE_OFF) {
                 raw_spin_unlock_irq(&ctx->lock);
-                /*
-                 * Reload the task pointer, it might have been changed by
-                 * a concurrent perf_event_context_sched_out().
-                 */
-                task = ctx->task;
-                goto retry;
-        }
-
-        /*
-         * Since we have the lock this context can't be scheduled
-         * in, so we can change the state safely.
-         */
-        if (event->state == PERF_EVENT_STATE_INACTIVE) {
-                update_group_times(event);
-                event->state = PERF_EVENT_STATE_OFF;
+                return;
         }
         raw_spin_unlock_irq(&ctx->lock);
+
+        event_function_call(event, __perf_event_disable,
+                            ___perf_event_disable, event);
 }
 
 /*
@@ -2067,6 +2058,18 @@ static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
                 ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
 }
 
+static void ___perf_install_in_context(void *info)
+{
+        struct perf_event *event = info;
+        struct perf_event_context *ctx = event->ctx;
+
+        /*
+         * Since the task isn't running, its safe to add the event, us holding
+         * the ctx->lock ensures the task won't get scheduled in.
+         */
+        add_event_to_ctx(event, ctx);
+}
+
 /*
  * Cross CPU call to install and enable a performance event
  *
@@ -2143,48 +2146,14 @@ perf_install_in_context(struct perf_event_context *ctx,
                         struct perf_event *event,
                         int cpu)
 {
-        struct task_struct *task = ctx->task;
-
         lockdep_assert_held(&ctx->mutex);
 
         event->ctx = ctx;
         if (event->cpu != -1)
                 event->cpu = cpu;
 
-        if (!task) {
-                /*
-                 * Per cpu events are installed via an smp call and
-                 * the install is always successful.
-                 */
-                cpu_function_call(cpu, __perf_install_in_context, event);
-                return;
-        }
-
-retry:
-        if (!task_function_call(task, __perf_install_in_context, event))
-                return;
-
-        raw_spin_lock_irq(&ctx->lock);
-        /*
-         * If we failed to find a running task, but find the context active now
-         * that we've acquired the ctx->lock, retry.
-         */
-        if (ctx->is_active) {
-                raw_spin_unlock_irq(&ctx->lock);
-                /*
-                 * Reload the task pointer, it might have been changed by
-                 * a concurrent perf_event_context_sched_out().
-                 */
-                task = ctx->task;
-                goto retry;
-        }
-
-        /*
-         * Since the task isn't running, its safe to add the event, us holding
-         * the ctx->lock ensures the task won't get scheduled in.
-         */
-        add_event_to_ctx(event, ctx);
-        raw_spin_unlock_irq(&ctx->lock);
+        event_function_call(event, __perf_install_in_context,
+                            ___perf_install_in_context, event);
 }
 
 /*
@@ -2287,6 +2256,11 @@ unlock:
         return 0;
 }
 
+void ___perf_event_enable(void *info)
+{
+        __perf_event_mark_enabled((struct perf_event *)info);
+}
+
 /*
  * Enable a event.
  *
@@ -2299,58 +2273,26 @@ unlock:
 static void _perf_event_enable(struct perf_event *event)
 {
         struct perf_event_context *ctx = event->ctx;
-        struct task_struct *task = ctx->task;
 
-        if (!task) {
-                /*
-                 * Enable the event on the cpu that it's on
-                 */
-                cpu_function_call(event->cpu, __perf_event_enable, event);
+        raw_spin_lock_irq(&ctx->lock);
+        if (event->state >= PERF_EVENT_STATE_INACTIVE) {
+                raw_spin_unlock_irq(&ctx->lock);
                 return;
         }
 
-        raw_spin_lock_irq(&ctx->lock);
-        if (event->state >= PERF_EVENT_STATE_INACTIVE)
-                goto out;
-
         /*
          * If the event is in error state, clear that first.
-         * That way, if we see the event in error state below, we
-         * know that it has gone back into error state, as distinct
-         * from the task having been scheduled away before the
-         * cross-call arrived.
+         *
+         * That way, if we see the event in error state below, we know that it
+         * has gone back into error state, as distinct from the task having
+         * been scheduled away before the cross-call arrived.
          */
         if (event->state == PERF_EVENT_STATE_ERROR)
                 event->state = PERF_EVENT_STATE_OFF;
-
-retry:
-        if (!ctx->is_active) {
-                __perf_event_mark_enabled(event);
-                goto out;
-        }
-
         raw_spin_unlock_irq(&ctx->lock);
 
-        if (!task_function_call(task, __perf_event_enable, event))
-                return;
-
-        raw_spin_lock_irq(&ctx->lock);
-
-        /*
-         * If the context is active and the event is still off,
-         * we need to retry the cross-call.
-         */
-        if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF) {
-                /*
-                 * task could have been flipped by a concurrent
-                 * perf_event_context_sched_out()
-                 */
-                task = ctx->task;
-                goto retry;
-        }
-
-out:
-        raw_spin_unlock_irq(&ctx->lock);
+        event_function_call(event, __perf_event_enable,
+                            ___perf_event_enable, event);
 }
 
 /*
@@ -4149,6 +4091,22 @@ struct period_event {
         u64 value;
 };
 
+static void ___perf_event_period(void *info)
+{
+        struct period_event *pe = info;
+        struct perf_event *event = pe->event;
+        u64 value = pe->value;
+
+        if (event->attr.freq) {
+                event->attr.sample_freq = value;
+        } else {
+                event->attr.sample_period = value;
+                event->hw.sample_period = value;
+        }
+
+        local64_set(&event->hw.period_left, 0);
+}
+
 static int __perf_event_period(void *info)
 {
         struct period_event *pe = info;
@@ -4185,8 +4143,6 @@ static int __perf_event_period(void *info)
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
         struct period_event pe = { .event = event, };
-        struct perf_event_context *ctx = event->ctx;
-        struct task_struct *task;
         u64 value;
 
         if (!is_sampling_event(event))
@@ -4201,34 +4157,10 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
         if (event->attr.freq && value > sysctl_perf_event_sample_rate)
                 return -EINVAL;
 
-        task = ctx->task;
         pe.value = value;
 
-        if (!task) {
-                cpu_function_call(event->cpu, __perf_event_period, &pe);
-                return 0;
-        }
-
-retry:
-        if (!task_function_call(task, __perf_event_period, &pe))
-                return 0;
-
-        raw_spin_lock_irq(&ctx->lock);
-        if (ctx->is_active) {
-                raw_spin_unlock_irq(&ctx->lock);
-                task = ctx->task;
-                goto retry;
-        }
-
-        if (event->attr.freq) {
-                event->attr.sample_freq = value;
-        } else {
-                event->attr.sample_period = value;
-                event->hw.sample_period = value;
-        }
-
-        local64_set(&event->hw.period_left, 0);
-        raw_spin_unlock_irq(&ctx->lock);
+        event_function_call(event, __perf_event_period,
+                            ___perf_event_period, &pe);
 
         return 0;
 }
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
index 18e422b259cf..d62de8bf022d 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -16,6 +16,10 @@
 #include <linux/kernel.h>
 #include <linux/atomic.h>
 
+#ifdef CONFIG_X86
+#include <asm/processor.h>      /* for boot_cpu_has below */
+#endif
+
 #define TEST(bit, op, c_op, val)                                \
 do {                                                            \
         atomic##bit##_set(&v, v0);                              \
diff --git a/tools/Makefile b/tools/Makefile
index 7dc820a8c1f1..0ba0df3b516f 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -96,7 +96,7 @@ cgroup_install firewire_install hv_install lguest_install perf_install usb_insta
         $(call descend,$(@:_install=),install)
 
 selftests_install:
-        $(call descend,testing/$(@:_clean=),install)
+        $(call descend,testing/$(@:_install=),install)
 
 turbostat_install x86_energy_perf_policy_install:
         $(call descend,power/x86/$(@:_install=),install)
diff --git a/tools/build/Makefile b/tools/build/Makefile
index a93036272d43..0d5a0e3a8fa9 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -25,7 +25,7 @@ export Q srctree CC LD
 MAKEFLAGS := --no-print-directory
 build     := -f $(srctree)/tools/build/Makefile.build dir=. obj
 
-all: fixdep
+all: $(OUTPUT)fixdep
 
 clean:
         $(call QUIET_CLEAN, fixdep)
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 37ff4c9f92f1..02db3cdff20f 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -7,7 +7,7 @@ endif
 
 feature_check = $(eval $(feature_check_code))
 define feature_check_code
-  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) $(OUTPUT_FEATURES)test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
 endef
 
 feature_set = $(eval $(feature_set_code))
@@ -101,7 +101,6 @@ ifeq ($(feature-all), 1)
   #
   $(foreach feat,$(FEATURE_TESTS),$(call feature_set,$(feat)))
 else
-  $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS=$(LDFLAGS) -i -j -C $(feature_dir) $(addsuffix .bin,$(FEATURE_TESTS)) >/dev/null 2>&1)
   $(foreach feat,$(FEATURE_TESTS),$(call feature_check,$(feat)))
 endif
 
@@ -123,13 +122,31 @@ define feature_print_text_code
     MSG = $(shell printf '...%30s: %s' $(1) $(2))
 endef
 
+#
+# generates feature value assignment for name, like:
+#   $(call feature_assign,dwarf) == feature-dwarf=1
+#
+feature_assign = feature-$(1)=$(feature-$(1))
+
 FEATURE_DUMP_FILENAME = $(OUTPUT)FEATURE-DUMP$(FEATURE_USER)
-FEATURE_DUMP := $(foreach feat,$(FEATURE_DISPLAY),feature-$(feat)($(feature-$(feat))))
-FEATURE_DUMP_FILE := $(shell touch $(FEATURE_DUMP_FILENAME); cat $(FEATURE_DUMP_FILENAME))
+FEATURE_DUMP := $(shell touch $(FEATURE_DUMP_FILENAME); cat $(FEATURE_DUMP_FILENAME))
 
-ifeq ($(dwarf-post-unwind),1)
-  FEATURE_DUMP += dwarf-post-unwind($(dwarf-post-unwind-text))
-endif
+feature_dump_check = $(eval $(feature_dump_check_code))
+define feature_dump_check_code
+  ifeq ($(findstring $(1),$(FEATURE_DUMP)),)
+    $(2) := 1
+  endif
+endef
+
+#
+# First check if any test from FEATURE_DISPLAY
+# and set feature_display := 1 if it does
+$(foreach feat,$(FEATURE_DISPLAY),$(call feature_dump_check,$(call feature_assign,$(feat)),feature_display))
+
+#
+# Now also check if any other test changed,
+# so we force FEATURE-DUMP generation
+$(foreach feat,$(FEATURE_TESTS),$(call feature_dump_check,$(call feature_assign,$(feat)),feature_dump_changed))
 
 # The $(feature_display) controls the default detection message
 # output. It's set if:
@@ -138,13 +155,13 @@ endif
 # - one of the $(FEATURE_DISPLAY) is not detected
 # - VF is enabled
 
-ifneq ("$(FEATURE_DUMP)","$(FEATURE_DUMP_FILE)")
-  $(shell echo "$(FEATURE_DUMP)" > $(FEATURE_DUMP_FILENAME))
-  feature_display := 1
+ifeq ($(feature_dump_changed),1)
+  $(shell rm -f $(FEATURE_DUMP_FILENAME))
+  $(foreach feat,$(FEATURE_TESTS),$(shell echo "$(call feature_assign,$(feat))" >> $(FEATURE_DUMP_FILENAME)))
 endif
 
 feature_display_check = $(eval $(feature_check_display_code))
-define feature_display_check_code
+define feature_check_display_code
   ifneq ($(feature-$(1)), 1)
     feature_display := 1
   endif
@@ -161,11 +178,6 @@ ifeq ($(feature_display),1)
   $(info )
   $(info Auto-detecting system features:)
   $(foreach feat,$(FEATURE_DISPLAY),$(call feature_print_status,$(feat),))
-
-  ifeq ($(dwarf-post-unwind),1)
-    $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text))
-  endif
-
   ifneq ($(feature_verbose),1)
     $(info )
   endif
diff --git a/tools/build/Makefile.include b/tools/build/Makefile.include
index 4e09ad617a60..be630bed66d2 100644
--- a/tools/build/Makefile.include
+++ b/tools/build/Makefile.include
@@ -4,7 +4,7 @@ ifdef CROSS_COMPILE
 fixdep:
 else
 fixdep:
-        $(Q)$(MAKE) -C $(srctree)/tools/build fixdep
+        $(Q)$(MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= $(OUTPUT)fixdep
 endif
 
 .PHONY: fixdep
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index cea04ce9f35c..bf8f0352264d 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -1,4 +1,3 @@
-
 FILES=                                  \
         test-all.bin                    \
         test-backtrace.bin              \
@@ -38,38 +37,40 @@ FILES=					\
         test-bpf.bin                    \
         test-get_cpuid.bin
 
+FILES := $(addprefix $(OUTPUT),$(FILES))
+
 CC := $(CROSS_COMPILE)gcc -MD
 PKG_CONFIG := $(CROSS_COMPILE)pkg-config
 
 all: $(FILES)
 
-__BUILD = $(CC) $(CFLAGS) -Wall -Werror -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS)
-  BUILD = $(__BUILD) > $(OUTPUT)$(@:.bin=.make.output) 2>&1
+__BUILD = $(CC) $(CFLAGS) -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS)
+  BUILD = $(__BUILD) > $(@:.bin=.make.output) 2>&1
 
 ###############################
 
-test-all.bin:
+$(OUTPUT)test-all.bin:
         $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma
 
-test-hello.bin:
+$(OUTPUT)test-hello.bin:
         $(BUILD)
 
-test-pthread-attr-setaffinity-np.bin:
+$(OUTPUT)test-pthread-attr-setaffinity-np.bin:
         $(BUILD) -D_GNU_SOURCE -lpthread
 
-test-stackprotector-all.bin:
+$(OUTPUT)test-stackprotector-all.bin:
         $(BUILD) -fstack-protector-all
 
-test-fortify-source.bin:
+$(OUTPUT)test-fortify-source.bin:
         $(BUILD) -O2 -D_FORTIFY_SOURCE=2
 
-test-bionic.bin:
+$(OUTPUT)test-bionic.bin:
         $(BUILD)
 
-test-libelf.bin:
+$(OUTPUT)test-libelf.bin:
         $(BUILD) -lelf
 
-test-glibc.bin:
+$(OUTPUT)test-glibc.bin:
         $(BUILD)
 
 DWARFLIBS := -ldw
@@ -77,37 +78,37 @@ ifeq ($(findstring -static,${LDFLAGS}),-static)
 DWARFLIBS += -lelf -lebl -lz -llzma -lbz2
 endif
 
-test-dwarf.bin:
+$(OUTPUT)test-dwarf.bin:
         $(BUILD) $(DWARFLIBS)
 
-test-libelf-mmap.bin:
+$(OUTPUT)test-libelf-mmap.bin:
         $(BUILD) -lelf
 
-test-libelf-getphdrnum.bin:
+$(OUTPUT)test-libelf-getphdrnum.bin:
         $(BUILD) -lelf
 
-test-libnuma.bin:
+$(OUTPUT)test-libnuma.bin:
         $(BUILD) -lnuma
 
-test-numa_num_possible_cpus.bin:
+$(OUTPUT)test-numa_num_possible_cpus.bin:
         $(BUILD) -lnuma
 
-test-libunwind.bin:
+$(OUTPUT)test-libunwind.bin:
         $(BUILD) -lelf
 
-test-libunwind-debug-frame.bin:
+$(OUTPUT)test-libunwind-debug-frame.bin:
         $(BUILD) -lelf
 
-test-libaudit.bin:
+$(OUTPUT)test-libaudit.bin:
         $(BUILD) -laudit
 
-test-libslang.bin:
+$(OUTPUT)test-libslang.bin:
         $(BUILD) -I/usr/include/slang -lslang
 
-test-gtk2.bin:
+$(OUTPUT)test-gtk2.bin:
         $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
 
-test-gtk2-infobar.bin:
+$(OUTPUT)test-gtk2-infobar.bin:
         $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
 
 grep-libs  = $(filter -l%,$(1))
@@ -119,63 +120,63 @@ 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)
 
-test-libperl.bin:
+$(OUTPUT)test-libperl.bin:
         $(BUILD) $(FLAGS_PERL_EMBED)
 
-test-libpython.bin:
+$(OUTPUT)test-libpython.bin:
         $(BUILD)
 
-test-libpython-version.bin:
+$(OUTPUT)test-libpython-version.bin:
         $(BUILD)
 
-test-libbfd.bin:
+$(OUTPUT)test-libbfd.bin:
         $(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
 
-test-liberty.bin:
-        $(CC) $(CFLAGS) -Wall -Werror -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty
+$(OUTPUT)test-liberty.bin:
+        $(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty
 
-test-liberty-z.bin:
-        $(CC) $(CFLAGS) -Wall -Werror -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty -lz
+$(OUTPUT)test-liberty-z.bin:
+        $(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty -lz
 
-test-cplus-demangle.bin:
+$(OUTPUT)test-cplus-demangle.bin:
         $(BUILD) -liberty
 
-test-backtrace.bin:
+$(OUTPUT)test-backtrace.bin:
         $(BUILD)
 
-test-timerfd.bin:
+$(OUTPUT)test-timerfd.bin:
         $(BUILD)
 
-test-libdw-dwarf-unwind.bin:
+$(OUTPUT)test-libdw-dwarf-unwind.bin:
         $(BUILD) # -ldw provided by $(FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind)
 
-test-libbabeltrace.bin:
+$(OUTPUT)test-libbabeltrace.bin:
         $(BUILD) # -lbabeltrace provided by $(FEATURE_CHECK_LDFLAGS-libbabeltrace)
 
-test-sync-compare-and-swap.bin:
+$(OUTPUT)test-sync-compare-and-swap.bin:
         $(BUILD)
 
-test-compile-32.bin:
-        $(CC) -m32 -o $(OUTPUT)$@ test-compile.c
+$(OUTPUT)test-compile-32.bin:
+        $(CC) -m32 -o $@ test-compile.c
 
-test-compile-x32.bin:
-        $(CC) -mx32 -o $(OUTPUT)$@ test-compile.c
+$(OUTPUT)test-compile-x32.bin:
+        $(CC) -mx32 -o $@ test-compile.c
 
-test-zlib.bin:
+$(OUTPUT)test-zlib.bin:
         $(BUILD) -lz
 
-test-lzma.bin:
+$(OUTPUT)test-lzma.bin:
         $(BUILD) -llzma
 
-test-get_cpuid.bin:
+$(OUTPUT)test-get_cpuid.bin:
         $(BUILD)
 
-test-bpf.bin:
+$(OUTPUT)test-bpf.bin:
         $(BUILD)
 
--include *.d
+-include $(OUTPUT)*.d
 
 ###############################
 
 clean:
-        rm -f $(FILES) *.d $(FILES:.bin=.make.output)
+        rm -f $(FILES) $(OUTPUT)*.d $(FILES:.bin=.make.output)
diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index 40bd21488032..28f5493da491 100644
--- a/tools/perf/util/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -11,6 +11,8 @@ int __bitmap_weight(const unsigned long *bitmap, int bits);
 void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
                  const unsigned long *bitmap2, int bits);
 
+#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
+
 #define BITMAP_LAST_WORD_MASK(nbits)                                    \
 (                                                                       \
         ((nbits) % BITS_PER_LONG) ?                                     \
diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h
new file mode 100644
index 000000000000..e26223f1f287
--- /dev/null
+++ b/tools/include/linux/string.h
@@ -0,0 +1,15 @@
+#ifndef _TOOLS_LINUX_STRING_H_
+#define _TOOLS_LINUX_STRING_H_
+
+
+#include <linux/types.h>        /* for size_t */
+
+void *memdup(const void *src, size_t len);
+
+int strtobool(const char *s, bool *res);
+
+#ifndef __UCLIBC__
+extern size_t strlcpy(char *dest, const char *src, size_t size);
+#endif
+
+#endif /* _LINUX_STRING_H_ */
diff --git a/tools/perf/util/bitmap.c b/tools/lib/bitmap.c
index 0a1adc1111fd..0a1adc1111fd 100644
--- a/tools/perf/util/bitmap.c
+++ b/tools/lib/bitmap.c
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index a3caaf3eafbd..919b71780710 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -71,7 +71,21 @@ FEATURE_DISPLAY = libelf bpf
 INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi
 FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES)
 
+check_feat := 1
+NON_CHECK_FEAT_TARGETS := clean TAGS tags cscope help
+ifdef MAKECMDGOALS
+ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),)
+  check_feat := 0
+endif
+endif
+
+ifeq ($(check_feat),1)
+ifeq ($(FEATURES_DUMP),)
 include $(srctree)/tools/build/Makefile.feature
+else
+include $(FEATURES_DUMP)
+endif
+endif
 
 export prefix libdir src obj
 
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index a6331050ab79..5bdc6eab6852 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -83,3 +83,17 @@ int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
         log_buf[0] = 0;
         return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
 }
+
+int bpf_map_update_elem(int fd, void *key, void *value,
+                        u64 flags)
+{
+        union bpf_attr attr;
+
+        bzero(&attr, sizeof(attr));
+        attr.map_fd = fd;
+        attr.key = ptr_to_u64(key);
+        attr.value = ptr_to_u64(value);
+        attr.flags = flags;
+
+        return sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 854b7361b784..a76465541292 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -20,4 +20,6 @@ int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
                      u32 kern_version, char *log_buf,
                      size_t log_buf_sz);
 
+int bpf_map_update_elem(int fd, void *key, void *value,
+                        u64 flags);
 #endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e176bad19bcb..8334a5a9d5d7 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -152,29 +152,36 @@ struct bpf_program {
         } *reloc_desc;
         int nr_reloc;
 
-        int fd;
+        struct {
+                int nr;
+                int *fds;
+        } instances;
+        bpf_program_prep_t preprocessor;
 
         struct bpf_object *obj;
         void *priv;
         bpf_program_clear_priv_t clear_priv;
 };
 
+struct bpf_map {
+        int fd;
+        char *name;
+        struct bpf_map_def def;
+        void *priv;
+        bpf_map_clear_priv_t clear_priv;
+};
+
 static LIST_HEAD(bpf_objects_list);
 
 struct bpf_object {
         char license[64];
         u32 kern_version;
-        void *maps_buf;
-        size_t maps_buf_sz;
 
         struct bpf_program *programs;
         size_t nr_programs;
-        int *map_fds;
-        /*
-         * This field is required because maps_buf will be freed and
-         * maps_buf_sz will be set to 0 after loaded.
-         */
-        size_t nr_map_fds;
+        struct bpf_map *maps;
+        size_t nr_maps;
+
         bool loaded;
 
         /*
@@ -188,6 +195,7 @@ struct bpf_object {
                 Elf *elf;
                 GElf_Ehdr ehdr;
                 Elf_Data *symbols;
+                size_t strtabidx;
                 struct {
                         GElf_Shdr shdr;
                         Elf_Data *data;
@@ -206,10 +214,25 @@ struct bpf_object {
 
 static void bpf_program__unload(struct bpf_program *prog)
 {
+        int i;
+
         if (!prog)
                 return;
 
-        zclose(prog->fd);
+        /*
+         * If the object is opened but the program was never loaded,
+         * it is possible that prog->instances.nr == -1.
+         */
+        if (prog->instances.nr > 0) {
+                for (i = 0; i < prog->instances.nr; i++)
+                        zclose(prog->instances.fds[i]);
+        } else if (prog->instances.nr != -1) {
+                pr_warning("Internal error: instances.nr is %d\n",
+                           prog->instances.nr);
+        }
+
+        prog->instances.nr = -1;
+        zfree(&prog->instances.fds);
 }
 
 static void bpf_program__exit(struct bpf_program *prog)
@@ -260,7 +283,8 @@ bpf_program__init(void *data, size_t size, char *name, int idx,
         memcpy(prog->insns, data,
                prog->insns_cnt * sizeof(struct bpf_insn));
         prog->idx = idx;
-        prog->fd = -1;
+        prog->instances.fds = NULL;
+        prog->instances.nr = -1;
 
         return 0;
 errout:
@@ -469,21 +493,77 @@ static int
 bpf_object__init_maps(struct bpf_object *obj, void *data,
                       size_t size)
 {
-        if (size == 0) {
+        size_t nr_maps;
+        int i;
+
+        nr_maps = size / sizeof(struct bpf_map_def);
+        if (!data || !nr_maps) {
                 pr_debug("%s doesn't need map definition\n",
                          obj->path);
                 return 0;
         }
 
-        obj->maps_buf = malloc(size);
-        if (!obj->maps_buf) {
-                pr_warning("malloc maps failed: %s\n", obj->path);
+        pr_debug("maps in %s: %zd bytes\n", obj->path, size);
+
+        obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
+        if (!obj->maps) {
+                pr_warning("alloc maps for object failed\n");
                 return -ENOMEM;
         }
+        obj->nr_maps = nr_maps;
 
-        obj->maps_buf_sz = size;
-        memcpy(obj->maps_buf, data, size);
-        pr_debug("maps in %s: %ld bytes\n", obj->path, (long)size);
+        for (i = 0; i < nr_maps; i++) {
+                struct bpf_map_def *def = &obj->maps[i].def;
+
+                /*
+                 * fill all fd with -1 so won't close incorrect
+                 * fd (fd=0 is stdin) when failure (zclose won't close
+                 * negative fd)).
+                 */
+                obj->maps[i].fd = -1;
+
+                /* Save map definition into obj->maps */
+                *def = ((struct bpf_map_def *)data)[i];
+        }
+        return 0;
+}
+
+static int
+bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx)
+{
+        int i;
+        Elf_Data *symbols = obj->efile.symbols;
+
+        if (!symbols || maps_shndx < 0)
+                return -EINVAL;
+
+        for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+                GElf_Sym sym;
+                size_t map_idx;
+                const char *map_name;
+
+                if (!gelf_getsym(symbols, i, &sym))
+                        continue;
+                if (sym.st_shndx != maps_shndx)
+                        continue;
+
+                map_name = elf_strptr(obj->efile.elf,
+                                      obj->efile.strtabidx,
+                                      sym.st_name);
+                map_idx = sym.st_value / sizeof(struct bpf_map_def);
+                if (map_idx >= obj->nr_maps) {
+                        pr_warning("index of map \"%s\" is buggy: %zu > %zu\n",
+                                   map_name, map_idx, obj->nr_maps);
+                        continue;
+                }
+                obj->maps[map_idx].name = strdup(map_name);
+                if (!obj->maps[map_idx].name) {
+                        pr_warning("failed to alloc map name\n");
+                        return -ENOMEM;
+                }
+                pr_debug("map %zu is \"%s\"\n", map_idx,
+                         obj->maps[map_idx].name);
+        }
         return 0;
 }
 
@@ -492,7 +572,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
         Elf *elf = obj->efile.elf;
         GElf_Ehdr *ep = &obj->efile.ehdr;
         Elf_Scn *scn = NULL;
-        int idx = 0, err = 0;
+        int idx = 0, err = 0, maps_shndx = -1;
 
         /* Elf is corrupted/truncated, avoid calling elf_strptr. */
         if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
@@ -542,16 +622,19 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
                         err = bpf_object__init_kversion(obj,
                                                         data->d_buf,
                                                         data->d_size);
-                else if (strcmp(name, "maps") == 0)
+                else if (strcmp(name, "maps") == 0) {
                         err = bpf_object__init_maps(obj, data->d_buf,
                                                     data->d_size);
-                else if (sh.sh_type == SHT_SYMTAB) {
+                        maps_shndx = idx;
+                } else if (sh.sh_type == SHT_SYMTAB) {
                         if (obj->efile.symbols) {
                                 pr_warning("bpf: multiple SYMTAB in %s\n",
                                            obj->path);
                                 err = -LIBBPF_ERRNO__FORMAT;
-                        } else
+                        } else {
                                 obj->efile.symbols = data;
+                                obj->efile.strtabidx = sh.sh_link;
+                        }
                 } else if ((sh.sh_type == SHT_PROGBITS) &&
                            (sh.sh_flags & SHF_EXECINSTR) &&
                            (data->d_size > 0)) {
@@ -586,6 +669,13 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
                 if (err)
                         goto out;
         }
+
+        if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
+                pr_warning("Corrupted ELF file: index of strtab invalid\n");
+                return LIBBPF_ERRNO__FORMAT;
+        }
+        if (maps_shndx >= 0)
+                err = bpf_object__init_maps_name(obj, maps_shndx);
 out:
         return err;
 }
@@ -668,37 +758,15 @@ static int
 bpf_object__create_maps(struct bpf_object *obj)
 {
         unsigned int i;
-        size_t nr_maps;
-        int *pfd;
-
-        nr_maps = obj->maps_buf_sz / sizeof(struct bpf_map_def);
-        if (!obj->maps_buf || !nr_maps) {
-                pr_debug("don't need create maps for %s\n",
-                         obj->path);
-                return 0;
-        }
-
-        obj->map_fds = malloc(sizeof(int) * nr_maps);
-        if (!obj->map_fds) {
-                pr_warning("realloc perf_bpf_map_fds failed\n");
-                return -ENOMEM;
-        }
-        obj->nr_map_fds = nr_maps;
 
-        /* fill all fd with -1 */
-        memset(obj->map_fds, -1, sizeof(int) * nr_maps);
-
-        pfd = obj->map_fds;
-        for (i = 0; i < nr_maps; i++) {
-                struct bpf_map_def def;
+        for (i = 0; i < obj->nr_maps; i++) {
+                struct bpf_map_def *def = &obj->maps[i].def;
+                int *pfd = &obj->maps[i].fd;
 
-                def = *(struct bpf_map_def *)(obj->maps_buf +
-                                i * sizeof(struct bpf_map_def));
-
-                *pfd = bpf_create_map(def.type,
-                                      def.key_size,
-                                      def.value_size,
-                                      def.max_entries);
+                *pfd = bpf_create_map(def->type,
+                                      def->key_size,
+                                      def->value_size,
+                                      def->max_entries);
                 if (*pfd < 0) {
                         size_t j;
                         int err = *pfd;
@@ -706,22 +774,17 @@ bpf_object__create_maps(struct bpf_object *obj)
                         pr_warning("failed to create map: %s\n",
                                    strerror(errno));
                         for (j = 0; j < i; j++)
-                                zclose(obj->map_fds[j]);
-                        obj->nr_map_fds = 0;
-                        zfree(&obj->map_fds);
+                                zclose(obj->maps[j].fd);
                         return err;
                 }
                 pr_debug("create map: fd=%d\n", *pfd);
-                pfd++;
         }
 
-        zfree(&obj->maps_buf);
-        obj->maps_buf_sz = 0;
         return 0;
 }
 
 static int
-bpf_program__relocate(struct bpf_program *prog, int *map_fds)
+bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
 {
         int i;
 
@@ -741,7 +804,7 @@ bpf_program__relocate(struct bpf_program *prog, int *map_fds)
                         return -LIBBPF_ERRNO__RELOC;
                 }
                 insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
-                insns[insn_idx].imm = map_fds[map_idx];
+                insns[insn_idx].imm = obj->maps[map_idx].fd;
         }
 
         zfree(&prog->reloc_desc);
@@ -760,7 +823,7 @@ bpf_object__relocate(struct bpf_object *obj)
         for (i = 0; i < obj->nr_programs; i++) {
                 prog = &obj->programs[i];
 
-                err = bpf_program__relocate(prog, obj->map_fds);
+                err = bpf_program__relocate(prog, obj);
                 if (err) {
                         pr_warning("failed to relocate '%s'\n",
                                    prog->section_name);
@@ -784,8 +847,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
                 Elf_Data *data = obj->efile.reloc[i].data;
                 int idx = shdr->sh_info;
                 struct bpf_program *prog;
-                size_t nr_maps = obj->maps_buf_sz /
-                                 sizeof(struct bpf_map_def);
+                size_t nr_maps = obj->nr_maps;
 
                 if (shdr->sh_type != SHT_REL) {
                         pr_warning("internal error at %d\n", __LINE__);
@@ -860,13 +922,73 @@ static int
 bpf_program__load(struct bpf_program *prog,
                   char *license, u32 kern_version)
 {
-        int err, fd;
+        int err = 0, fd, i;
 
-        err = load_program(prog->insns, prog->insns_cnt,
-                           license, kern_version, &fd);
-        if (!err)
-                prog->fd = fd;
+        if (prog->instances.nr < 0 || !prog->instances.fds) {
+                if (prog->preprocessor) {
+                        pr_warning("Internal error: can't load program '%s'\n",
+                                   prog->section_name);
+                        return -LIBBPF_ERRNO__INTERNAL;
+                }
+
+                prog->instances.fds = malloc(sizeof(int));
+                if (!prog->instances.fds) {
+                        pr_warning("Not enough memory for BPF fds\n");
+                        return -ENOMEM;
+                }
+                prog->instances.nr = 1;
+                prog->instances.fds[0] = -1;
+        }
+
+        if (!prog->preprocessor) {
+                if (prog->instances.nr != 1) {
+                        pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
+                                   prog->section_name, prog->instances.nr);
+                }
+                err = load_program(prog->insns, prog->insns_cnt,
+                                   license, kern_version, &fd);
+                if (!err)
+                        prog->instances.fds[0] = fd;
+                goto out;
+        }
+
+        for (i = 0; i < prog->instances.nr; i++) {
+                struct bpf_prog_prep_result result;
+                bpf_program_prep_t preprocessor = prog->preprocessor;
+
+                bzero(&result, sizeof(result));
+                err = preprocessor(prog, i, prog->insns,
+                                   prog->insns_cnt, &result);
+                if (err) {
+                        pr_warning("Preprocessing the %dth instance of program '%s' failed\n",
+                                   i, prog->section_name);
+                        goto out;
+                }
+
+                if (!result.new_insn_ptr || !result.new_insn_cnt) {
+                        pr_debug("Skip loading the %dth instance of program '%s'\n",
+                                 i, prog->section_name);
+                        prog->instances.fds[i] = -1;
+                        if (result.pfd)
+                                *result.pfd = -1;
+                        continue;
+                }
+
+                err = load_program(result.new_insn_ptr,
+                                   result.new_insn_cnt,
+                                   license, kern_version, &fd);
+
+                if (err) {
+                        pr_warning("Loading the %dth instance of program '%s' failed\n",
+                                        i, prog->section_name);
+                        goto out;
+                }
 
+                if (result.pfd)
+                        *result.pfd = fd;
+                prog->instances.fds[i] = fd;
+        }
+out:
         if (err)
                 pr_warning("failed to load program '%s'\n",
                            prog->section_name);
@@ -970,10 +1092,8 @@ int bpf_object__unload(struct bpf_object *obj)
         if (!obj)
                 return -EINVAL;
 
-        for (i = 0; i < obj->nr_map_fds; i++)
-                zclose(obj->map_fds[i]);
-        zfree(&obj->map_fds);
-        obj->nr_map_fds = 0;
+        for (i = 0; i < obj->nr_maps; i++)
+                zclose(obj->maps[i].fd);
 
         for (i = 0; i < obj->nr_programs; i++)
                 bpf_program__unload(&obj->programs[i]);
@@ -1016,7 +1136,16 @@ void bpf_object__close(struct bpf_object *obj)
         bpf_object__elf_finish(obj);
         bpf_object__unload(obj);
 
-        zfree(&obj->maps_buf);
+        for (i = 0; i < obj->nr_maps; i++) {
+                zfree(&obj->maps[i].name);
+                if (obj->maps[i].clear_priv)
+                        obj->maps[i].clear_priv(&obj->maps[i],
+                                                obj->maps[i].priv);
+                obj->maps[i].priv = NULL;
+                obj->maps[i].clear_priv = NULL;
+        }
+        zfree(&obj->maps);
+        obj->nr_maps = 0;
 
         if (obj->programs && obj->nr_programs) {
                 for (i = 0; i < obj->nr_programs; i++)
@@ -1121,5 +1250,142 @@ const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
 
 int bpf_program__fd(struct bpf_program *prog)
 {
-        return prog->fd;
+        return bpf_program__nth_fd(prog, 0);
+}
+
+int bpf_program__set_prep(struct bpf_program *prog, int nr_instances,
+                          bpf_program_prep_t prep)
+{
+        int *instances_fds;
+
+        if (nr_instances <= 0 || !prep)
+                return -EINVAL;
+
+        if (prog->instances.nr > 0 || prog->instances.fds) {
+                pr_warning("Can't set pre-processor after loading\n");
+                return -EINVAL;
+        }
+
+        instances_fds = malloc(sizeof(int) * nr_instances);
+        if (!instances_fds) {
+                pr_warning("alloc memory failed for fds\n");
+                return -ENOMEM;
+        }
+
+        /* fill all fd with -1 */
+        memset(instances_fds, -1, sizeof(int) * nr_instances);
+
+        prog->instances.nr = nr_instances;
+        prog->instances.fds = instances_fds;
+        prog->preprocessor = prep;
+        return 0;
+}
+
+int bpf_program__nth_fd(struct bpf_program *prog, int n)
+{
+        int fd;
+
+        if (n >= prog->instances.nr || n < 0) {
+                pr_warning("Can't get the %dth fd from program %s: only %d instances\n",
+                           n, prog->section_name, prog->instances.nr);
+                return -EINVAL;
+        }
+
+        fd = prog->instances.fds[n];
+        if (fd < 0) {
+                pr_warning("%dth instance of program '%s' is invalid\n",
+                           n, prog->section_name);
+                return -ENOENT;
+        }
+
+        return fd;
+}
+
+int bpf_map__get_fd(struct bpf_map *map)
+{
+        if (!map)
+                return -EINVAL;
+
+        return map->fd;
+}
+
+int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef)
+{
+        if (!map || !pdef)
+                return -EINVAL;
+
+        *pdef = map->def;
+        return 0;
+}
+
+const char *bpf_map__get_name(struct bpf_map *map)
+{
+        if (!map)
+                return NULL;
+        return map->name;
+}
+
+int bpf_map__set_private(struct bpf_map *map, void *priv,
+                         bpf_map_clear_priv_t clear_priv)
+{
+        if (!map)
+                return -EINVAL;
+
+        if (map->priv) {
+                if (map->clear_priv)
+                        map->clear_priv(map, map->priv);
+        }
+
+        map->priv = priv;
+        map->clear_priv = clear_priv;
+        return 0;
+}
+
+int bpf_map__get_private(struct bpf_map *map, void **ppriv)
+{
+        if (!map)
+                return -EINVAL;
+
+        if (ppriv)
+                *ppriv = map->priv;
+        return 0;
+}
+
+struct bpf_map *
+bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
+{
+        size_t idx;
+        struct bpf_map *s, *e;
+
+        if (!obj || !obj->maps)
+                return NULL;
+
+        s = obj->maps;
+        e = obj->maps + obj->nr_maps;
+
+        if (prev == NULL)
+                return s;
+
+        if ((prev < s) || (prev >= e)) {
+                pr_warning("error in %s: map handler doesn't belong to object\n",
+                           __func__);
+                return NULL;
+        }
+
+        idx = (prev - obj->maps) + 1;
+        if (idx >= obj->nr_maps)
+                return NULL;
+        return &obj->maps[idx];
+}
+
+struct bpf_map *
+bpf_object__get_map_by_name(struct bpf_object *obj, const char *name)
+{
+        struct bpf_map *pos;
+
+        bpf_map__for_each(pos, obj) {
+                if (pos->name && !strcmp(pos->name, name))
+                        return pos;
+        }
+        return NULL;
 }
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index c9a9aef2806c..a51594c7b518 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -88,6 +88,70 @@ const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
 
 int bpf_program__fd(struct bpf_program *prog);
 
+struct bpf_insn;
+
+/*
+ * Libbpf allows callers to adjust BPF programs before being loaded
+ * into kernel. One program in an object file can be transform into
+ * multiple variants to be attached to different code.
+ *
+ * bpf_program_prep_t, bpf_program__set_prep and bpf_program__nth_fd
+ * are APIs for this propose.
+ *
+ * - bpf_program_prep_t:
+ *   It defines 'preprocessor', which is a caller defined function
+ *   passed to libbpf through bpf_program__set_prep(), and will be
+ *   called before program is loaded. The processor should adjust
+ *   the program one time for each instances according to the number
+ *   passed to it.
+ *
+ * - bpf_program__set_prep:
+ *   Attachs a preprocessor to a BPF program. The number of instances
+ *   whould be created is also passed through this function.
+ *
+ * - bpf_program__nth_fd:
+ *   After the program is loaded, get resuling fds from bpf program for
+ *   each instances.
+ *
+ * If bpf_program__set_prep() is not used, the program whould be loaded
+ * without adjustment during bpf_object__load(). The program has only
+ * one instance. In this case bpf_program__fd(prog) is equal to
+ * bpf_program__nth_fd(prog, 0).
+ */
+
+struct bpf_prog_prep_result {
+        /*
+         * If not NULL, load new instruction array.
+         * If set to NULL, don't load this instance.
+         */
+        struct bpf_insn *new_insn_ptr;
+        int new_insn_cnt;
+
+        /* If not NULL, result fd is set to it */
+        int *pfd;
+};
+
+/*
+ * Parameters of bpf_program_prep_t:
+ *  - prog:     The bpf_program being loaded.
+ *  - n:        Index of instance being generated.
+ *  - insns:    BPF instructions array.
+ *  - insns_cnt:Number of instructions in insns.
+ *  - res:      Output parameter, result of transformation.
+ *
+ * Return value:
+ *  - Zero: pre-processing success.
+ *  - Non-zero: pre-processing, stop loading.
+ */
+typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n,
+                                  struct bpf_insn *insns, int insns_cnt,
+                                  struct bpf_prog_prep_result *res);
+
+int bpf_program__set_prep(struct bpf_program *prog, int nr_instance,
+                          bpf_program_prep_t prep);
+
+int bpf_program__nth_fd(struct bpf_program *prog, int n);
+
 /*
  * We don't need __attribute__((packed)) now since it is
  * unnecessary for 'bpf_map_def' because they are all aligned.
@@ -101,4 +165,28 @@ struct bpf_map_def {
         unsigned int max_entries;
 };
 
+/*
+ * There is another 'struct bpf_map' in include/linux/map.h. However,
+ * it is not a uapi header so no need to consider name clash.
+ */
+struct bpf_map;
+struct bpf_map *
+bpf_object__get_map_by_name(struct bpf_object *obj, const char *name);
+
+struct bpf_map *
+bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
+#define bpf_map__for_each(pos, obj)             \
+        for ((pos) = bpf_map__next(NULL, (obj));        \
+             (pos) != NULL;                             \
+             (pos) = bpf_map__next((pos), (obj)))
+
+int bpf_map__get_fd(struct bpf_map *map);
+int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef);
+const char *bpf_map__get_name(struct bpf_map *map);
+
+typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
+int bpf_map__set_private(struct bpf_map *map, void *priv,
+                         bpf_map_clear_priv_t clear_priv);
+int bpf_map__get_private(struct bpf_map *map, void **ppriv);
+
 #endif
diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c
new file mode 100644
index 000000000000..9122a9e80046
--- /dev/null
+++ b/tools/lib/find_bit.c
@@ -0,0 +1,84 @@
+/* bit search implementation
+ *
+ * Copied from lib/find_bit.c to tools/lib/find_bit.c
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * Copyright (C) 2008 IBM Corporation
+ * 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au>
+ * (Inspired by David Howell's find_next_bit implementation)
+ *
+ * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease
+ * size and improve performance, 2015.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/bitops.h>
+#include <linux/bitmap.h>
+#include <linux/kernel.h>
+
+#if !defined(find_next_bit)
+
+/*
+ * This is a common helper function for find_next_bit and
+ * find_next_zero_bit.  The difference is the "invert" argument, which
+ * is XORed with each fetched word before searching it for one bits.
+ */
+static unsigned long _find_next_bit(const unsigned long *addr,
+                unsigned long nbits, unsigned long start, unsigned long invert)
+{
+        unsigned long tmp;
+
+        if (!nbits || start >= nbits)
+                return nbits;
+
+        tmp = addr[start / BITS_PER_LONG] ^ invert;
+
+        /* Handle 1st word. */
+        tmp &= BITMAP_FIRST_WORD_MASK(start);
+        start = round_down(start, BITS_PER_LONG);
+
+        while (!tmp) {
+                start += BITS_PER_LONG;
+                if (start >= nbits)
+                        return nbits;
+
+                tmp = addr[start / BITS_PER_LONG] ^ invert;
+        }
+
+        return min(start + __ffs(tmp), nbits);
+}
+#endif
+
+#ifndef find_next_bit
+/*
+ * Find the next set bit in a memory region.
+ */
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+                            unsigned long offset)
+{
+        return _find_next_bit(addr, size, offset, 0UL);
+}
+#endif
+
+#ifndef find_first_bit
+/*
+ * Find the first set bit in a memory region.
+ */
+unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
+{
+        unsigned long idx;
+
+        for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
+                if (addr[idx])
+                        return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size);
+        }
+
+        return size;
+}
+#endif
diff --git a/tools/lib/string.c b/tools/lib/string.c
new file mode 100644
index 000000000000..bd239bc1d557
--- /dev/null
+++ b/tools/lib/string.c
@@ -0,0 +1,89 @@
+/*
+ *  linux/tools/lib/string.c
+ *
+ *  Copied from linux/lib/string.c, where it is:
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  More specifically, the first copied function was strtobool, which
+ *  was introduced by:
+ *
+ *  d0f1fed29e6e ("Add a strtobool function matching semantics of existing in kernel equivalents")
+ *  Author: Jonathan Cameron <jic23@cam.ac.uk>
+ */
+
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <linux/string.h>
+#include <linux/compiler.h>
+
+/**
+ * memdup - duplicate region of memory
+ *
+ * @src: memory region to duplicate
+ * @len: memory region length
+ */
+void *memdup(const void *src, size_t len)
+{
+        void *p = malloc(len);
+
+        if (p)
+                memcpy(p, src, len);
+
+        return p;
+}
+
+/**
+ * strtobool - convert common user inputs into boolean values
+ * @s: input string
+ * @res: result
+ *
+ * This routine returns 0 iff the first character is one of 'Yy1Nn0'.
+ * Otherwise it will return -EINVAL.  Value pointed to by res is
+ * updated upon finding a match.
+ */
+int strtobool(const char *s, bool *res)
+{
+        switch (s[0]) {
+        case 'y':
+        case 'Y':
+        case '1':
+                *res = true;
+                break;
+        case 'n':
+        case 'N':
+        case '0':
+                *res = false;
+                break;
+        default:
+                return -EINVAL;
+        }
+        return 0;
+}
+
+/**
+ * strlcpy - Copy a C-string into a sized buffer
+ * @dest: Where to copy the string to
+ * @src: Where to copy the string from
+ * @size: size of destination buffer
+ *
+ * Compatible with *BSD: the result is always a valid
+ * NUL-terminated string that fits in the buffer (unless,
+ * of course, the buffer size is zero). It does not pad
+ * out the result like strncpy() does.
+ *
+ * If libc has strlcpy() then that version will override this
+ * implementation:
+ */
+size_t __weak strlcpy(char *dest, const char *src, size_t size)
+{
+        size_t ret = strlen(src);
+
+        if (size) {
+                size_t len = (ret >= size) ? size - 1 : ret;
+                memcpy(dest, src, len);
+                dest[len] = '\0';
+        }
+        return ret;
+}
diff --git a/tools/lib/subcmd/Build b/tools/lib/subcmd/Build
new file mode 100644
index 000000000000..ee31288788c1
--- /dev/null
+++ b/tools/lib/subcmd/Build
@@ -0,0 +1,7 @@
+libsubcmd-y += exec-cmd.o
+libsubcmd-y += help.o
+libsubcmd-y += pager.o
+libsubcmd-y += parse-options.o
+libsubcmd-y += run-command.o
+libsubcmd-y += sigchain.o
+libsubcmd-y += subcmd-config.o
diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile
new file mode 100644
index 000000000000..629cf8c14e68
--- /dev/null
+++ b/tools/lib/subcmd/Makefile
@@ -0,0 +1,48 @@
+include ../../scripts/Makefile.include
+include ../../perf/config/utilities.mak         # QUIET_CLEAN
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
+RM = rm -f
+
+MAKEFLAGS += --no-print-directory
+
+LIBFILE = $(OUTPUT)libsubcmd.a
+
+CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+
+CFLAGS += -I$(srctree)/tools/include/
+CFLAGS += -I$(srctree)/include/uapi
+CFLAGS += -I$(srctree)/include
+
+SUBCMD_IN := $(OUTPUT)libsubcmd-in.o
+
+all:
+
+export srctree OUTPUT CC LD CFLAGS V
+include $(srctree)/tools/build/Makefile.include
+
+all: fixdep $(LIBFILE)
+
+$(SUBCMD_IN): FORCE
+        @$(MAKE) $(build)=libsubcmd
+
+$(LIBFILE): $(SUBCMD_IN)
+        $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(SUBCMD_IN)
+
+clean:
+        $(call QUIET_CLEAN, libsubcmd) $(RM) $(LIBFILE); \
+        find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM)
+
+FORCE:
+
+.PHONY: clean FORCE
diff --git a/tools/lib/subcmd/exec-cmd.c b/tools/lib/subcmd/exec-cmd.c
new file mode 100644
index 000000000000..1ae833af1a4a
--- /dev/null
+++ b/tools/lib/subcmd/exec-cmd.c
@@ -0,0 +1,209 @@
+#include <linux/compiler.h>
+#include <linux/string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "subcmd-util.h"
+#include "exec-cmd.h"
+#include "subcmd-config.h"
+
+#define MAX_ARGS        32
+#define PATH_MAX        4096
+
+static const char *argv_exec_path;
+static const char *argv0_path;
+
+void exec_cmd_init(const char *exec_name, const char *prefix,
+                   const char *exec_path, const char *exec_path_env)
+{
+        subcmd_config.exec_name         = exec_name;
+        subcmd_config.prefix            = prefix;
+        subcmd_config.exec_path         = exec_path;
+        subcmd_config.exec_path_env     = exec_path_env;
+}
+
+#define is_dir_sep(c) ((c) == '/')
+
+static int is_absolute_path(const char *path)
+{
+        return path[0] == '/';
+}
+
+static const char *get_pwd_cwd(void)
+{
+        static char cwd[PATH_MAX + 1];
+        char *pwd;
+        struct stat cwd_stat, pwd_stat;
+        if (getcwd(cwd, PATH_MAX) == NULL)
+                return NULL;
+        pwd = getenv("PWD");
+        if (pwd && strcmp(pwd, cwd)) {
+                stat(cwd, &cwd_stat);
+                if (!stat(pwd, &pwd_stat) &&
+                    pwd_stat.st_dev == cwd_stat.st_dev &&
+                    pwd_stat.st_ino == cwd_stat.st_ino) {
+                        strlcpy(cwd, pwd, PATH_MAX);
+                }
+        }
+        return cwd;
+}
+
+static const char *make_nonrelative_path(const char *path)
+{
+        static char buf[PATH_MAX + 1];
+
+        if (is_absolute_path(path)) {
+                if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX)
+                        die("Too long path: %.*s", 60, path);
+        } else {
+                const char *cwd = get_pwd_cwd();
+                if (!cwd)
+                        die("Cannot determine the current working directory");
+                if (snprintf(buf, PATH_MAX, "%s/%s", cwd, path) >= PATH_MAX)
+                        die("Too long path: %.*s", 60, path);
+        }
+        return buf;
+}
+
+char *system_path(const char *path)
+{
+        char *buf = NULL;
+
+        if (is_absolute_path(path))
+                return strdup(path);
+
+        astrcatf(&buf, "%s/%s", subcmd_config.prefix, path);
+
+        return buf;
+}
+
+const char *extract_argv0_path(const char *argv0)
+{
+        const char *slash;
+
+        if (!argv0 || !*argv0)
+                return NULL;
+        slash = argv0 + strlen(argv0);
+
+        while (argv0 <= slash && !is_dir_sep(*slash))
+                slash--;
+
+        if (slash >= argv0) {
+                argv0_path = strndup(argv0, slash - argv0);
+                return argv0_path ? slash + 1 : NULL;
+        }
+
+        return argv0;
+}
+
+void set_argv_exec_path(const char *exec_path)
+{
+        argv_exec_path = exec_path;
+        /*
+         * Propagate this setting to external programs.
+         */
+        setenv(subcmd_config.exec_path_env, exec_path, 1);
+}
+
+
+/* Returns the highest-priority location to look for subprograms. */
+char *get_argv_exec_path(void)
+{
+        char *env;
+
+        if (argv_exec_path)
+                return strdup(argv_exec_path);
+
+        env = getenv(subcmd_config.exec_path_env);
+        if (env && *env)
+                return strdup(env);
+
+        return system_path(subcmd_config.exec_path);
+}
+
+static void add_path(char **out, const char *path)
+{
+        if (path && *path) {
+                if (is_absolute_path(path))
+                        astrcat(out, path);
+                else
+                        astrcat(out, make_nonrelative_path(path));
+
+                astrcat(out, ":");
+        }
+}
+
+void setup_path(void)
+{
+        const char *old_path = getenv("PATH");
+        char *new_path = NULL;
+        char *tmp = get_argv_exec_path();
+
+        add_path(&new_path, tmp);
+        add_path(&new_path, argv0_path);
+        free(tmp);
+
+        if (old_path)
+                astrcat(&new_path, old_path);
+        else
+                astrcat(&new_path, "/usr/local/bin:/usr/bin:/bin");
+
+        setenv("PATH", new_path, 1);
+
+        free(new_path);
+}
+
+static const char **prepare_exec_cmd(const char **argv)
+{
+        int argc;
+        const char **nargv;
+
+        for (argc = 0; argv[argc]; argc++)
+                ; /* just counting */
+        nargv = malloc(sizeof(*nargv) * (argc + 2));
+
+        nargv[0] = subcmd_config.exec_name;
+        for (argc = 0; argv[argc]; argc++)
+                nargv[argc + 1] = argv[argc];
+        nargv[argc + 1] = NULL;
+        return nargv;
+}
+
+int execv_cmd(const char **argv) {
+        const char **nargv = prepare_exec_cmd(argv);
+
+        /* execvp() can only ever return if it fails */
+        execvp(subcmd_config.exec_name, (char **)nargv);
+
+        free(nargv);
+        return -1;
+}
+
+
+int execl_cmd(const char *cmd,...)
+{
+        int argc;
+        const char *argv[MAX_ARGS + 1];
+        const char *arg;
+        va_list param;
+
+        va_start(param, cmd);
+        argv[0] = cmd;
+        argc = 1;
+        while (argc < MAX_ARGS) {
+                arg = argv[argc++] = va_arg(param, char *);
+                if (!arg)
+                        break;
+        }
+        va_end(param);
+        if (MAX_ARGS <= argc) {
+                fprintf(stderr, " Error: too many args to run %s\n", cmd);
+                return -1;
+        }
+
+        argv[argc] = NULL;
+        return execv_cmd(argv);
+}
diff --git a/tools/lib/subcmd/exec-cmd.h b/tools/lib/subcmd/exec-cmd.h
new file mode 100644
index 000000000000..5d08bda31d90
--- /dev/null
+++ b/tools/lib/subcmd/exec-cmd.h
@@ -0,0 +1,16 @@
+#ifndef __SUBCMD_EXEC_CMD_H
+#define __SUBCMD_EXEC_CMD_H
+
+extern void exec_cmd_init(const char *exec_name, const char *prefix,
+                          const char *exec_path, const char *exec_path_env);
+
+extern void set_argv_exec_path(const char *exec_path);
+extern const char *extract_argv0_path(const char *path);
+extern void setup_path(void);
+extern int execv_cmd(const char **argv); /* NULL terminated */
+extern int execl_cmd(const char *cmd, ...);
+/* get_argv_exec_path and system_path return malloc'd string, caller must free it */
+extern char *get_argv_exec_path(void);
+extern char *system_path(const char *path);
+
+#endif /* __SUBCMD_EXEC_CMD_H */
diff --git a/tools/perf/util/help.c b/tools/lib/subcmd/help.c
index 86c37c472263..e228c3cb3716 100644
--- a/tools/perf/util/help.c
+++ b/tools/lib/subcmd/help.c
@@ -1,9 +1,15 @@
-#include "cache.h"
-#include "../builtin.h"
-#include "exec_cmd.h"
-#include "levenshtein.h"
-#include "help.h"
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
 #include <termios.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <dirent.h>
+#include "subcmd-util.h"
+#include "help.h"
+#include "exec-cmd.h"
 
 void add_cmdname(struct cmdnames *cmds, const char *name, size_t len)
 {
@@ -17,7 +23,7 @@ void add_cmdname(struct cmdnames *cmds, const char *name, size_t len)
         cmds->names[cmds->cnt++] = ent;
 }
 
-static void clean_cmdnames(struct cmdnames *cmds)
+void clean_cmdnames(struct cmdnames *cmds)
 {
         unsigned int i;
 
@@ -28,14 +34,14 @@ static void clean_cmdnames(struct cmdnames *cmds)
         cmds->alloc = 0;
 }
 
-static int cmdname_compare(const void *a_, const void *b_)
+int cmdname_compare(const void *a_, const void *b_)
 {
         struct cmdname *a = *(struct cmdname **)a_;
         struct cmdname *b = *(struct cmdname **)b_;
         return strcmp(a->name, b->name);
 }
 
-static void uniq(struct cmdnames *cmds)
+void uniq(struct cmdnames *cmds)
 {
         unsigned int i, j;
 
@@ -71,6 +77,28 @@ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
         cmds->cnt = cj;
 }
 
+static void get_term_dimensions(struct winsize *ws)
+{
+        char *s = getenv("LINES");
+
+        if (s != NULL) {
+                ws->ws_row = atoi(s);
+                s = getenv("COLUMNS");
+                if (s != NULL) {
+                        ws->ws_col = atoi(s);
+                        if (ws->ws_row && ws->ws_col)
+                                return;
+                }
+        }
+#ifdef TIOCGWINSZ
+        if (ioctl(1, TIOCGWINSZ, ws) == 0 &&
+            ws->ws_row && ws->ws_col)
+                return;
+#endif
+        ws->ws_row = 25;
+        ws->ws_col = 80;
+}
+
 static void pretty_print_string_list(struct cmdnames *cmds, int longest)
 {
         int cols = 1, rows;
@@ -114,6 +142,14 @@ static int is_executable(const char *name)
         return st.st_mode & S_IXUSR;
 }
 
+static int has_extension(const char *filename, const char *ext)
+{
+        size_t len = strlen(filename);
+        size_t extlen = strlen(ext);
+
+        return len > extlen && !memcmp(filename + len - extlen, ext, extlen);
+}
+
 static void list_commands_in_dir(struct cmdnames *cmds,
                                          const char *path,
                                          const char *prefix)
@@ -121,8 +157,7 @@ static void list_commands_in_dir(struct cmdnames *cmds,
         int prefix_len;
         DIR *dir = opendir(path);
         struct dirent *de;
-        struct strbuf buf = STRBUF_INIT;
-        int len;
+        char *buf = NULL;
 
         if (!dir)
                 return;
@@ -130,8 +165,7 @@ static void list_commands_in_dir(struct cmdnames *cmds,
                 prefix = "perf-";
         prefix_len = strlen(prefix);
 
-        strbuf_addf(&buf, "%s/", path);
-        len = buf.len;
+        astrcatf(&buf, "%s/", path);
 
         while ((de = readdir(dir)) != NULL) {
                 int entlen;
@@ -139,9 +173,8 @@ static void list_commands_in_dir(struct cmdnames *cmds,
                 if (prefixcmp(de->d_name, prefix))
                         continue;
 
-                strbuf_setlen(&buf, len);
-                strbuf_addstr(&buf, de->d_name);
-                if (!is_executable(buf.buf))
+                astrcat(&buf, de->d_name);
+                if (!is_executable(buf))
                         continue;
 
                 entlen = strlen(de->d_name) - prefix_len;
@@ -151,7 +184,7 @@ static void list_commands_in_dir(struct cmdnames *cmds,
                 add_cmdname(cmds, de->d_name + prefix_len, entlen);
         }
         closedir(dir);
-        strbuf_release(&buf);
+        free(buf);
 }
 
 void load_command_list(const char *prefix,
@@ -159,7 +192,7 @@ void load_command_list(const char *prefix,
                 struct cmdnames *other_cmds)
 {
         const char *env_path = getenv("PATH");
-        const char *exec_path = perf_exec_path();
+        char *exec_path = get_argv_exec_path();
 
         if (exec_path) {
                 list_commands_in_dir(main_cmds, exec_path, prefix);
@@ -172,7 +205,7 @@ void load_command_list(const char *prefix,
                 char *paths, *path, *colon;
                 path = paths = strdup(env_path);
                 while (1) {
-                        if ((colon = strchr(path, PATH_SEP)))
+                        if ((colon = strchr(path, ':')))
                                 *colon = 0;
                         if (!exec_path || strcmp(path, exec_path))
                                 list_commands_in_dir(other_cmds, path, prefix);
@@ -187,6 +220,7 @@ void load_command_list(const char *prefix,
                       sizeof(*other_cmds->names), cmdname_compare);
                 uniq(other_cmds);
         }
+        free(exec_path);
         exclude_cmds(other_cmds, main_cmds);
 }
 
@@ -203,13 +237,14 @@ void list_commands(const char *title, struct cmdnames *main_cmds,
                         longest = other_cmds->names[i]->len;
 
         if (main_cmds->cnt) {
-                const char *exec_path = perf_exec_path();
+                char *exec_path = get_argv_exec_path();
                 printf("available %s in '%s'\n", title, exec_path);
                 printf("----------------");
                 mput_char('-', strlen(title) + strlen(exec_path));
                 putchar('\n');
                 pretty_print_string_list(main_cmds, longest);
                 putchar('\n');
+                free(exec_path);
         }
 
         if (other_cmds->cnt) {
@@ -231,109 +266,3 @@ int is_in_cmdlist(struct cmdnames *c, const char *s)
                         return 1;
         return 0;
 }
-
-static int autocorrect;
-static struct cmdnames aliases;
-
-static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
-{
-        if (!strcmp(var, "help.autocorrect"))
-                autocorrect = perf_config_int(var,value);
-        /* Also use aliases for command lookup */
-        if (!prefixcmp(var, "alias."))
-                add_cmdname(&aliases, var + 6, strlen(var + 6));
-
-        return perf_default_config(var, value, cb);
-}
-
-static int levenshtein_compare(const void *p1, const void *p2)
-{
-        const struct cmdname *const *c1 = p1, *const *c2 = p2;
-        const char *s1 = (*c1)->name, *s2 = (*c2)->name;
-        int l1 = (*c1)->len;
-        int l2 = (*c2)->len;
-        return l1 != l2 ? l1 - l2 : strcmp(s1, s2);
-}
-
-static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
-{
-        unsigned int i;
-
-        ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc);
-
-        for (i = 0; i < old->cnt; i++)
-                cmds->names[cmds->cnt++] = old->names[i];
-        zfree(&old->names);
-        old->cnt = 0;
-}
-
-const char *help_unknown_cmd(const char *cmd)
-{
-        unsigned int i, n = 0, best_similarity = 0;
-        struct cmdnames main_cmds, other_cmds;
-
-        memset(&main_cmds, 0, sizeof(main_cmds));
-        memset(&other_cmds, 0, sizeof(main_cmds));
-        memset(&aliases, 0, sizeof(aliases));
-
-        perf_config(perf_unknown_cmd_config, NULL);
-
-        load_command_list("perf-", &main_cmds, &other_cmds);
-
-        add_cmd_list(&main_cmds, &aliases);
-        add_cmd_list(&main_cmds, &other_cmds);
-        qsort(main_cmds.names, main_cmds.cnt,
-              sizeof(main_cmds.names), cmdname_compare);
-        uniq(&main_cmds);
-
-        if (main_cmds.cnt) {
-                /* This reuses cmdname->len for similarity index */
-                for (i = 0; i < main_cmds.cnt; ++i)
-                        main_cmds.names[i]->len =
-                                levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4);
-
-                qsort(main_cmds.names, main_cmds.cnt,
-                      sizeof(*main_cmds.names), levenshtein_compare);
-
-                best_similarity = main_cmds.names[0]->len;
-                n = 1;
-                while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len)
-                        ++n;
-        }
-
-        if (autocorrect && n == 1) {
-                const char *assumed = main_cmds.names[0]->name;
-
-                main_cmds.names[0] = NULL;
-                clean_cmdnames(&main_cmds);
-                fprintf(stderr, "WARNING: You called a perf program named '%s', "
-                        "which does not exist.\n"
-                        "Continuing under the assumption that you meant '%s'\n",
-                        cmd, assumed);
-                if (autocorrect > 0) {
-                        fprintf(stderr, "in %0.1f seconds automatically...\n",
-                                (float)autocorrect/10.0);
-                        poll(NULL, 0, autocorrect * 100);
-                }
-                return assumed;
-        }
-
-        fprintf(stderr, "perf: '%s' is not a perf-command. See 'perf --help'.\n", cmd);
-
-        if (main_cmds.cnt && best_similarity < 6) {
-                fprintf(stderr, "\nDid you mean %s?\n",
-                        n < 2 ? "this": "one of these");
-
-                for (i = 0; i < n; i++)
-                        fprintf(stderr, "\t%s\n", main_cmds.names[i]->name);
-        }
-
-        exit(1);
-}
-
-int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused,
-                const char *prefix __maybe_unused)
-{
-        printf("perf version %s\n", perf_version_string);
-        return 0;
-}
diff --git a/tools/perf/util/help.h b/tools/lib/subcmd/help.h
index 7f5c6dedd714..e145a020780c 100644
--- a/tools/perf/util/help.h
+++ b/tools/lib/subcmd/help.h
@@ -1,12 +1,14 @@
-#ifndef __PERF_HELP_H
-#define __PERF_HELP_H
+#ifndef __SUBCMD_HELP_H
+#define __SUBCMD_HELP_H
+
+#include <sys/types.h>
 
 struct cmdnames {
         size_t alloc;
         size_t cnt;
         struct cmdname {
                 size_t len; /* also used for similarity index in help.c */
-                char name[FLEX_ARRAY];
+                char name[];
         } **names;
 };
 
@@ -20,10 +22,13 @@ void load_command_list(const char *prefix,
                 struct cmdnames *main_cmds,
                 struct cmdnames *other_cmds);
 void add_cmdname(struct cmdnames *cmds, const char *name, size_t len);
+void clean_cmdnames(struct cmdnames *cmds);
+int cmdname_compare(const void *a, const void *b);
+void uniq(struct cmdnames *cmds);
 /* Here we require that excludes is a sorted list. */
 void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes);
 int is_in_cmdlist(struct cmdnames *c, const char *s);
 void list_commands(const char *title, struct cmdnames *main_cmds,
                    struct cmdnames *other_cmds);
 
-#endif /* __PERF_HELP_H */
+#endif /* __SUBCMD_HELP_H */
diff --git a/tools/perf/util/pager.c b/tools/lib/subcmd/pager.c
index 53ef006a951c..d50f3b58606b 100644
--- a/tools/perf/util/pager.c
+++ b/tools/lib/subcmd/pager.c
@@ -1,6 +1,12 @@
-#include "cache.h"
+#include <sys/select.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+#include "pager.h"
 #include "run-command.h"
 #include "sigchain.h"
+#include "subcmd-config.h"
 
 /*
  * This is split up from the rest of git so that we can do
@@ -9,6 +15,11 @@
 
 static int spawned_pager;
 
+void pager_init(const char *pager_env)
+{
+        subcmd_config.pager_env = pager_env;
+}
+
 static void pager_preexec(void)
 {
         /*
@@ -46,7 +57,7 @@ static void wait_for_pager_signal(int signo)
 
 void setup_pager(void)
 {
-        const char *pager = getenv("PERF_PAGER");
+        const char *pager = getenv(subcmd_config.pager_env);
 
         if (!isatty(1))
                 return;
@@ -85,11 +96,5 @@ void setup_pager(void)
 
 int pager_in_use(void)
 {
-        const char *env;
-
-        if (spawned_pager)
-                return 1;
-
-        env = getenv("PERF_PAGER_IN_USE");
-        return env ? perf_config_bool("PERF_PAGER_IN_USE", env) : 0;
+        return spawned_pager;
 }
diff --git a/tools/lib/subcmd/pager.h b/tools/lib/subcmd/pager.h
new file mode 100644
index 000000000000..8b83714ecf73
--- /dev/null
+++ b/tools/lib/subcmd/pager.h
@@ -0,0 +1,9 @@
+#ifndef __SUBCMD_PAGER_H
+#define __SUBCMD_PAGER_H
+
+extern void pager_init(const char *pager_env);
+
+extern void setup_pager(void);
+extern int pager_in_use(void);
+
+#endif /* __SUBCMD_PAGER_H */
diff --git a/tools/perf/util/parse-options.c b/tools/lib/subcmd/parse-options.c
index 9fca09296eb3..981bb4481fd5 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -1,37 +1,66 @@
-#include "util.h"
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+#include <ctype.h>
+#include "subcmd-util.h"
 #include "parse-options.h"
-#include "cache.h"
-#include "header.h"
-#include <linux/string.h>
+#include "subcmd-config.h"
+#include "pager.h"
 
 #define OPT_SHORT 1
 #define OPT_UNSET 2
 
-static struct strbuf error_buf = STRBUF_INIT;
+char *error_buf;
 
 static int opterror(const struct option *opt, const char *reason, int flags)
 {
         if (flags & OPT_SHORT)
-                return error("switch `%c' %s", opt->short_name, reason);
-        if (flags & OPT_UNSET)
-                return error("option `no-%s' %s", opt->long_name, reason);
-        return error("option `%s' %s", opt->long_name, reason);
+                fprintf(stderr, " Error: switch `%c' %s", opt->short_name, reason);
+        else if (flags & OPT_UNSET)
+                fprintf(stderr, " Error: option `no-%s' %s", opt->long_name, reason);
+        else
+                fprintf(stderr, " Error: option `%s' %s", opt->long_name, reason);
+
+        return -1;
+}
+
+static const char *skip_prefix(const char *str, const char *prefix)
+{
+        size_t len = strlen(prefix);
+        return strncmp(str, prefix, len) ? NULL : str + len;
+}
+
+static void optwarning(const struct option *opt, const char *reason, int flags)
+{
+        if (flags & OPT_SHORT)
+                fprintf(stderr, " Warning: switch `%c' %s", opt->short_name, reason);
+        else if (flags & OPT_UNSET)
+                fprintf(stderr, " Warning: option `no-%s' %s", opt->long_name, reason);
+        else
+                fprintf(stderr, " Warning: option `%s' %s", opt->long_name, reason);
 }
 
 static int get_arg(struct parse_opt_ctx_t *p, const struct option *opt,
                    int flags, const char **arg)
 {
+        const char *res;
+
         if (p->opt) {
-                *arg = p->opt;
+                res = p->opt;
                 p->opt = NULL;
         } else if ((opt->flags & PARSE_OPT_LASTARG_DEFAULT) && (p->argc == 1 ||
                     **(p->argv + 1) == '-')) {
-                *arg = (const char *)opt->defval;
+                res = (const char *)opt->defval;
         } else if (p->argc > 1) {
                 p->argc--;
-                *arg = *++p->argv;
+                res = *++p->argv;
         } else
                 return opterror(opt, "requires a value", flags);
+        if (arg)
+                *arg = res;
         return 0;
 }
 
@@ -55,11 +84,11 @@ static int get_value(struct parse_opt_ctx_t *p,
 
                         if (((flags & OPT_SHORT) && p->excl_opt->short_name) ||
                             p->excl_opt->long_name == NULL) {
-                                scnprintf(msg, sizeof(msg), "cannot be used with switch `%c'",
-                                          p->excl_opt->short_name);
+                                snprintf(msg, sizeof(msg), "cannot be used with switch `%c'",
+                                         p->excl_opt->short_name);
                         } else {
-                                scnprintf(msg, sizeof(msg), "cannot be used with %s",
-                                          p->excl_opt->long_name);
+                                snprintf(msg, sizeof(msg), "cannot be used with %s",
+                                         p->excl_opt->long_name);
                         }
                         opterror(opt, msg, flags);
                         return -3;
@@ -91,6 +120,64 @@ static int get_value(struct parse_opt_ctx_t *p,
                 }
         }
 
+        if (opt->flags & PARSE_OPT_NOBUILD) {
+                char reason[128];
+                bool noarg = false;
+
+                err = snprintf(reason, sizeof(reason),
+                                opt->flags & PARSE_OPT_CANSKIP ?
+                                        "is being ignored because %s " :
+                                        "is not available because %s",
+                                opt->build_opt);
+                reason[sizeof(reason) - 1] = '\0';
+
+                if (err < 0)
+                        strncpy(reason, opt->flags & PARSE_OPT_CANSKIP ?
+                                        "is being ignored" :
+                                        "is not available",
+                                        sizeof(reason));
+
+                if (!(opt->flags & PARSE_OPT_CANSKIP))
+                        return opterror(opt, reason, flags);
+
+                err = 0;
+                if (unset)
+                        noarg = true;
+                if (opt->flags & PARSE_OPT_NOARG)
+                        noarg = true;
+                if (opt->flags & PARSE_OPT_OPTARG && !p->opt)
+                        noarg = true;
+
+                switch (opt->type) {
+                case OPTION_BOOLEAN:
+                case OPTION_INCR:
+                case OPTION_BIT:
+                case OPTION_SET_UINT:
+                case OPTION_SET_PTR:
+                case OPTION_END:
+                case OPTION_ARGUMENT:
+                case OPTION_GROUP:
+                        noarg = true;
+                        break;
+                case OPTION_CALLBACK:
+                case OPTION_STRING:
+                case OPTION_INTEGER:
+                case OPTION_UINTEGER:
+                case OPTION_LONG:
+                case OPTION_U64:
+                default:
+                        break;
+                }
+
+                if (!noarg)
+                        err = get_arg(p, opt, flags, NULL);
+                if (err)
+                        return err;
+
+                optwarning(opt, reason, flags);
+                return 0;
+        }
+
         switch (opt->type) {
         case OPTION_BIT:
                 if (unset)
@@ -327,14 +414,16 @@ match:
                 return get_value(p, options, flags);
         }
 
-        if (ambiguous_option)
-                return error("Ambiguous option: %s "
-                        "(could be --%s%s or --%s%s)",
-                        arg,
-                        (ambiguous_flags & OPT_UNSET) ?  "no-" : "",
-                        ambiguous_option->long_name,
-                        (abbrev_flags & OPT_UNSET) ?  "no-" : "",
-                        abbrev_option->long_name);
+        if (ambiguous_option) {
+                 fprintf(stderr,
+                         " Error: Ambiguous option: %s (could be --%s%s or --%s%s)",
+                         arg,
+                         (ambiguous_flags & OPT_UNSET) ?  "no-" : "",
+                         ambiguous_option->long_name,
+                         (abbrev_flags & OPT_UNSET) ?  "no-" : "",
+                         abbrev_option->long_name);
+                 return -1;
+        }
         if (abbrev_option)
                 return get_value(p, abbrev_option, abbrev_flags);
         return -2;
@@ -346,7 +435,7 @@ static void check_typos(const char *arg, const struct option *options)
                 return;
 
         if (!prefixcmp(arg, "no-")) {
-                error ("did you mean `--%s` (with two dashes ?)", arg);
+                fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg);
                 exit(129);
         }
 
@@ -354,14 +443,14 @@ static void check_typos(const char *arg, const struct option *options)
                 if (!options->long_name)
                         continue;
                 if (!prefixcmp(options->long_name, arg)) {
-                        error ("did you mean `--%s` (with two dashes ?)", arg);
+                        fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg);
                         exit(129);
                 }
         }
 }
 
-void parse_options_start(struct parse_opt_ctx_t *ctx,
-                         int argc, const char **argv, int flags)
+static void parse_options_start(struct parse_opt_ctx_t *ctx,
+                                int argc, const char **argv, int flags)
 {
         memset(ctx, 0, sizeof(*ctx));
         ctx->argc = argc - 1;
@@ -378,9 +467,9 @@ static int usage_with_options_internal(const char * const *,
                                        const struct option *, int,
                                        struct parse_opt_ctx_t *);
 
-int parse_options_step(struct parse_opt_ctx_t *ctx,
-                       const struct option *options,
-                       const char * const usagestr[])
+static int parse_options_step(struct parse_opt_ctx_t *ctx,
+                              const struct option *options,
+                              const char * const usagestr[])
 {
         int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP);
         int excl_short_opt = 1;
@@ -489,7 +578,7 @@ exclusive:
         return PARSE_OPT_HELP;
 }
 
-int parse_options_end(struct parse_opt_ctx_t *ctx)
+static int parse_options_end(struct parse_opt_ctx_t *ctx)
 {
         memmove(ctx->out + ctx->cpidx, ctx->argv, ctx->argc * sizeof(*ctx->out));
         ctx->out[ctx->cpidx + ctx->argc] = NULL;
@@ -501,22 +590,20 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o
 {
         struct parse_opt_ctx_t ctx;
 
-        perf_env__set_cmdline(&perf_env, argc, argv);
-
         /* build usage string if it's not provided */
         if (subcommands && !usagestr[0]) {
-                struct strbuf buf = STRBUF_INIT;
+                char *buf = NULL;
+
+                astrcatf(&buf, "%s %s [<options>] {", subcmd_config.exec_name, argv[0]);
 
-                strbuf_addf(&buf, "perf %s [<options>] {", argv[0]);
                 for (int i = 0; subcommands[i]; i++) {
                         if (i)
-                                strbuf_addstr(&buf, "|");
-                        strbuf_addstr(&buf, subcommands[i]);
+                                astrcat(&buf, "|");
+                        astrcat(&buf, subcommands[i]);
                 }
-                strbuf_addstr(&buf, "}");
+                astrcat(&buf, "}");
 
-                usagestr[0] = strdup(buf.buf);
-                strbuf_release(&buf);
+                usagestr[0] = buf;
         }
 
         parse_options_start(&ctx, argc, argv, flags);
@@ -541,13 +628,11 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o
                 putchar('\n');
                 exit(130);
         default: /* PARSE_OPT_UNKNOWN */
-                if (ctx.argv[0][1] == '-') {
-                        strbuf_addf(&error_buf, "unknown option `%s'",
-                                    ctx.argv[0] + 2);
-                } else {
-                        strbuf_addf(&error_buf, "unknown switch `%c'",
-                                    *ctx.opt);
-                }
+                if (ctx.argv[0][1] == '-')
+                        astrcatf(&error_buf, "unknown option `%s'",
+                                 ctx.argv[0] + 2);
+                else
+                        astrcatf(&error_buf, "unknown switch `%c'", *ctx.opt);
                 usage_with_options(usagestr, options);
         }
 
@@ -647,6 +732,10 @@ static void print_option_help(const struct option *opts, int full)
                 pad = USAGE_OPTS_WIDTH;
         }
         fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help);
+        if (opts->flags & PARSE_OPT_NOBUILD)
+                fprintf(stderr, "%*s(not built-in because %s)\n",
+                        USAGE_OPTS_WIDTH + USAGE_GAP, "",
+                        opts->build_opt);
 }
 
 static int option__cmp(const void *va, const void *vb)
@@ -672,16 +761,18 @@ static int option__cmp(const void *va, const void *vb)
 
 static struct option *options__order(const struct option *opts)
 {
-        int nr_opts = 0;
+        int nr_opts = 0, len;
         const struct option *o = opts;
         struct option *ordered;
 
         for (o = opts; o->type != OPTION_END; o++)
                 ++nr_opts;
 
-        ordered = memdup(opts, sizeof(*o) * (nr_opts + 1));
-        if (ordered == NULL)
+        len = sizeof(*o) * (nr_opts + 1);
+        ordered = malloc(len);
+        if (!ordered)
                 goto out;
+        memcpy(ordered, opts, len);
 
         qsort(ordered, nr_opts, sizeof(*o), option__cmp);
 out:
@@ -719,9 +810,9 @@ static bool option__in_argv(const struct option *opt, const struct parse_opt_ctx
         return false;
 }
 
-int usage_with_options_internal(const char * const *usagestr,
-                                const struct option *opts, int full,
-                                struct parse_opt_ctx_t *ctx)
+static int usage_with_options_internal(const char * const *usagestr,
+                                       const struct option *opts, int full,
+                                       struct parse_opt_ctx_t *ctx)
 {
         struct option *ordered;
 
@@ -730,9 +821,9 @@ int usage_with_options_internal(const char * const *usagestr,
 
         setup_pager();
 
-        if (strbuf_avail(&error_buf)) {
-                fprintf(stderr, "  Error: %s\n", error_buf.buf);
-                strbuf_release(&error_buf);
+        if (error_buf) {
+                fprintf(stderr, "  Error: %s\n", error_buf);
+                zfree(&error_buf);
         }
 
         fprintf(stderr, "\n Usage: %s\n", *usagestr++);
@@ -768,7 +859,6 @@ int usage_with_options_internal(const char * const *usagestr,
 void usage_with_options(const char * const *usagestr,
                         const struct option *opts)
 {
-        exit_browser(false);
         usage_with_options_internal(usagestr, opts, 0, NULL);
         exit(129);
 }
@@ -777,13 +867,15 @@ void usage_with_options_msg(const char * const *usagestr,
                             const struct option *opts, const char *fmt, ...)
 {
         va_list ap;
-
-        exit_browser(false);
+        char *tmp = error_buf;
 
         va_start(ap, fmt);
-        strbuf_addv(&error_buf, fmt, ap);
+        if (vasprintf(&error_buf, fmt, ap) == -1)
+                die("vasprintf failed");
         va_end(ap);
 
+        free(tmp);
+
         usage_with_options_internal(usagestr, opts, 0, NULL);
         exit(129);
 }
@@ -853,15 +945,39 @@ int parse_opt_verbosity_cb(const struct option *opt,
         return 0;
 }
 
-void set_option_flag(struct option *opts, int shortopt, const char *longopt,
-                     int flag)
+static struct option *
+find_option(struct option *opts, int shortopt, const char *longopt)
 {
         for (; opts->type != OPTION_END; opts++) {
                 if ((shortopt && opts->short_name == shortopt) ||
                     (opts->long_name && longopt &&
-                     !strcmp(opts->long_name, longopt))) {
-                        opts->flags |= flag;
-                        break;
-                }
+                     !strcmp(opts->long_name, longopt)))
+                        return opts;
         }
+        return NULL;
+}
+
+void set_option_flag(struct option *opts, int shortopt, const char *longopt,
+                     int flag)
+{
+        struct option *opt = find_option(opts, shortopt, longopt);
+
+        if (opt)
+                opt->flags |= flag;
+        return;
+}
+
+void set_option_nobuild(struct option *opts, int shortopt,
+                        const char *longopt,
+                        const char *build_opt,
+                        bool can_skip)
+{
+        struct option *opt = find_option(opts, shortopt, longopt);
+
+        if (!opt)
+                return;
+
+        opt->flags |= PARSE_OPT_NOBUILD;
+        opt->flags |= can_skip ? PARSE_OPT_CANSKIP : 0;
+        opt->build_opt = build_opt;
 }
diff --git a/tools/perf/util/parse-options.h b/tools/lib/subcmd/parse-options.h
index a8e407bc251e..13a2cc1d6140 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -1,8 +1,8 @@
-#ifndef __PERF_PARSE_OPTIONS_H
-#define __PERF_PARSE_OPTIONS_H
+#ifndef __SUBCMD_PARSE_OPTIONS_H
+#define __SUBCMD_PARSE_OPTIONS_H
 
-#include <linux/kernel.h>
 #include <stdbool.h>
+#include <stdint.h>
 
 enum parse_opt_type {
         /* special types */
@@ -41,6 +41,8 @@ enum parse_opt_option_flags {
         PARSE_OPT_DISABLED = 32,
         PARSE_OPT_EXCLUSIVE = 64,
         PARSE_OPT_NOEMPTY  = 128,
+        PARSE_OPT_NOBUILD  = 256,
+        PARSE_OPT_CANSKIP  = 512,
 };
 
 struct option;
@@ -96,6 +98,7 @@ struct option {
         void *value;
         const char *argh;
         const char *help;
+        const char *build_opt;
 
         int flags;
         parse_opt_cb *callback;
@@ -149,6 +152,9 @@ struct option {
 /* parse_options() will filter out the processed options and leave the
  * non-option argments in argv[].
  * Returns the number of arguments left in argv[].
+ *
+ * NOTE: parse_options() and parse_options_subcommand() may call exit() in the
+ * case of an error (or for 'special' options like --list-cmds or --list-opts).
  */
 extern int parse_options(int argc, const char **argv,
                          const struct option *options,
@@ -195,15 +201,6 @@ extern int parse_options_usage(const char * const *usagestr,
                                const char *optstr,
                                bool short_opt);
 
-extern void parse_options_start(struct parse_opt_ctx_t *ctx,
-                                int argc, const char **argv, int flags);
-
-extern int parse_options_step(struct parse_opt_ctx_t *ctx,
-                              const struct option *options,
-                              const char * const usagestr[]);
-
-extern int parse_options_end(struct parse_opt_ctx_t *ctx);
-
 
 /*----- some often used options -----*/
 extern int parse_opt_abbrev_cb(const struct option *, const char *, int);
@@ -226,4 +223,7 @@ extern int parse_opt_verbosity_cb(const struct option *, const char *, int);
 extern const char *parse_options_fix_filename(const char *prefix, const char *file);
 
 void set_option_flag(struct option *opts, int sopt, const char *lopt, int flag);
-#endif /* __PERF_PARSE_OPTIONS_H */
+void set_option_nobuild(struct option *opts, int shortopt, const char *longopt,
+                        const char *build_opt, bool can_skip);
+
+#endif /* __SUBCMD_PARSE_OPTIONS_H */
diff --git a/tools/perf/util/run-command.c b/tools/lib/subcmd/run-command.c
index 34622b53e733..f4f6c9eb8e59 100644
--- a/tools/perf/util/run-command.c
+++ b/tools/lib/subcmd/run-command.c
@@ -1,7 +1,15 @@
-#include "cache.h"
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/wait.h>
+#include "subcmd-util.h"
 #include "run-command.h"
-#include "exec_cmd.h"
-#include "debug.h"
+#include "exec-cmd.h"
+
+#define STRERR_BUFSIZE 128
 
 static inline void close_pair(int fd[2])
 {
@@ -112,8 +120,8 @@ int start_command(struct child_process *cmd)
                 }
                 if (cmd->preexec_cb)
                         cmd->preexec_cb();
-                if (cmd->perf_cmd) {
-                        execv_perf_cmd(cmd->argv);
+                if (cmd->exec_cmd) {
+                        execv_cmd(cmd->argv);
                 } else {
                         execvp(cmd->argv[0], (char *const*) cmd->argv);
                 }
@@ -164,8 +172,8 @@ static int wait_or_whine(pid_t pid)
                 if (waiting < 0) {
                         if (errno == EINTR)
                                 continue;
-                        error("waitpid failed (%s)",
-                              strerror_r(errno, sbuf, sizeof(sbuf)));
+                        fprintf(stderr, " Error: waitpid failed (%s)",
+                                strerror_r(errno, sbuf, sizeof(sbuf)));
                         return -ERR_RUN_COMMAND_WAITPID;
                 }
                 if (waiting != pid)
@@ -207,7 +215,7 @@ static void prepare_run_command_v_opt(struct child_process *cmd,
         memset(cmd, 0, sizeof(*cmd));
         cmd->argv = argv;
         cmd->no_stdin = opt & RUN_COMMAND_NO_STDIN ? 1 : 0;
-        cmd->perf_cmd = opt & RUN_PERF_CMD ? 1 : 0;
+        cmd->exec_cmd = opt & RUN_EXEC_CMD ? 1 : 0;
         cmd->stdout_to_stderr = opt & RUN_COMMAND_STDOUT_TO_STDERR ? 1 : 0;
 }
 
diff --git a/tools/perf/util/run-command.h b/tools/lib/subcmd/run-command.h
index 1ef264d5069c..fe2befea1e73 100644
--- a/tools/perf/util/run-command.h
+++ b/tools/lib/subcmd/run-command.h
@@ -1,5 +1,7 @@
-#ifndef __PERF_RUN_COMMAND_H
-#define __PERF_RUN_COMMAND_H
+#ifndef __SUBCMD_RUN_COMMAND_H
+#define __SUBCMD_RUN_COMMAND_H
+
+#include <unistd.h>
 
 enum {
         ERR_RUN_COMMAND_FORK = 10000,
@@ -41,7 +43,7 @@ struct child_process {
         unsigned no_stdin:1;
         unsigned no_stdout:1;
         unsigned no_stderr:1;
-        unsigned perf_cmd:1; /* if this is to be perf sub-command */
+        unsigned exec_cmd:1; /* if this is to be external sub-command */
         unsigned stdout_to_stderr:1;
         void (*preexec_cb)(void);
 };
@@ -51,8 +53,8 @@ int finish_command(struct child_process *);
 int run_command(struct child_process *);
 
 #define RUN_COMMAND_NO_STDIN 1
-#define RUN_PERF_CMD         2  /*If this is to be perf sub-command */
+#define RUN_EXEC_CMD         2  /*If this is to be external sub-command */
 #define RUN_COMMAND_STDOUT_TO_STDERR 4
 int run_command_v_opt(const char **argv, int opt);
 
-#endif /* __PERF_RUN_COMMAND_H */
+#endif /* __SUBCMD_RUN_COMMAND_H */
diff --git a/tools/perf/util/sigchain.c b/tools/lib/subcmd/sigchain.c
index ba785e9b1841..3537c348a18e 100644
--- a/tools/perf/util/sigchain.c
+++ b/tools/lib/subcmd/sigchain.c
@@ -1,5 +1,6 @@
+#include <signal.h>
+#include "subcmd-util.h"
 #include "sigchain.h"
-#include "cache.h"
 
 #define SIGCHAIN_MAX_SIGNALS 32
 
diff --git a/tools/perf/util/sigchain.h b/tools/lib/subcmd/sigchain.h
index 959d64eb5557..0c919f2874ca 100644
--- a/tools/perf/util/sigchain.h
+++ b/tools/lib/subcmd/sigchain.h
@@ -1,5 +1,5 @@
-#ifndef __PERF_SIGCHAIN_H
-#define __PERF_SIGCHAIN_H
+#ifndef __SUBCMD_SIGCHAIN_H
+#define __SUBCMD_SIGCHAIN_H
 
 typedef void (*sigchain_fun)(int);
 
@@ -7,4 +7,4 @@ int sigchain_pop(int sig);
 
 void sigchain_push_common(sigchain_fun f);
 
-#endif /* __PERF_SIGCHAIN_H */
+#endif /* __SUBCMD_SIGCHAIN_H */
diff --git a/tools/lib/subcmd/subcmd-config.c b/tools/lib/subcmd/subcmd-config.c
new file mode 100644
index 000000000000..d017c728bd1b
--- /dev/null
+++ b/tools/lib/subcmd/subcmd-config.c
@@ -0,0 +1,11 @@
+#include "subcmd-config.h"
+
+#define UNDEFINED "SUBCMD_HAS_NOT_BEEN_INITIALIZED"
+
+struct subcmd_config subcmd_config = {
+        .exec_name      = UNDEFINED,
+        .prefix         = UNDEFINED,
+        .exec_path      = UNDEFINED,
+        .exec_path_env  = UNDEFINED,
+        .pager_env      = UNDEFINED,
+};
diff --git a/tools/lib/subcmd/subcmd-config.h b/tools/lib/subcmd/subcmd-config.h
new file mode 100644
index 000000000000..cc8514030b5c
--- /dev/null
+++ b/tools/lib/subcmd/subcmd-config.h
@@ -0,0 +1,14 @@
+#ifndef __PERF_SUBCMD_CONFIG_H
+#define __PERF_SUBCMD_CONFIG_H
+
+struct subcmd_config {
+        const char *exec_name;
+        const char *prefix;
+        const char *exec_path;
+        const char *exec_path_env;
+        const char *pager_env;
+};
+
+extern struct subcmd_config subcmd_config;
+
+#endif /* __PERF_SUBCMD_CONFIG_H */
diff --git a/tools/lib/subcmd/subcmd-util.h b/tools/lib/subcmd/subcmd-util.h
new file mode 100644
index 000000000000..fc2e45d8aaf1
--- /dev/null
+++ b/tools/lib/subcmd/subcmd-util.h
@@ -0,0 +1,91 @@
+#ifndef __SUBCMD_UTIL_H
+#define __SUBCMD_UTIL_H
+
+#include <stdarg.h>
+#include <stdlib.h>
+#include <stdio.h>
+
+#define NORETURN __attribute__((__noreturn__))
+
+static inline void report(const char *prefix, const char *err, va_list params)
+{
+        char msg[1024];
+        vsnprintf(msg, sizeof(msg), err, params);
+        fprintf(stderr, " %s%s\n", prefix, msg);
+}
+
+static NORETURN inline void die(const char *err, ...)
+{
+        va_list params;
+
+        va_start(params, err);
+        report(" Fatal: ", err, params);
+        exit(128);
+        va_end(params);
+}
+
+#define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
+
+#define alloc_nr(x) (((x)+16)*3/2)
+
+/*
+ * Realloc the buffer pointed at by variable 'x' so that it can hold
+ * at least 'nr' entries; the number of entries currently allocated
+ * is 'alloc', using the standard growing factor alloc_nr() macro.
+ *
+ * DO NOT USE any expression with side-effect for 'x' or 'alloc'.
+ */
+#define ALLOC_GROW(x, nr, alloc) \
+        do { \
+                if ((nr) > alloc) { \
+                        if (alloc_nr(alloc) < (nr)) \
+                                alloc = (nr); \
+                        else \
+                                alloc = alloc_nr(alloc); \
+                        x = xrealloc((x), alloc * sizeof(*(x))); \
+                } \
+        } while(0)
+
+static inline void *xrealloc(void *ptr, size_t size)
+{
+        void *ret = realloc(ptr, size);
+        if (!ret && !size)
+                ret = realloc(ptr, 1);
+        if (!ret) {
+                ret = realloc(ptr, size);
+                if (!ret && !size)
+                        ret = realloc(ptr, 1);
+                if (!ret)
+                        die("Out of memory, realloc failed");
+        }
+        return ret;
+}
+
+#define astrcatf(out, fmt, ...)                                         \
+({                                                                      \
+        char *tmp = *(out);                                             \
+        if (asprintf((out), "%s" fmt, tmp ?: "", ## __VA_ARGS__) == -1) \
+                die("asprintf failed");                                 \
+        free(tmp);                                                      \
+})
+
+static inline void astrcat(char **out, const char *add)
+{
+        char *tmp = *out;
+
+        if (asprintf(out, "%s%s", tmp ?: "", add) == -1)
+                die("asprintf failed");
+
+        free(tmp);
+}
+
+static inline int prefixcmp(const char *str, const char *prefix)
+{
+        for (; ; str++, prefix++)
+                if (!*prefix)
+                        return 0;
+                else if (*str != *prefix)
+                        return (unsigned char)*prefix - (unsigned char)*str;
+}
+
+#endif /* __SUBCMD_UTIL_H */
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 2a912df6771b..ea69ce35e902 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -4735,73 +4735,80 @@ static int is_printable_array(char *p, unsigned int len)
         return 1;
 }
 
-static void print_event_fields(struct trace_seq *s, void *data,
-                               int size __maybe_unused,
-                               struct event_format *event)
+void pevent_print_field(struct trace_seq *s, void *data,
+                        struct format_field *field)
 {
-        struct format_field *field;
         unsigned long long val;
         unsigned int offset, len, i;
-
-        field = event->format.fields;
-        while (field) {
-                trace_seq_printf(s, " %s=", field->name);
-                if (field->flags & FIELD_IS_ARRAY) {
-                        offset = field->offset;
-                        len = field->size;
-                        if (field->flags & FIELD_IS_DYNAMIC) {
-                                val = pevent_read_number(event->pevent, data + offset, len);
-                                offset = val;
-                                len = offset >> 16;
-                                offset &= 0xffff;
-                        }
-                        if (field->flags & FIELD_IS_STRING &&
-                            is_printable_array(data + offset, len)) {
-                                trace_seq_printf(s, "%s", (char *)data + offset);
-                        } else {
-                                trace_seq_puts(s, "ARRAY[");
-                                for (i = 0; i < len; i++) {
-                                        if (i)
-                                                trace_seq_puts(s, ", ");
-                                        trace_seq_printf(s, "%02x",
-                                                         *((unsigned char *)data + offset + i));
-                                }
-                                trace_seq_putc(s, ']');
-                                field->flags &= ~FIELD_IS_STRING;
-                        }
+        struct pevent *pevent = field->event->pevent;
+
+        if (field->flags & FIELD_IS_ARRAY) {
+                offset = field->offset;
+                len = field->size;
+                if (field->flags & FIELD_IS_DYNAMIC) {
+                        val = pevent_read_number(pevent, data + offset, len);
+                        offset = val;
+                        len = offset >> 16;
+                        offset &= 0xffff;
+                }
+                if (field->flags & FIELD_IS_STRING &&
+                    is_printable_array(data + offset, len)) {
+                        trace_seq_printf(s, "%s", (char *)data + offset);
                 } else {
-                        val = pevent_read_number(event->pevent, data + field->offset,
-                                                 field->size);
-                        if (field->flags & FIELD_IS_POINTER) {
-                                trace_seq_printf(s, "0x%llx", val);
-                        } else if (field->flags & FIELD_IS_SIGNED) {
-                                switch (field->size) {
-                                case 4:
-                                        /*
-                                         * If field is long then print it in hex.
-                                         * A long usually stores pointers.
-                                         */
-                                        if (field->flags & FIELD_IS_LONG)
-                                                trace_seq_printf(s, "0x%x", (int)val);
-                                        else
-                                                trace_seq_printf(s, "%d", (int)val);
-                                        break;
-                                case 2:
-                                        trace_seq_printf(s, "%2d", (short)val);
-                                        break;
-                                case 1:
-                                        trace_seq_printf(s, "%1d", (char)val);
-                                        break;
-                                default:
-                                        trace_seq_printf(s, "%lld", val);
-                                }
-                        } else {
+                        trace_seq_puts(s, "ARRAY[");
+                        for (i = 0; i < len; i++) {
+                                if (i)
+                                        trace_seq_puts(s, ", ");
+                                trace_seq_printf(s, "%02x",
+                                                 *((unsigned char *)data + offset + i));
+                        }
+                        trace_seq_putc(s, ']');
+                        field->flags &= ~FIELD_IS_STRING;
+                }
+        } else {
+                val = pevent_read_number(pevent, data + field->offset,
+                                         field->size);
+                if (field->flags & FIELD_IS_POINTER) {
+                        trace_seq_printf(s, "0x%llx", val);
+                } else if (field->flags & FIELD_IS_SIGNED) {
+                        switch (field->size) {
+                        case 4:
+                                /*
+                                 * If field is long then print it in hex.
+                                 * A long usually stores pointers.
+                                 */
                                 if (field->flags & FIELD_IS_LONG)
-                                        trace_seq_printf(s, "0x%llx", val);
+                                        trace_seq_printf(s, "0x%x", (int)val);
                                 else
-                                        trace_seq_printf(s, "%llu", val);
+                                        trace_seq_printf(s, "%d", (int)val);
+                                break;
+                        case 2:
+                                trace_seq_printf(s, "%2d", (short)val);
+                                break;
+                        case 1:
+                                trace_seq_printf(s, "%1d", (char)val);
+                                break;
+                        default:
+                                trace_seq_printf(s, "%lld", val);
                         }
+                } else {
+                        if (field->flags & FIELD_IS_LONG)
+                                trace_seq_printf(s, "0x%llx", val);
+                        else
+                                trace_seq_printf(s, "%llu", val);
                 }
+        }
+}
+
+void pevent_print_fields(struct trace_seq *s, void *data,
+                         int size __maybe_unused, struct event_format *event)
+{
+        struct format_field *field;
+
+        field = event->format.fields;
+        while (field) {
+                trace_seq_printf(s, " %s=", field->name);
+                pevent_print_field(s, data, field);
                 field = field->next;
         }
 }
@@ -4827,7 +4834,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 
         if (event->flags & EVENT_FL_FAILED) {
                 trace_seq_printf(s, "[FAILED TO PARSE]");
-                print_event_fields(s, data, size, event);
+                pevent_print_fields(s, data, size, event);
                 return;
         }
 
@@ -4968,13 +4975,12 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
                                     sizeof(long) != 8) {
                                         char *p;
 
-                                        ls = 2;
                                         /* make %l into %ll */
-                                        p = strchr(format, 'l');
-                                        if (p)
+                                        if (ls == 1 && (p = strchr(format, 'l')))
                                                 memmove(p+1, p, strlen(p)+1);
                                         else if (strcmp(format, "%p") == 0)
                                                 strcpy(format, "0x%llx");
+                                        ls = 2;
                                 }
                                 switch (ls) {
                                 case -2:
@@ -5302,7 +5308,7 @@ void pevent_event_info(struct trace_seq *s, struct event_format *event,
         int print_pretty = 1;
 
         if (event->pevent->print_raw || (event->flags & EVENT_FL_PRINTRAW))
-                print_event_fields(s, record->data, record->size, event);
+                pevent_print_fields(s, record->data, record->size, event);
         else {
 
                 if (event->handler && !(event->flags & EVENT_FL_NOHANDLE))
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 6fc83c7edbe9..706d9bc24066 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -705,6 +705,10 @@ struct cmdline *pevent_data_pid_from_comm(struct pevent *pevent, const char *com
                                           struct cmdline *next);
 int pevent_cmdline_pid(struct pevent *pevent, struct cmdline *cmdline);
 
+void pevent_print_field(struct trace_seq *s, void *data,
+                        struct format_field *field);
+void pevent_print_fields(struct trace_seq *s, void *data,
+                         int size __maybe_unused, struct event_format *event);
 void pevent_event_info(struct trace_seq *s, struct event_format *event,
                        struct pevent_record *record);
 int pevent_strerror(struct pevent *pevent, enum pevent_errno errnum,
diff --git a/tools/lib/util/find_next_bit.c b/tools/lib/util/find_next_bit.c
deleted file mode 100644
index 41b44f65a79e..000000000000
--- a/tools/lib/util/find_next_bit.c
+++ /dev/null
@@ -1,89 +0,0 @@
-/* find_next_bit.c: fallback find next bit implementation
- *
- * Copied from lib/find_next_bit.c to tools/lib/next_bit.c
- *
- * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/bitops.h>
-#include <asm/types.h>
-#include <asm/byteorder.h>
-
-#define BITOP_WORD(nr)          ((nr) / BITS_PER_LONG)
-
-#ifndef find_next_bit
-/*
- * Find the next set bit in a memory region.
- */
-unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
-                            unsigned long offset)
-{
-        const unsigned long *p = addr + BITOP_WORD(offset);
-        unsigned long result = offset & ~(BITS_PER_LONG-1);
-        unsigned long tmp;
-
-        if (offset >= size)
-                return size;
-        size -= result;
-        offset %= BITS_PER_LONG;
-        if (offset) {
-                tmp = *(p++);
-                tmp &= (~0UL << offset);
-                if (size < BITS_PER_LONG)
-                        goto found_first;
-                if (tmp)
-                        goto found_middle;
-                size -= BITS_PER_LONG;
-                result += BITS_PER_LONG;
-        }
-        while (size & ~(BITS_PER_LONG-1)) {
-                if ((tmp = *(p++)))
-                        goto found_middle;
-                result += BITS_PER_LONG;
-                size -= BITS_PER_LONG;
-        }
-        if (!size)
-                return result;
-        tmp = *p;
-
-found_first:
-        tmp &= (~0UL >> (BITS_PER_LONG - size));
-        if (tmp == 0UL)         /* Are any bits set? */
-                return result + size;   /* Nope. */
-found_middle:
-        return result + __ffs(tmp);
-}
-#endif
-
-#ifndef find_first_bit
-/*
- * Find the first set bit in a memory region.
- */
-unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
-{
-        const unsigned long *p = addr;
-        unsigned long result = 0;
-        unsigned long tmp;
-
-        while (size & ~(BITS_PER_LONG-1)) {
-                if ((tmp = *(p++)))
-                        goto found;
-                result += BITS_PER_LONG;
-                size -= BITS_PER_LONG;
-        }
-        if (!size)
-                return result;
-
-        tmp = (*p) & (~0UL >> (BITS_PER_LONG - size));
-        if (tmp == 0UL)         /* Are any bits set? */
-                return result + size;   /* Nope. */
-found:
-        return result + __ffs(tmp);
-}
-#endif
diff --git a/tools/perf/Build b/tools/perf/Build
index 72237455b400..6b67e6f4179f 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -1,5 +1,6 @@
 perf-y += builtin-bench.o
 perf-y += builtin-annotate.o
+perf-y += builtin-config.o
 perf-y += builtin-diff.o
 perf-y += builtin-evlist.o
 perf-y += builtin-help.o
@@ -19,6 +20,7 @@ perf-y += builtin-kvm.o
 perf-y += builtin-inject.o
 perf-y += builtin-mem.o
 perf-y += builtin-data.o
+perf-y += builtin-version.o
 
 perf-$(CONFIG_AUDIT) += builtin-trace.o
 perf-$(CONFIG_LIBELF) += builtin-probe.o
@@ -34,8 +36,12 @@ paths += -DPERF_MAN_PATH="BUILD_STR($(mandir_SQ))"
 
 CFLAGS_builtin-help.o      += $(paths)
 CFLAGS_builtin-timechart.o += $(paths)
-CFLAGS_perf.o              += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" -include $(OUTPUT)PERF-VERSION-FILE
+CFLAGS_perf.o              += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))"       \
+                              -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))"   \
+                              -DPREFIX="BUILD_STR($(prefix_SQ))"                \
+                              -include $(OUTPUT)PERF-VERSION-FILE
 CFLAGS_builtin-trace.o     += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))"
+CFLAGS_builtin-report.o    += -DTIPDIR="BUILD_STR($(tipdir_SQ))"
 
 libperf-y += util/
 libperf-y += arch/
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
new file mode 100644
index 000000000000..b9ca1e304158
--- /dev/null
+++ b/tools/perf/Documentation/perf-config.txt
@@ -0,0 +1,103 @@
+perf-config(1)
+==============
+
+NAME
+----
+perf-config - Get and set variables in a configuration file.
+
+SYNOPSIS
+--------
+[verse]
+'perf config' -l | --list
+
+DESCRIPTION
+-----------
+You can manage variables in a configuration file with this command.
+
+OPTIONS
+-------
+
+-l::
+--list::
+        Show current config variables, name and value, for all sections.
+
+CONFIGURATION FILE
+------------------
+
+The perf configuration file contains many variables to change various
+aspects of each of its tools, including output, disk usage, etc.
+The '$HOME/.perfconfig' file is used to store a per-user configuration.
+The file '$(sysconfdir)/perfconfig' can be used to
+store a system-wide default configuration.
+
+Syntax
+~~~~~~
+
+The file consist of sections. A section starts with its name
+surrounded by square brackets and continues till the next section
+begins. Each variable must be in a section, and have the form
+'name = value', for example:
+
+        [section]
+                name1 = value1
+                name2 = value2
+
+Section names are case sensitive and can contain any characters except
+newline (double quote `"` and backslash have to be escaped as `\"` and `\\`,
+respectively). Section headers can't span multiple lines.
+
+Example
+~~~~~~~
+
+Given a $HOME/.perfconfig like this:
+
+#
+# This is the config file, and
+# a '#' and ';' character indicates a comment
+#
+
+        [colors]
+                # Color variables
+                top = red, default
+                medium = green, default
+                normal = lightgray, default
+                selected = white, lightgray
+                code = blue, default
+                addr = magenta, default
+                root = white, blue
+
+        [tui]
+                # Defaults if linked with libslang
+                report = on
+                annotate = on
+                top = on
+
+        [buildid]
+                # Default, disable using /dev/null
+                dir = ~/.debug
+
+        [annotate]
+                # Defaults
+                hide_src_code = false
+                use_offset = true
+                jump_arrows = true
+                show_nr_jumps = false
+
+        [help]
+                # Format can be man, info, web or html
+                format = man
+                autocorrect = 0
+
+        [ui]
+                show-headers = true
+
+        [call-graph]
+                # fp (framepointer), dwarf
+                record-mode = fp
+                print-type = graph
+                order = caller
+                sort-key = function
+
+SEE ALSO
+--------
+linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt
index 1ceb3700ffbb..6f7200fb85cf 100644
--- a/tools/perf/Documentation/perf-evlist.txt
+++ b/tools/perf/Documentation/perf-evlist.txt
@@ -32,6 +32,9 @@ OPTIONS
 --group::
         Show event group information.
 
+--trace-fields::
+        Show tracepoint field names.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-list[1],
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index e630a7d2c348..3a1a32f5479f 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -207,11 +207,23 @@ comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-
 In per-thread mode with inheritance mode on (default), samples are captured only when
 the thread executes on the designated CPUs. Default is to monitor all CPUs.
 
+-B::
+--no-buildid::
+Do not save the build ids of binaries in the perf.data files. This skips
+post processing after recording, which sometimes makes the final step in
+the recording process to take a long time, as it needs to process all
+events looking for mmap records. The downside is that it can misresolve
+symbols if the workload binaries used when recording get locally rebuilt
+or upgraded, because the only key available in this case is the
+pathname. You can also set the "record.build-id" config variable to
+'skip to have this behaviour permanently.
+
 -N::
 --no-buildid-cache::
 Do not update the buildid cache. This saves some overhead in situations
 where the information in the perf.data file (which includes buildids)
-is sufficient.
+is sufficient.  You can also set the "record.build-id" config variable to
+'no-cache' to have the same effect.
 
 -G name,...::
 --cgroup name,...::
@@ -314,11 +326,17 @@ This option sets the time out limit. The default value is 500 ms.
 Record context switch events i.e. events of type PERF_RECORD_SWITCH or
 PERF_RECORD_SWITCH_CPU_WIDE.
 
---clang-path::
+--clang-path=PATH::
 Path to clang binary to use for compiling BPF scriptlets.
+(enabled when BPF support is on)
 
---clang-opt::
+--clang-opt=OPTIONS::
 Options passed to clang when compiling BPF scriptlets.
+(enabled when BPF support is on)
+
+--vmlinux=PATH::
+Specify vmlinux path which has debuginfo.
+(enabled when BPF prologue is on)
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 5ce8da1e1256..8a301f6afb37 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -117,6 +117,30 @@ OPTIONS
         And default sort keys are changed to comm, dso_from, symbol_from, dso_to
         and symbol_to, see '--branch-stack'.
 
+        If the data file has tracepoint event(s), following (dynamic) sort keys
+        are also available:
+        trace, trace_fields, [<event>.]<field>[/raw]
+
+        - trace: pretty printed trace output in a single column
+        - trace_fields: fields in tracepoints in separate columns
+        - <field name>: optional event and field name for a specific field
+
+        The last form consists of event and field names.  If event name is
+        omitted, it searches all events for matching field name.  The matched
+        field will be shown only for the event has the field.  The event name
+        supports substring match so user doesn't need to specify full subsystem
+        and event name everytime.  For example, 'sched:sched_switch' event can
+        be shortened to 'switch' as long as it's not ambiguous.  Also event can
+        be specified by its index (starting from 1) preceded by the '%'.
+        So '%1' is the first event, '%2' is the second, and so on.
+
+        The field name can have '/raw' suffix which disables pretty printing
+        and shows raw field value like hex numbers.  The --raw-trace option
+        has the same effect for all dynamic sort keys.
+
+        The default sort keys are changed to 'trace' if all events in the data
+        file are tracepoint.
+
 -F::
 --fields=::
         Specify output field - multiple keys can be specified in CSV format.
@@ -170,17 +194,18 @@ OPTIONS
         Dump raw trace in ASCII.
 
 -g::
---call-graph=<print_type,threshold[,print_limit],order,sort_key,branch>::
+--call-graph=<print_type,threshold[,print_limit],order,sort_key[,branch],value>::
         Display call chains using type, min percent threshold, print limit,
-        call order, sort key and branch.  Note that ordering of parameters is not
-        fixed so any parement can be given in an arbitraty order.  One exception
-        is the print_limit which should be preceded by threshold.
+        call order, sort key, optional branch and value.  Note that ordering of
+        parameters is not fixed so any parement can be given in an arbitraty order.
+        One exception is the print_limit which should be preceded by threshold.
 
         print_type can be either:
         - flat: single column, linear exposure of call chains.
         - graph: use a graph tree, displaying absolute overhead rates. (default)
         - fractal: like graph, but displays relative rates. Each branch of
                  the tree is considered as a new profiled object.
+        - folded: call chains are displayed in a line, separated by semicolons
         - none: disable call chain display.
 
         threshold is a percentage value which specifies a minimum percent to be
@@ -204,6 +229,11 @@ OPTIONS
         - branch: include last branch information in callgraph when available.
                   Usually more convenient to use --branch-history for this.
 
+        value can be:
+        - percent: diplay overhead percent (default)
+        - period: display event period
+        - count: display event count
+
 --children::
         Accumulate callchain of children to parent entry so that then can
         show up in the output.  The output will have a new "Children" column
@@ -365,6 +395,9 @@ include::itrace.txt[]
 --socket-filter::
         Only report the samples on the processor socket that match with this filter
 
+--raw-trace::
+        When displaying traceevent output, do not use print fmt or plugins.
+
 include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 4e074a660826..52ef7a9d50aa 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -10,6 +10,8 @@ SYNOPSIS
 [verse]
 'perf stat' [-e <EVENT> | --event=EVENT] [-a] <command>
 'perf stat' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>]
+'perf stat' [-e <EVENT> | --event=EVENT] [-a] record [-o file] -- <command> [<options>]
+'perf stat' report [-i file]
 
 DESCRIPTION
 -----------
@@ -22,6 +24,11 @@ OPTIONS
 <command>...::
         Any command you can specify in a shell.
 
+record::
+        See STAT RECORD.
+
+report::
+        See STAT REPORT.
 
 -e::
 --event=::
@@ -159,6 +166,33 @@ filter out the startup phase of the program, which is often very different.
 
 Print statistics of transactional execution if supported.
 
+STAT RECORD
+-----------
+Stores stat data into perf data file.
+
+-o file::
+--output file::
+Output file name.
+
+STAT REPORT
+-----------
+Reads and reports stat data from perf data file.
+
+-i file::
+--input file::
+Input file name.
+
+--per-socket::
+Aggregate counts per processor socket for system-wide mode measurements.
+
+--per-core::
+Aggregate counts per physical processor for system-wide mode measurements.
+
+-A::
+--no-aggr::
+Do not aggregate counts across all monitored CPUs.
+
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 556cec09bf50..b0e60e17db38 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -230,6 +230,9 @@ Default is to monitor all CPUS.
         The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
         Note that this feature may not be available on all processors.
 
+--raw-trace::
+        When displaying traceevent output, do not use print fmt or plugins.
+
 INTERACTIVE PROMPTING KEYS
 --------------------------
 
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
new file mode 100644
index 000000000000..a1c10e360db5
--- /dev/null
+++ b/tools/perf/Documentation/tips.txt
@@ -0,0 +1,14 @@
+For a higher level overview, try: perf report --sort comm,dso
+Sample related events with: perf record -e '{cycles,instructions}:S'
+Compare performance results with: perf diff [<old file> <new file>]
+Boolean options have negative forms, e.g.: perf report --no-children
+Customize output of perf script with: perf script -F event,ip,sym
+Generate a script for your data: perf script -g <lang>
+Save output of perf stat using: perf stat record <target workload>
+Create an archive with symtabs to analyse on other machine: perf archive
+Search options using a keyword: perf report -h <keyword>
+Use parent filter to see specific call path: perf report -p <regex>
+List events using substring match: perf list <keyword>
+To see list of saved events and attributes: perf evlist -v
+Use --symfs <dir> if your symbol files are in non-standard locations
+To see callchains in a more compact form: perf report -g folded
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 39c38cb45b00..ddf922f93aa1 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,6 +1,7 @@
 tools/perf
 tools/arch/alpha/include/asm/barrier.h
 tools/arch/arm/include/asm/barrier.h
+tools/arch/arm64/include/asm/barrier.h
 tools/arch/ia64/include/asm/barrier.h
 tools/arch/mips/include/asm/barrier.h
 tools/arch/powerpc/include/asm/barrier.h
@@ -20,14 +21,17 @@ tools/lib/traceevent
 tools/lib/bpf
 tools/lib/api
 tools/lib/bpf
+tools/lib/subcmd
 tools/lib/hweight.c
 tools/lib/rbtree.c
+tools/lib/string.c
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
-tools/lib/util/find_next_bit.c
+tools/lib/find_bit.c
 tools/include/asm/atomic.h
 tools/include/asm/barrier.h
 tools/include/asm/bug.h
+tools/include/asm-generic/atomic-gcc.h
 tools/include/asm-generic/barrier.h
 tools/include/asm-generic/bitops/arch_hweight.h
 tools/include/asm-generic/bitops/atomic.h
@@ -50,6 +54,7 @@ tools/include/linux/log2.h
 tools/include/linux/poison.h
 tools/include/linux/rbtree.h
 tools/include/linux/rbtree_augmented.h
+tools/include/linux/string.h
 tools/include/linux/types.h
 tools/include/linux/err.h
 include/asm-generic/bitops/arch_hweight.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 0d19d5447d6c..0a22407e1d7d 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -145,9 +145,10 @@ BISON   = bison
 STRIP   = strip
 AWK     = awk
 
-LIB_DIR          = $(srctree)/tools/lib/api/
+LIB_DIR         = $(srctree)/tools/lib/api/
 TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
-BPF_DIR = $(srctree)/tools/lib/bpf/
+BPF_DIR         = $(srctree)/tools/lib/bpf/
+SUBCMD_DIR      = $(srctree)/tools/lib/subcmd/
 
 # include config/Makefile by default and rule out
 # non-config cases
@@ -184,15 +185,17 @@ strip-libs = $(filter-out -l%,$(1))
 ifneq ($(OUTPUT),)
   TE_PATH=$(OUTPUT)
   BPF_PATH=$(OUTPUT)
+  SUBCMD_PATH=$(OUTPUT)
 ifneq ($(subdir),)
-  LIB_PATH=$(OUTPUT)/../lib/api/
+  API_PATH=$(OUTPUT)/../lib/api/
 else
-  LIB_PATH=$(OUTPUT)
+  API_PATH=$(OUTPUT)
 endif
 else
   TE_PATH=$(TRACE_EVENT_DIR)
-  LIB_PATH=$(LIB_DIR)
+  API_PATH=$(LIB_DIR)
   BPF_PATH=$(BPF_DIR)
+  SUBCMD_PATH=$(SUBCMD_DIR)
 endif
 
 LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
@@ -201,11 +204,13 @@ export LIBTRACEEVENT
 LIBTRACEEVENT_DYNAMIC_LIST = $(TE_PATH)libtraceevent-dynamic-list
 LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYNAMIC_LIST)
 
-LIBAPI = $(LIB_PATH)libapi.a
+LIBAPI = $(API_PATH)libapi.a
 export LIBAPI
 
 LIBBPF = $(BPF_PATH)libbpf.a
 
+LIBSUBCMD = $(SUBCMD_PATH)libsubcmd.a
+
 # python extension build directories
 PYTHON_EXTBUILD     := $(OUTPUT)python_ext_build/
 PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/
@@ -257,7 +262,7 @@ export PERL_PATH
 
 LIB_FILE=$(OUTPUT)libperf.a
 
-PERFLIBS = $(LIB_FILE) $(LIBAPI) $(LIBTRACEEVENT)
+PERFLIBS = $(LIB_FILE) $(LIBAPI) $(LIBTRACEEVENT) $(LIBSUBCMD)
 ifndef NO_LIBBPF
   PERFLIBS += $(LIBBPF)
 endif
@@ -420,7 +425,7 @@ $(LIBTRACEEVENT)-clean:
         $(call QUIET_CLEAN, libtraceevent)
         $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) O=$(OUTPUT) clean >/dev/null
 
-install-traceevent-plugins: $(LIBTRACEEVENT)
+install-traceevent-plugins: libtraceevent_plugins
         $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) install_plugins
 
 $(LIBAPI): fixdep FORCE
@@ -431,12 +436,19 @@ $(LIBAPI)-clean:
         $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
 
 $(LIBBPF): fixdep FORCE
-        $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a
+        $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(realpath $(OUTPUT)FEATURE-DUMP)
 
 $(LIBBPF)-clean:
         $(call QUIET_CLEAN, libbpf)
         $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) clean >/dev/null
 
+$(LIBSUBCMD): fixdep FORCE
+        $(Q)$(MAKE) -C $(SUBCMD_DIR) O=$(OUTPUT) $(OUTPUT)libsubcmd.a
+
+$(LIBSUBCMD)-clean:
+        $(call QUIET_CLEAN, libsubcmd)
+        $(Q)$(MAKE) -C $(SUBCMD_DIR) O=$(OUTPUT) clean
+
 help:
         @echo 'Perf make targets:'
         @echo '  doc            - make *all* documentation (see below)'
@@ -476,7 +488,7 @@ INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html
 $(DOC_TARGETS):
         $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all)
 
-TAG_FOLDERS= . ../lib/traceevent ../lib/api ../lib/symbol ../include ../lib/bpf
+TAG_FOLDERS= . ../lib ../include
 TAG_FILES= ../../include/uapi/linux/perf_event.h
 
 TAGS:
@@ -555,6 +567,9 @@ endif
         $(call QUIET_INSTALL, perf_completion-script) \
                 $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
                 $(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
+        $(call QUIET_INSTALL, perf-tip) \
+                $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(tip_instdir_SQ)'; \
+                $(INSTALL) Documentation/tips.txt -t '$(DESTDIR_SQ)$(tip_instdir_SQ)'
 
 install-tests: all install-gtk
         $(call QUIET_INSTALL, tests) \
@@ -582,15 +597,16 @@ $(INSTALL_DOC_TARGETS):
 #
 config-clean:
         $(call QUIET_CLEAN, config)
-        $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
+        $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null
 
-clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean config-clean
+clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean
         $(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
-        $(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
+        $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
         $(Q)$(RM) $(OUTPUT).config-detected
         $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
         $(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
-                $(OUTPUT)util/intel-pt-decoder/inat-tables.c
+                $(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \
+                $(OUTPUT)tests/llvm-src-{base,kbuild,prologue}.c
         $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
         $(python-clean)
 
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index 7ed00f4b0908..b48de2f5813c 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -2,10 +2,10 @@
 #define ARCH_TESTS_H
 
 /* Tests */
-int test__rdpmc(void);
-int test__perf_time_to_tsc(void);
-int test__insn_x86(void);
-int test__intel_cqm_count_nmi_context(void);
+int test__rdpmc(int subtest);
+int test__perf_time_to_tsc(int subtest);
+int test__insn_x86(int subtest);
+int test__intel_cqm_count_nmi_context(int subtest);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c
index b6115dfd28f0..08d9b2bc185c 100644
--- a/tools/perf/arch/x86/tests/insn-x86.c
+++ b/tools/perf/arch/x86/tests/insn-x86.c
@@ -171,7 +171,7 @@ static int test_data_set(struct test_data *dat_set, int x86_64)
  * verbose (-v) option to see all the instructions and whether or not they
  * decoded successfuly.
  */
-int test__insn_x86(void)
+int test__insn_x86(int subtest __maybe_unused)
 {
         int ret = 0;
 
diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
index d28c1b6a3b54..3e89ba825f6b 100644
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -33,7 +33,7 @@ static pid_t spawn(void)
  * the last read counter value to avoid triggering a WARN_ON_ONCE() in
  * smp_call_function_many() caused by sending IPIs from NMI context.
  */
-int test__intel_cqm_count_nmi_context(void)
+int test__intel_cqm_count_nmi_context(int subtest __maybe_unused)
 {
         struct perf_evlist *evlist = NULL;
         struct perf_evsel *evsel = NULL;
@@ -54,7 +54,7 @@ int test__intel_cqm_count_nmi_context(void)
 
         ret = parse_events(evlist, "intel_cqm/llc_occupancy/", NULL);
         if (ret) {
-                pr_debug("parse_events failed\n");
+                pr_debug("parse_events failed, is \"intel_cqm/llc_occupancy/\" available?\n");
                 err = TEST_SKIP;
                 goto out;
         }
diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index 658cd200af74..9d29ee283ac5 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -35,13 +35,12 @@
  * %0 is returned, otherwise %-1 is returned.  If TSC conversion is not
  * supported then then the test passes but " (not supported)" is printed.
  */
-int test__perf_time_to_tsc(void)
+int test__perf_time_to_tsc(int subtest __maybe_unused)
 {
         struct record_opts opts = {
                 .mmap_pages          = UINT_MAX,
                 .user_freq           = UINT_MAX,
                 .user_interval       = ULLONG_MAX,
-                .freq                = 4000,
                 .target              = {
                         .uses_mmap   = true,
                 },
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index e7688214c7cf..7bb0d13c235f 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -149,7 +149,7 @@ out_close:
         return 0;
 }
 
-int test__rdpmc(void)
+int test__rdpmc(int subtest __maybe_unused)
 {
         int status = 0;
         int wret = 0;
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index ff63649fa9ac..465970370f3e 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -5,6 +5,7 @@ libperf-y += kvm-stat.o
 libperf-y += perf_regs.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
+libperf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
 
 libperf-$(CONFIG_LIBUNWIND)          += unwind-libunwind.o
 libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 9b94ce520917..8d8150f1cf9b 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -327,7 +327,7 @@ static int intel_bts_snapshot_start(struct auxtrace_record *itr)
 
         evlist__for_each(btsr->evlist, evsel) {
                 if (evsel->attr.type == btsr->intel_bts_pmu->type)
-                        return perf_evlist__disable_event(btsr->evlist, evsel);
+                        return perf_evsel__disable(evsel);
         }
         return -EINVAL;
 }
@@ -340,7 +340,7 @@ static int intel_bts_snapshot_finish(struct auxtrace_record *itr)
 
         evlist__for_each(btsr->evlist, evsel) {
                 if (evsel->attr.type == btsr->intel_bts_pmu->type)
-                        return perf_evlist__enable_event(btsr->evlist, evsel);
+                        return perf_evsel__enable(evsel);
         }
         return -EINVAL;
 }
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index b02af064f0f9..f05daacc9e78 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -26,7 +26,7 @@
 #include "../../util/evlist.h"
 #include "../../util/evsel.h"
 #include "../../util/cpumap.h"
-#include "../../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../../util/parse-events.h"
 #include "../../util/pmu.h"
 #include "../../util/debug.h"
@@ -725,7 +725,7 @@ static int intel_pt_snapshot_start(struct auxtrace_record *itr)
 
         evlist__for_each(ptr->evlist, evsel) {
                 if (evsel->attr.type == ptr->intel_pt_pmu->type)
-                        return perf_evlist__disable_event(ptr->evlist, evsel);
+                        return perf_evsel__disable(evsel);
         }
         return -EINVAL;
 }
@@ -738,7 +738,7 @@ static int intel_pt_snapshot_finish(struct auxtrace_record *itr)
 
         evlist__for_each(ptr->evlist, evsel) {
                 if (evsel->attr.type == ptr->intel_pt_pmu->type)
-                        return perf_evlist__enable_event(ptr->evlist, evsel);
+                        return perf_evsel__enable(evsel);
         }
         return -EINVAL;
 }
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index fc9bebd2cca0..0999ac536d86 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -11,7 +11,7 @@
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/stat.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../util/header.h"
 #include "bench.h"
 #include "futex.h"
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index bc6a16adbca8..6a18ce21f865 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -5,7 +5,7 @@
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/stat.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../util/header.h"
 #include "bench.h"
 #include "futex.h"
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index ad0d9b5342fb..718238683013 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -11,7 +11,7 @@
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/stat.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../util/header.h"
 #include "bench.h"
 #include "futex.h"
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 6d8c9fa2a16c..91aaf2a1fa90 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -10,7 +10,7 @@
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/stat.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../util/header.h"
 #include "bench.h"
 #include "futex.h"
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index e5e41d3bdce7..f416bd705f66 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -11,7 +11,7 @@
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/stat.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../util/header.h"
 #include "bench.h"
 #include "futex.h"
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index 9419b944220f..a91aa85d80ff 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -8,7 +8,7 @@
 
 #include "../perf.h"
 #include "../util/util.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../util/header.h"
 #include "../util/cloexec.h"
 #include "bench.h"
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 492df2752a2d..5049d6357a46 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -7,7 +7,7 @@
 #include "../perf.h"
 #include "../builtin.h"
 #include "../util/util.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../util/cloexec.h"
 
 #include "bench.h"
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index d4ff1b539cfd..bfaf9503de8e 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -11,7 +11,7 @@
 
 #include "../perf.h"
 #include "../util/util.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../builtin.h"
 #include "bench.h"
 
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 005cc283790c..1dc2d13cc272 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -10,7 +10,7 @@
  */
 #include "../perf.h"
 #include "../util/util.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../builtin.h"
 #include "bench.h"
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 2bf9b3fd9e61..cc5c1267c738 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -21,7 +21,7 @@
 #include "util/evsel.h"
 #include "util/annotate.h"
 #include "util/event.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-events.h"
 #include "util/thread.h"
 #include "util/sort.h"
@@ -47,7 +47,7 @@ struct perf_annotate {
 };
 
 static int perf_evsel__add_sample(struct perf_evsel *evsel,
-                                  struct perf_sample *sample __maybe_unused,
+                                  struct perf_sample *sample,
                                   struct addr_location *al,
                                   struct perf_annotate *ann)
 {
@@ -72,7 +72,10 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
                 return 0;
         }
 
-        he = __hists__add_entry(hists, al, NULL, NULL, NULL, 1, 1, 0, true);
+        sample->period = 1;
+        sample->weight = 1;
+
+        he = __hists__add_entry(hists, al, NULL, NULL, NULL, sample, true);
         if (he == NULL)
                 return -ENOMEM;
 
@@ -343,18 +346,19 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
                 return ret;
 
         argc = parse_options(argc, argv, options, annotate_usage, 0);
+        if (argc) {
+                /*
+                 * Special case: if there's an argument left then assume that
+                 * it's a symbol filter:
+                 */
+                if (argc > 1)
+                        usage_with_options(annotate_usage, options);
 
-        if (annotate.use_stdio)
-                use_browser = 0;
-        else if (annotate.use_tui)
-                use_browser = 1;
-        else if (annotate.use_gtk)
-                use_browser = 2;
+                annotate.sym_hist_filter = argv[0];
+        }
 
         file.path  = input_name;
 
-        setup_browser(true);
-
         annotate.session = perf_session__new(&file, false, &annotate.tool);
         if (annotate.session == NULL)
                 return -1;
@@ -366,19 +370,17 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
         if (ret < 0)
                 goto out_delete;
 
-        if (setup_sorting() < 0)
+        if (setup_sorting(NULL) < 0)
                 usage_with_options(annotate_usage, options);
 
-        if (argc) {
-                /*
-                 * Special case: if there's an argument left then assume that
-                 * it's a symbol filter:
-                 */
-                if (argc > 1)
-                        usage_with_options(annotate_usage, options);
+        if (annotate.use_stdio)
+                use_browser = 0;
+        else if (annotate.use_tui)
+                use_browser = 1;
+        else if (annotate.use_gtk)
+                use_browser = 2;
 
-                annotate.sym_hist_filter = argv[0];
-        }
+        setup_browser(true);
 
         ret = __cmd_annotate(&annotate);
 
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index b17aed36ca16..a1cddc6bbf0f 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -16,7 +16,7 @@
  */
 #include "perf.h"
 #include "util/util.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "builtin.h"
 #include "bench/bench.h"
 
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 7b8450cd33c2..d93bff7fc0e4 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -16,7 +16,7 @@
 #include "util/cache.h"
 #include "util/debug.h"
 #include "util/header.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/strlist.h"
 #include "util/build-id.h"
 #include "util/session.h"
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 6419f57b0850..5e914ee79eb3 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -12,7 +12,7 @@
 #include "util/build-id.h"
 #include "util/cache.h"
 #include "util/debug.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/session.h"
 #include "util/symbol.h"
 #include "util/data.h"
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
new file mode 100644
index 000000000000..f04e804a9fad
--- /dev/null
+++ b/tools/perf/builtin-config.c
@@ -0,0 +1,66 @@
+/*
+ * builtin-config.c
+ *
+ * Copyright (C) 2015, Taeung Song <treeze.taeung@gmail.com>
+ *
+ */
+#include "builtin.h"
+
+#include "perf.h"
+
+#include "util/cache.h"
+#include <subcmd/parse-options.h>
+#include "util/util.h"
+#include "util/debug.h"
+
+static const char * const config_usage[] = {
+        "perf config [options]",
+        NULL
+};
+
+enum actions {
+        ACTION_LIST = 1
+} actions;
+
+static struct option config_options[] = {
+        OPT_SET_UINT('l', "list", &actions,
+                     "show current config variables", ACTION_LIST),
+        OPT_END()
+};
+
+static int show_config(const char *key, const char *value,
+                       void *cb __maybe_unused)
+{
+        if (value)
+                printf("%s=%s\n", key, value);
+        else
+                printf("%s\n", key);
+
+        return 0;
+}
+
+int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+        int ret = 0;
+
+        argc = parse_options(argc, argv, config_options, config_usage,
+                             PARSE_OPT_STOP_AT_NON_OPTION);
+
+        switch (actions) {
+        case ACTION_LIST:
+                if (argc) {
+                        pr_err("Error: takes no arguments\n");
+                        parse_options_usage(config_usage, config_options, "l", 1);
+                } else {
+                        ret = perf_config(show_config, NULL);
+                        if (ret < 0)
+                                pr_err("Nothing configured, "
+                                       "please check your ~/.perfconfig file\n");
+                }
+                break;
+        default:
+                usage_with_options(config_usage, config_options);
+        }
+
+        return ret;
+}
diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c
index d6525bc54d13..b97bc1518b44 100644
--- a/tools/perf/builtin-data.c
+++ b/tools/perf/builtin-data.c
@@ -2,7 +2,7 @@
 #include "builtin.h"
 #include "perf.h"
 #include "debug.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 #include "data-convert-bt.h"
 
 typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 0b180a885ba3..36ccc2b8827f 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -311,11 +311,11 @@ static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair,
 }
 
 static int hists__add_entry(struct hists *hists,
-                            struct addr_location *al, u64 period,
-                            u64 weight, u64 transaction)
+                            struct addr_location *al,
+                            struct perf_sample *sample)
 {
-        if (__hists__add_entry(hists, al, NULL, NULL, NULL, period, weight,
-                               transaction, true) != NULL)
+        if (__hists__add_entry(hists, al, NULL, NULL, NULL,
+                               sample, true) != NULL)
                 return 0;
         return -ENOMEM;
 }
@@ -336,8 +336,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
                 return -1;
         }
 
-        if (hists__add_entry(hists, &al, sample->period,
-                             sample->weight, sample->transaction)) {
+        if (hists__add_entry(hists, &al, sample)) {
                 pr_warning("problem incrementing symbol period, skipping event\n");
                 goto out_put;
         }
@@ -1208,7 +1207,7 @@ static int ui_init(void)
                 BUG_ON(1);
         }
 
-        list_add(&fmt->sort_list, &perf_hpp__sort_list);
+        perf_hpp__register_sort_field(fmt);
         return 0;
 }
 
@@ -1280,7 +1279,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 
         sort__mode = SORT_MODE__DIFF;
 
-        if (setup_sorting() < 0)
+        if (setup_sorting(NULL) < 0)
                 usage_with_options(diff_usage, options);
 
         setup_pager();
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index f4d62510acbb..8a31f511e1a0 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -12,7 +12,7 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/parse-events.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/session.h"
 #include "util/data.h"
 #include "util/debug.h"
@@ -26,14 +26,22 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
                 .mode = PERF_DATA_MODE_READ,
                 .force = details->force,
         };
+        bool has_tracepoint = false;
 
         session = perf_session__new(&file, 0, NULL);
         if (session == NULL)
                 return -1;
 
-        evlist__for_each(session->evlist, pos)
+        evlist__for_each(session->evlist, pos) {
                 perf_evsel__fprintf(pos, details, stdout);
 
+                if (pos->attr.type == PERF_TYPE_TRACEPOINT)
+                        has_tracepoint = true;
+        }
+
+        if (has_tracepoint && !details->trace_fields)
+                printf("# Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events\n");
+
         perf_session__delete(session);
         return 0;
 }
@@ -49,6 +57,7 @@ int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused)
         OPT_BOOLEAN('g', "group", &details.event_group,
                     "Show event group information"),
         OPT_BOOLEAN('f', "force", &details.force, "don't complain, do it"),
+        OPT_BOOLEAN(0, "trace-fields", &details.trace_fields, "Show tracepoint fields"),
         OPT_END()
         };
         const char * const evlist_usage[] = {
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index a7d588bf3cdd..96c1a4cfbbbf 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -6,11 +6,11 @@
 #include "perf.h"
 #include "util/cache.h"
 #include "builtin.h"
-#include "util/exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "common-cmds.h"
-#include "util/parse-options.h"
-#include "util/run-command.h"
-#include "util/help.h"
+#include <subcmd/parse-options.h>
+#include <subcmd/run-command.h>
+#include <subcmd/help.h>
 #include "util/debug.h"
 
 static struct man_viewer_list {
@@ -407,7 +407,7 @@ static int get_html_page_path(struct strbuf *page_path, const char *page)
 #ifndef open_html
 static void open_html(const char *path)
 {
-        execl_perf_cmd("web--browse", "-c", "help.browser", path, NULL);
+        execl_cmd("web--browse", "-c", "help.browser", path, NULL);
 }
 #endif
 
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 99d127fe9c35..0022e02ed31a 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -18,7 +18,7 @@
 #include "util/data.h"
 #include "util/auxtrace.h"
 
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 
 #include <linux/list.h>
 
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 93ce665f976f..118010553d0c 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -12,7 +12,7 @@
 #include "util/tool.h"
 #include "util/callchain.h"
 
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/trace-event.h"
 #include "util/data.h"
 #include "util/cpumap.h"
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index dd94b4ca2213..4418d9214872 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -10,7 +10,7 @@
 #include "util/header.h"
 #include "util/session.h"
 #include "util/intlist.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/trace-event.h"
 #include "util/debug.h"
 #include "util/tool.h"
@@ -1351,7 +1351,6 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
         disable_buildid_cache();
 
         use_browser = 0;
-        setup_browser(false);
 
         if (argc) {
                 argc = parse_options(argc, argv, live_options,
@@ -1409,8 +1408,6 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
         err = kvm_events_live_report(kvm);
 
 out:
-        exit_browser(0);
-
         if (kvm->session)
                 perf_session__delete(kvm->session);
         kvm->session = NULL;
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index bf679e2c978b..5e22db4684b8 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -14,7 +14,7 @@
 #include "util/parse-events.h"
 #include "util/cache.h"
 #include "util/pmu.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 
 int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 {
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index de16aaed516e..ce3bfb48b26f 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -9,7 +9,7 @@
 #include "util/thread.h"
 #include "util/header.h"
 
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/trace-event.h"
 
 #include "util/debug.h"
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 80170aace5d4..390170041696 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -1,7 +1,7 @@
 #include "builtin.h"
 #include "perf.h"
 
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/trace-event.h"
 #include "util/tool.h"
 #include "util/session.h"
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 132afc97676c..9af859b28b15 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -37,7 +37,7 @@
 #include "util/strfilter.h"
 #include "util/symbol.h"
 #include "util/debug.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/probe-finder.h"
 #include "util/probe-event.h"
 #include "util/probe-file.h"
@@ -249,6 +249,9 @@ static int opt_show_vars(const struct option *opt,
 
         return ret;
 }
+#else
+# define opt_show_lines NULL
+# define opt_show_vars NULL
 #endif
 static int opt_add_probe_event(const struct option *opt,
                               const char *str, int unset __maybe_unused)
@@ -473,7 +476,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
                 opt_add_probe_event),
         OPT_BOOLEAN('f', "force", &probe_conf.force_add, "forcibly add events"
                     " with existing name"),
-#ifdef HAVE_DWARF_SUPPORT
         OPT_CALLBACK('L', "line", NULL,
                      "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]",
                      "Show source code lines.", opt_show_lines),
@@ -490,7 +492,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
                    "directory", "path to kernel source"),
         OPT_BOOLEAN('\0', "no-inlines", &probe_conf.no_inlines,
                 "Don't search inlined functions"),
-#endif
         OPT__DRY_RUN(&probe_event_dry_run),
         OPT_INTEGER('\0', "max-probes", &probe_conf.max_probes,
                  "Set how many probe points can be found for a probe."),
@@ -521,6 +522,16 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 #ifdef HAVE_DWARF_SUPPORT
         set_option_flag(options, 'L', "line", PARSE_OPT_EXCLUSIVE);
         set_option_flag(options, 'V', "vars", PARSE_OPT_EXCLUSIVE);
+#else
+# define set_nobuild(s, l, c) set_option_nobuild(options, s, l, "NO_DWARF=1", c)
+        set_nobuild('L', "line", false);
+        set_nobuild('V', "vars", false);
+        set_nobuild('\0', "externs", false);
+        set_nobuild('\0', "range", false);
+        set_nobuild('k', "vmlinux", true);
+        set_nobuild('s', "source", true);
+        set_nobuild('\0', "no-inlines", true);
+# undef set_nobuild
 #endif
         set_option_flag(options, 'F', "funcs", PARSE_OPT_EXCLUSIVE);
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 199fc31e3919..dc4e0adf5c5b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -11,7 +11,7 @@
 
 #include "util/build-id.h"
 #include "util/util.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-events.h"
 
 #include "util/callchain.h"
@@ -452,6 +452,8 @@ static void record__init_features(struct record *rec)
 
         if (!rec->opts.full_auxtrace)
                 perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
+
+        perf_header__clear_feat(&session->header, HEADER_STAT);
 }
 
 static volatile int workload_exec_errno;
@@ -813,8 +815,12 @@ int record_parse_callchain_opt(const struct option *opt,
         }
 
         ret = parse_callchain_record_opt(arg, &callchain_param);
-        if (!ret)
+        if (!ret) {
+                /* Enable data address sampling for DWARF unwind. */
+                if (callchain_param.record_mode == CALLCHAIN_DWARF)
+                        record->sample_address = true;
                 callchain_debug();
+        }
 
         return ret;
 }
@@ -837,6 +843,19 @@ int record_callchain_opt(const struct option *opt,
 
 static int perf_record_config(const char *var, const char *value, void *cb)
 {
+        struct record *rec = cb;
+
+        if (!strcmp(var, "record.build-id")) {
+                if (!strcmp(value, "cache"))
+                        rec->no_buildid_cache = false;
+                else if (!strcmp(value, "no-cache"))
+                        rec->no_buildid_cache = true;
+                else if (!strcmp(value, "skip"))
+                        rec->no_buildid = true;
+                else
+                        return -1;
+                return 0;
+        }
         if (!strcmp(var, "record.call-graph"))
                 var = "call-graph.record-mode"; /* fall-through */
 
@@ -1113,12 +1132,12 @@ struct option __record_options[] = {
                         "per thread proc mmap processing timeout in ms"),
         OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
                     "Record context switch events"),
-#ifdef HAVE_LIBBPF_SUPPORT
         OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path",
                    "clang binary to use for compiling BPF scriptlets"),
         OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options",
                    "options passed to clang when compiling BPF scriptlets"),
-#endif
+        OPT_STRING(0, "vmlinux", &symbol_conf.vmlinux_name,
+                   "file", "vmlinux pathname"),
         OPT_END()
 };
 
@@ -1130,6 +1149,27 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
         struct record *rec = &record;
         char errbuf[BUFSIZ];
 
+#ifndef HAVE_LIBBPF_SUPPORT
+# define set_nobuild(s, l, c) set_option_nobuild(record_options, s, l, "NO_LIBBPF=1", c)
+        set_nobuild('\0', "clang-path", true);
+        set_nobuild('\0', "clang-opt", true);
+# undef set_nobuild
+#endif
+
+#ifndef HAVE_BPF_PROLOGUE
+# if !defined (HAVE_DWARF_SUPPORT)
+#  define REASON  "NO_DWARF=1"
+# elif !defined (HAVE_LIBBPF_SUPPORT)
+#  define REASON  "NO_LIBBPF=1"
+# else
+#  define REASON  "this architecture doesn't support BPF prologue"
+# endif
+# define set_nobuild(s, l, c) set_option_nobuild(record_options, s, l, REASON, c)
+        set_nobuild('\0', "vmlinux", true);
+# undef set_nobuild
+# undef REASON
+#endif
+
         rec->evlist = perf_evlist__new();
         if (rec->evlist == NULL)
                 return -ENOMEM;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index f256fac1e722..d5a42ee12529 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -27,7 +27,7 @@
 #include "util/session.h"
 #include "util/tool.h"
 
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-events.h"
 
 #include "util/thread.h"
@@ -45,7 +45,6 @@ struct report {
         struct perf_tool        tool;
         struct perf_session     *session;
         bool                    use_tui, use_gtk, use_stdio;
-        bool                    hide_unresolved;
         bool                    dont_use_callchains;
         bool                    show_full_info;
         bool                    show_threads;
@@ -146,7 +145,7 @@ static int process_sample_event(struct perf_tool *tool,
         struct hist_entry_iter iter = {
                 .evsel                  = evsel,
                 .sample                 = sample,
-                .hide_unresolved        = rep->hide_unresolved,
+                .hide_unresolved        = symbol_conf.hide_unresolved,
                 .add_entry_cb           = hist_iter__report_callback,
         };
         int ret = 0;
@@ -157,7 +156,7 @@ static int process_sample_event(struct perf_tool *tool,
                 return -1;
         }
 
-        if (rep->hide_unresolved && al.sym == NULL)
+        if (symbol_conf.hide_unresolved && al.sym == NULL)
                 goto out_put;
 
         if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
@@ -434,7 +433,7 @@ static int report__browse_hists(struct report *rep)
         int ret;
         struct perf_session *session = rep->session;
         struct perf_evlist *evlist = session->evlist;
-        const char *help = "For a higher level overview, try: perf report --sort comm,dso";
+        const char *help = perf_tip(TIPDIR);
 
         switch (use_browser) {
         case 1:
@@ -514,20 +513,26 @@ static int __cmd_report(struct report *rep)
         if (rep->cpu_list) {
                 ret = perf_session__cpu_bitmap(session, rep->cpu_list,
                                                rep->cpu_bitmap);
-                if (ret)
+                if (ret) {
+                        ui__error("failed to set cpu bitmap\n");
                         return ret;
+                }
         }
 
         if (rep->show_threads)
                 perf_read_values_init(&rep->show_threads_values);
 
         ret = report__setup_sample_type(rep);
-        if (ret)
+        if (ret) {
+                /* report__setup_sample_type() already showed error message */
                 return ret;
+        }
 
         ret = perf_session__process_events(session);
-        if (ret)
+        if (ret) {
+                ui__error("failed to process sample\n");
                 return ret;
+        }
 
         report__warn_kptr_restrict(rep);
 
@@ -625,7 +630,7 @@ parse_percent_limit(const struct option *opt, const char *str,
         return 0;
 }
 
-#define CALLCHAIN_DEFAULT_OPT  "graph,0.5,caller,function"
+#define CALLCHAIN_DEFAULT_OPT  "graph,0.5,caller,function,percent"
 
 const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n"
                                      CALLCHAIN_REPORT_HELP
@@ -708,7 +713,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
         OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
                     "Only display entries with parent-match"),
         OPT_CALLBACK_DEFAULT('g', "call-graph", &report,
-                             "print_type,threshold[,print_limit],order,sort_key[,branch]",
+                             "print_type,threshold[,print_limit],order,sort_key[,branch],value",
                              report_callchain_help, &report_parse_callchain_opt,
                              callchain_default_opt),
         OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
@@ -740,7 +745,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
         OPT_STRING_NOEMPTY('t', "field-separator", &symbol_conf.field_sep, "separator",
                    "separator for columns, no spaces will be added between "
                    "columns '.' is reserved."),
-        OPT_BOOLEAN('U', "hide-unresolved", &report.hide_unresolved,
+        OPT_BOOLEAN('U', "hide-unresolved", &symbol_conf.hide_unresolved,
                     "Only display entries resolved to a symbol"),
         OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
                     "Look for files with symbols relative to this directory"),
@@ -783,6 +788,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                     "Show callgraph from reference event"),
         OPT_INTEGER(0, "socket-filter", &report.socket_filter,
                     "only show processor socket that match with this filter"),
+        OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace,
+                    "Show raw trace event output (do not use print fmt or plugins)"),
         OPT_END()
         };
         struct perf_data_file file = {
@@ -796,6 +803,16 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
         perf_config(report__config, &report);
 
         argc = parse_options(argc, argv, options, report_usage, 0);
+        if (argc) {
+                /*
+                 * Special case: if there's an argument left then assume that
+                 * it's a symbol filter:
+                 */
+                if (argc > 1)
+                        usage_with_options(report_usage, options);
+
+                report.symbol_filter_str = argv[0];
+        }
 
         if (symbol_conf.vmlinux_name &&
             access(symbol_conf.vmlinux_name, R_OK)) {
@@ -882,7 +899,7 @@ repeat:
                 symbol_conf.cumulate_callchain = false;
         }
 
-        if (setup_sorting() < 0) {
+        if (setup_sorting(session->evlist) < 0) {
                 if (sort_order)
                         parse_options_usage(report_usage, options, "s", 1);
                 if (field_order)
@@ -941,17 +958,6 @@ repeat:
         if (symbol__init(&session->header.env) < 0)
                 goto error;
 
-        if (argc) {
-                /*
-                 * Special case: if there's an argument left then assume that
-                 * it's a symbol filter:
-                 */
-                if (argc > 1)
-                        usage_with_options(report_usage, options);
-
-                report.symbol_filter_str = argv[0];
-        }
-
         sort__setup_elide(stdout);
 
         ret = __cmd_report(&report);
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index e3d3e32c0a93..871b55ae22a4 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -12,7 +12,7 @@
 #include "util/tool.h"
 #include "util/cloexec.h"
 
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/trace-event.h"
 
 #include "util/debug.h"
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 72b5deb4bd79..c691214d820f 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3,9 +3,9 @@
 #include "perf.h"
 #include "util/cache.h"
 #include "util/debug.h"
-#include "util/exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "util/header.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/perf_regs.h"
 #include "util/session.h"
 #include "util/tool.h"
@@ -18,7 +18,11 @@
 #include "util/sort.h"
 #include "util/data.h"
 #include "util/auxtrace.h"
+#include "util/cpumap.h"
+#include "util/thread_map.h"
+#include "util/stat.h"
 #include <linux/bitmap.h>
+#include "asm/bug.h"
 
 static char const               *script_name;
 static char const               *generate_script_lang;
@@ -32,6 +36,7 @@ static bool			print_flags;
 static bool                     nanosecs;
 static const char               *cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+static struct perf_stat_config  stat_config;
 
 unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH;
 
@@ -130,6 +135,18 @@ static struct {
 
                 .invalid_fields = PERF_OUTPUT_TRACE,
         },
+
+        [PERF_TYPE_BREAKPOINT] = {
+                .user_set = false,
+
+                .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+                              PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+                              PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+                              PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
+                              PERF_OUTPUT_PERIOD,
+
+                .invalid_fields = PERF_OUTPUT_TRACE,
+        },
 };
 
 static bool output_set_by_user(void)
@@ -204,6 +221,9 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
         struct perf_event_attr *attr = &evsel->attr;
         bool allow_user_set;
 
+        if (perf_header__has_feat(&session->header, HEADER_STAT))
+                return 0;
+
         allow_user_set = perf_header__has_feat(&session->header,
                                                HEADER_AUXTRACE);
 
@@ -588,8 +608,35 @@ static void print_sample_flags(u32 flags)
         printf("  %-4s ", str);
 }
 
-static void process_event(union perf_event *event, struct perf_sample *sample,
-                          struct perf_evsel *evsel, struct addr_location *al)
+struct perf_script {
+        struct perf_tool        tool;
+        struct perf_session     *session;
+        bool                    show_task_events;
+        bool                    show_mmap_events;
+        bool                    show_switch_events;
+        bool                    allocated;
+        struct cpu_map          *cpus;
+        struct thread_map       *threads;
+        int                     name_width;
+};
+
+static int perf_evlist__max_name_len(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel;
+        int max = 0;
+
+        evlist__for_each(evlist, evsel) {
+                int len = strlen(perf_evsel__name(evsel));
+
+                max = MAX(len, max);
+        }
+
+        return max;
+}
+
+static void process_event(struct perf_script *script, union perf_event *event,
+                          struct perf_sample *sample, struct perf_evsel *evsel,
+                          struct addr_location *al)
 {
         struct thread *thread = al->thread;
         struct perf_event_attr *attr = &evsel->attr;
@@ -604,7 +651,12 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 
         if (PRINT_FIELD(EVNAME)) {
                 const char *evname = perf_evsel__name(evsel);
-                printf("%s: ", evname ? evname : "[unknown]");
+
+                if (!script->name_width)
+                        script->name_width = perf_evlist__max_name_len(script->session->evlist);
+
+                printf("%*s: ", script->name_width,
+                       evname ? evname : "[unknown]");
         }
 
         if (print_flags)
@@ -643,65 +695,81 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
         printf("\n");
 }
 
-static int default_start_script(const char *script __maybe_unused,
-                                int argc __maybe_unused,
-                                const char **argv __maybe_unused)
-{
-        return 0;
-}
+static struct scripting_ops     *scripting_ops;
 
-static int default_flush_script(void)
+static void __process_stat(struct perf_evsel *counter, u64 tstamp)
 {
-        return 0;
+        int nthreads = thread_map__nr(counter->threads);
+        int ncpus = perf_evsel__nr_cpus(counter);
+        int cpu, thread;
+        static int header_printed;
+
+        if (counter->system_wide)
+                nthreads = 1;
+
+        if (!header_printed) {
+                printf("%3s %8s %15s %15s %15s %15s %s\n",
+                       "CPU", "THREAD", "VAL", "ENA", "RUN", "TIME", "EVENT");
+                header_printed = 1;
+        }
+
+        for (thread = 0; thread < nthreads; thread++) {
+                for (cpu = 0; cpu < ncpus; cpu++) {
+                        struct perf_counts_values *counts;
+
+                        counts = perf_counts(counter->counts, cpu, thread);
+
+                        printf("%3d %8d %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %s\n",
+                                counter->cpus->map[cpu],
+                                thread_map__pid(counter->threads, thread),
+                                counts->val,
+                                counts->ena,
+                                counts->run,
+                                tstamp,
+                                perf_evsel__name(counter));
+                }
+        }
 }
 
-static int default_stop_script(void)
+static void process_stat(struct perf_evsel *counter, u64 tstamp)
 {
-        return 0;
+        if (scripting_ops && scripting_ops->process_stat)
+                scripting_ops->process_stat(&stat_config, counter, tstamp);
+        else
+                __process_stat(counter, tstamp);
 }
 
-static int default_generate_script(struct pevent *pevent __maybe_unused,
-                                   const char *outfile __maybe_unused)
+static void process_stat_interval(u64 tstamp)
 {
-        return 0;
+        if (scripting_ops && scripting_ops->process_stat_interval)
+                scripting_ops->process_stat_interval(tstamp);
 }
 
-static struct scripting_ops default_scripting_ops = {
-        .start_script           = default_start_script,
-        .flush_script           = default_flush_script,
-        .stop_script            = default_stop_script,
-        .process_event          = process_event,
-        .generate_script        = default_generate_script,
-};
-
-static struct scripting_ops     *scripting_ops;
-
 static void setup_scripting(void)
 {
         setup_perl_scripting();
         setup_python_scripting();
-
-        scripting_ops = &default_scripting_ops;
 }
 
 static int flush_scripting(void)
 {
-        return scripting_ops->flush_script();
+        return scripting_ops ? scripting_ops->flush_script() : 0;
 }
 
 static int cleanup_scripting(void)
 {
         pr_debug("\nperf script stopped\n");
 
-        return scripting_ops->stop_script();
+        return scripting_ops ? scripting_ops->stop_script() : 0;
 }
 
-static int process_sample_event(struct perf_tool *tool __maybe_unused,
+static int process_sample_event(struct perf_tool *tool,
                                 union perf_event *event,
                                 struct perf_sample *sample,
                                 struct perf_evsel *evsel,
                                 struct machine *machine)
 {
+        struct perf_script *scr = container_of(tool, struct perf_script, tool);
         struct addr_location al;
 
         if (debug_mode) {
@@ -727,20 +795,16 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
         if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
                 goto out_put;
 
-        scripting_ops->process_event(event, sample, evsel, &al);
+        if (scripting_ops)
+                scripting_ops->process_event(event, sample, evsel, &al);
+        else
+                process_event(scr, event, sample, evsel, &al);
+
 out_put:
         addr_location__put(&al);
         return 0;
 }
 
-struct perf_script {
-        struct perf_tool        tool;
-        struct perf_session     *session;
-        bool                    show_task_events;
-        bool                    show_mmap_events;
-        bool                    show_switch_events;
-};
-
 static int process_attr(struct perf_tool *tool, union perf_event *event,
                         struct perf_evlist **pevlist)
 {
@@ -1156,6 +1220,8 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
                         type = PERF_TYPE_TRACEPOINT;
                 else if (!strcmp(str, "raw"))
                         type = PERF_TYPE_RAW;
+                else if (!strcmp(str, "break"))
+                        type = PERF_TYPE_BREAKPOINT;
                 else {
                         fprintf(stderr, "Invalid event type in field string.\n");
                         rc = -EINVAL;
@@ -1421,7 +1487,7 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
         char first_half[BUFSIZ];
         char *script_root;
 
-        snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+        snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
 
         scripts_dir = opendir(scripts_path);
         if (!scripts_dir)
@@ -1542,7 +1608,7 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
         if (!session)
                 return -1;
 
-        snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+        snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
 
         scripts_dir = opendir(scripts_path);
         if (!scripts_dir) {
@@ -1600,7 +1666,7 @@ static char *get_script_path(const char *script_root, const char *suffix)
         char lang_path[MAXPATHLEN];
         char *__script_root;
 
-        snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+        snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
 
         scripts_dir = opendir(scripts_path);
         if (!scripts_dir)
@@ -1695,6 +1761,87 @@ static void script__setup_sample_type(struct perf_script *script)
         }
 }
 
+static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
+                                    union perf_event *event,
+                                    struct perf_session *session)
+{
+        struct stat_round_event *round = &event->stat_round;
+        struct perf_evsel *counter;
+
+        evlist__for_each(session->evlist, counter) {
+                perf_stat_process_counter(&stat_config, counter);
+                process_stat(counter, round->time);
+        }
+
+        process_stat_interval(round->time);
+        return 0;
+}
+
+static int process_stat_config_event(struct perf_tool *tool __maybe_unused,
+                                     union perf_event *event,
+                                     struct perf_session *session __maybe_unused)
+{
+        perf_event__read_stat_config(&stat_config, &event->stat_config);
+        return 0;
+}
+
+static int set_maps(struct perf_script *script)
+{
+        struct perf_evlist *evlist = script->session->evlist;
+
+        if (!script->cpus || !script->threads)
+                return 0;
+
+        if (WARN_ONCE(script->allocated, "stats double allocation\n"))
+                return -EINVAL;
+
+        perf_evlist__set_maps(evlist, script->cpus, script->threads);
+
+        if (perf_evlist__alloc_stats(evlist, true))
+                return -ENOMEM;
+
+        script->allocated = true;
+        return 0;
+}
+
+static
+int process_thread_map_event(struct perf_tool *tool,
+                             union perf_event *event,
+                             struct perf_session *session __maybe_unused)
+{
+        struct perf_script *script = container_of(tool, struct perf_script, tool);
+
+        if (script->threads) {
+                pr_warning("Extra thread map event, ignoring.\n");
+                return 0;
+        }
+
+        script->threads = thread_map__new_event(&event->thread_map);
+        if (!script->threads)
+                return -ENOMEM;
+
+        return set_maps(script);
+}
+
+static
+int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
+                          union perf_event *event,
+                          struct perf_session *session __maybe_unused)
+{
+        struct perf_script *script = container_of(tool, struct perf_script, tool);
+
+        if (script->cpus) {
+                pr_warning("Extra cpu map event, ignoring.\n");
+                return 0;
+        }
+
+        script->cpus = cpu_map__new_data(&event->cpu_map.data);
+        if (!script->cpus)
+                return -ENOMEM;
+
+        return set_maps(script);
+}
+
 int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 {
         bool show_full_info = false;
@@ -1723,6 +1870,11 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
                         .auxtrace_info   = perf_event__process_auxtrace_info,
                         .auxtrace        = perf_event__process_auxtrace,
                         .auxtrace_error  = perf_event__process_auxtrace_error,
+                        .stat            = perf_event__process_stat_event,
+                        .stat_round      = process_stat_round_event,
+                        .stat_config     = process_stat_config_event,
+                        .thread_map      = process_thread_map_event,
+                        .cpu_map         = process_cpu_map_event,
                         .ordered_events  = true,
                         .ordering_requires_timestamps = true,
                 },
@@ -1836,7 +1988,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
                 scripting_max_stack = itrace_synth_opts.callchain_sz;
 
         /* make sure PERF_EXEC_PATH is set for scripts */
-        perf_set_argv_exec_path(perf_exec_path());
+        set_argv_exec_path(get_argv_exec_path());
 
         if (argc && !script_name && !rec_script_path && !rep_script_path) {
                 int live_pipe[2];
@@ -2076,6 +2228,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
         flush_scripting();
 
 out_delete:
+        perf_evlist__free_stats(session->evlist);
         perf_session__delete(session);
 
         if (script_started)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e77880b5094d..7f568244662b 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -45,7 +45,7 @@
 #include "builtin.h"
 #include "util/cgroup.h"
 #include "util/util.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-events.h"
 #include "util/pmu.h"
 #include "util/event.h"
@@ -59,6 +59,9 @@
 #include "util/thread.h"
 #include "util/thread_map.h"
 #include "util/counts.h"
+#include "util/session.h"
+#include "util/tool.h"
+#include "asm/bug.h"
 
 #include <stdlib.h>
 #include <sys/prctl.h>
@@ -126,6 +129,21 @@ static bool			append_file;
 static const char               *output_name;
 static int                      output_fd;
 
+struct perf_stat {
+        bool                     record;
+        struct perf_data_file    file;
+        struct perf_session     *session;
+        u64                      bytes_written;
+        struct perf_tool         tool;
+        bool                     maps_allocated;
+        struct cpu_map          *cpus;
+        struct thread_map       *threads;
+        enum aggr_mode           aggr_mode;
+};
+
+static struct perf_stat         perf_stat;
+#define STAT_RECORD             perf_stat.record
+
 static volatile int done = 0;
 
 static struct perf_stat_config stat_config = {
@@ -161,15 +179,43 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 
         attr->inherit = !no_inherit;
 
-        if (target__has_cpu(&target))
-                return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
+        /*
+         * Some events get initialized with sample_(period/type) set,
+         * like tracepoints. Clear it up for counting.
+         */
+        attr->sample_period = 0;
+
+        /*
+         * But set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless
+         * while avoiding that older tools show confusing messages.
+         *
+         * However for pipe sessions we need to keep it zero,
+         * because script's perf_evsel__check_attr is triggered
+         * by attr->sample_type != 0, and we can't run it on
+         * stat sessions.
+         */
+        if (!(STAT_RECORD && perf_stat.file.is_pipe))
+                attr->sample_type = PERF_SAMPLE_IDENTIFIER;
 
-        if (!target__has_task(&target) && perf_evsel__is_group_leader(evsel)) {
+        /*
+         * Disabling all counters initially, they will be enabled
+         * either manually by us or by kernel via enable_on_exec
+         * set later.
+         */
+        if (perf_evsel__is_group_leader(evsel)) {
                 attr->disabled = 1;
-                if (!initial_delay)
+
+                /*
+                 * In case of initial_delay we enable tracee
+                 * events manually.
+                 */
+                if (target__none(&target) && !initial_delay)
                         attr->enable_on_exec = 1;
         }
 
+        if (target__has_cpu(&target))
+                return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
+
         return perf_evsel__open_per_thread(evsel, evsel_list->threads);
 }
 
@@ -185,6 +231,42 @@ static inline int nsec_counter(struct perf_evsel *evsel)
         return 0;
 }
 
+static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
+                                     union perf_event *event,
+                                     struct perf_sample *sample __maybe_unused,
+                                     struct machine *machine __maybe_unused)
+{
+        if (perf_data_file__write(&perf_stat.file, event, event->header.size) < 0) {
+                pr_err("failed to write perf data, error: %m\n");
+                return -1;
+        }
+
+        perf_stat.bytes_written += event->header.size;
+        return 0;
+}
+
+static int write_stat_round_event(u64 tm, u64 type)
+{
+        return perf_event__synthesize_stat_round(NULL, tm, type,
+                                                 process_synthesized_event,
+                                                 NULL);
+}
+
+#define WRITE_STAT_ROUND_EVENT(time, interval) \
+        write_stat_round_event(time, PERF_STAT_ROUND_TYPE__ ## interval)
+
+#define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
+
+static int
+perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread,
+                             struct perf_counts_values *count)
+{
+        struct perf_sample_id *sid = SID(counter, cpu, thread);
+
+        return perf_event__synthesize_stat(NULL, cpu, thread, sid->id, count,
+                                           process_synthesized_event, NULL);
+}
+
 /*
  * Read out the results of a single counter:
  * do not aggregate counts across CPUs in system-wide mode
@@ -208,6 +290,13 @@ static int read_counter(struct perf_evsel *counter)
                         count = perf_counts(counter->counts, cpu, thread);
                         if (perf_evsel__read(counter, cpu, thread, count))
                                 return -1;
+
+                        if (STAT_RECORD) {
+                                if (perf_evsel__write_stat_event(counter, cpu, thread, count)) {
+                                        pr_err("failed to write stat event\n");
+                                        return -1;
+                                }
+                        }
                 }
         }
 
@@ -241,21 +330,26 @@ static void process_interval(void)
         clock_gettime(CLOCK_MONOTONIC, &ts);
         diff_timespec(&rs, &ts, &ref_time);
 
+        if (STAT_RECORD) {
+                if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSECS_PER_SEC + rs.tv_nsec, INTERVAL))
+                        pr_err("failed to write stat round event\n");
+        }
+
         print_counters(&rs, 0, NULL);
 }
 
-static void handle_initial_delay(void)
+static void enable_counters(void)
 {
-        struct perf_evsel *counter;
-
-        if (initial_delay) {
-                const int ncpus = cpu_map__nr(evsel_list->cpus),
-                        nthreads = thread_map__nr(evsel_list->threads);
-
+        if (initial_delay)
                 usleep(initial_delay * 1000);
-                evlist__for_each(evsel_list, counter)
-                        perf_evsel__enable(counter, ncpus, nthreads);
-        }
+
+        /*
+         * We need to enable counters only if:
+         * - we don't have tracee (attaching to task or cpu)
+         * - we have initial delay configured
+         */
+        if (!target__none(&target) || initial_delay)
+                perf_evlist__enable(evsel_list);
 }
 
 static volatile int workload_exec_errno;
@@ -271,6 +365,135 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
         workload_exec_errno = info->si_value.sival_int;
 }
 
+static bool has_unit(struct perf_evsel *counter)
+{
+        return counter->unit && *counter->unit;
+}
+
+static bool has_scale(struct perf_evsel *counter)
+{
+        return counter->scale != 1;
+}
+
+static int perf_stat_synthesize_config(bool is_pipe)
+{
+        struct perf_evsel *counter;
+        int err;
+
+        if (is_pipe) {
+                err = perf_event__synthesize_attrs(NULL, perf_stat.session,
+                                                   process_synthesized_event);
+                if (err < 0) {
+                        pr_err("Couldn't synthesize attrs.\n");
+                        return err;
+                }
+        }
+
+        /*
+         * Synthesize other events stuff not carried within
+         * attr event - unit, scale, name
+         */
+        evlist__for_each(evsel_list, counter) {
+                if (!counter->supported)
+                        continue;
+
+                /*
+                 * Synthesize unit and scale only if it's defined.
+                 */
+                if (has_unit(counter)) {
+                        err = perf_event__synthesize_event_update_unit(NULL, counter, process_synthesized_event);
+                        if (err < 0) {
+                                pr_err("Couldn't synthesize evsel unit.\n");
+                                return err;
+                        }
+                }
+
+                if (has_scale(counter)) {
+                        err = perf_event__synthesize_event_update_scale(NULL, counter, process_synthesized_event);
+                        if (err < 0) {
+                                pr_err("Couldn't synthesize evsel scale.\n");
+                                return err;
+                        }
+                }
+
+                if (counter->own_cpus) {
+                        err = perf_event__synthesize_event_update_cpus(NULL, counter, process_synthesized_event);
+                        if (err < 0) {
+                                pr_err("Couldn't synthesize evsel scale.\n");
+                                return err;
+                        }
+                }
+
+                /*
+                 * Name is needed only for pipe output,
+                 * perf.data carries event names.
+                 */
+                if (is_pipe) {
+                        err = perf_event__synthesize_event_update_name(NULL, counter, process_synthesized_event);
+                        if (err < 0) {
+                                pr_err("Couldn't synthesize evsel name.\n");
+                                return err;
+                        }
+                }
+        }
+
+        err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads,
+                                                process_synthesized_event,
+                                                NULL);
+        if (err < 0) {
+                pr_err("Couldn't synthesize thread map.\n");
+                return err;
+        }
+
+        err = perf_event__synthesize_cpu_map(NULL, evsel_list->cpus,
+                                             process_synthesized_event, NULL);
+        if (err < 0) {
+                pr_err("Couldn't synthesize thread map.\n");
+                return err;
+        }
+
+        err = perf_event__synthesize_stat_config(NULL, &stat_config,
+                                                 process_synthesized_event, NULL);
+        if (err < 0) {
+                pr_err("Couldn't synthesize config.\n");
+                return err;
+        }
+
+        return 0;
+}
+
+#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+
+static int __store_counter_ids(struct perf_evsel *counter,
+                               struct cpu_map *cpus,
+                               struct thread_map *threads)
+{
+        int cpu, thread;
+
+        for (cpu = 0; cpu < cpus->nr; cpu++) {
+                for (thread = 0; thread < threads->nr; thread++) {
+                        int fd = FD(counter, cpu, thread);
+
+                        if (perf_evlist__id_add_fd(evsel_list, counter,
+                                                   cpu, thread, fd) < 0)
+                                return -1;
+                }
+        }
+
+        return 0;
+}
+
+static int store_counter_ids(struct perf_evsel *counter)
+{
+        struct cpu_map *cpus = counter->cpus;
+        struct thread_map *threads = counter->threads;
+
+        if (perf_evsel__alloc_id(counter, cpus->nr, threads->nr))
+                return -ENOMEM;
+
+        return __store_counter_ids(counter, cpus, threads);
+}
+
 static int __run_perf_stat(int argc, const char **argv)
 {
         int interval = stat_config.interval;
@@ -281,6 +504,7 @@ static int __run_perf_stat(int argc, const char **argv)
         size_t l;
         int status = 0;
         const bool forks = (argc > 0);
+        bool is_pipe = STAT_RECORD ? perf_stat.file.is_pipe : false;
 
         if (interval) {
                 ts.tv_sec  = interval / 1000;
@@ -291,7 +515,7 @@ static int __run_perf_stat(int argc, const char **argv)
         }
 
         if (forks) {
-                if (perf_evlist__prepare_workload(evsel_list, &target, argv, false,
+                if (perf_evlist__prepare_workload(evsel_list, &target, argv, is_pipe,
                                                   workload_exec_failed_signal) < 0) {
                         perror("failed to prepare workload");
                         return -1;
@@ -335,6 +559,9 @@ static int __run_perf_stat(int argc, const char **argv)
                 l = strlen(counter->unit);
                 if (l > unit_width)
                         unit_width = l;
+
+                if (STAT_RECORD && store_counter_ids(counter))
+                        return -1;
         }
 
         if (perf_evlist__apply_filters(evsel_list, &counter)) {
@@ -344,6 +571,24 @@ static int __run_perf_stat(int argc, const char **argv)
                 return -1;
         }
 
+        if (STAT_RECORD) {
+                int err, fd = perf_data_file__fd(&perf_stat.file);
+
+                if (is_pipe) {
+                        err = perf_header__write_pipe(perf_data_file__fd(&perf_stat.file));
+                } else {
+                        err = perf_session__write_header(perf_stat.session, evsel_list,
+                                                         fd, false);
+                }
+
+                if (err < 0)
+                        return err;
+
+                err = perf_stat_synthesize_config(is_pipe);
+                if (err < 0)
+                        return err;
+        }
+
         /*
          * Enable counters and exec the command:
          */
@@ -352,7 +597,7 @@ static int __run_perf_stat(int argc, const char **argv)
 
         if (forks) {
                 perf_evlist__start_workload(evsel_list);
-                handle_initial_delay();
+                enable_counters();
 
                 if (interval) {
                         while (!waitpid(child_pid, &status, WNOHANG)) {
@@ -371,7 +616,7 @@ static int __run_perf_stat(int argc, const char **argv)
                 if (WIFSIGNALED(status))
                         psignal(WTERMSIG(status), argv[0]);
         } else {
-                handle_initial_delay();
+                enable_counters();
                 while (!done) {
                         nanosleep(&ts, NULL);
                         if (interval)
@@ -810,8 +1055,8 @@ static void print_header(int argc, const char **argv)
                 else if (target.cpu_list)
                         fprintf(output, "\'CPU(s) %s", target.cpu_list);
                 else if (!target__has_task(&target)) {
-                        fprintf(output, "\'%s", argv[0]);
-                        for (i = 1; i < argc; i++)
+                        fprintf(output, "\'%s", argv ? argv[0] : "pipe");
+                        for (i = 1; argv && (i < argc); i++)
                                 fprintf(output, " %s", argv[i]);
                 } else if (target.pid)
                         fprintf(output, "process id \'%s", target.pid);
@@ -847,6 +1092,10 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
         struct perf_evsel *counter;
         char buf[64], *prefix = NULL;
 
+        /* Do not print anything if we record to the pipe. */
+        if (STAT_RECORD && perf_stat.file.is_pipe)
+                return;
+
         if (interval)
                 print_interval(prefix = buf, ts);
         else
@@ -1077,6 +1326,109 @@ static int perf_stat_init_aggr_mode(void)
         return cpus_aggr_map ? 0 : -ENOMEM;
 }
 
+static void perf_stat__exit_aggr_mode(void)
+{
+        cpu_map__put(aggr_map);
+        cpu_map__put(cpus_aggr_map);
+        aggr_map = NULL;
+        cpus_aggr_map = NULL;
+}
+
+static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, int idx)
+{
+        int cpu;
+
+        if (idx > map->nr)
+                return -1;
+
+        cpu = map->map[idx];
+
+        if (cpu >= env->nr_cpus_online)
+                return -1;
+
+        return cpu;
+}
+
+static int perf_env__get_socket(struct cpu_map *map, int idx, void *data)
+{
+        struct perf_env *env = data;
+        int cpu = perf_env__get_cpu(env, map, idx);
+
+        return cpu == -1 ? -1 : env->cpu[cpu].socket_id;
+}
+
+static int perf_env__get_core(struct cpu_map *map, int idx, void *data)
+{
+        struct perf_env *env = data;
+        int core = -1, cpu = perf_env__get_cpu(env, map, idx);
+
+        if (cpu != -1) {
+                int socket_id = env->cpu[cpu].socket_id;
+
+                /*
+                 * Encode socket in upper 16 bits
+                 * core_id is relative to socket, and
+                 * we need a global id. So we combine
+                 * socket + core id.
+                 */
+                core = (socket_id << 16) | (env->cpu[cpu].core_id & 0xffff);
+        }
+
+        return core;
+}
+
+static int perf_env__build_socket_map(struct perf_env *env, struct cpu_map *cpus,
+                                      struct cpu_map **sockp)
+{
+        return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env);
+}
+
+static int perf_env__build_core_map(struct perf_env *env, struct cpu_map *cpus,
+                                    struct cpu_map **corep)
+{
+        return cpu_map__build_map(cpus, corep, perf_env__get_core, env);
+}
+
+static int perf_stat__get_socket_file(struct cpu_map *map, int idx)
+{
+        return perf_env__get_socket(map, idx, &perf_stat.session->header.env);
+}
+
+static int perf_stat__get_core_file(struct cpu_map *map, int idx)
+{
+        return perf_env__get_core(map, idx, &perf_stat.session->header.env);
+}
+
+static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
+{
+        struct perf_env *env = &st->session->header.env;
+
+        switch (stat_config.aggr_mode) {
+        case AGGR_SOCKET:
+                if (perf_env__build_socket_map(env, evsel_list->cpus, &aggr_map)) {
+                        perror("cannot build socket map");
+                        return -1;
+                }
+                aggr_get_id = perf_stat__get_socket_file;
+                break;
+        case AGGR_CORE:
+                if (perf_env__build_core_map(env, evsel_list->cpus, &aggr_map)) {
+                        perror("cannot build core map");
+                        return -1;
+                }
+                aggr_get_id = perf_stat__get_core_file;
+                break;
+        case AGGR_NONE:
+        case AGGR_GLOBAL:
+        case AGGR_THREAD:
+        case AGGR_UNSET:
+        default:
+                break;
+        }
+
+        return 0;
+}
+
 /*
  * Add default attributes, if there were no attributes specified or
  * if -d/--detailed, -d -d or -d -d -d is used:
@@ -1236,6 +1588,225 @@ static int add_default_attributes(void)
         return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
 }
 
+static const char * const recort_usage[] = {
+        "perf stat record [<options>]",
+        NULL,
+};
+
+static void init_features(struct perf_session *session)
+{
+        int feat;
+
+        for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
+                perf_header__set_feat(&session->header, feat);
+
+        perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
+        perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
+        perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
+        perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
+}
+
+static int __cmd_record(int argc, const char **argv)
+{
+        struct perf_session *session;
+        struct perf_data_file *file = &perf_stat.file;
+
+        argc = parse_options(argc, argv, stat_options, record_usage,
+                             PARSE_OPT_STOP_AT_NON_OPTION);
+
+        if (output_name)
+                file->path = output_name;
+
+        if (run_count != 1 || forever) {
+                pr_err("Cannot use -r option with perf stat record.\n");
+                return -1;
+        }
+
+        session = perf_session__new(file, false, NULL);
+        if (session == NULL) {
+                pr_err("Perf session creation failed.\n");
+                return -1;
+        }
+
+        init_features(session);
+
+        session->evlist   = evsel_list;
+        perf_stat.session = session;
+        perf_stat.record  = true;
+        return argc;
+}
+
+static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
+                                    union perf_event *event,
+                                    struct perf_session *session)
+{
+        struct stat_round_event *round = &event->stat_round;
+        struct perf_evsel *counter;
+        struct timespec tsh, *ts = NULL;
+        const char **argv = session->header.env.cmdline_argv;
+        int argc = session->header.env.nr_cmdline;
+
+        evlist__for_each(evsel_list, counter)
+                perf_stat_process_counter(&stat_config, counter);
+
+        if (round->type == PERF_STAT_ROUND_TYPE__FINAL)
+                update_stats(&walltime_nsecs_stats, round->time);
+
+        if (stat_config.interval && round->time) {
+                tsh.tv_sec  = round->time / NSECS_PER_SEC;
+                tsh.tv_nsec = round->time % NSECS_PER_SEC;
+                ts = &tsh;
+        }
+
+        print_counters(ts, argc, argv);
+        return 0;
+}
+
+static
+int process_stat_config_event(struct perf_tool *tool __maybe_unused,
+                              union perf_event *event,
+                              struct perf_session *session __maybe_unused)
+{
+        struct perf_stat *st = container_of(tool, struct perf_stat, tool);
+
+        perf_event__read_stat_config(&stat_config, &event->stat_config);
+
+        if (cpu_map__empty(st->cpus)) {
+                if (st->aggr_mode != AGGR_UNSET)
+                        pr_warning("warning: processing task data, aggregation mode not set\n");
+                return 0;
+        }
+
+        if (st->aggr_mode != AGGR_UNSET)
+                stat_config.aggr_mode = st->aggr_mode;
+
+        if (perf_stat.file.is_pipe)
+                perf_stat_init_aggr_mode();
+        else
+                perf_stat_init_aggr_mode_file(st);
+
+        return 0;
+}
+
+static int set_maps(struct perf_stat *st)
+{
+        if (!st->cpus || !st->threads)
+                return 0;
+
+        if (WARN_ONCE(st->maps_allocated, "stats double allocation\n"))
+                return -EINVAL;
+
+        perf_evlist__set_maps(evsel_list, st->cpus, st->threads);
+
+        if (perf_evlist__alloc_stats(evsel_list, true))
+                return -ENOMEM;
+
+        st->maps_allocated = true;
+        return 0;
+}
+
+static
+int process_thread_map_event(struct perf_tool *tool __maybe_unused,
+                             union perf_event *event,
+                             struct perf_session *session __maybe_unused)
+{
+        struct perf_stat *st = container_of(tool, struct perf_stat, tool);
+
+        if (st->threads) {
+                pr_warning("Extra thread map event, ignoring.\n");
+                return 0;
+        }
+
+        st->threads = thread_map__new_event(&event->thread_map);
+        if (!st->threads)
+                return -ENOMEM;
+
+        return set_maps(st);
+}
+
+static
+int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
+                          union perf_event *event,
+                          struct perf_session *session __maybe_unused)
+{
+        struct perf_stat *st = container_of(tool, struct perf_stat, tool);
+        struct cpu_map *cpus;
+
+        if (st->cpus) {
+                pr_warning("Extra cpu map event, ignoring.\n");
+                return 0;
+        }
+
+        cpus = cpu_map__new_data(&event->cpu_map.data);
+        if (!cpus)
+                return -ENOMEM;
+
+        st->cpus = cpus;
+        return set_maps(st);
+}
+
+static const char * const report_usage[] = {
+        "perf stat report [<options>]",
+        NULL,
+};
+
+static struct perf_stat perf_stat = {
+        .tool = {
+                .attr           = perf_event__process_attr,
+                .event_update   = perf_event__process_event_update,
+                .thread_map     = process_thread_map_event,
+                .cpu_map        = process_cpu_map_event,
+                .stat_config    = process_stat_config_event,
+                .stat           = perf_event__process_stat_event,
+                .stat_round     = process_stat_round_event,
+        },
+        .aggr_mode = AGGR_UNSET,
+};
+
+static int __cmd_report(int argc, const char **argv)
+{
+        struct perf_session *session;
+        const struct option options[] = {
+        OPT_STRING('i', "input", &input_name, "file", "input file name"),
+        OPT_SET_UINT(0, "per-socket", &perf_stat.aggr_mode,
+                     "aggregate counts per processor socket", AGGR_SOCKET),
+        OPT_SET_UINT(0, "per-core", &perf_stat.aggr_mode,
+                     "aggregate counts per physical processor core", AGGR_CORE),
+        OPT_SET_UINT('A', "no-aggr", &perf_stat.aggr_mode,
+                     "disable CPU count aggregation", AGGR_NONE),
+        OPT_END()
+        };
+        struct stat st;
+        int ret;
+
+        argc = parse_options(argc, argv, options, report_usage, 0);
+
+        if (!input_name || !strlen(input_name)) {
+                if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
+                        input_name = "-";
+                else
+                        input_name = "perf.data";
+        }
+
+        perf_stat.file.path = input_name;
+        perf_stat.file.mode = PERF_DATA_MODE_READ;
+
+        session = perf_session__new(&perf_stat.file, false, &perf_stat.tool);
+        if (session == NULL)
+                return -1;
+
+        perf_stat.session  = session;
+        stat_config.output = stderr;
+        evsel_list         = session->evlist;
+
+        ret = perf_session__process_events(session);
+        if (ret)
+                return ret;
+
+        perf_session__delete(session);
+        return 0;
+}
+
 int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 {
         const char * const stat_usage[] = {
@@ -1246,6 +1817,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
         const char *mode;
         FILE *output = stderr;
         unsigned int interval;
+        const char * const stat_subcommands[] = { "record", "report" };
 
         setlocale(LC_ALL, "");
 
@@ -1253,12 +1825,30 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
         if (evsel_list == NULL)
                 return -ENOMEM;
 
-        argc = parse_options(argc, argv, stat_options, stat_usage,
-                PARSE_OPT_STOP_AT_NON_OPTION);
+        argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands,
+                                        (const char **) stat_usage,
+                                        PARSE_OPT_STOP_AT_NON_OPTION);
+
+        if (csv_sep) {
+                csv_output = true;
+                if (!strcmp(csv_sep, "\\t"))
+                        csv_sep = "\t";
+        } else
+                csv_sep = DEFAULT_SEPARATOR;
+
+        if (argc && !strncmp(argv[0], "rec", 3)) {
+                argc = __cmd_record(argc, argv);
+                if (argc < 0)
+                        return -1;
+        } else if (argc && !strncmp(argv[0], "rep", 3))
+                return __cmd_report(argc, argv);
 
         interval = stat_config.interval;
 
-        if (output_name && strcmp(output_name, "-"))
+        /*
+         * For record command the -o is already taken care of.
+         */
+        if (!STAT_RECORD && output_name && strcmp(output_name, "-"))
                 output = NULL;
 
         if (output_name && output_fd) {
@@ -1296,13 +1886,6 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 
         stat_config.output = output;
 
-        if (csv_sep) {
-                csv_output = true;
-                if (!strcmp(csv_sep, "\\t"))
-                        csv_sep = "\t";
-        } else
-                csv_sep = DEFAULT_SEPARATOR;
-
         /*
          * let the spreadsheet do the pretty-printing
          */
@@ -1425,6 +2008,42 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
         if (!forever && status != -1 && !interval)
                 print_counters(NULL, argc, argv);
 
+        if (STAT_RECORD) {
+                /*
+                 * We synthesize the kernel mmap record just so that older tools
+                 * don't emit warnings about not being able to resolve symbols
+                 * due to /proc/sys/kernel/kptr_restrict settings and instear provide
+                 * a saner message about no samples being in the perf.data file.
+                 *
+                 * This also serves to suppress a warning about f_header.data.size == 0
+                 * in header.c at the moment 'perf stat record' gets introduced, which
+                 * is not really needed once we start adding the stat specific PERF_RECORD_
+                 * records, but the need to suppress the kptr_restrict messages in older
+                 * tools remain  -acme
+                 */
+                int fd = perf_data_file__fd(&perf_stat.file);
+                int err = perf_event__synthesize_kernel_mmap((void *)&perf_stat,
+                                                             process_synthesized_event,
+                                                             &perf_stat.session->machines.host);
+                if (err) {
+                        pr_warning("Couldn't synthesize the kernel mmap record, harmless, "
+                                   "older tools may produce warnings about this file\n.");
+                }
+
+                if (!interval) {
+                        if (WRITE_STAT_ROUND_EVENT(walltime_nsecs_stats.max, FINAL))
+                                pr_err("failed to write stat round event\n");
+                }
+
+                if (!perf_stat.file.is_pipe) {
+                        perf_stat.session->header.data_size += perf_stat.bytes_written;
+                        perf_session__write_header(perf_stat.session, evsel_list, fd, true);
+                }
+
+                perf_session__delete(perf_stat.session);
+        }
+
+        perf_stat__exit_aggr_mode();
         perf_evlist__free_stats(evsel_list);
 out:
         perf_evlist__delete(evsel_list);
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 30e59620179d..bd7a7757176f 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -30,7 +30,7 @@
 
 #include "perf.h"
 #include "util/header.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-events.h"
 #include "util/event.h"
 #include "util/session.h"
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 7e2e72e6d9d1..bf01cbb0ef23 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -34,7 +34,7 @@
 #include "util/top.h"
 #include "util/util.h"
 #include <linux/rbtree.h>
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-events.h"
 #include "util/cpumap.h"
 #include "util/xyarray.h"
@@ -175,42 +175,40 @@ static void perf_top__record_precise_ip(struct perf_top *top,
                                         int counter, u64 ip)
 {
         struct annotation *notes;
-        struct symbol *sym;
+        struct symbol *sym = he->ms.sym;
         int err = 0;
 
-        if (he == NULL || he->ms.sym == NULL ||
-            ((top->sym_filter_entry == NULL ||
-              top->sym_filter_entry->ms.sym != he->ms.sym) && use_browser != 1))
+        if (sym == NULL || (use_browser == 0 &&
+                            (top->sym_filter_entry == NULL ||
+                             top->sym_filter_entry->ms.sym != sym)))
                 return;
 
-        sym = he->ms.sym;
         notes = symbol__annotation(sym);
 
         if (pthread_mutex_trylock(&notes->lock))
                 return;
 
-        ip = he->ms.map->map_ip(he->ms.map, ip);
-
-        if (ui__has_annotation())
-                err = hist_entry__inc_addr_samples(he, counter, ip);
+        err = hist_entry__inc_addr_samples(he, counter, ip);
 
         pthread_mutex_unlock(&notes->lock);
 
-        /*
-         * This function is now called with he->hists->lock held.
-         * Release it before going to sleep.
-         */
-        pthread_mutex_unlock(&he->hists->lock);
+        if (unlikely(err)) {
+                /*
+                 * This function is now called with he->hists->lock held.
+                 * Release it before going to sleep.
+                 */
+                pthread_mutex_unlock(&he->hists->lock);
+
+                if (err == -ERANGE && !he->ms.map->erange_warned)
+                        ui__warn_map_erange(he->ms.map, sym, ip);
+                else if (err == -ENOMEM) {
+                        pr_err("Not enough memory for annotating '%s' symbol!\n",
+                               sym->name);
+                        sleep(1);
+                }
 
-        if (err == -ERANGE && !he->ms.map->erange_warned)
-                ui__warn_map_erange(he->ms.map, sym, ip);
-        else if (err == -ENOMEM) {
-                pr_err("Not enough memory for annotating '%s' symbol!\n",
-                       sym->name);
-                sleep(1);
+                pthread_mutex_lock(&he->hists->lock);
         }
-
-        pthread_mutex_lock(&he->hists->lock);
 }
 
 static void perf_top__show_details(struct perf_top *top)
@@ -687,14 +685,8 @@ static int hist_iter__top_callback(struct hist_entry_iter *iter,
         struct hist_entry *he = iter->he;
         struct perf_evsel *evsel = iter->evsel;
 
-        if (sort__has_sym && single) {
-                u64 ip = al->addr;
-
-                if (al->map)
-                        ip = al->map->unmap_ip(al->map, ip);
-
-                perf_top__record_precise_ip(top, he, evsel->idx, ip);
-        }
+        if (sort__has_sym && single)
+                perf_top__record_precise_ip(top, he, evsel->idx, al->addr);
 
         hist__account_cycles(iter->sample->branch_stack, al, iter->sample,
                      !(top->record_opts.branch_stack & PERF_SAMPLE_BRANCH_ANY));
@@ -964,7 +956,7 @@ static int __cmd_top(struct perf_top *top)
         if (ret)
                 goto out_delete;
 
-        if (perf_session__register_idle_thread(top->session) == NULL)
+        if (perf_session__register_idle_thread(top->session) < 0)
                 goto out_delete;
 
         machine__synthesize_threads(&top->session->machines.host, &opts->target,
@@ -1218,6 +1210,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
         OPT_CALLBACK('j', "branch-filter", &opts->branch_stack,
                      "branch filter mask", "branch stack filter modes",
                      parse_branch_stack),
+        OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace,
+                    "Show raw trace event output (do not use print fmt or plugins)"),
         OPT_END()
         };
         const char * const top_usage[] = {
@@ -1239,11 +1233,17 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
         if (argc)
                 usage_with_options(top_usage, options);
 
+        if (!top.evlist->nr_entries &&
+            perf_evlist__add_default(top.evlist) < 0) {
+                pr_err("Not enough memory for event selector list\n");
+                goto out_delete_evlist;
+        }
+
         sort__mode = SORT_MODE__TOP;
         /* display thread wants entries to be collapsed in a different tree */
         sort__need_collapse = 1;
 
-        if (setup_sorting() < 0) {
+        if (setup_sorting(top.evlist) < 0) {
                 if (sort_order)
                         parse_options_usage(top_usage, options, "s", 1);
                 if (field_order)
@@ -1279,12 +1279,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
         if (target__none(target))
                 target->system_wide = true;
 
-        if (perf_evlist__create_maps(top.evlist, target) < 0)
-                usage_with_options(top_usage, options);
-
-        if (!top.evlist->nr_entries &&
-            perf_evlist__add_default(top.evlist) < 0) {
-                ui__error("Not enough memory for event selector list\n");
+        if (perf_evlist__create_maps(top.evlist, target) < 0) {
+                ui__error("Couldn't create thread/CPU maps: %s\n",
+                          errno == ENOENT ? "No such process" : strerror_r(errno, errbuf, sizeof(errbuf)));
                 goto out_delete_evlist;
         }
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c783d8fd3a80..20916dd77aac 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -22,11 +22,11 @@
 #include "util/color.h"
 #include "util/debug.h"
 #include "util/evlist.h"
-#include "util/exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "util/machine.h"
 #include "util/session.h"
 #include "util/thread.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/strlist.h"
 #include "util/intlist.h"
 #include "util/thread_map.h"
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
new file mode 100644
index 000000000000..9b10cda6b6dc
--- /dev/null
+++ b/tools/perf/builtin-version.c
@@ -0,0 +1,10 @@
+#include "util/util.h"
+#include "builtin.h"
+#include "perf.h"
+
+int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused,
+                const char *prefix __maybe_unused)
+{
+        printf("perf version %s\n", perf_version_string);
+        return 0;
+}
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 3688ad29085f..3f871b54e261 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -17,6 +17,7 @@ extern int cmd_annotate(int argc, const char **argv, const char *prefix);
 extern int cmd_bench(int argc, const char **argv, const char *prefix);
 extern int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
 extern int cmd_buildid_list(int argc, const char **argv, const char *prefix);
+extern int cmd_config(int argc, const char **argv, const char *prefix);
 extern int cmd_diff(int argc, const char **argv, const char *prefix);
 extern int cmd_evlist(int argc, const char **argv, const char *prefix);
 extern int cmd_help(int argc, const char **argv, const char *prefix);
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 00fcaf8a5b8d..ab5cbaa170d0 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -9,6 +9,7 @@ perf-buildid-cache		mainporcelain common
 perf-buildid-list               mainporcelain common
 perf-data                       mainporcelain common
 perf-diff                       mainporcelain common
+perf-config                     mainporcelain common
 perf-evlist                     mainporcelain common
 perf-inject                     mainporcelain common
 perf-kmem                       mainporcelain common
@@ -25,4 +26,4 @@ perf-stat			mainporcelain common
 perf-test                       mainporcelain common
 perf-timechart                  mainporcelain common
 perf-top                        mainporcelain common
-perf-trace                      mainporcelain common
+perf-trace                      mainporcelain audit
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index de89ec574361..254d06e39bea 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -135,8 +135,6 @@ endif
 
 ifeq ($(DEBUG),0)
   CFLAGS += -O6
-else
-  CFLAGS += $(call cc-option,-Og,-O0)
 endif
 
 ifdef PARSER_DEBUG
@@ -318,6 +316,18 @@ ifndef NO_LIBELF
       CFLAGS += -DHAVE_LIBBPF_SUPPORT
       $(call detected,CONFIG_LIBBPF)
     endif
+
+    ifndef NO_DWARF
+      ifdef PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
+        CFLAGS += -DHAVE_BPF_PROLOGUE
+        $(call detected,CONFIG_BPF_PROLOGUE)
+      else
+        msg := $(warning BPF prologue is not supported by architecture $(ARCH), missing regs_query_register_offset());
+      endif
+    else
+      msg := $(warning DWARF support is off, BPF prologue is disabled);
+    endif
+
   endif # NO_LIBBPF
 endif # NO_LIBELF
 
@@ -681,6 +691,7 @@ sharedir = $(prefix)/share
 template_dir = share/perf-core/templates
 STRACE_GROUPS_DIR = share/perf-core/strace/groups
 htmldir = share/doc/perf-doc
+tipdir = share/doc/perf-tip
 ifeq ($(prefix),/usr)
 sysconfdir = /etc
 ETC_PERFCONFIG = $(sysconfdir)/perfconfig
@@ -707,6 +718,7 @@ infodir_SQ = $(subst ','\'',$(infodir))
 perfexecdir_SQ = $(subst ','\'',$(perfexecdir))
 template_dir_SQ = $(subst ','\'',$(template_dir))
 htmldir_SQ = $(subst ','\'',$(htmldir))
+tipdir_SQ = $(subst ','\'',$(tipdir))
 prefix_SQ = $(subst ','\'',$(prefix))
 sysconfdir_SQ = $(subst ','\'',$(sysconfdir))
 libdir_SQ = $(subst ','\'',$(libdir))
@@ -714,12 +726,15 @@ libdir_SQ = $(subst ','\'',$(libdir))
 ifneq ($(filter /%,$(firstword $(perfexecdir))),)
 perfexec_instdir = $(perfexecdir)
 STRACE_GROUPS_INSTDIR = $(STRACE_GROUPS_DIR)
+tip_instdir = $(tipdir)
 else
 perfexec_instdir = $(prefix)/$(perfexecdir)
 STRACE_GROUPS_INSTDIR = $(prefix)/$(STRACE_GROUPS_DIR)
+tip_instdir = $(prefix)/$(tipdir)
 endif
 perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
 STRACE_GROUPS_INSTDIR_SQ = $(subst ','\'',$(STRACE_GROUPS_INSTDIR))
+tip_instdir_SQ = $(subst ','\'',$(tip_instdir))
 
 # If we install to $(HOME) we keep the traceevent default:
 # $(HOME)/.traceevent/plugins
@@ -741,6 +756,10 @@ ifeq ($(VF),1)
   $(call print_var,sysconfdir)
   $(call print_var,LIBUNWIND_DIR)
   $(call print_var,LIBDW_DIR)
+
+  ifeq ($(dwarf-post-unwind),1)
+    $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text))
+  endif
   $(info )
 endif
 
@@ -756,6 +775,7 @@ $(call detected_var,ETC_PERFCONFIG_SQ)
 $(call detected_var,STRACE_GROUPS_DIR_SQ)
 $(call detected_var,prefix_SQ)
 $(call detected_var,perfexecdir_SQ)
+$(call detected_var,tipdir_SQ)
 $(call detected_var,LIBDIR)
 $(call detected_var,GTK_CFLAGS)
 $(call detected_var,PERL_EMBED_CCOPTS)
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
index 0ebef09c0842..c16ce833079c 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/perf/config/utilities.mak
@@ -177,22 +177,3 @@ $(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2)))
 endef
 _ge_attempt = $(if $(get-executable),$(get-executable),$(call _gea_err,$(2)))
 _gea_err  = $(if $(1),$(error Please set '$(1)' appropriately))
-
-# try-run
-# Usage: option = $(call try-run, $(CC)...-o "$$TMP",option-ok,otherwise)
-# Exit code chooses option. "$$TMP" is can be used as temporary file and
-# is automatically cleaned up.
-try-run = $(shell set -e;               \
-        TMP="$(TMPOUT).$$$$.tmp";       \
-        TMPO="$(TMPOUT).$$$$.o";        \
-        if ($(1)) >/dev/null 2>&1;      \
-        then echo "$(2)";               \
-        else echo "$(3)";               \
-        fi;                             \
-        rm -f "$$TMP" "$$TMPO")
-
-# cc-option
-# Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586)
-
-cc-option = $(call try-run,\
-        $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 3d4c7c09adea..a929618b8eb6 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -9,16 +9,18 @@
 #include "builtin.h"
 
 #include "util/env.h"
-#include "util/exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "util/cache.h"
 #include "util/quote.h"
-#include "util/run-command.h"
+#include <subcmd/run-command.h>
 #include "util/parse-events.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/bpf-loader.h"
 #include "util/debug.h"
 #include <api/fs/tracing_path.h>
 #include <pthread.h>
+#include <stdlib.h>
+#include <time.h>
 
 const char perf_usage_string[] =
         "perf [--version] [--help] [OPTIONS] COMMAND [ARGS]";
@@ -39,6 +41,7 @@ struct cmd_struct {
 static struct cmd_struct commands[] = {
         { "buildid-cache", cmd_buildid_cache, 0 },
         { "buildid-list", cmd_buildid_list, 0 },
+        { "config",     cmd_config,     0 },
         { "diff",       cmd_diff,       0 },
         { "evlist",     cmd_evlist,     0 },
         { "help",       cmd_help,       0 },
@@ -118,7 +121,7 @@ static void commit_pager_choice(void)
 {
         switch (use_pager) {
         case 0:
-                setenv("PERF_PAGER", "cat", 1);
+                setenv(PERF_PAGER_ENVIRONMENT, "cat", 1);
                 break;
         case 1:
                 /* setup_pager(); */
@@ -182,9 +185,9 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
                 if (!prefixcmp(cmd, CMD_EXEC_PATH)) {
                         cmd += strlen(CMD_EXEC_PATH);
                         if (*cmd == '=')
-                                perf_set_argv_exec_path(cmd + 1);
+                                set_argv_exec_path(cmd + 1);
                         else {
-                                puts(perf_exec_path());
+                                puts(get_argv_exec_path());
                                 exit(0);
                         }
                 } else if (!strcmp(cmd, "--html-path")) {
@@ -383,6 +386,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
                 use_pager = 1;
         commit_pager_choice();
 
+        perf_env__set_cmdline(&perf_env, argc, argv);
         status = p->fn(argc, argv, prefix);
         exit_browser(status);
         perf_env__exit(&perf_env);
@@ -528,14 +532,20 @@ int main(int argc, const char **argv)
         const char *cmd;
         char sbuf[STRERR_BUFSIZE];
 
+        /* libsubcmd init */
+        exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT);
+        pager_init(PERF_PAGER_ENVIRONMENT);
+
         /* The page_size is placed in util object. */
         page_size = sysconf(_SC_PAGE_SIZE);
         cacheline_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE);
 
-        cmd = perf_extract_argv0_path(argv[0]);
+        cmd = extract_argv0_path(argv[0]);
         if (!cmd)
                 cmd = "perf-help";
 
+        srandom(time(NULL));
+
         /* get debugfs/tracefs mount point from /proc/mounts */
         tracing_path_mount();
 
diff --git a/tools/perf/scripts/python/stat-cpi.py b/tools/perf/scripts/python/stat-cpi.py
new file mode 100644
index 000000000000..8b60f343dd07
--- /dev/null
+++ b/tools/perf/scripts/python/stat-cpi.py
@@ -0,0 +1,77 @@
+#!/usr/bin/env python
+
+data    = {}
+times   = []
+threads = []
+cpus    = []
+
+def get_key(time, event, cpu, thread):
+    return "%d-%s-%d-%d" % (time, event, cpu, thread)
+
+def store_key(time, cpu, thread):
+    if (time not in times):
+        times.append(time)
+
+    if (cpu not in cpus):
+        cpus.append(cpu)
+
+    if (thread not in threads):
+        threads.append(thread)
+
+def store(time, event, cpu, thread, val, ena, run):
+    #print "event %s cpu %d, thread %d, time %d, val %d, ena %d, run %d" % \
+    #      (event, cpu, thread, time, val, ena, run)
+
+    store_key(time, cpu, thread)
+    key = get_key(time, event, cpu, thread)
+    data[key] = [ val, ena, run]
+
+def get(time, event, cpu, thread):
+    key = get_key(time, event, cpu, thread)
+    return data[key][0]
+
+def stat__cycles_k(cpu, thread, time, val, ena, run):
+    store(time, "cycles", cpu, thread, val, ena, run);
+
+def stat__instructions_k(cpu, thread, time, val, ena, run):
+    store(time, "instructions", cpu, thread, val, ena, run);
+
+def stat__cycles_u(cpu, thread, time, val, ena, run):
+    store(time, "cycles", cpu, thread, val, ena, run);
+
+def stat__instructions_u(cpu, thread, time, val, ena, run):
+    store(time, "instructions", cpu, thread, val, ena, run);
+
+def stat__cycles(cpu, thread, time, val, ena, run):
+    store(time, "cycles", cpu, thread, val, ena, run);
+
+def stat__instructions(cpu, thread, time, val, ena, run):
+    store(time, "instructions", cpu, thread, val, ena, run);
+
+def stat__interval(time):
+    for cpu in cpus:
+        for thread in threads:
+            cyc = get(time, "cycles", cpu, thread)
+            ins = get(time, "instructions", cpu, thread)
+            cpi = 0
+
+            if ins != 0:
+                cpi = cyc/float(ins)
+
+            print "%15f: cpu %d, thread %d -> cpi %f (%d/%d)" % (time/(float(1000000000)), cpu, thread, cpi, cyc, ins)
+
+def trace_end():
+    pass
+# XXX trace_end callback could be used as an alternative place
+#     to compute same values as in the script above:
+#
+#    for time in times:
+#        for cpu in cpus:
+#            for thread in threads:
+#                cyc = get(time, "cycles", cpu, thread)
+#                ins = get(time, "instructions", cpu, thread)
+#
+#                if ins != 0:
+#                    cpi = cyc/float(ins)
+#
+#                print "time %.9f, cpu %d, thread %d -> cpi %f" % (time/(float(1000000000)), cpu, thread, cpi)
diff --git a/tools/perf/tests/.gitignore b/tools/perf/tests/.gitignore
index 489fc9ffbcb0..bf016c439fbd 100644
--- a/tools/perf/tests/.gitignore
+++ b/tools/perf/tests/.gitignore
@@ -1,2 +1,3 @@
 llvm-src-base.c
 llvm-src-kbuild.c
+llvm-src-prologue.c
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index f41ebf8849fe..614899b88b37 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -31,24 +31,34 @@ perf-y += sample-parsing.o
 perf-y += parse-no-sample-id-all.o
 perf-y += kmod-path.o
 perf-y += thread-map.o
-perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o
+perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o
 perf-y += bpf.o
 perf-y += topology.o
+perf-y += cpumap.o
+perf-y += stat.o
+perf-y += event_update.o
 
-$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c
+$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
         $(call rule_mkdir)
         $(Q)echo '#include <tests/llvm.h>' > $@
         $(Q)echo 'const char test_llvm__bpf_base_prog[] =' >> $@
         $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
         $(Q)echo ';' >> $@
 
-$(OUTPUT)tests/llvm-src-kbuild.c: tests/bpf-script-test-kbuild.c
+$(OUTPUT)tests/llvm-src-kbuild.c: tests/bpf-script-test-kbuild.c tests/Build
         $(call rule_mkdir)
         $(Q)echo '#include <tests/llvm.h>' > $@
         $(Q)echo 'const char test_llvm__bpf_test_kbuild_prog[] =' >> $@
         $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
         $(Q)echo ';' >> $@
 
+$(OUTPUT)tests/llvm-src-prologue.c: tests/bpf-script-test-prologue.c tests/Build
+        $(call rule_mkdir)
+        $(Q)echo '#include <tests/llvm.h>' > $@
+        $(Q)echo 'const char test_llvm__bpf_test_prologue_prog[] =' >> $@
+        $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
+        $(Q)echo ';' >> $@
+
 ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64))
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 endif
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 638875a0960a..28d1605b0338 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -24,7 +24,7 @@
 #include <linux/kernel.h>
 #include "../perf.h"
 #include "util.h"
-#include "exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "tests.h"
 
 #define ENV "PERF_TEST_ATTR"
@@ -153,7 +153,7 @@ static int run_dir(const char *d, const char *perf)
         return system(cmd);
 }
 
-int test__attr(void)
+int test__attr(int subtest __maybe_unused)
 {
         struct stat st;
         char path_perf[PATH_MAX];
@@ -164,7 +164,7 @@ int test__attr(void)
                 return run_dir("./tests", "./perf");
 
         /* Then installed path. */
-        snprintf(path_dir,  PATH_MAX, "%s/tests", perf_exec_path());
+        snprintf(path_dir,  PATH_MAX, "%s/tests", get_argv_exec_path());
         snprintf(path_perf, PATH_MAX, "%s/perf", BINDIR);
 
         if (!lstat(path_dir, &st) &&
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index a02b035fd5aa..fb80c9eb6a95 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -111,7 +111,7 @@ static long long bp_count(int fd)
         return count;
 }
 
-int test__bp_signal(void)
+int test__bp_signal(int subtest __maybe_unused)
 {
         struct sigaction sa;
         long long count1, count2;
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
index e76537724491..89f92fa67cc4 100644
--- a/tools/perf/tests/bp_signal_overflow.c
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -58,7 +58,7 @@ static long long bp_count(int fd)
 #define EXECUTIONS 10000
 #define THRESHOLD  100
 
-int test__bp_signal_overflow(void)
+int test__bp_signal_overflow(int subtest __maybe_unused)
 {
         struct perf_event_attr pe;
         struct sigaction sa;
diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c
new file mode 100644
index 000000000000..7230e62c70fc
--- /dev/null
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -0,0 +1,35 @@
+/*
+ * bpf-script-test-prologue.c
+ * Test BPF prologue
+ */
+#ifndef LINUX_VERSION_CODE
+# error Need LINUX_VERSION_CODE
+# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
+#endif
+#define SEC(NAME) __attribute__((section(NAME), used))
+
+#include <uapi/linux/fs.h>
+
+#define FMODE_READ              0x1
+#define FMODE_WRITE             0x2
+
+static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) =
+        (void *) 6;
+
+SEC("func=null_lseek file->f_mode offset orig")
+int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode,
+                         unsigned long offset, unsigned long orig)
+{
+        if (err)
+                return 0;
+        if (f_mode & FMODE_WRITE)
+                return 0;
+        if (offset & 1)
+                return 0;
+        if (orig == SEEK_CUR)
+                return 0;
+        return 1;
+}
+
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index ec16f7812c8b..33689a0cf821 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -19,6 +19,29 @@ static int epoll_pwait_loop(void)
         return 0;
 }
 
+#ifdef HAVE_BPF_PROLOGUE
+
+static int llseek_loop(void)
+{
+        int fds[2], i;
+
+        fds[0] = open("/dev/null", O_RDONLY);
+        fds[1] = open("/dev/null", O_RDWR);
+
+        if (fds[0] < 0 || fds[1] < 0)
+                return -1;
+
+        for (i = 0; i < NR_ITERS; i++) {
+                lseek(fds[i % 2], i, (i / 2) % 2 ? SEEK_CUR : SEEK_SET);
+                lseek(fds[(i + 1) % 2], i, (i / 2) % 2 ? SEEK_CUR : SEEK_SET);
+        }
+        close(fds[0]);
+        close(fds[1]);
+        return 0;
+}
+
+#endif
+
 static struct {
         enum test_llvm__testcase prog_id;
         const char *desc;
@@ -37,6 +60,17 @@ static struct {
                 &epoll_pwait_loop,
                 (NR_ITERS + 1) / 2,
         },
+#ifdef HAVE_BPF_PROLOGUE
+        {
+                LLVM_TESTCASE_BPF_PROLOGUE,
+                "Test BPF prologue generation",
+                "[bpf_prologue_test]",
+                "fix kbuild first",
+                "check your vmlinux setting?",
+                &llseek_loop,
+                (NR_ITERS + 1) / 4,
+        },
+#endif
 };
 
 static int do_test(struct bpf_object *obj, int (*func)(void),
@@ -68,8 +102,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
         err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj);
         if (err || list_empty(&parse_evlist.list)) {
                 pr_debug("Failed to add events selected by BPF\n");
-                if (!err)
-                        return TEST_FAIL;
+                return TEST_FAIL;
         }
 
         snprintf(pid, sizeof(pid), "%d", getpid());
@@ -123,8 +156,10 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
                 }
         }
 
-        if (count != expect)
+        if (count != expect) {
                 pr_debug("BPF filter result incorrect\n");
+                goto out_delete_evlist;
+        }
 
         ret = TEST_OK;
 
@@ -146,7 +181,7 @@ prepare_bpf(void *obj_buf, size_t obj_buf_sz, const char *name)
         return obj;
 }
 
-static int __test__bpf(int index)
+static int __test__bpf(int idx)
 {
         int ret;
         void *obj_buf;
@@ -154,54 +189,72 @@ static int __test__bpf(int index)
         struct bpf_object *obj;
 
         ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
-                                       bpf_testcase_table[index].prog_id,
+                                       bpf_testcase_table[idx].prog_id,
                                        true);
         if (ret != TEST_OK || !obj_buf || !obj_buf_sz) {
                 pr_debug("Unable to get BPF object, %s\n",
-                         bpf_testcase_table[index].msg_compile_fail);
-                if (index == 0)
+                         bpf_testcase_table[idx].msg_compile_fail);
+                if (idx == 0)
                         return TEST_SKIP;
                 else
                         return TEST_FAIL;
         }
 
         obj = prepare_bpf(obj_buf, obj_buf_sz,
-                          bpf_testcase_table[index].name);
+                          bpf_testcase_table[idx].name);
         if (!obj) {
                 ret = TEST_FAIL;
                 goto out;
         }
 
         ret = do_test(obj,
-                      bpf_testcase_table[index].target_func,
-                      bpf_testcase_table[index].expect_result);
+                      bpf_testcase_table[idx].target_func,
+                      bpf_testcase_table[idx].expect_result);
 out:
         bpf__clear();
         return ret;
 }
 
-int test__bpf(void)
+int test__bpf_subtest_get_nr(void)
+{
+        return (int)ARRAY_SIZE(bpf_testcase_table);
+}
+
+const char *test__bpf_subtest_get_desc(int i)
+{
+        if (i < 0 || i >= (int)ARRAY_SIZE(bpf_testcase_table))
+                return NULL;
+        return bpf_testcase_table[i].desc;
+}
+
+int test__bpf(int i)
 {
-        unsigned int i;
         int err;
 
+        if (i < 0 || i >= (int)ARRAY_SIZE(bpf_testcase_table))
+                return TEST_FAIL;
+
         if (geteuid() != 0) {
                 pr_debug("Only root can run BPF test\n");
                 return TEST_SKIP;
         }
 
-        for (i = 0; i < ARRAY_SIZE(bpf_testcase_table); i++) {
-                err = __test__bpf(i);
+        err = __test__bpf(i);
+        return err;
+}
 
-                if (err != TEST_OK)
-                        return err;
-        }
+#else
+int test__bpf_subtest_get_nr(void)
+{
+        return 0;
+}
 
-        return TEST_OK;
+const char *test__bpf_subtest_get_desc(int i __maybe_unused)
+{
+        return NULL;
 }
 
-#else
-int test__bpf(void)
+int test__bpf(int i __maybe_unused)
 {
         pr_debug("Skip BPF test because BPF support is not compiled\n");
         return TEST_SKIP;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 80c442eab767..f2b1dcac45d3 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -11,7 +11,7 @@
 #include "tests.h"
 #include "debug.h"
 #include "color.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 #include "symbol.h"
 
 struct test __weak arch_tests[] = {
@@ -160,6 +160,11 @@ static struct test generic_tests[] = {
         {
                 .desc = "Test LLVM searching and compiling",
                 .func = test__llvm,
+                .subtest = {
+                        .skip_if_fail   = true,
+                        .get_nr         = test__llvm_subtest_get_nr,
+                        .get_desc       = test__llvm_subtest_get_desc,
+                },
         },
         {
                 .desc = "Test topology in session",
@@ -168,6 +173,35 @@ static struct test generic_tests[] = {
         {
                 .desc = "Test BPF filter",
                 .func = test__bpf,
+                .subtest = {
+                        .skip_if_fail   = true,
+                        .get_nr         = test__bpf_subtest_get_nr,
+                        .get_desc       = test__bpf_subtest_get_desc,
+                },
+        },
+        {
+                .desc = "Test thread map synthesize",
+                .func = test__thread_map_synthesize,
+        },
+        {
+                .desc = "Test cpu map synthesize",
+                .func = test__cpu_map_synthesize,
+        },
+        {
+                .desc = "Test stat config synthesize",
+                .func = test__synthesize_stat_config,
+        },
+        {
+                .desc = "Test stat synthesize",
+                .func = test__synthesize_stat,
+        },
+        {
+                .desc = "Test stat round synthesize",
+                .func = test__synthesize_stat_round,
+        },
+        {
+                .desc = "Test attr update synthesize",
+                .func = test__event_update,
         },
         {
                 .func = NULL,
@@ -203,7 +237,7 @@ static bool perf_test__matches(struct test *test, int curr, int argc, const char
         return false;
 }
 
-static int run_test(struct test *test)
+static int run_test(struct test *test, int subtest)
 {
         int status, err = -1, child = fork();
         char sbuf[STRERR_BUFSIZE];
@@ -216,7 +250,22 @@ static int run_test(struct test *test)
 
         if (!child) {
                 pr_debug("test child forked, pid %d\n", getpid());
-                err = test->func();
+                if (!verbose) {
+                        int nullfd = open("/dev/null", O_WRONLY);
+                        if (nullfd >= 0) {
+                                close(STDERR_FILENO);
+                                close(STDOUT_FILENO);
+
+                                dup2(nullfd, STDOUT_FILENO);
+                                dup2(STDOUT_FILENO, STDERR_FILENO);
+                                close(nullfd);
+                        }
+                } else {
+                        signal(SIGSEGV, sighandler_dump_stack);
+                        signal(SIGFPE, sighandler_dump_stack);
+                }
+
+                err = test->func(subtest);
                 exit(err);
         }
 
@@ -237,6 +286,40 @@ static int run_test(struct test *test)
         for (j = 0; j < ARRAY_SIZE(tests); j++) \
                 for (t = &tests[j][0]; t->func; t++)
 
+static int test_and_print(struct test *t, bool force_skip, int subtest)
+{
+        int err;
+
+        if (!force_skip) {
+                pr_debug("\n--- start ---\n");
+                err = run_test(t, subtest);
+                pr_debug("---- end ----\n");
+        } else {
+                pr_debug("\n--- force skipped ---\n");
+                err = TEST_SKIP;
+        }
+
+        if (!t->subtest.get_nr)
+                pr_debug("%s:", t->desc);
+        else
+                pr_debug("%s subtest %d:", t->desc, subtest);
+
+        switch (err) {
+        case TEST_OK:
+                pr_info(" Ok\n");
+                break;
+        case TEST_SKIP:
+                color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n");
+                break;
+        case TEST_FAIL:
+        default:
+                color_fprintf(stderr, PERF_COLOR_RED, " FAILED!\n");
+                break;
+        }
+
+        return err;
+}
+
 static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 {
         struct test *t;
@@ -264,21 +347,43 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
                         continue;
                 }
 
-                pr_debug("\n--- start ---\n");
-                err = run_test(t);
-                pr_debug("---- end ----\n%s:", t->desc);
-
-                switch (err) {
-                case TEST_OK:
-                        pr_info(" Ok\n");
-                        break;
-                case TEST_SKIP:
-                        color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n");
-                        break;
-                case TEST_FAIL:
-                default:
-                        color_fprintf(stderr, PERF_COLOR_RED, " FAILED!\n");
-                        break;
+                if (!t->subtest.get_nr) {
+                        test_and_print(t, false, -1);
+                } else {
+                        int subn = t->subtest.get_nr();
+                        /*
+                         * minus 2 to align with normal testcases.
+                         * For subtest we print additional '.x' in number.
+                         * for example:
+                         *
+                         * 35: Test LLVM searching and compiling                        :
+                         * 35.1: Basic BPF llvm compiling test                          : Ok
+                         */
+                        int subw = width > 2 ? width - 2 : width;
+                        bool skip = false;
+                        int subi;
+
+                        if (subn <= 0) {
+                                color_fprintf(stderr, PERF_COLOR_YELLOW,
+                                              " Skip (not compiled in)\n");
+                                continue;
+                        }
+                        pr_info("\n");
+
+                        for (subi = 0; subi < subn; subi++) {
+                                int len = strlen(t->subtest.get_desc(subi));
+
+                                if (subw < len)
+                                        subw = len;
+                        }
+
+                        for (subi = 0; subi < subn; subi++) {
+                                pr_info("%2d.%1d: %-*s:", i, subi + 1, subw,
+                                        t->subtest.get_desc(subi));
+                                err = test_and_print(t, skip, subi);
+                                if (err != TEST_OK && t->subtest.skip_if_fail)
+                                        skip = true;
+                        }
                 }
         }
 
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index a767a6400c5c..313a48c6b2bc 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -433,7 +433,6 @@ enum {
 
 static int do_test_code_reading(bool try_kcore)
 {
-        struct machines machines;
         struct machine *machine;
         struct thread *thread;
         struct record_opts opts = {
@@ -459,8 +458,7 @@ static int do_test_code_reading(bool try_kcore)
 
         pid = getpid();
 
-        machines__init(&machines);
-        machine = &machines.host;
+        machine = machine__new_host();
 
         ret = machine__create_kernel_maps(machine);
         if (ret < 0) {
@@ -549,6 +547,13 @@ static int do_test_code_reading(bool try_kcore)
                 if (ret < 0) {
                         if (!excl_kernel) {
                                 excl_kernel = true;
+                                /*
+                                 * Both cpus and threads are now owned by evlist
+                                 * and will be freed by following perf_evlist__set_maps
+                                 * call. Getting refference to keep them alive.
+                                 */
+                                cpu_map__get(cpus);
+                                thread_map__get(threads);
                                 perf_evlist__set_maps(evlist, NULL, NULL);
                                 perf_evlist__delete(evlist);
                                 evlist = NULL;
@@ -594,14 +599,13 @@ out_err:
                 cpu_map__put(cpus);
                 thread_map__put(threads);
         }
-        machines__destroy_kernel_maps(&machines);
         machine__delete_threads(machine);
-        machines__exit(&machines);
+        machine__delete(machine);
 
         return err;
 }
 
-int test__code_reading(void)
+int test__code_reading(int subtest __maybe_unused)
 {
         int ret;
 
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
new file mode 100644
index 000000000000..4cb6418a8ffc
--- /dev/null
+++ b/tools/perf/tests/cpumap.c
@@ -0,0 +1,88 @@
+#include "tests.h"
+#include "cpumap.h"
+
+static int process_event_mask(struct perf_tool *tool __maybe_unused,
+                         union perf_event *event,
+                         struct perf_sample *sample __maybe_unused,
+                         struct machine *machine __maybe_unused)
+{
+        struct cpu_map_event *map_event = &event->cpu_map;
+        struct cpu_map_mask *mask;
+        struct cpu_map_data *data;
+        struct cpu_map *map;
+        int i;
+
+        data = &map_event->data;
+
+        TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__MASK);
+
+        mask = (struct cpu_map_mask *)data->data;
+
+        TEST_ASSERT_VAL("wrong nr",   mask->nr == 1);
+
+        for (i = 0; i < 20; i++) {
+                TEST_ASSERT_VAL("wrong cpu", test_bit(i, mask->mask));
+        }
+
+        map = cpu_map__new_data(data);
+        TEST_ASSERT_VAL("wrong nr",  map->nr == 20);
+
+        for (i = 0; i < 20; i++) {
+                TEST_ASSERT_VAL("wrong cpu", map->map[i] == i);
+        }
+
+        cpu_map__put(map);
+        return 0;
+}
+
+static int process_event_cpus(struct perf_tool *tool __maybe_unused,
+                         union perf_event *event,
+                         struct perf_sample *sample __maybe_unused,
+                         struct machine *machine __maybe_unused)
+{
+        struct cpu_map_event *map_event = &event->cpu_map;
+        struct cpu_map_entries *cpus;
+        struct cpu_map_data *data;
+        struct cpu_map *map;
+
+        data = &map_event->data;
+
+        TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__CPUS);
+
+        cpus = (struct cpu_map_entries *)data->data;
+
+        TEST_ASSERT_VAL("wrong nr",   cpus->nr == 2);
+        TEST_ASSERT_VAL("wrong cpu",  cpus->cpu[0] == 1);
+        TEST_ASSERT_VAL("wrong cpu",  cpus->cpu[1] == 256);
+
+        map = cpu_map__new_data(data);
+        TEST_ASSERT_VAL("wrong nr",  map->nr == 2);
+        TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1);
+        TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256);
+        TEST_ASSERT_VAL("wrong refcnt", atomic_read(&map->refcnt) == 1);
+        cpu_map__put(map);
+        return 0;
+}
+
+
+int test__cpu_map_synthesize(int subtest __maybe_unused)
+{
+        struct cpu_map *cpus;
+
+        /* This one is better stores in mask. */
+        cpus = cpu_map__new("0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19");
+
+        TEST_ASSERT_VAL("failed to synthesize map",
+                !perf_event__synthesize_cpu_map(NULL, cpus, process_event_mask, NULL));
+
+        cpu_map__put(cpus);
+
+        /* This one is better stores in cpu values. */
+        cpus = cpu_map__new("1,256");
+
+        TEST_ASSERT_VAL("failed to synthesize map",
+                !perf_event__synthesize_cpu_map(NULL, cpus, process_event_cpus, NULL));
+
+        cpu_map__put(cpus);
+        return 0;
+}
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index a218aeaf56a0..dc673ff7c437 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -110,7 +110,7 @@ static int dso__data_fd(struct dso *dso, struct machine *machine)
         return fd;
 }
 
-int test__dso_data(void)
+int test__dso_data(int subtest __maybe_unused)
 {
         struct machine machine;
         struct dso *dso;
@@ -245,7 +245,7 @@ static int set_fd_limit(int n)
         return setrlimit(RLIMIT_NOFILE, &rlim);
 }
 
-int test__dso_data_cache(void)
+int test__dso_data_cache(int subtest __maybe_unused)
 {
         struct machine machine;
         long nr_end, nr = open_files_cnt();
@@ -302,7 +302,7 @@ int test__dso_data_cache(void)
         return 0;
 }
 
-int test__dso_data_reopen(void)
+int test__dso_data_reopen(int subtest __maybe_unused)
 {
         struct machine machine;
         long nr_end, nr = open_files_cnt();
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 07221793a3ac..1c5c0221cea2 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -51,6 +51,12 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
                 "krava_1",
                 "test__dwarf_unwind"
         };
+        /*
+         * The funcs[MAX_STACK] array index, based on the
+         * callchain order setup.
+         */
+        int idx = callchain_param.order == ORDER_CALLER ?
+                  MAX_STACK - *cnt - 1 : *cnt;
 
         if (*cnt >= MAX_STACK) {
                 pr_debug("failed: crossed the max stack value %d\n", MAX_STACK);
@@ -63,8 +69,10 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
                 return -1;
         }
 
-        pr_debug("got: %s 0x%" PRIx64 "\n", symbol, entry->ip);
-        return strcmp((const char *) symbol, funcs[(*cnt)++]);
+        (*cnt)++;
+        pr_debug("got: %s 0x%" PRIx64 ", expecting %s\n",
+                 symbol, entry->ip, funcs[idx]);
+        return strcmp((const char *) symbol, funcs[idx]);
 }
 
 __attribute__ ((noinline))
@@ -105,8 +113,16 @@ static int compare(void *p1, void *p2)
         /* Any possible value should be 'thread' */
         struct thread *thread = *(struct thread **)p1;
 
-        if (global_unwind_retval == -INT_MAX)
+        if (global_unwind_retval == -INT_MAX) {
+                /* Call unwinder twice for both callchain orders. */
+                callchain_param.order = ORDER_CALLER;
+
                 global_unwind_retval = unwind_thread(thread);
+                if (!global_unwind_retval) {
+                        callchain_param.order = ORDER_CALLEE;
+                        global_unwind_retval = unwind_thread(thread);
+                }
+        }
 
         return p1 - p2;
 }
@@ -142,21 +158,23 @@ static int krava_1(struct thread *thread)
         return krava_2(thread);
 }
 
-int test__dwarf_unwind(void)
+int test__dwarf_unwind(int subtest __maybe_unused)
 {
-        struct machines machines;
         struct machine *machine;
         struct thread *thread;
         int err = -1;
 
-        machines__init(&machines);
-
-        machine = machines__find(&machines, HOST_KERNEL_ID);
+        machine = machine__new_host();
         if (!machine) {
                 pr_err("Could not get machine\n");
                 return -1;
         }
 
+        if (machine__create_kernel_maps(machine)) {
+                pr_err("Failed to create kernel maps\n");
+                return -1;
+        }
+
         callchain_param.record_mode = CALLCHAIN_DWARF;
 
         if (init_live_machine(machine)) {
@@ -178,7 +196,6 @@ int test__dwarf_unwind(void)
 
  out:
         machine__delete_threads(machine);
-        machine__exit(machine);
-        machines__exit(&machines);
+        machine__delete(machine);
         return err;
 }
diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
new file mode 100644
index 000000000000..012eab5d1df1
--- /dev/null
+++ b/tools/perf/tests/event_update.c
@@ -0,0 +1,117 @@
+#include <linux/compiler.h>
+#include "evlist.h"
+#include "evsel.h"
+#include "machine.h"
+#include "tests.h"
+#include "debug.h"
+
+static int process_event_unit(struct perf_tool *tool __maybe_unused,
+                              union perf_event *event,
+                              struct perf_sample *sample __maybe_unused,
+                              struct machine *machine __maybe_unused)
+{
+        struct event_update_event *ev = (struct event_update_event *) event;
+
+        TEST_ASSERT_VAL("wrong id", ev->id == 123);
+        TEST_ASSERT_VAL("wrong id", ev->type == PERF_EVENT_UPDATE__UNIT);
+        TEST_ASSERT_VAL("wrong unit", !strcmp(ev->data, "KRAVA"));
+        return 0;
+}
+
+static int process_event_scale(struct perf_tool *tool __maybe_unused,
+                               union perf_event *event,
+                               struct perf_sample *sample __maybe_unused,
+                               struct machine *machine __maybe_unused)
+{
+        struct event_update_event *ev = (struct event_update_event *) event;
+        struct event_update_event_scale *ev_data;
+
+        ev_data = (struct event_update_event_scale *) ev->data;
+
+        TEST_ASSERT_VAL("wrong id", ev->id == 123);
+        TEST_ASSERT_VAL("wrong id", ev->type == PERF_EVENT_UPDATE__SCALE);
+        TEST_ASSERT_VAL("wrong scale", ev_data->scale = 0.123);
+        return 0;
+}
+
+struct event_name {
+        struct perf_tool tool;
+        const char *name;
+};
+
+static int process_event_name(struct perf_tool *tool,
+                              union perf_event *event,
+                              struct perf_sample *sample __maybe_unused,
+                              struct machine *machine __maybe_unused)
+{
+        struct event_name *tmp = container_of(tool, struct event_name, tool);
+        struct event_update_event *ev = (struct event_update_event*) event;
+
+        TEST_ASSERT_VAL("wrong id", ev->id == 123);
+        TEST_ASSERT_VAL("wrong id", ev->type == PERF_EVENT_UPDATE__NAME);
+        TEST_ASSERT_VAL("wrong name", !strcmp(ev->data, tmp->name));
+        return 0;
+}
+
+static int process_event_cpus(struct perf_tool *tool __maybe_unused,
+                              union perf_event *event,
+                              struct perf_sample *sample __maybe_unused,
+                              struct machine *machine __maybe_unused)
+{
+        struct event_update_event *ev = (struct event_update_event*) event;
+        struct event_update_event_cpus *ev_data;
+        struct cpu_map *map;
+
+        ev_data = (struct event_update_event_cpus*) ev->data;
+
+        map = cpu_map__new_data(&ev_data->cpus);
+
+        TEST_ASSERT_VAL("wrong id", ev->id == 123);
+        TEST_ASSERT_VAL("wrong type", ev->type == PERF_EVENT_UPDATE__CPUS);
+        TEST_ASSERT_VAL("wrong cpus", map->nr == 3);
+        TEST_ASSERT_VAL("wrong cpus", map->map[0] == 1);
+        TEST_ASSERT_VAL("wrong cpus", map->map[1] == 2);
+        TEST_ASSERT_VAL("wrong cpus", map->map[2] == 3);
+        cpu_map__put(map);
+        return 0;
+}
+
+int test__event_update(int subtest __maybe_unused)
+{
+        struct perf_evlist *evlist;
+        struct perf_evsel *evsel;
+        struct event_name tmp;
+
+        evlist = perf_evlist__new_default();
+        TEST_ASSERT_VAL("failed to get evlist", evlist);
+
+        evsel = perf_evlist__first(evlist);
+
+        TEST_ASSERT_VAL("failed to allos ids",
+                        !perf_evsel__alloc_id(evsel, 1, 1));
+
+        perf_evlist__id_add(evlist, evsel, 0, 0, 123);
+
+        evsel->unit = strdup("KRAVA");
+
+        TEST_ASSERT_VAL("failed to synthesize attr update unit",
+                        !perf_event__synthesize_event_update_unit(NULL, evsel, process_event_unit));
+
+        evsel->scale = 0.123;
+
+        TEST_ASSERT_VAL("failed to synthesize attr update scale",
+                        !perf_event__synthesize_event_update_scale(NULL, evsel, process_event_scale));
+
+        tmp.name = perf_evsel__name(evsel);
+
+        TEST_ASSERT_VAL("failed to synthesize attr update name",
+                        !perf_event__synthesize_event_update_name(&tmp.tool, evsel, process_event_name));
+
+        evsel->own_cpus = cpu_map__new("1,2,3");
+
+        TEST_ASSERT_VAL("failed to synthesize attr update cpus",
+                        !perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus));
+
+        cpu_map__put(evsel->own_cpus);
+        return 0;
+}
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 3fa715987a5e..2de4a4f2c3ed 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -95,7 +95,7 @@ out_delete_evlist:
 #define perf_evsel__name_array_test(names) \
         __perf_evsel__name_array_test(names, ARRAY_SIZE(names))
 
-int test__perf_evsel__roundtrip_name_test(void)
+int test__perf_evsel__roundtrip_name_test(int subtest __maybe_unused)
 {
         int err = 0, ret = 0;
 
@@ -103,7 +103,8 @@ int test__perf_evsel__roundtrip_name_test(void)
         if (err)
                 ret = err;
 
-        err = perf_evsel__name_array_test(perf_evsel__sw_names);
+        err = __perf_evsel__name_array_test(perf_evsel__sw_names,
+                                            PERF_COUNT_SW_DUMMY + 1);
         if (err)
                 ret = err;
 
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 790e413d9a1f..1984b3bbfe15 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -32,7 +32,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
         return ret;
 }
 
-int test__perf_evsel__tp_sched_test(void)
+int test__perf_evsel__tp_sched_test(int subtest __maybe_unused)
 {
         struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch");
         int ret = 0;
diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
index d24b837951d4..c809463edbe5 100644
--- a/tools/perf/tests/fdarray.c
+++ b/tools/perf/tests/fdarray.c
@@ -25,7 +25,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE
         return printed + fdarray__fprintf(fda, fp);
 }
 
-int test__fdarray__filter(void)
+int test__fdarray__filter(int subtest __maybe_unused)
 {
         int nr_fds, expected_fd[2], fd, err = TEST_FAIL;
         struct fdarray *fda = fdarray__new(5, 5);
@@ -103,7 +103,7 @@ out:
         return err;
 }
 
-int test__fdarray__add(void)
+int test__fdarray__add(int subtest __maybe_unused)
 {
         int err = TEST_FAIL;
         struct fdarray *fda = fdarray__new(2, 2);
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index ce80b274b097..bcfd081ee1d2 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -87,6 +87,11 @@ struct machine *setup_fake_machine(struct machines *machines)
                 return NULL;
         }
 
+        if (machine__create_kernel_maps(machine)) {
+                pr_debug("Cannot create kernel maps\n");
+                return NULL;
+        }
+
         for (i = 0; i < ARRAY_SIZE(fake_threads); i++) {
                 struct thread *thread;
 
@@ -150,7 +155,6 @@ struct machine *setup_fake_machine(struct machines *machines)
 out:
         pr_debug("Not enough memory for machine setup\n");
         machine__delete_threads(machine);
-        machine__delete(machine);
         return NULL;
 }
 
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 7ed737019de7..e36089212061 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -281,7 +281,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine)
         symbol_conf.cumulate_callchain = false;
         perf_evsel__reset_sample_bit(evsel, CALLCHAIN);
 
-        setup_sorting();
+        setup_sorting(NULL);
         callchain_register_param(&callchain_param);
 
         err = add_hist_entries(hists, machine);
@@ -428,7 +428,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine)
         symbol_conf.cumulate_callchain = false;
         perf_evsel__set_sample_bit(evsel, CALLCHAIN);
 
-        setup_sorting();
+        setup_sorting(NULL);
         callchain_register_param(&callchain_param);
 
         err = add_hist_entries(hists, machine);
@@ -486,7 +486,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
         symbol_conf.cumulate_callchain = true;
         perf_evsel__reset_sample_bit(evsel, CALLCHAIN);
 
-        setup_sorting();
+        setup_sorting(NULL);
         callchain_register_param(&callchain_param);
 
         err = add_hist_entries(hists, machine);
@@ -670,7 +670,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
         symbol_conf.cumulate_callchain = true;
         perf_evsel__set_sample_bit(evsel, CALLCHAIN);
 
-        setup_sorting();
+        setup_sorting(NULL);
         callchain_register_param(&callchain_param);
 
         err = add_hist_entries(hists, machine);
@@ -686,7 +686,7 @@ out:
         return err;
 }
 
-int test__hists_cumulate(void)
+int test__hists_cumulate(int subtest __maybe_unused)
 {
         int err = TEST_FAIL;
         struct machines machines;
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 818acf875dd0..2a784befd9ce 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -104,7 +104,7 @@ out:
         return TEST_FAIL;
 }
 
-int test__hists_filter(void)
+int test__hists_filter(int subtest __maybe_unused)
 {
         int err = TEST_FAIL;
         struct machines machines;
@@ -122,7 +122,7 @@ int test__hists_filter(void)
                 goto out;
 
         /* default sort order (comm,dso,sym) will be used */
-        if (setup_sorting() < 0)
+        if (setup_sorting(NULL) < 0)
                 goto out;
 
         machines__init(&machines);
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 8c102b011424..c764d69ac6ef 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -64,7 +64,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
         struct perf_evsel *evsel;
         struct addr_location al;
         struct hist_entry *he;
-        struct perf_sample sample = { .period = 1, };
+        struct perf_sample sample = { .period = 1, .weight = 1, };
         size_t i = 0, k;
 
         /*
@@ -90,7 +90,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
                                 goto out;
 
                         he = __hists__add_entry(hists, &al, NULL,
-                                                NULL, NULL, 1, 1, 0, true);
+                                                NULL, NULL, &sample, true);
                         if (he == NULL) {
                                 addr_location__put(&al);
                                 goto out;
@@ -116,7 +116,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
                                 goto out;
 
                         he = __hists__add_entry(hists, &al, NULL,
-                                                NULL, NULL, 1, 1, 0, true);
+                                                NULL, NULL, &sample, true);
                         if (he == NULL) {
                                 addr_location__put(&al);
                                 goto out;
@@ -274,7 +274,7 @@ static int validate_link(struct hists *leader, struct hists *other)
         return __validate_link(leader, 0) || __validate_link(other, 1);
 }
 
-int test__hists_link(void)
+int test__hists_link(int subtest __maybe_unused)
 {
         int err = -1;
         struct hists *hists, *first_hists;
@@ -294,7 +294,7 @@ int test__hists_link(void)
                 goto out;
 
         /* default sort order (comm,dso,sym) will be used */
-        if (setup_sorting() < 0)
+        if (setup_sorting(NULL) < 0)
                 goto out;
 
         machines__init(&machines);
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index adbebc852cc8..ebe6cd485b5d 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -134,7 +134,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine)
         field_order = NULL;
         sort_order = NULL; /* equivalent to sort_order = "comm,dso,sym" */
 
-        setup_sorting();
+        setup_sorting(NULL);
 
         /*
          * expected output:
@@ -236,7 +236,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine)
         field_order = "overhead,cpu";
         sort_order = "pid";
 
-        setup_sorting();
+        setup_sorting(NULL);
 
         /*
          * expected output:
@@ -292,7 +292,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
         field_order = "comm,overhead,dso";
         sort_order = NULL;
 
-        setup_sorting();
+        setup_sorting(NULL);
 
         /*
          * expected output:
@@ -366,7 +366,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
         field_order = "dso,sym,comm,overhead,dso";
         sort_order = "sym";
 
-        setup_sorting();
+        setup_sorting(NULL);
 
         /*
          * expected output:
@@ -468,7 +468,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine)
         field_order = "cpu,pid,comm,dso,sym";
         sort_order = "dso,pid";
 
-        setup_sorting();
+        setup_sorting(NULL);
 
         /*
          * expected output:
@@ -576,7 +576,7 @@ out:
         return err;
 }
 
-int test__hists_output(void)
+int test__hists_output(int subtest __maybe_unused)
 {
         int err = TEST_FAIL;
         struct machines machines;
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index a2e2269aa093..ddb78fae064a 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -49,13 +49,12 @@ static int find_comm(struct perf_evlist *evlist, const char *comm)
  * when an event is disabled but a dummy software event is not disabled.  If the
  * test passes %0 is returned, otherwise %-1 is returned.
  */
-int test__keep_tracking(void)
+int test__keep_tracking(int subtest __maybe_unused)
 {
         struct record_opts opts = {
                 .mmap_pages          = UINT_MAX,
                 .user_freq           = UINT_MAX,
                 .user_interval       = ULLONG_MAX,
-                .freq                = 4000,
                 .target              = {
                         .uses_mmap   = true,
                 },
@@ -124,7 +123,7 @@ int test__keep_tracking(void)
 
         evsel = perf_evlist__last(evlist);
 
-        CHECK__(perf_evlist__disable_event(evlist, evsel));
+        CHECK__(perf_evsel__disable(evsel));
 
         comm = "Test COMM 2";
         CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0));
diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c
index 08c433b4bf4f..d2af78193153 100644
--- a/tools/perf/tests/kmod-path.c
+++ b/tools/perf/tests/kmod-path.c
@@ -49,7 +49,7 @@ static int test_is_kernel_module(const char *path, int cpumode, bool expect)
 #define M(path, c, e) \
         TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e))
 
-int test__kmod_path__parse(void)
+int test__kmod_path__parse(int subtest __maybe_unused)
 {
         /* path                alloc_name  alloc_ext   kmod  comp   name     ext */
         T("/xxxx/xxxx/x-x.ko", true      , true      , true, false, "[x_x]", NULL);
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index bc4cf507cde5..06f45c1d4256 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -44,13 +44,17 @@ static struct {
                 .source = test_llvm__bpf_test_kbuild_prog,
                 .desc = "Test kbuild searching",
         },
+        [LLVM_TESTCASE_BPF_PROLOGUE] = {
+                .source = test_llvm__bpf_test_prologue_prog,
+                .desc = "Compile source for BPF prologue generation test",
+        },
 };
 
 
 int
 test_llvm__fetch_bpf_obj(void **p_obj_buf,
                          size_t *p_obj_buf_sz,
-                         enum test_llvm__testcase index,
+                         enum test_llvm__testcase idx,
                          bool force)
 {
         const char *source;
@@ -59,11 +63,11 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf,
         char *tmpl_new = NULL, *clang_opt_new = NULL;
         int err, old_verbose, ret = TEST_FAIL;
 
-        if (index >= __LLVM_TESTCASE_MAX)
+        if (idx >= __LLVM_TESTCASE_MAX)
                 return TEST_FAIL;
 
-        source = bpf_source_table[index].source;
-        desc = bpf_source_table[index].desc;
+        source = bpf_source_table[idx].source;
+        desc = bpf_source_table[idx].desc;
 
         perf_config(perf_config_cb, NULL);
 
@@ -127,44 +131,39 @@ out:
         return ret;
 }
 
-int test__llvm(void)
+int test__llvm(int subtest)
 {
-        enum test_llvm__testcase i;
+        int ret;
+        void *obj_buf = NULL;
+        size_t obj_buf_sz = 0;
 
-        for (i = 0; i < __LLVM_TESTCASE_MAX; i++) {
-                int ret;
-                void *obj_buf = NULL;
-                size_t obj_buf_sz = 0;
+        if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX))
+                return TEST_FAIL;
 
-                ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
-                                               i, false);
+        ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
+                                       subtest, false);
 
-                if (ret == TEST_OK) {
-                        ret = test__bpf_parsing(obj_buf, obj_buf_sz);
-                        if (ret != TEST_OK)
-                                pr_debug("Failed to parse test case '%s'\n",
-                                         bpf_source_table[i].desc);
-                }
-                free(obj_buf);
-
-                switch (ret) {
-                case TEST_SKIP:
-                        return TEST_SKIP;
-                case TEST_OK:
-                        break;
-                default:
-                        /*
-                         * Test 0 is the basic LLVM test. If test 0
-                         * fail, the basic LLVM support not functional
-                         * so the whole test should fail. If other test
-                         * case fail, it can be fixed by adjusting
-                         * config so don't report error.
-                         */
-                        if (i == 0)
-                                return TEST_FAIL;
-                        else
-                                return TEST_SKIP;
+        if (ret == TEST_OK) {
+                ret = test__bpf_parsing(obj_buf, obj_buf_sz);
+                if (ret != TEST_OK) {
+                        pr_debug("Failed to parse test case '%s'\n",
+                                 bpf_source_table[subtest].desc);
                 }
         }
-        return TEST_OK;
+        free(obj_buf);
+
+        return ret;
+}
+
+int test__llvm_subtest_get_nr(void)
+{
+        return __LLVM_TESTCASE_MAX;
+}
+
+const char *test__llvm_subtest_get_desc(int subtest)
+{
+        if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX))
+                return NULL;
+
+        return bpf_source_table[subtest].desc;
 }
diff --git a/tools/perf/tests/llvm.h b/tools/perf/tests/llvm.h
index d91d8f44efee..5150b4d6ef50 100644
--- a/tools/perf/tests/llvm.h
+++ b/tools/perf/tests/llvm.h
@@ -6,10 +6,12 @@
 
 extern const char test_llvm__bpf_base_prog[];
 extern const char test_llvm__bpf_test_kbuild_prog[];
+extern const char test_llvm__bpf_test_prologue_prog[];
 
 enum test_llvm__testcase {
         LLVM_TESTCASE_BASE,
         LLVM_TESTCASE_KBUILD,
+        LLVM_TESTCASE_BPF_PROLOGUE,
         __LLVM_TESTCASE_MAX,
 };
 
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 8ea3dffc5065..c1fbb8e884c0 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -259,7 +259,8 @@ $(run_O):
 tarpkg:
         @cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \
         echo "- $@: $$cmd" && echo $$cmd > $@ && \
-        ( eval $$cmd ) >> $@ 2>&1
+        ( eval $$cmd ) >> $@ 2>&1 && \
+        rm -f $@
 
 make_kernelsrc:
         @echo "- make -C <kernelsrc> tools/perf"
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 4495493c9431..359e98fcd94c 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -16,7 +16,7 @@
  * Then it checks if the number of syscalls reported as perf events by
  * the kernel corresponds to the number of syscalls made.
  */
-int test__basic_mmap(void)
+int test__basic_mmap(int subtest __maybe_unused)
 {
         int err = -1;
         union perf_event *event;
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 145050e2e544..0c5ce44f723f 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -149,7 +149,6 @@ static int synth_process(struct machine *machine)
 
 static int mmap_events(synth_cb synth)
 {
-        struct machines machines;
         struct machine *machine;
         int err, i;
 
@@ -162,8 +161,7 @@ static int mmap_events(synth_cb synth)
          */
         TEST_ASSERT_VAL("failed to create threads", !threads_create());
 
-        machines__init(&machines);
-        machine = &machines.host;
+        machine = machine__new_host();
 
         dump_trace = verbose > 1 ? 1 : 0;
 
@@ -203,7 +201,7 @@ static int mmap_events(synth_cb synth)
         }
 
         machine__delete_threads(machine);
-        machines__exit(&machines);
+        machine__delete(machine);
         return err;
 }
 
@@ -221,7 +219,7 @@ static int mmap_events(synth_cb synth)
  *
  * by using all thread objects.
  */
-int test__mmap_thread_lookup(void)
+int test__mmap_thread_lookup(int subtest __maybe_unused)
 {
         /* perf_event__synthesize_threads synthesize */
         TEST_ASSERT_VAL("failed with sythesizing all",
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index 2006485a2859..53c2273e8859 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -7,7 +7,7 @@
 #include "debug.h"
 #include "stat.h"
 
-int test__openat_syscall_event_on_all_cpus(void)
+int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused)
 {
         int err = -1, fd, cpu;
         struct cpu_map *cpus;
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 5e811cd8f1c3..eb99a105f31c 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -6,7 +6,7 @@
 #include "tests.h"
 #include "debug.h"
 
-int test__syscall_openat_tp_fields(void)
+int test__syscall_openat_tp_fields(int subtest __maybe_unused)
 {
         struct record_opts opts = {
                 .target = {
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index 033b54797b8a..1184f9ba6499 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -5,7 +5,7 @@
 #include "debug.h"
 #include "tests.h"
 
-int test__openat_syscall_event(void)
+int test__openat_syscall_event(int subtest __maybe_unused)
 {
         int err = -1, fd;
         struct perf_evsel *evsel;
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 636d7b42d844..abe8849d1d70 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1765,7 +1765,7 @@ static void debug_warn(const char *warn, va_list params)
         fprintf(stderr, " Warning: %s\n", msg);
 }
 
-int test__parse_events(void)
+int test__parse_events(int subtest __maybe_unused)
 {
         int ret1, ret2 = 0;
 
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 2c63ea658541..294c76b01b41 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -67,7 +67,7 @@ struct test_attr_event {
  *
  * Return: %0 on success, %-1 if the test fails.
  */
-int test__parse_no_sample_id_all(void)
+int test__parse_no_sample_id_all(int subtest __maybe_unused)
 {
         int err;
 
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 7a228a2a070b..1cc78cefe399 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -32,7 +32,7 @@ realloc:
         return cpu;
 }
 
-int test__PERF_RECORD(void)
+int test__PERF_RECORD(int subtest __maybe_unused)
 {
         struct record_opts opts = {
                 .target = {
@@ -40,12 +40,11 @@ int test__PERF_RECORD(void)
                         .uses_mmap = true,
                 },
                 .no_buffering = true,
-                .freq         = 10,
                 .mmap_pages   = 256,
         };
         cpu_set_t cpu_mask;
         size_t cpu_mask_size = sizeof(cpu_mask);
-        struct perf_evlist *evlist = perf_evlist__new_default();
+        struct perf_evlist *evlist = perf_evlist__new_dummy();
         struct perf_evsel *evsel;
         struct perf_sample sample;
         const char *cmd = "sleep";
@@ -61,6 +60,9 @@ int test__PERF_RECORD(void)
         int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
         char sbuf[STRERR_BUFSIZE];
 
+        if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */
+                evlist = perf_evlist__new_default();
+
         if (evlist == NULL || argv == NULL) {
                 pr_debug("Not enough memory to create evlist\n");
                 goto out;
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index faa04e9d5d5f..1e2ba2602930 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -133,7 +133,7 @@ static struct list_head *test_terms_list(void)
         return &terms;
 }
 
-int test__pmu(void)
+int test__pmu(int subtest __maybe_unused)
 {
         char *format = test_format_dir_get();
         LIST_HEAD(formats);
diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c
index 7760277c6def..7a52834ee0d0 100644
--- a/tools/perf/tests/python-use.c
+++ b/tools/perf/tests/python-use.c
@@ -4,11 +4,12 @@
 
 #include <stdio.h>
 #include <stdlib.h>
+#include <linux/compiler.h>
 #include "tests.h"
 
 extern int verbose;
 
-int test__python_use(void)
+int test__python_use(int subtest __maybe_unused)
 {
         char *cmd;
         int ret;
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 30c02181e78b..5f23710b9fee 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -290,7 +290,7 @@ out_free:
  * checks sample format bits separately and together.  If the test passes %0 is
  * returned, otherwise %-1 is returned.
  */
-int test__sample_parsing(void)
+int test__sample_parsing(int subtest __maybe_unused)
 {
         const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
         u64 sample_type;
diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c
new file mode 100644
index 000000000000..6a20ff2326bb
--- /dev/null
+++ b/tools/perf/tests/stat.c
@@ -0,0 +1,111 @@
+#include <linux/compiler.h>
+#include "event.h"
+#include "tests.h"
+#include "stat.h"
+#include "counts.h"
+#include "debug.h"
+
+static bool has_term(struct stat_config_event *config,
+                     u64 tag, u64 val)
+{
+        unsigned i;
+
+        for (i = 0; i < config->nr; i++) {
+                if ((config->data[i].tag == tag) &&
+                    (config->data[i].val == val))
+                        return true;
+        }
+
+        return false;
+}
+
+static int process_stat_config_event(struct perf_tool *tool __maybe_unused,
+                                     union perf_event *event,
+                                     struct perf_sample *sample __maybe_unused,
+                                     struct machine *machine __maybe_unused)
+{
+        struct stat_config_event *config = &event->stat_config;
+        struct perf_stat_config stat_config;
+
+#define HAS(term, val) \
+        has_term(config, PERF_STAT_CONFIG_TERM__##term, val)
+
+        TEST_ASSERT_VAL("wrong nr",        config->nr == PERF_STAT_CONFIG_TERM__MAX);
+        TEST_ASSERT_VAL("wrong aggr_mode", HAS(AGGR_MODE, AGGR_CORE));
+        TEST_ASSERT_VAL("wrong scale",     HAS(SCALE, 1));
+        TEST_ASSERT_VAL("wrong interval",  HAS(INTERVAL, 1));
+
+#undef HAS
+
+        perf_event__read_stat_config(&stat_config, config);
+
+        TEST_ASSERT_VAL("wrong aggr_mode", stat_config.aggr_mode == AGGR_CORE);
+        TEST_ASSERT_VAL("wrong scale",     stat_config.scale == 1);
+        TEST_ASSERT_VAL("wrong interval",  stat_config.interval == 1);
+        return 0;
+}
+
+int test__synthesize_stat_config(int subtest __maybe_unused)
+{
+        struct perf_stat_config stat_config = {
+                .aggr_mode      = AGGR_CORE,
+                .scale          = 1,
+                .interval       = 1,
+        };
+
+        TEST_ASSERT_VAL("failed to synthesize stat_config",
+                !perf_event__synthesize_stat_config(NULL, &stat_config, process_stat_config_event, NULL));
+
+        return 0;
+}
+
+static int process_stat_event(struct perf_tool *tool __maybe_unused,
+                              union perf_event *event,
+                              struct perf_sample *sample __maybe_unused,
+                              struct machine *machine __maybe_unused)
+{
+        struct stat_event *st = &event->stat;
+
+        TEST_ASSERT_VAL("wrong cpu",    st->cpu    == 1);
+        TEST_ASSERT_VAL("wrong thread", st->thread == 2);
+        TEST_ASSERT_VAL("wrong id",     st->id     == 3);
+        TEST_ASSERT_VAL("wrong val",    st->val    == 100);
+        TEST_ASSERT_VAL("wrong run",    st->ena    == 200);
+        TEST_ASSERT_VAL("wrong ena",    st->run    == 300);
+        return 0;
+}
+
+int test__synthesize_stat(int subtest __maybe_unused)
+{
+        struct perf_counts_values count;
+
+        count.val = 100;
+        count.ena = 200;
+        count.run = 300;
+
+        TEST_ASSERT_VAL("failed to synthesize stat_config",
+                !perf_event__synthesize_stat(NULL, 1, 2, 3, &count, process_stat_event, NULL));
+
+        return 0;
+}
+
+static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
+                                    union perf_event *event,
+                                    struct perf_sample *sample __maybe_unused,
+                                    struct machine *machine __maybe_unused)
+{
+        struct stat_round_event *stat_round = &event->stat_round;
+
+        TEST_ASSERT_VAL("wrong time", stat_round->time == 0xdeadbeef);
+        TEST_ASSERT_VAL("wrong type", stat_round->type == PERF_STAT_ROUND_TYPE__INTERVAL);
+        return 0;
+}
+
+int test__synthesize_stat_round(int subtest __maybe_unused)
+{
+        TEST_ASSERT_VAL("failed to synthesize stat_config",
+                !perf_event__synthesize_stat_round(NULL, 0xdeadbeef, PERF_STAT_ROUND_TYPE__INTERVAL,
+                                                   process_stat_round_event, NULL));
+
+        return 0;
+}
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 5b83f56a3b6f..36e8ce1550e3 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -122,7 +122,7 @@ out_delete_evlist:
         return err;
 }
 
-int test__sw_clock_freq(void)
+int test__sw_clock_freq(int subtest __maybe_unused)
 {
         int ret;
 
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index a02af503100c..ebd80168d51e 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -305,7 +305,7 @@ out_free_nodes:
  * evsel->system_wide and evsel->tracking flags (respectively) with other events
  * sometimes enabled or disabled.
  */
-int test__switch_tracking(void)
+int test__switch_tracking(int subtest __maybe_unused)
 {
         const char *sched_switch = "sched:sched_switch";
         struct switch_tracking switch_tracking = { .tids = NULL, };
@@ -455,7 +455,7 @@ int test__switch_tracking(void)
 
         perf_evlist__enable(evlist);
 
-        err = perf_evlist__disable_event(evlist, cpu_clocks_evsel);
+        err = perf_evsel__disable(cpu_clocks_evsel);
         if (err) {
                 pr_debug("perf_evlist__disable_event failed!\n");
                 goto out_err;
@@ -474,7 +474,7 @@ int test__switch_tracking(void)
                 goto out_err;
         }
 
-        err = perf_evlist__disable_event(evlist, cycles_evsel);
+        err = perf_evsel__disable(cycles_evsel);
         if (err) {
                 pr_debug("perf_evlist__disable_event failed!\n");
                 goto out_err;
@@ -500,7 +500,7 @@ int test__switch_tracking(void)
                 goto out_err;
         }
 
-        err = perf_evlist__enable_event(evlist, cycles_evsel);
+        err = perf_evsel__enable(cycles_evsel);
         if (err) {
                 pr_debug("perf_evlist__disable_event failed!\n");
                 goto out_err;
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index add16385f13e..2dfff7ac8ef3 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -31,7 +31,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
  * if the number of exit event reported by the kernel is 1 or not
  * in order to check the kernel returns correct number of event.
  */
-int test__task_exit(void)
+int test__task_exit(int subtest __maybe_unused)
 {
         int err = -1;
         union perf_event *event;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 3c8734a3abbc..82b2b5e6ba7c 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -1,6 +1,8 @@
 #ifndef TESTS_H
 #define TESTS_H
 
+#include <stdbool.h>
+
 #define TEST_ASSERT_VAL(text, cond)                                      \
 do {                                                                     \
         if (!(cond)) {                                                   \
@@ -26,48 +28,63 @@ enum {
 
 struct test {
         const char *desc;
-        int (*func)(void);
+        int (*func)(int subtest);
+        struct {
+                bool skip_if_fail;
+                int (*get_nr)(void);
+                const char *(*get_desc)(int subtest);
+        } subtest;
 };
 
 /* Tests */
-int test__vmlinux_matches_kallsyms(void);
-int test__openat_syscall_event(void);
-int test__openat_syscall_event_on_all_cpus(void);
-int test__basic_mmap(void);
-int test__PERF_RECORD(void);
-int test__perf_evsel__roundtrip_name_test(void);
-int test__perf_evsel__tp_sched_test(void);
-int test__syscall_openat_tp_fields(void);
-int test__pmu(void);
-int test__attr(void);
-int test__dso_data(void);
-int test__dso_data_cache(void);
-int test__dso_data_reopen(void);
-int test__parse_events(void);
-int test__hists_link(void);
-int test__python_use(void);
-int test__bp_signal(void);
-int test__bp_signal_overflow(void);
-int test__task_exit(void);
-int test__sw_clock_freq(void);
-int test__code_reading(void);
-int test__sample_parsing(void);
-int test__keep_tracking(void);
-int test__parse_no_sample_id_all(void);
-int test__dwarf_unwind(void);
-int test__hists_filter(void);
-int test__mmap_thread_lookup(void);
-int test__thread_mg_share(void);
-int test__hists_output(void);
-int test__hists_cumulate(void);
-int test__switch_tracking(void);
-int test__fdarray__filter(void);
-int test__fdarray__add(void);
-int test__kmod_path__parse(void);
-int test__thread_map(void);
-int test__llvm(void);
-int test__bpf(void);
-int test_session_topology(void);
+int test__vmlinux_matches_kallsyms(int subtest);
+int test__openat_syscall_event(int subtest);
+int test__openat_syscall_event_on_all_cpus(int subtest);
+int test__basic_mmap(int subtest);
+int test__PERF_RECORD(int subtest);
+int test__perf_evsel__roundtrip_name_test(int subtest);
+int test__perf_evsel__tp_sched_test(int subtest);
+int test__syscall_openat_tp_fields(int subtest);
+int test__pmu(int subtest);
+int test__attr(int subtest);
+int test__dso_data(int subtest);
+int test__dso_data_cache(int subtest);
+int test__dso_data_reopen(int subtest);
+int test__parse_events(int subtest);
+int test__hists_link(int subtest);
+int test__python_use(int subtest);
+int test__bp_signal(int subtest);
+int test__bp_signal_overflow(int subtest);
+int test__task_exit(int subtest);
+int test__sw_clock_freq(int subtest);
+int test__code_reading(int subtest);
+int test__sample_parsing(int subtest);
+int test__keep_tracking(int subtest);
+int test__parse_no_sample_id_all(int subtest);
+int test__dwarf_unwind(int subtest);
+int test__hists_filter(int subtest);
+int test__mmap_thread_lookup(int subtest);
+int test__thread_mg_share(int subtest);
+int test__hists_output(int subtest);
+int test__hists_cumulate(int subtest);
+int test__switch_tracking(int subtest);
+int test__fdarray__filter(int subtest);
+int test__fdarray__add(int subtest);
+int test__kmod_path__parse(int subtest);
+int test__thread_map(int subtest);
+int test__llvm(int subtest);
+const char *test__llvm_subtest_get_desc(int subtest);
+int test__llvm_subtest_get_nr(void);
+int test__bpf(int subtest);
+const char *test__bpf_subtest_get_desc(int subtest);
+int test__bpf_subtest_get_nr(void);
+int test_session_topology(int subtest);
+int test__thread_map_synthesize(int subtest);
+int test__cpu_map_synthesize(int subtest);
+int test__synthesize_stat_config(int subtest);
+int test__synthesize_stat(int subtest);
+int test__synthesize_stat_round(int subtest);
+int test__event_update(int subtest);
 
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index 138a0e3431fa..fccde848fe9c 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -4,7 +4,7 @@
 #include "thread_map.h"
 #include "debug.h"
 
-int test__thread_map(void)
+int test__thread_map(int subtest __maybe_unused)
 {
         struct thread_map *map;
 
@@ -40,3 +40,46 @@ int test__thread_map(void)
         thread_map__put(map);
         return 0;
 }
+
+static int process_event(struct perf_tool *tool __maybe_unused,
+                         union perf_event *event,
+                         struct perf_sample *sample __maybe_unused,
+                         struct machine *machine __maybe_unused)
+{
+        struct thread_map_event *map = &event->thread_map;
+        struct thread_map *threads;
+
+        TEST_ASSERT_VAL("wrong nr",   map->nr == 1);
+        TEST_ASSERT_VAL("wrong pid",  map->entries[0].pid == (u64) getpid());
+        TEST_ASSERT_VAL("wrong comm", !strcmp(map->entries[0].comm, "perf"));
+
+        threads = thread_map__new_event(&event->thread_map);
+        TEST_ASSERT_VAL("failed to alloc map", threads);
+
+        TEST_ASSERT_VAL("wrong nr", threads->nr == 1);
+        TEST_ASSERT_VAL("wrong pid",
+                        thread_map__pid(threads, 0) == getpid());
+        TEST_ASSERT_VAL("wrong comm",
+                        thread_map__comm(threads, 0) &&
+                        !strcmp(thread_map__comm(threads, 0), "perf"));
+        TEST_ASSERT_VAL("wrong refcnt",
+                        atomic_read(&threads->refcnt) == 1);
+        thread_map__put(threads);
+        return 0;
+}
+
+int test__thread_map_synthesize(int subtest __maybe_unused)
+{
+        struct thread_map *threads;
+
+        /* test map on current pid */
+        threads = thread_map__new_by_pid(getpid());
+        TEST_ASSERT_VAL("failed to alloc map", threads);
+
+        thread_map__read_comms(threads);
+
+        TEST_ASSERT_VAL("failed to synthesize map",
+                !perf_event__synthesize_thread_map2(NULL, threads, process_event, NULL));
+
+        return 0;
+}
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index 01fabb19d746..188b63140fc8 100644
--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -4,7 +4,7 @@
 #include "map.h"
 #include "debug.h"
 
-int test__thread_mg_share(void)
+int test__thread_mg_share(int subtest __maybe_unused)
 {
         struct machines machines;
         struct machine *machine;
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index f5bb096c3bd9..98fe69ac553c 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -84,7 +84,7 @@ static int check_cpu_topology(char *path, struct cpu_map *map)
         return 0;
 }
 
-int test_session_topology(void)
+int test_session_topology(int subtest __maybe_unused)
 {
         char path[PATH_MAX];
         struct cpu_map *map;
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index d677e018e504..f0bfc9e8fd9f 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -18,7 +18,7 @@ static int vmlinux_matches_kallsyms_filter(struct map *map __maybe_unused,
 
 #define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x))
 
-int test__vmlinux_matches_kallsyms(void)
+int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 {
         int err = -1;
         struct rb_node *nd;
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index e9703c0829f1..d37202121689 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -528,7 +528,7 @@ static struct ui_browser_colorset {
                 .colorset = HE_COLORSET_SELECTED,
                 .name     = "selected",
                 .fg       = "black",
-                .bg       = "lightgray",
+                .bg       = "yellow",
         },
         {
                 .colorset = HE_COLORSET_CODE,
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 81def6c3f24b..901d481e6cea 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -178,12 +178,51 @@ static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
         return n;
 }
 
+static int callchain_node__count_flat_rows(struct callchain_node *node)
+{
+        struct callchain_list *chain;
+        char folded_sign = 0;
+        int n = 0;
+
+        list_for_each_entry(chain, &node->parent_val, list) {
+                if (!folded_sign) {
+                        /* only check first chain list entry */
+                        folded_sign = callchain_list__folded(chain);
+                        if (folded_sign == '+')
+                                return 1;
+                }
+                n++;
+        }
+
+        list_for_each_entry(chain, &node->val, list) {
+                if (!folded_sign) {
+                        /* node->parent_val list might be empty */
+                        folded_sign = callchain_list__folded(chain);
+                        if (folded_sign == '+')
+                                return 1;
+                }
+                n++;
+        }
+
+        return n;
+}
+
+static int callchain_node__count_folded_rows(struct callchain_node *node __maybe_unused)
+{
+        return 1;
+}
+
 static int callchain_node__count_rows(struct callchain_node *node)
 {
         struct callchain_list *chain;
         bool unfolded = false;
         int n = 0;
 
+        if (callchain_param.mode == CHAIN_FLAT)
+                return callchain_node__count_flat_rows(node);
+        else if (callchain_param.mode == CHAIN_FOLDED)
+                return callchain_node__count_folded_rows(node);
+
         list_for_each_entry(chain, &node->val, list) {
                 ++n;
                 unfolded = chain->unfolded;
@@ -263,7 +302,7 @@ static void callchain_node__init_have_children(struct callchain_node *node,
         chain = list_entry(node->val.next, struct callchain_list, list);
         chain->has_children = has_sibling;
 
-        if (!list_empty(&node->val)) {
+        if (node->val.next != node->val.prev) {
                 chain = list_entry(node->val.prev, struct callchain_list, list);
                 chain->has_children = !RB_EMPTY_ROOT(&node->rb_root);
         }
@@ -279,6 +318,9 @@ static void callchain__init_have_children(struct rb_root *root)
         for (nd = rb_first(root); nd; nd = rb_next(nd)) {
                 struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
                 callchain_node__init_have_children(node, has_sibling);
+                if (callchain_param.mode == CHAIN_FLAT ||
+                    callchain_param.mode == CHAIN_FOLDED)
+                        callchain_node__make_parent_list(node);
         }
 }
 
@@ -577,6 +619,231 @@ static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_u
 
 #define LEVEL_OFFSET_STEP 3
 
+static int hist_browser__show_callchain_list(struct hist_browser *browser,
+                                             struct callchain_node *node,
+                                             struct callchain_list *chain,
+                                             unsigned short row, u64 total,
+                                             bool need_percent, int offset,
+                                             print_callchain_entry_fn print,
+                                             struct callchain_print_arg *arg)
+{
+        char bf[1024], *alloc_str;
+        const char *str;
+
+        if (arg->row_offset != 0) {
+                arg->row_offset--;
+                return 0;
+        }
+
+        alloc_str = NULL;
+        str = callchain_list__sym_name(chain, bf, sizeof(bf),
+                                       browser->show_dso);
+
+        if (need_percent) {
+                char buf[64];
+
+                callchain_node__scnprintf_value(node, buf, sizeof(buf),
+                                                total);
+
+                if (asprintf(&alloc_str, "%s %s", buf, str) < 0)
+                        str = "Not enough memory!";
+                else
+                        str = alloc_str;
+        }
+
+        print(browser, chain, str, offset, row, arg);
+
+        free(alloc_str);
+        return 1;
+}
+
+static int hist_browser__show_callchain_flat(struct hist_browser *browser,
+                                             struct rb_root *root,
+                                             unsigned short row, u64 total,
+                                             print_callchain_entry_fn print,
+                                             struct callchain_print_arg *arg,
+                                             check_output_full_fn is_output_full)
+{
+        struct rb_node *node;
+        int first_row = row, offset = LEVEL_OFFSET_STEP;
+        bool need_percent;
+
+        node = rb_first(root);
+        need_percent = node && rb_next(node);
+
+        while (node) {
+                struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
+                struct rb_node *next = rb_next(node);
+                struct callchain_list *chain;
+                char folded_sign = ' ';
+                int first = true;
+                int extra_offset = 0;
+
+                list_for_each_entry(chain, &child->parent_val, list) {
+                        bool was_first = first;
+
+                        if (first)
+                                first = false;
+                        else if (need_percent)
+                                extra_offset = LEVEL_OFFSET_STEP;
+
+                        folded_sign = callchain_list__folded(chain);
+
+                        row += hist_browser__show_callchain_list(browser, child,
+                                                        chain, row, total,
+                                                        was_first && need_percent,
+                                                        offset + extra_offset,
+                                                        print, arg);
+
+                        if (is_output_full(browser, row))
+                                goto out;
+
+                        if (folded_sign == '+')
+                                goto next;
+                }
+
+                list_for_each_entry(chain, &child->val, list) {
+                        bool was_first = first;
+
+                        if (first)
+                                first = false;
+                        else if (need_percent)
+                                extra_offset = LEVEL_OFFSET_STEP;
+
+                        folded_sign = callchain_list__folded(chain);
+
+                        row += hist_browser__show_callchain_list(browser, child,
+                                                        chain, row, total,
+                                                        was_first && need_percent,
+                                                        offset + extra_offset,
+                                                        print, arg);
+
+                        if (is_output_full(browser, row))
+                                goto out;
+
+                        if (folded_sign == '+')
+                                break;
+                }
+
+next:
+                if (is_output_full(browser, row))
+                        break;
+                node = next;
+        }
+out:
+        return row - first_row;
+}
+
+static char *hist_browser__folded_callchain_str(struct hist_browser *browser,
+                                                struct callchain_list *chain,
+                                                char *value_str, char *old_str)
+{
+        char bf[1024];
+        const char *str;
+        char *new;
+
+        str = callchain_list__sym_name(chain, bf, sizeof(bf),
+                                       browser->show_dso);
+        if (old_str) {
+                if (asprintf(&new, "%s%s%s", old_str,
+                             symbol_conf.field_sep ?: ";", str) < 0)
+                        new = NULL;
+        } else {
+                if (value_str) {
+                        if (asprintf(&new, "%s %s", value_str, str) < 0)
+                                new = NULL;
+                } else {
+                        if (asprintf(&new, "%s", str) < 0)
+                                new = NULL;
+                }
+        }
+        return new;
+}
+
+static int hist_browser__show_callchain_folded(struct hist_browser *browser,
+                                               struct rb_root *root,
+                                               unsigned short row, u64 total,
+                                               print_callchain_entry_fn print,
+                                               struct callchain_print_arg *arg,
+                                               check_output_full_fn is_output_full)
+{
+        struct rb_node *node;
+        int first_row = row, offset = LEVEL_OFFSET_STEP;
+        bool need_percent;
+
+        node = rb_first(root);
+        need_percent = node && rb_next(node);
+
+        while (node) {
+                struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
+                struct rb_node *next = rb_next(node);
+                struct callchain_list *chain, *first_chain = NULL;
+                int first = true;
+                char *value_str = NULL, *value_str_alloc = NULL;
+                char *chain_str = NULL, *chain_str_alloc = NULL;
+
+                if (arg->row_offset != 0) {
+                        arg->row_offset--;
+                        goto next;
+                }
+
+                if (need_percent) {
+                        char buf[64];
+
+                        callchain_node__scnprintf_value(child, buf, sizeof(buf), total);
+                        if (asprintf(&value_str, "%s", buf) < 0) {
+                                value_str = (char *)"<...>";
+                                goto do_print;
+                        }
+                        value_str_alloc = value_str;
+                }
+
+                list_for_each_entry(chain, &child->parent_val, list) {
+                        chain_str = hist_browser__folded_callchain_str(browser,
+                                                chain, value_str, chain_str);
+                        if (first) {
+                                first = false;
+                                first_chain = chain;
+                        }
+
+                        if (chain_str == NULL) {
+                                chain_str = (char *)"Not enough memory!";
+                                goto do_print;
+                        }
+
+                        chain_str_alloc = chain_str;
+                }
+
+                list_for_each_entry(chain, &child->val, list) {
+                        chain_str = hist_browser__folded_callchain_str(browser,
+                                                chain, value_str, chain_str);
+                        if (first) {
+                                first = false;
+                                first_chain = chain;
+                        }
+
+                        if (chain_str == NULL) {
+                                chain_str = (char *)"Not enough memory!";
+                                goto do_print;
+                        }
+
+                        chain_str_alloc = chain_str;
+                }
+
+do_print:
+                print(browser, first_chain, chain_str, offset, row++, arg);
+                free(value_str_alloc);
+                free(chain_str_alloc);
+
+next:
+                if (is_output_full(browser, row))
+                        break;
+                node = next;
+        }
+
+        return row - first_row;
+}
+
 static int hist_browser__show_callchain(struct hist_browser *browser,
                                         struct rb_root *root, int level,
                                         unsigned short row, u64 total,
@@ -595,15 +862,12 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
         while (node) {
                 struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
                 struct rb_node *next = rb_next(node);
-                u64 cumul = callchain_cumul_hits(child);
                 struct callchain_list *chain;
                 char folded_sign = ' ';
                 int first = true;
                 int extra_offset = 0;
 
                 list_for_each_entry(chain, &child->val, list) {
-                        char bf[1024], *alloc_str;
-                        const char *str;
                         bool was_first = first;
 
                         if (first)
@@ -612,31 +876,16 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
                                 extra_offset = LEVEL_OFFSET_STEP;
 
                         folded_sign = callchain_list__folded(chain);
-                        if (arg->row_offset != 0) {
-                                arg->row_offset--;
-                                goto do_next;
-                        }
-
-                        alloc_str = NULL;
-                        str = callchain_list__sym_name(chain, bf, sizeof(bf),
-                                                       browser->show_dso);
-
-                        if (was_first && need_percent) {
-                                double percent = cumul * 100.0 / total;
-
-                                if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
-                                        str = "Not enough memory!";
-                                else
-                                        str = alloc_str;
-                        }
 
-                        print(browser, chain, str, offset + extra_offset, row, arg);
+                        row += hist_browser__show_callchain_list(browser, child,
+                                                        chain, row, total,
+                                                        was_first && need_percent,
+                                                        offset + extra_offset,
+                                                        print, arg);
 
-                        free(alloc_str);
-
-                        if (is_output_full(browser, ++row))
+                        if (is_output_full(browser, row))
                                 goto out;
-do_next:
+
                         if (folded_sign == '+')
                                 break;
                 }
@@ -792,7 +1041,8 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                 hist_browser__gotorc(browser, row, 0);
 
                 perf_hpp__for_each_format(fmt) {
-                        if (perf_hpp__should_skip(fmt) || column++ < browser->b.horiz_scroll)
+                        if (perf_hpp__should_skip(fmt, entry->hists) ||
+                            column++ < browser->b.horiz_scroll)
                                 continue;
 
                         if (current_entry && browser->b.navkeypressed) {
@@ -847,10 +1097,22 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                                 total = entry->stat.period;
                 }
 
-                printed += hist_browser__show_callchain(browser,
+                if (callchain_param.mode == CHAIN_FLAT) {
+                        printed += hist_browser__show_callchain_flat(browser,
+                                        &entry->sorted_chain, row, total,
+                                        hist_browser__show_callchain_entry, &arg,
+                                        hist_browser__check_output_full);
+                } else if (callchain_param.mode == CHAIN_FOLDED) {
+                        printed += hist_browser__show_callchain_folded(browser,
+                                        &entry->sorted_chain, row, total,
+                                        hist_browser__show_callchain_entry, &arg,
+                                        hist_browser__check_output_full);
+                } else {
+                        printed += hist_browser__show_callchain(browser,
                                         &entry->sorted_chain, 1, row, total,
                                         hist_browser__show_callchain_entry, &arg,
                                         hist_browser__check_output_full);
+                }
 
                 if (arg.is_current_entry)
                         browser->he_selection = entry;
@@ -883,7 +1145,7 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
         }
 
         perf_hpp__for_each_format(fmt) {
-                if (perf_hpp__should_skip(fmt)  || column++ < browser->b.horiz_scroll)
+                if (perf_hpp__should_skip(fmt, hists)  || column++ < browser->b.horiz_scroll)
                         continue;
 
                 ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
@@ -1153,7 +1415,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
                 printed += fprintf(fp, "%c ", folded_sign);
 
         perf_hpp__for_each_format(fmt) {
-                if (perf_hpp__should_skip(fmt))
+                if (perf_hpp__should_skip(fmt, he->hists))
                         continue;
 
                 if (!first) {
@@ -1802,10 +2064,9 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
         SLang_reset_tty();
         SLang_init_tty(0, 0, 0);
 
-        if (min_pcnt) {
+        if (min_pcnt)
                 browser->min_pcnt = min_pcnt;
-                hist_browser__update_nr_entries(browser);
-        }
+        hist_browser__update_nr_entries(browser);
 
         browser->pstack = pstack__new(3);
         if (browser->pstack == NULL)
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 4b3585eed1e8..0f8dcfdfb10f 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -89,8 +89,8 @@ void perf_gtk__init_hpp(void)
                                 perf_gtk__hpp_color_overhead_acc;
 }
 
-static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
-                                    GtkTreeIter *parent, int col, u64 total)
+static void perf_gtk__add_callchain_flat(struct rb_root *root, GtkTreeStore *store,
+                                         GtkTreeIter *parent, int col, u64 total)
 {
         struct rb_node *nd;
         bool has_single_node = (rb_first(root) == rb_last(root));
@@ -100,13 +100,132 @@ static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
                 struct callchain_list *chain;
                 GtkTreeIter iter, new_parent;
                 bool need_new_parent;
-                double percent;
-                u64 hits, child_total;
 
                 node = rb_entry(nd, struct callchain_node, rb_node);
 
-                hits = callchain_cumul_hits(node);
-                percent = 100.0 * hits / total;
+                new_parent = *parent;
+                need_new_parent = !has_single_node;
+
+                callchain_node__make_parent_list(node);
+
+                list_for_each_entry(chain, &node->parent_val, list) {
+                        char buf[128];
+
+                        gtk_tree_store_append(store, &iter, &new_parent);
+
+                        callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
+                        gtk_tree_store_set(store, &iter, 0, buf, -1);
+
+                        callchain_list__sym_name(chain, buf, sizeof(buf), false);
+                        gtk_tree_store_set(store, &iter, col, buf, -1);
+
+                        if (need_new_parent) {
+                                /*
+                                 * Only show the top-most symbol in a callchain
+                                 * if it's not the only callchain.
+                                 */
+                                new_parent = iter;
+                                need_new_parent = false;
+                        }
+                }
+
+                list_for_each_entry(chain, &node->val, list) {
+                        char buf[128];
+
+                        gtk_tree_store_append(store, &iter, &new_parent);
+
+                        callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
+                        gtk_tree_store_set(store, &iter, 0, buf, -1);
+
+                        callchain_list__sym_name(chain, buf, sizeof(buf), false);
+                        gtk_tree_store_set(store, &iter, col, buf, -1);
+
+                        if (need_new_parent) {
+                                /*
+                                 * Only show the top-most symbol in a callchain
+                                 * if it's not the only callchain.
+                                 */
+                                new_parent = iter;
+                                need_new_parent = false;
+                        }
+                }
+        }
+}
+
+static void perf_gtk__add_callchain_folded(struct rb_root *root, GtkTreeStore *store,
+                                           GtkTreeIter *parent, int col, u64 total)
+{
+        struct rb_node *nd;
+
+        for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+                struct callchain_node *node;
+                struct callchain_list *chain;
+                GtkTreeIter iter;
+                char buf[64];
+                char *str, *str_alloc = NULL;
+                bool first = true;
+
+                node = rb_entry(nd, struct callchain_node, rb_node);
+
+                callchain_node__make_parent_list(node);
+
+                list_for_each_entry(chain, &node->parent_val, list) {
+                        char name[1024];
+
+                        callchain_list__sym_name(chain, name, sizeof(name), false);
+
+                        if (asprintf(&str, "%s%s%s",
+                                     first ? "" : str_alloc,
+                                     first ? "" : symbol_conf.field_sep ?: "; ",
+                                     name) < 0)
+                                return;
+
+                        first = false;
+                        free(str_alloc);
+                        str_alloc = str;
+                }
+
+                list_for_each_entry(chain, &node->val, list) {
+                        char name[1024];
+
+                        callchain_list__sym_name(chain, name, sizeof(name), false);
+
+                        if (asprintf(&str, "%s%s%s",
+                                     first ? "" : str_alloc,
+                                     first ? "" : symbol_conf.field_sep ?: "; ",
+                                     name) < 0)
+                                return;
+
+                        first = false;
+                        free(str_alloc);
+                        str_alloc = str;
+                }
+
+                gtk_tree_store_append(store, &iter, parent);
+
+                callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
+                gtk_tree_store_set(store, &iter, 0, buf, -1);
+
+                gtk_tree_store_set(store, &iter, col, str, -1);
+
+                free(str_alloc);
+        }
+}
+
+static void perf_gtk__add_callchain_graph(struct rb_root *root, GtkTreeStore *store,
+                                          GtkTreeIter *parent, int col, u64 total)
+{
+        struct rb_node *nd;
+        bool has_single_node = (rb_first(root) == rb_last(root));
+
+        for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+                struct callchain_node *node;
+                struct callchain_list *chain;
+                GtkTreeIter iter, new_parent;
+                bool need_new_parent;
+                u64 child_total;
+
+                node = rb_entry(nd, struct callchain_node, rb_node);
 
                 new_parent = *parent;
                 need_new_parent = !has_single_node && (node->val_nr > 1);
@@ -116,7 +235,7 @@ static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
 
                         gtk_tree_store_append(store, &iter, &new_parent);
 
-                        scnprintf(buf, sizeof(buf), "%5.2f%%", percent);
+                        callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
                         gtk_tree_store_set(store, &iter, 0, buf, -1);
 
                         callchain_list__sym_name(chain, buf, sizeof(buf), false);
@@ -138,11 +257,22 @@ static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
                         child_total = total;
 
                 /* Now 'iter' contains info of the last callchain_list */
-                perf_gtk__add_callchain(&node->rb_root, store, &iter, col,
-                                        child_total);
+                perf_gtk__add_callchain_graph(&node->rb_root, store, &iter, col,
+                                              child_total);
         }
 }
 
+static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
+                                    GtkTreeIter *parent, int col, u64 total)
+{
+        if (callchain_param.mode == CHAIN_FLAT)
+                perf_gtk__add_callchain_flat(root, store, parent, col, total);
+        else if (callchain_param.mode == CHAIN_FOLDED)
+                perf_gtk__add_callchain_folded(root, store, parent, col, total);
+        else
+                perf_gtk__add_callchain_graph(root, store, parent, col, total);
+}
+
 static void on_row_activated(GtkTreeView *view, GtkTreePath *path,
                              GtkTreeViewColumn *col __maybe_unused,
                              gpointer user_data __maybe_unused)
@@ -188,7 +318,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
         col_idx = 0;
 
         perf_hpp__for_each_format(fmt) {
-                if (perf_hpp__should_skip(fmt))
+                if (perf_hpp__should_skip(fmt, hists))
                         continue;
 
                 /*
@@ -238,7 +368,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
                 col_idx = 0;
 
                 perf_hpp__for_each_format(fmt) {
-                        if (perf_hpp__should_skip(fmt))
+                        if (perf_hpp__should_skip(fmt, h->hists))
                                 continue;
 
                         if (fmt->color)
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 5029ba2b55af..bf2a66e254ea 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -443,7 +443,6 @@ LIST_HEAD(perf_hpp__sort_list);
 
 void perf_hpp__init(void)
 {
-        struct list_head *list;
         int i;
 
         for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
@@ -484,17 +483,6 @@ void perf_hpp__init(void)
 
         if (symbol_conf.show_total_period)
                 hpp_dimension__add_output(PERF_HPP__PERIOD);
-
-        /* prepend overhead field for backward compatiblity.  */
-        list = &perf_hpp__format[PERF_HPP__OVERHEAD].sort_list;
-        if (list_empty(list))
-                list_add(list, &perf_hpp__sort_list);
-
-        if (symbol_conf.cumulate_callchain) {
-                list = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC].sort_list;
-                if (list_empty(list))
-                        list_add(list, &perf_hpp__sort_list);
-        }
 }
 
 void perf_hpp__column_register(struct perf_hpp_fmt *format)
@@ -619,7 +607,7 @@ unsigned int hists__sort_list_width(struct hists *hists)
         struct perf_hpp dummy_hpp;
 
         perf_hpp__for_each_format(fmt) {
-                if (perf_hpp__should_skip(fmt))
+                if (perf_hpp__should_skip(fmt, hists))
                         continue;
 
                 if (first)
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index dfcbc90146ef..387110d50b00 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -34,10 +34,10 @@ static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
         return ret;
 }
 
-static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
+static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
+                                     struct callchain_list *chain,
                                      int depth, int depth_mask, int period,
-                                     u64 total_samples, u64 hits,
-                                     int left_margin)
+                                     u64 total_samples, int left_margin)
 {
         int i;
         size_t ret = 0;
@@ -50,10 +50,9 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
                 else
                         ret += fprintf(fp, " ");
                 if (!period && i == depth - 1) {
-                        double percent;
-
-                        percent = hits * 100.0 / total_samples;
-                        ret += percent_color_fprintf(fp, "--%2.2f%%-- ", percent);
+                        ret += fprintf(fp, "--");
+                        ret += callchain_node__fprintf_value(node, fp, total_samples);
+                        ret += fprintf(fp, "--");
                 } else
                         ret += fprintf(fp, "%s", "          ");
         }
@@ -82,13 +81,14 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
                                          int depth_mask, int left_margin)
 {
         struct rb_node *node, *next;
-        struct callchain_node *child;
+        struct callchain_node *child = NULL;
         struct callchain_list *chain;
         int new_depth_mask = depth_mask;
         u64 remaining;
         size_t ret = 0;
         int i;
         uint entries_printed = 0;
+        int cumul_count = 0;
 
         remaining = total_samples;
 
@@ -100,6 +100,7 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
                 child = rb_entry(node, struct callchain_node, rb_node);
                 cumul = callchain_cumul_hits(child);
                 remaining -= cumul;
+                cumul_count += callchain_cumul_counts(child);
 
                 /*
                  * The depth mask manages the output of pipes that show
@@ -120,10 +121,9 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
                                                    left_margin);
                 i = 0;
                 list_for_each_entry(chain, &child->val, list) {
-                        ret += ipchain__fprintf_graph(fp, chain, depth,
+                        ret += ipchain__fprintf_graph(fp, child, chain, depth,
                                                       new_depth_mask, i++,
                                                       total_samples,
-                                                      cumul,
                                                       left_margin);
                 }
 
@@ -143,14 +143,23 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 
         if (callchain_param.mode == CHAIN_GRAPH_REL &&
                 remaining && remaining != total_samples) {
+                struct callchain_node rem_node = {
+                        .hit = remaining,
+                };
 
                 if (!rem_sq_bracket)
                         return ret;
 
+                if (callchain_param.value == CCVAL_COUNT && child && child->parent) {
+                        rem_node.count = child->parent->children_count - cumul_count;
+                        if (rem_node.count <= 0)
+                                return ret;
+                }
+
                 new_depth_mask &= ~(1 << (depth - 1));
-                ret += ipchain__fprintf_graph(fp, &rem_hits, depth,
+                ret += ipchain__fprintf_graph(fp, &rem_node, &rem_hits, depth,
                                               new_depth_mask, 0, total_samples,
-                                              remaining, left_margin);
+                                              left_margin);
         }
 
         return ret;
@@ -243,12 +252,11 @@ static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *tree,
         struct rb_node *rb_node = rb_first(tree);
 
         while (rb_node) {
-                double percent;
-
                 chain = rb_entry(rb_node, struct callchain_node, rb_node);
-                percent = chain->hit * 100.0 / total_samples;
 
-                ret = percent_color_fprintf(fp, "           %6.2f%%\n", percent);
+                ret += fprintf(fp, "           ");
+                ret += callchain_node__fprintf_value(chain, fp, total_samples);
+                ret += fprintf(fp, "\n");
                 ret += __callchain__fprintf_flat(fp, chain, total_samples);
                 ret += fprintf(fp, "\n");
                 if (++entries_printed == callchain_param.print_limit)
@@ -260,6 +268,57 @@ static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *tree,
         return ret;
 }
 
+static size_t __callchain__fprintf_folded(FILE *fp, struct callchain_node *node)
+{
+        const char *sep = symbol_conf.field_sep ?: ";";
+        struct callchain_list *chain;
+        size_t ret = 0;
+        char bf[1024];
+        bool first;
+
+        if (!node)
+                return 0;
+
+        ret += __callchain__fprintf_folded(fp, node->parent);
+
+        first = (ret == 0);
+        list_for_each_entry(chain, &node->val, list) {
+                if (chain->ip >= PERF_CONTEXT_MAX)
+                        continue;
+                ret += fprintf(fp, "%s%s", first ? "" : sep,
+                               callchain_list__sym_name(chain,
+                                                bf, sizeof(bf), false));
+                first = false;
+        }
+
+        return ret;
+}
+
+static size_t callchain__fprintf_folded(FILE *fp, struct rb_root *tree,
+                                        u64 total_samples)
+{
+        size_t ret = 0;
+        u32 entries_printed = 0;
+        struct callchain_node *chain;
+        struct rb_node *rb_node = rb_first(tree);
+
+        while (rb_node) {
+
+                chain = rb_entry(rb_node, struct callchain_node, rb_node);
+
+                ret += callchain_node__fprintf_value(chain, fp, total_samples);
+                ret += fprintf(fp, " ");
+                ret += __callchain__fprintf_folded(fp, chain);
+                ret += fprintf(fp, "\n");
+                if (++entries_printed == callchain_param.print_limit)
+                        break;
+
+                rb_node = rb_next(rb_node);
+        }
+
+        return ret;
+}
+
 static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
                                             u64 total_samples, int left_margin,
                                             FILE *fp)
@@ -278,6 +337,9 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
         case CHAIN_FLAT:
                 return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
                 break;
+        case CHAIN_FOLDED:
+                return callchain__fprintf_folded(fp, &he->sorted_chain, total_samples);
+                break;
         case CHAIN_NONE:
                 break;
         default:
@@ -323,7 +385,7 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
                 return 0;
 
         perf_hpp__for_each_format(fmt) {
-                if (perf_hpp__should_skip(fmt))
+                if (perf_hpp__should_skip(fmt, he->hists))
                         continue;
 
                 /*
@@ -402,7 +464,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
         fprintf(fp, "# ");
 
         perf_hpp__for_each_format(fmt) {
-                if (perf_hpp__should_skip(fmt))
+                if (perf_hpp__should_skip(fmt, hists))
                         continue;
 
                 if (!first)
@@ -428,7 +490,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
         perf_hpp__for_each_format(fmt) {
                 unsigned int i;
 
-                if (perf_hpp__should_skip(fmt))
+                if (perf_hpp__should_skip(fmt, hists))
                         continue;
 
                 if (!first)
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 591b3fe3ed49..5eec53a3f4ac 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -6,24 +6,20 @@ libperf-y += config.o
 libperf-y += ctype.o
 libperf-y += db-export.o
 libperf-y += env.o
-libperf-y += environment.o
 libperf-y += event.o
 libperf-y += evlist.o
 libperf-y += evsel.o
-libperf-y += exec_cmd.o
-libperf-y += find_next_bit.o
-libperf-y += help.o
+libperf-y += find_bit.o
 libperf-y += kallsyms.o
 libperf-y += levenshtein.o
 libperf-y += llvm-utils.o
-libperf-y += parse-options.o
 libperf-y += parse-events.o
 libperf-y += perf_regs.o
 libperf-y += path.o
 libperf-y += rbtree.o
+libperf-y += libstring.o
 libperf-y += bitmap.o
 libperf-y += hweight.o
-libperf-y += run-command.o
 libperf-y += quote.o
 libperf-y += strbuf.o
 libperf-y += string.o
@@ -32,11 +28,9 @@ libperf-y += strfilter.o
 libperf-y += top.o
 libperf-y += usage.o
 libperf-y += wrapper.o
-libperf-y += sigchain.o
 libperf-y += dso.o
 libperf-y += symbol.o
 libperf-y += color.o
-libperf-y += pager.o
 libperf-y += header.o
 libperf-y += callchain.o
 libperf-y += values.o
@@ -86,8 +80,11 @@ libperf-$(CONFIG_AUXTRACE) += intel-pt.o
 libperf-$(CONFIG_AUXTRACE) += intel-bts.o
 libperf-y += parse-branch-options.o
 libperf-y += parse-regs-options.o
+libperf-y += term.o
+libperf-y += help-unknown-cmd.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
+libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
 libperf-$(CONFIG_LIBELF) += symbol-elf.o
 libperf-$(CONFIG_LIBELF) += probe-file.o
 libperf-$(CONFIG_LIBELF) += probe-event.o
@@ -110,7 +107,6 @@ libperf-$(CONFIG_ZLIB) += zlib.o
 libperf-$(CONFIG_LZMA) += lzma.o
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
-CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="BUILD_STR($(prefix_SQ))"
 
 $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
         $(call rule_mkdir)
@@ -136,8 +132,10 @@ CFLAGS_pmu-bison.o          += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
 $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
 $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
 
-CFLAGS_find_next_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+CFLAGS_bitmap.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+CFLAGS_find_bit.o      += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_rbtree.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+CFLAGS_libstring.o     += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_hweight.o       += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_parse-events.o  += -Wno-redundant-decls
 
@@ -145,7 +143,11 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE
         $(call rule_mkdir)
         $(call if_changed_dep,cc_o_c)
 
-$(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c FORCE
+$(OUTPUT)util/bitmap.o: ../lib/bitmap.c FORCE
+        $(call rule_mkdir)
+        $(call if_changed_dep,cc_o_c)
+
+$(OUTPUT)util/find_bit.o: ../lib/find_bit.c FORCE
         $(call rule_mkdir)
         $(call if_changed_dep,cc_o_c)
 
@@ -153,6 +155,10 @@ $(OUTPUT)util/rbtree.o: ../lib/rbtree.c FORCE
         $(call rule_mkdir)
         $(call if_changed_dep,cc_o_c)
 
+$(OUTPUT)util/libstring.o: ../lib/string.c FORCE
+        $(call rule_mkdir)
+        $(call if_changed_dep,cc_o_c)
+
 $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
         $(call rule_mkdir)
         $(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 1dd1949b0e79..b795b6994144 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -65,6 +65,11 @@ static int call__parse(struct ins_operands *ops)
 
         name++;
 
+#ifdef __arm__
+        if (strchr(name, '+'))
+                return -1;
+#endif
+
         tok = strchr(name, '>');
         if (tok == NULL)
                 return -1;
@@ -246,7 +251,11 @@ static int mov__parse(struct ins_operands *ops)
                 return -1;
 
         target = ++s;
+#ifdef __arm__
+        comment = strchr(s, ';');
+#else
         comment = strchr(s, '#');
+#endif
 
         if (comment != NULL)
                 s = comment - 1;
@@ -354,6 +363,20 @@ static struct ins instructions[] = {
         { .name = "addq",  .ops  = &mov_ops, },
         { .name = "addw",  .ops  = &mov_ops, },
         { .name = "and",   .ops  = &mov_ops, },
+#ifdef __arm__
+        { .name = "b",     .ops  = &jump_ops, }, // might also be a call
+        { .name = "bcc",   .ops  = &jump_ops, },
+        { .name = "bcs",   .ops  = &jump_ops, },
+        { .name = "beq",   .ops  = &jump_ops, },
+        { .name = "bge",   .ops  = &jump_ops, },
+        { .name = "bgt",   .ops  = &jump_ops, },
+        { .name = "bhi",   .ops  = &jump_ops, },
+        { .name = "bl",    .ops  = &call_ops, },
+        { .name = "blt",   .ops  = &jump_ops, },
+        { .name = "bls",   .ops  = &jump_ops, },
+        { .name = "blx",   .ops  = &call_ops, },
+        { .name = "bne",   .ops  = &jump_ops, },
+#endif
         { .name = "bts",   .ops  = &mov_ops, },
         { .name = "call",  .ops  = &call_ops, },
         { .name = "callq", .ops  = &call_ops, },
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 7f10430af39c..360fda01f3b0 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -45,7 +45,7 @@
 #include "event.h"
 #include "session.h"
 #include "debug.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 
 #include "intel-pt.h"
 #include "intel-bts.h"
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 4c50411371db..540a7efa657e 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -5,11 +5,15 @@
  * Copyright (C) 2015 Huawei Inc.
  */
 
+#include <linux/bpf.h>
 #include <bpf/libbpf.h>
 #include <linux/err.h>
+#include <linux/string.h>
 #include "perf.h"
 #include "debug.h"
 #include "bpf-loader.h"
+#include "bpf-prologue.h"
+#include "llvm-utils.h"
 #include "probe-event.h"
 #include "probe-finder.h" // for MAX_PROBES
 #include "llvm-utils.h"
@@ -32,6 +36,10 @@ DEFINE_PRINT_FN(debug, 1)
 
 struct bpf_prog_priv {
         struct perf_probe_event pev;
+        bool need_prologue;
+        struct bpf_insn *insns_buf;
+        int nr_types;
+        int *type_mapping;
 };
 
 static bool libbpf_initialized;
@@ -106,10 +114,178 @@ bpf_prog_priv__clear(struct bpf_program *prog __maybe_unused,
         struct bpf_prog_priv *priv = _priv;
 
         cleanup_perf_probe_events(&priv->pev, 1);
+        zfree(&priv->insns_buf);
+        zfree(&priv->type_mapping);
         free(priv);
 }
 
 static int
+prog_config__exec(const char *value, struct perf_probe_event *pev)
+{
+        pev->uprobes = true;
+        pev->target = strdup(value);
+        if (!pev->target)
+                return -ENOMEM;
+        return 0;
+}
+
+static int
+prog_config__module(const char *value, struct perf_probe_event *pev)
+{
+        pev->uprobes = false;
+        pev->target = strdup(value);
+        if (!pev->target)
+                return -ENOMEM;
+        return 0;
+}
+
+static int
+prog_config__bool(const char *value, bool *pbool, bool invert)
+{
+        int err;
+        bool bool_value;
+
+        if (!pbool)
+                return -EINVAL;
+
+        err = strtobool(value, &bool_value);
+        if (err)
+                return err;
+
+        *pbool = invert ? !bool_value : bool_value;
+        return 0;
+}
+
+static int
+prog_config__inlines(const char *value,
+                     struct perf_probe_event *pev __maybe_unused)
+{
+        return prog_config__bool(value, &probe_conf.no_inlines, true);
+}
+
+static int
+prog_config__force(const char *value,
+                   struct perf_probe_event *pev __maybe_unused)
+{
+        return prog_config__bool(value, &probe_conf.force_add, false);
+}
+
+static struct {
+        const char *key;
+        const char *usage;
+        const char *desc;
+        int (*func)(const char *, struct perf_probe_event *);
+} bpf_prog_config_terms[] = {
+        {
+                .key    = "exec",
+                .usage  = "exec=<full path of file>",
+                .desc   = "Set uprobe target",
+                .func   = prog_config__exec,
+        },
+        {
+                .key    = "module",
+                .usage  = "module=<module name>    ",
+                .desc   = "Set kprobe module",
+                .func   = prog_config__module,
+        },
+        {
+                .key    = "inlines",
+                .usage  = "inlines=[yes|no]        ",
+                .desc   = "Probe at inline symbol",
+                .func   = prog_config__inlines,
+        },
+        {
+                .key    = "force",
+                .usage  = "force=[yes|no]          ",
+                .desc   = "Forcibly add events with existing name",
+                .func   = prog_config__force,
+        },
+};
+
+static int
+do_prog_config(const char *key, const char *value,
+               struct perf_probe_event *pev)
+{
+        unsigned int i;
+
+        pr_debug("config bpf program: %s=%s\n", key, value);
+        for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++)
+                if (strcmp(key, bpf_prog_config_terms[i].key) == 0)
+                        return bpf_prog_config_terms[i].func(value, pev);
+
+        pr_debug("BPF: ERROR: invalid program config option: %s=%s\n",
+                 key, value);
+
+        pr_debug("\nHint: Valid options are:\n");
+        for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++)
+                pr_debug("\t%s:\t%s\n", bpf_prog_config_terms[i].usage,
+                         bpf_prog_config_terms[i].desc);
+        pr_debug("\n");
+
+        return -BPF_LOADER_ERRNO__PROGCONF_TERM;
+}
+
+static const char *
+parse_prog_config_kvpair(const char *config_str, struct perf_probe_event *pev)
+{
+        char *text = strdup(config_str);
+        char *sep, *line;
+        const char *main_str = NULL;
+        int err = 0;
+
+        if (!text) {
+                pr_debug("No enough memory: dup config_str failed\n");
+                return ERR_PTR(-ENOMEM);
+        }
+
+        line = text;
+        while ((sep = strchr(line, ';'))) {
+                char *equ;
+
+                *sep = '\0';
+                equ = strchr(line, '=');
+                if (!equ) {
+                        pr_warning("WARNING: invalid config in BPF object: %s\n",
+                                   line);
+                        pr_warning("\tShould be 'key=value'.\n");
+                        goto nextline;
+                }
+                *equ = '\0';
+
+                err = do_prog_config(line, equ + 1, pev);
+                if (err)
+                        break;
+nextline:
+                line = sep + 1;
+        }
+
+        if (!err)
+                main_str = config_str + (line - text);
+        free(text);
+
+        return err ? ERR_PTR(err) : main_str;
+}
+
+static int
+parse_prog_config(const char *config_str, struct perf_probe_event *pev)
+{
+        int err;
+        const char *main_str = parse_prog_config_kvpair(config_str, pev);
+
+        if (IS_ERR(main_str))
+                return PTR_ERR(main_str);
+
+        err = parse_perf_probe_command(main_str, pev);
+        if (err < 0) {
+                pr_debug("bpf: '%s' is not a valid config string\n",
+                         config_str);
+                /* parse failed, don't need clear pev. */
+                return -BPF_LOADER_ERRNO__CONFIG;
+        }
+        return 0;
+}
+
+static int
 config_bpf_program(struct bpf_program *prog)
 {
         struct perf_probe_event *pev = NULL;
@@ -117,6 +293,10 @@ config_bpf_program(struct bpf_program *prog)
         const char *config_str;
         int err;
 
+        /* Initialize per-program probing setting */
+        probe_conf.no_inlines = false;
+        probe_conf.force_add = false;
+
         config_str = bpf_program__title(prog, false);
         if (IS_ERR(config_str)) {
                 pr_debug("bpf: unable to get title for program\n");
@@ -131,13 +311,9 @@ config_bpf_program(struct bpf_program *prog)
         pev = &priv->pev;
 
         pr_debug("bpf: config program '%s'\n", config_str);
-        err = parse_perf_probe_command(config_str, pev);
-        if (err < 0) {
-                pr_debug("bpf: '%s' is not a valid config string\n",
-                         config_str);
-                err = -BPF_LOADER_ERRNO__CONFIG;
+        err = parse_prog_config(config_str, pev);
+        if (err)
                 goto errout;
-        }
 
         if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) {
                 pr_debug("bpf: '%s': group for event is set and not '%s'.\n",
@@ -197,6 +373,220 @@ static int bpf__prepare_probe(void)
         return err;
 }
 
+static int
+preproc_gen_prologue(struct bpf_program *prog, int n,
+                     struct bpf_insn *orig_insns, int orig_insns_cnt,
+                     struct bpf_prog_prep_result *res)
+{
+        struct probe_trace_event *tev;
+        struct perf_probe_event *pev;
+        struct bpf_prog_priv *priv;
+        struct bpf_insn *buf;
+        size_t prologue_cnt = 0;
+        int i, err;
+
+        err = bpf_program__get_private(prog, (void **)&priv);
+        if (err || !priv)
+                goto errout;
+
+        pev = &priv->pev;
+
+        if (n < 0 || n >= priv->nr_types)
+                goto errout;
+
+        /* Find a tev belongs to that type */
+        for (i = 0; i < pev->ntevs; i++) {
+                if (priv->type_mapping[i] == n)
+                        break;
+        }
+
+        if (i >= pev->ntevs) {
+                pr_debug("Internal error: prologue type %d not found\n", n);
+                return -BPF_LOADER_ERRNO__PROLOGUE;
+        }
+
+        tev = &pev->tevs[i];
+
+        buf = priv->insns_buf;
+        err = bpf__gen_prologue(tev->args, tev->nargs,
+                                buf, &prologue_cnt,
+                                BPF_MAXINSNS - orig_insns_cnt);
+        if (err) {
+                const char *title;
+
+                title = bpf_program__title(prog, false);
+                if (!title)
+                        title = "[unknown]";
+
+                pr_debug("Failed to generate prologue for program %s\n",
+                         title);
+                return err;
+        }
+
+        memcpy(&buf[prologue_cnt], orig_insns,
+               sizeof(struct bpf_insn) * orig_insns_cnt);
+
+        res->new_insn_ptr = buf;
+        res->new_insn_cnt = prologue_cnt + orig_insns_cnt;
+        res->pfd = NULL;
+        return 0;
+
+errout:
+        pr_debug("Internal error in preproc_gen_prologue\n");
+        return -BPF_LOADER_ERRNO__PROLOGUE;
+}
+
+/*
+ * compare_tev_args is reflexive, transitive and antisymmetric.
+ * I can proof it but this margin is too narrow to contain.
+ */
+static int compare_tev_args(const void *ptev1, const void *ptev2)
+{
+        int i, ret;
+        const struct probe_trace_event *tev1 =
+                *(const struct probe_trace_event **)ptev1;
+        const struct probe_trace_event *tev2 =
+                *(const struct probe_trace_event **)ptev2;
+
+        ret = tev2->nargs - tev1->nargs;
+        if (ret)
+                return ret;
+
+        for (i = 0; i < tev1->nargs; i++) {
+                struct probe_trace_arg *arg1, *arg2;
+                struct probe_trace_arg_ref *ref1, *ref2;
+
+                arg1 = &tev1->args[i];
+                arg2 = &tev2->args[i];
+
+                ret = strcmp(arg1->value, arg2->value);
+                if (ret)
+                        return ret;
+
+                ref1 = arg1->ref;
+                ref2 = arg2->ref;
+
+                while (ref1 && ref2) {
+                        ret = ref2->offset - ref1->offset;
+                        if (ret)
+                                return ret;
+
+                        ref1 = ref1->next;
+                        ref2 = ref2->next;
+                }
+
+                if (ref1 || ref2)
+                        return ref2 ? 1 : -1;
+        }
+
+        return 0;
+}
+
+/*
+ * Assign a type number to each tevs in a pev.
+ * mapping is an array with same slots as tevs in that pev.
+ * nr_types will be set to number of types.
+ */
+static int map_prologue(struct perf_probe_event *pev, int *mapping,
+                        int *nr_types)
+{
+        int i, type = 0;
+        struct probe_trace_event **ptevs;
+
+        size_t array_sz = sizeof(*ptevs) * pev->ntevs;
+
+        ptevs = malloc(array_sz);
+        if (!ptevs) {
+                pr_debug("No ehough memory: alloc ptevs failed\n");
+                return -ENOMEM;
+        }
+
+        pr_debug("In map_prologue, ntevs=%d\n", pev->ntevs);
+        for (i = 0; i < pev->ntevs; i++)
+                ptevs[i] = &pev->tevs[i];
+
+        qsort(ptevs, pev->ntevs, sizeof(*ptevs),
+              compare_tev_args);
+
+        for (i = 0; i < pev->ntevs; i++) {
+                int n;
+
+                n = ptevs[i] - pev->tevs;
+                if (i == 0) {
+                        mapping[n] = type;
+                        pr_debug("mapping[%d]=%d\n", n, type);
+                        continue;
+                }
+
+                if (compare_tev_args(ptevs + i, ptevs + i - 1) == 0)
+                        mapping[n] = type;
+                else
+                        mapping[n] = ++type;
+
+                pr_debug("mapping[%d]=%d\n", n, mapping[n]);
+        }
+        free(ptevs);
+        *nr_types = type + 1;
+
+        return 0;
+}
+
+static int hook_load_preprocessor(struct bpf_program *prog)
+{
+        struct perf_probe_event *pev;
+        struct bpf_prog_priv *priv;
+        bool need_prologue = false;
+        int err, i;
+
+        err = bpf_program__get_private(prog, (void **)&priv);
+        if (err || !priv) {
+                pr_debug("Internal error when hook preprocessor\n");
+                return -BPF_LOADER_ERRNO__INTERNAL;
+        }
+
+        pev = &priv->pev;
+        for (i = 0; i < pev->ntevs; i++) {
+                struct probe_trace_event *tev = &pev->tevs[i];
+
+                if (tev->nargs > 0) {
+                        need_prologue = true;
+                        break;
+                }
+        }
+
+        /*
+         * Since all tevs don't have argument, we don't need generate
+         * prologue.
+         */
+        if (!need_prologue) {
+                priv->need_prologue = false;
+                return 0;
+        }
+
+        priv->need_prologue = true;
+        priv->insns_buf = malloc(sizeof(struct bpf_insn) * BPF_MAXINSNS);
+        if (!priv->insns_buf) {
+                pr_debug("No enough memory: alloc insns_buf failed\n");
+                return -ENOMEM;
+        }
+
+        priv->type_mapping = malloc(sizeof(int) * pev->ntevs);
+        if (!priv->type_mapping) {
+                pr_debug("No enough memory: alloc type_mapping failed\n");
+                return -ENOMEM;
+        }
+        memset(priv->type_mapping, -1,
+               sizeof(int) * pev->ntevs);
+
+        err = map_prologue(pev, priv->type_mapping, &priv->nr_types);
+        if (err)
+                return err;
+
+        err = bpf_program__set_prep(prog, priv->nr_types,
+                                    preproc_gen_prologue);
+        return err;
+}
+
 int bpf__probe(struct bpf_object *obj)
 {
         int err = 0;
@@ -231,6 +621,18 @@ int bpf__probe(struct bpf_object *obj)
                         pr_debug("bpf_probe: failed to apply perf probe events");
                         goto out;
                 }
+
+                /*
+                 * After probing, let's consider prologue, which
+                 * adds program fetcher to BPF programs.
+                 *
+                 * hook_load_preprocessorr() hooks pre-processor
+                 * to bpf_program, let it generate prologue
+                 * dynamically during loading.
+                 */
+                err = hook_load_preprocessor(prog);
+                if (err)
+                        goto out;
         }
 out:
         return err < 0 ? err : 0;
@@ -314,7 +716,14 @@ int bpf__foreach_tev(struct bpf_object *obj,
                 for (i = 0; i < pev->ntevs; i++) {
                         tev = &pev->tevs[i];
 
-                        fd = bpf_program__fd(prog);
+                        if (priv->need_prologue) {
+                                int type = priv->type_mapping[i];
+
+                                fd = bpf_program__nth_fd(prog, type);
+                        } else {
+                                fd = bpf_program__fd(prog);
+                        }
+
                         if (fd < 0) {
                                 pr_debug("bpf: failed to get file descriptor\n");
                                 return fd;
@@ -340,6 +749,10 @@ static const char *bpf_loader_strerror_table[NR_ERRNO] = {
         [ERRCODE_OFFSET(EVENTNAME)]     = "No event name found in config string",
         [ERRCODE_OFFSET(INTERNAL)]      = "BPF loader internal error",
         [ERRCODE_OFFSET(COMPILE)]       = "Error when compiling BPF scriptlet",
+        [ERRCODE_OFFSET(PROGCONF_TERM)] = "Invalid program config term in config string",
+        [ERRCODE_OFFSET(PROLOGUE)]      = "Failed to generate prologue",
+        [ERRCODE_OFFSET(PROLOGUE2BIG)]  = "Prologue too big for program",
+        [ERRCODE_OFFSET(PROLOGUEOOB)]   = "Offset out of bound for prologue",
 };
 
 static int
@@ -420,7 +833,11 @@ int bpf__strerror_probe(struct bpf_object *obj __maybe_unused,
                         int err, char *buf, size_t size)
 {
         bpf__strerror_head(err, buf, size);
-        bpf__strerror_entry(EEXIST, "Probe point exist. Try use 'perf probe -d \"*\"'");
+        case BPF_LOADER_ERRNO__PROGCONF_TERM: {
+                scnprintf(buf, size, "%s (add -v to see detail)", emsg);
+                break;
+        }
+        bpf__strerror_entry(EEXIST, "Probe point exist. Try 'perf probe -d \"*\"' and set 'force=yes'");
         bpf__strerror_entry(EACCES, "You need to be root");
         bpf__strerror_entry(EPERM, "You need to be root, and /proc/sys/kernel/kptr_restrict should be 0");
         bpf__strerror_entry(ENOENT, "You need to check probing points in BPF file");
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 9caf3ae4acf3..6fdc0457e2b6 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -20,6 +20,10 @@ enum bpf_loader_errno {
         BPF_LOADER_ERRNO__EVENTNAME,    /* Event name is missing */
         BPF_LOADER_ERRNO__INTERNAL,     /* BPF loader internal error */
         BPF_LOADER_ERRNO__COMPILE,      /* Error when compiling BPF scriptlet */
+        BPF_LOADER_ERRNO__PROGCONF_TERM,/* Invalid program config term in config string */
+        BPF_LOADER_ERRNO__PROLOGUE,     /* Failed to generate prologue */
+        BPF_LOADER_ERRNO__PROLOGUE2BIG, /* Prologue too big for program */
+        BPF_LOADER_ERRNO__PROLOGUEOOB,  /* Offset out of bound for prologue */
         __BPF_LOADER_ERRNO__END,
 };
 
diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c
new file mode 100644
index 000000000000..6cdbee119ceb
--- /dev/null
+++ b/tools/perf/util/bpf-prologue.c
@@ -0,0 +1,455 @@
+/*
+ * bpf-prologue.c
+ *
+ * Copyright (C) 2015 He Kuang <hekuang@huawei.com>
+ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015 Huawei Inc.
+ */
+
+#include <bpf/libbpf.h>
+#include "perf.h"
+#include "debug.h"
+#include "bpf-loader.h"
+#include "bpf-prologue.h"
+#include "probe-finder.h"
+#include <dwarf-regs.h>
+#include <linux/filter.h>
+
+#define BPF_REG_SIZE            8
+
+#define JMP_TO_ERROR_CODE       -1
+#define JMP_TO_SUCCESS_CODE     -2
+#define JMP_TO_USER_CODE        -3
+
+struct bpf_insn_pos {
+        struct bpf_insn *begin;
+        struct bpf_insn *end;
+        struct bpf_insn *pos;
+};
+
+static inline int
+pos_get_cnt(struct bpf_insn_pos *pos)
+{
+        return pos->pos - pos->begin;
+}
+
+static int
+append_insn(struct bpf_insn new_insn, struct bpf_insn_pos *pos)
+{
+        if (!pos->pos)
+                return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
+
+        if (pos->pos + 1 >= pos->end) {
+                pr_err("bpf prologue: prologue too long\n");
+                pos->pos = NULL;
+                return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
+        }
+
+        *(pos->pos)++ = new_insn;
+        return 0;
+}
+
+static int
+check_pos(struct bpf_insn_pos *pos)
+{
+        if (!pos->pos || pos->pos >= pos->end)
+                return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
+        return 0;
+}
+
+/* Give it a shorter name */
+#define ins(i, p) append_insn((i), (p))
+
+/*
+ * Give a register name (in 'reg'), generate instruction to
+ * load register into an eBPF register rd:
+ *   'ldd target_reg, offset(ctx_reg)', where:
+ * ctx_reg is pre initialized to pointer of 'struct pt_regs'.
+ */
+static int
+gen_ldx_reg_from_ctx(struct bpf_insn_pos *pos, int ctx_reg,
+                     const char *reg, int target_reg)
+{
+        int offset = regs_query_register_offset(reg);
+
+        if (offset < 0) {
+                pr_err("bpf: prologue: failed to get register %s\n",
+                       reg);
+                return offset;
+        }
+        ins(BPF_LDX_MEM(BPF_DW, target_reg, ctx_reg, offset), pos);
+
+        return check_pos(pos);
+}
+
+/*
+ * Generate a BPF_FUNC_probe_read function call.
+ *
+ * src_base_addr_reg is a register holding base address,
+ * dst_addr_reg is a register holding dest address (on stack),
+ * result is:
+ *
+ *  *[dst_addr_reg] = *([src_base_addr_reg] + offset)
+ *
+ * Arguments of BPF_FUNC_probe_read:
+ *     ARG1: ptr to stack (dest)
+ *     ARG2: size (8)
+ *     ARG3: unsafe ptr (src)
+ */
+static int
+gen_read_mem(struct bpf_insn_pos *pos,
+             int src_base_addr_reg,
+             int dst_addr_reg,
+             long offset)
+{
+        /* mov arg3, src_base_addr_reg */
+        if (src_base_addr_reg != BPF_REG_ARG3)
+                ins(BPF_MOV64_REG(BPF_REG_ARG3, src_base_addr_reg), pos);
+        /* add arg3, #offset */
+        if (offset)
+                ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG3, offset), pos);
+
+        /* mov arg2, #reg_size */
+        ins(BPF_ALU64_IMM(BPF_MOV, BPF_REG_ARG2, BPF_REG_SIZE), pos);
+
+        /* mov arg1, dst_addr_reg */
+        if (dst_addr_reg != BPF_REG_ARG1)
+                ins(BPF_MOV64_REG(BPF_REG_ARG1, dst_addr_reg), pos);
+
+        /* Call probe_read  */
+        ins(BPF_EMIT_CALL(BPF_FUNC_probe_read), pos);
+        /*
+         * Error processing: if read fail, goto error code,
+         * will be relocated. Target should be the start of
+         * error processing code.
+         */
+        ins(BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, JMP_TO_ERROR_CODE),
+            pos);
+
+        return check_pos(pos);
+}
+
+/*
+ * Each arg should be bare register. Fetch and save them into argument
+ * registers (r3 - r5).
+ *
+ * BPF_REG_1 should have been initialized with pointer to
+ * 'struct pt_regs'.
+ */
+static int
+gen_prologue_fastpath(struct bpf_insn_pos *pos,
+                      struct probe_trace_arg *args, int nargs)
+{
+        int i, err = 0;
+
+        for (i = 0; i < nargs; i++) {
+                err = gen_ldx_reg_from_ctx(pos, BPF_REG_1, args[i].value,
+                                           BPF_PROLOGUE_START_ARG_REG + i);
+                if (err)
+                        goto errout;
+        }
+
+        return check_pos(pos);
+errout:
+        return err;
+}
+
+/*
+ * Slow path:
+ *   At least one argument has the form of 'offset($rx)'.
+ *
+ * Following code first stores them into stack, then loads all of then
+ * to r2 - r5.
+ * Before final loading, the final result should be:
+ *
+ * low address
+ * BPF_REG_FP - 24  ARG3
+ * BPF_REG_FP - 16  ARG2
+ * BPF_REG_FP - 8   ARG1
+ * BPF_REG_FP
+ * high address
+ *
+ * For each argument (described as: offn(...off2(off1(reg)))),
+ * generates following code:
+ *
+ *  r7 <- fp
+ *  r7 <- r7 - stack_offset  // Ideal code should initialize r7 using
+ *                           // fp before generating args. However,
+ *                           // eBPF won't regard r7 as stack pointer
+ *                           // if it is generated by minus 8 from
+ *                           // another stack pointer except fp.
+ *                           // This is why we have to set r7
+ *                           // to fp for each variable.
+ *  r3 <- value of 'reg'-> generated using gen_ldx_reg_from_ctx()
+ *  (r7) <- r3       // skip following instructions for bare reg
+ *  r3 <- r3 + off1  . // skip if off1 == 0
+ *  r2 <- 8           \
+ *  r1 <- r7           |-> generated by gen_read_mem()
+ *  call probe_read    /
+ *  jnei r0, 0, err  ./
+ *  r3 <- (r7)
+ *  r3 <- r3 + off2  . // skip if off2 == 0
+ *  r2 <- 8           \  // r2 may be broken by probe_read, so set again
+ *  r1 <- r7           |-> generated by gen_read_mem()
+ *  call probe_read    /
+ *  jnei r0, 0, err  ./
+ *  ...
+ */
+static int
+gen_prologue_slowpath(struct bpf_insn_pos *pos,
+                      struct probe_trace_arg *args, int nargs)
+{
+        int err, i;
+
+        for (i = 0; i < nargs; i++) {
+                struct probe_trace_arg *arg = &args[i];
+                const char *reg = arg->value;
+                struct probe_trace_arg_ref *ref = NULL;
+                int stack_offset = (i + 1) * -8;
+
+                pr_debug("prologue: fetch arg %d, base reg is %s\n",
+                         i, reg);
+
+                /* value of base register is stored into ARG3 */
+                err = gen_ldx_reg_from_ctx(pos, BPF_REG_CTX, reg,
+                                           BPF_REG_ARG3);
+                if (err) {
+                        pr_err("prologue: failed to get offset of register %s\n",
+                               reg);
+                        goto errout;
+                }
+
+                /* Make r7 the stack pointer. */
+                ins(BPF_MOV64_REG(BPF_REG_7, BPF_REG_FP), pos);
+                /* r7 += -8 */
+                ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, stack_offset), pos);
+                /*
+                 * Store r3 (base register) onto stack
+                 * Ensure fp[offset] is set.
+                 * fp is the only valid base register when storing
+                 * into stack. We are not allowed to use r7 as base
+                 * register here.
+                 */
+                ins(BPF_STX_MEM(BPF_DW, BPF_REG_FP, BPF_REG_ARG3,
+                                stack_offset), pos);
+
+                ref = arg->ref;
+                while (ref) {
+                        pr_debug("prologue: arg %d: offset %ld\n",
+                                 i, ref->offset);
+                        err = gen_read_mem(pos, BPF_REG_3, BPF_REG_7,
+                                           ref->offset);
+                        if (err) {
+                                pr_err("prologue: failed to generate probe_read function call\n");
+                                goto errout;
+                        }
+
+                        ref = ref->next;
+                        /*
+                         * Load previous result into ARG3. Use
+                         * BPF_REG_FP instead of r7 because verifier
+                         * allows FP based addressing only.
+                         */
+                        if (ref)
+                                ins(BPF_LDX_MEM(BPF_DW, BPF_REG_ARG3,
+                                                BPF_REG_FP, stack_offset), pos);
+                }
+        }
+
+        /* Final pass: read to registers */
+        for (i = 0; i < nargs; i++)
+                ins(BPF_LDX_MEM(BPF_DW, BPF_PROLOGUE_START_ARG_REG + i,
+                                BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos);
+
+        ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos);
+
+        return check_pos(pos);
+errout:
+        return err;
+}
+
+static int
+prologue_relocate(struct bpf_insn_pos *pos, struct bpf_insn *error_code,
+                  struct bpf_insn *success_code, struct bpf_insn *user_code)
+{
+        struct bpf_insn *insn;
+
+        if (check_pos(pos))
+                return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
+
+        for (insn = pos->begin; insn < pos->pos; insn++) {
+                struct bpf_insn *target;
+                u8 class = BPF_CLASS(insn->code);
+                u8 opcode;
+
+                if (class != BPF_JMP)
+                        continue;
+                opcode = BPF_OP(insn->code);
+                if (opcode == BPF_CALL)
+                        continue;
+
+                switch (insn->off) {
+                case JMP_TO_ERROR_CODE:
+                        target = error_code;
+                        break;
+                case JMP_TO_SUCCESS_CODE:
+                        target = success_code;
+                        break;
+                case JMP_TO_USER_CODE:
+                        target = user_code;
+                        break;
+                default:
+                        pr_err("bpf prologue: internal error: relocation failed\n");
+                        return -BPF_LOADER_ERRNO__PROLOGUE;
+                }
+
+                insn->off = target - (insn + 1);
+        }
+        return 0;
+}
+
+int bpf__gen_prologue(struct probe_trace_arg *args, int nargs,
+                      struct bpf_insn *new_prog, size_t *new_cnt,
+                      size_t cnt_space)
+{
+        struct bpf_insn *success_code = NULL;
+        struct bpf_insn *error_code = NULL;
+        struct bpf_insn *user_code = NULL;
+        struct bpf_insn_pos pos;
+        bool fastpath = true;
+        int err = 0, i;
+
+        if (!new_prog || !new_cnt)
+                return -EINVAL;
+
+        if (cnt_space > BPF_MAXINSNS)
+                cnt_space = BPF_MAXINSNS;
+
+        pos.begin = new_prog;
+        pos.end = new_prog + cnt_space;
+        pos.pos = new_prog;
+
+        if (!nargs) {
+                ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0),
+                    &pos);
+
+                if (check_pos(&pos))
+                        goto errout;
+
+                *new_cnt = pos_get_cnt(&pos);
+                return 0;
+        }
+
+        if (nargs > BPF_PROLOGUE_MAX_ARGS) {
+                pr_warning("bpf: prologue: %d arguments are dropped\n",
+                           nargs - BPF_PROLOGUE_MAX_ARGS);
+                nargs = BPF_PROLOGUE_MAX_ARGS;
+        }
+
+        /* First pass: validation */
+        for (i = 0; i < nargs; i++) {
+                struct probe_trace_arg_ref *ref = args[i].ref;
+
+                if (args[i].value[0] == '@') {
+                        /* TODO: fetch global variable */
+                        pr_err("bpf: prologue: global %s%+ld not support\n",
+                                args[i].value, ref ? ref->offset : 0);
+                        return -ENOTSUP;
+                }
+
+                while (ref) {
+                        /* fastpath is true if all args has ref == NULL */
+                        fastpath = false;
+
+                        /*
+                         * Instruction encodes immediate value using
+                         * s32, ref->offset is long. On systems which
+                         * can't fill long in s32, refuse to process if
+                         * ref->offset too large (or small).
+                         */
+#ifdef __LP64__
+#define OFFSET_MAX      ((1LL << 31) - 1)
+#define OFFSET_MIN      ((1LL << 31) * -1)
+                        if (ref->offset > OFFSET_MAX ||
+                                        ref->offset < OFFSET_MIN) {
+                                pr_err("bpf: prologue: offset out of bound: %ld\n",
+                                       ref->offset);
+                                return -BPF_LOADER_ERRNO__PROLOGUEOOB;
+                        }
+#endif
+                        ref = ref->next;
+                }
+        }
+        pr_debug("prologue: pass validation\n");
+
+        if (fastpath) {
+                /* If all variables are registers... */
+                pr_debug("prologue: fast path\n");
+                err = gen_prologue_fastpath(&pos, args, nargs);
+                if (err)
+                        goto errout;
+        } else {
+                pr_debug("prologue: slow path\n");
+
+                /* Initialization: move ctx to a callee saved register. */
+                ins(BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1), &pos);
+
+                err = gen_prologue_slowpath(&pos, args, nargs);
+                if (err)
+                        goto errout;
+                /*
+                 * start of ERROR_CODE (only slow pass needs error code)
+                 *   mov r2 <- 1  // r2 is error number
+                 *   mov r3 <- 0  // r3, r4... should be touched or
+                 *                // verifier would complain
+                 *   mov r4 <- 0
+                 *   ...
+                 *   goto usercode
+                 */
+                error_code = pos.pos;
+                ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 1),
+                    &pos);
+
+                for (i = 0; i < nargs; i++)
+                        ins(BPF_ALU64_IMM(BPF_MOV,
+                                          BPF_PROLOGUE_START_ARG_REG + i,
+                                          0),
+                            &pos);
+                ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_USER_CODE),
+                                &pos);
+        }
+
+        /*
+         * start of SUCCESS_CODE:
+         *   mov r2 <- 0
+         *   goto usercode  // skip
+         */
+        success_code = pos.pos;
+        ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0), &pos);
+
+        /*
+         * start of USER_CODE:
+         *   Restore ctx to r1
+         */
+        user_code = pos.pos;
+        if (!fastpath) {
+                /*
+                 * Only slow path needs restoring of ctx. In fast path,
+                 * register are loaded directly from r1.
+                 */
+                ins(BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX), &pos);
+                err = prologue_relocate(&pos, error_code, success_code,
+                                        user_code);
+                if (err)
+                        goto errout;
+        }
+
+        err = check_pos(&pos);
+        if (err)
+                goto errout;
+
+        *new_cnt = pos_get_cnt(&pos);
+        return 0;
+errout:
+        return err;
+}
diff --git a/tools/perf/util/bpf-prologue.h b/tools/perf/util/bpf-prologue.h
new file mode 100644
index 000000000000..d94cbea12899
--- /dev/null
+++ b/tools/perf/util/bpf-prologue.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright (C) 2015, He Kuang <hekuang@huawei.com>
+ * Copyright (C) 2015, Huawei Inc.
+ */
+#ifndef __BPF_PROLOGUE_H
+#define __BPF_PROLOGUE_H
+
+#include <linux/compiler.h>
+#include <linux/filter.h>
+#include "probe-event.h"
+
+#define BPF_PROLOGUE_MAX_ARGS 3
+#define BPF_PROLOGUE_START_ARG_REG BPF_REG_3
+#define BPF_PROLOGUE_FETCH_RESULT_REG BPF_REG_2
+
+#ifdef HAVE_BPF_PROLOGUE
+int bpf__gen_prologue(struct probe_trace_arg *args, int nargs,
+                      struct bpf_insn *new_prog, size_t *new_cnt,
+                      size_t cnt_space);
+#else
+static inline int
+bpf__gen_prologue(struct probe_trace_arg *args __maybe_unused,
+                  int nargs __maybe_unused,
+                  struct bpf_insn *new_prog __maybe_unused,
+                  size_t *new_cnt,
+                  size_t cnt_space __maybe_unused)
+{
+        if (!new_cnt)
+                return -EINVAL;
+        *new_cnt = 0;
+        return -ENOTSUP;
+}
+#endif
+#endif /* __BPF_PROLOGUE_H */
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index c861373aaed3..07b5d63947b1 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -4,9 +4,12 @@
 #include <stdbool.h>
 #include "util.h"
 #include "strbuf.h"
+#include <subcmd/pager.h>
 #include "../perf.h"
 #include "../ui/ui.h"
 
+#include <linux/string.h>
+
 #define CMD_EXEC_PATH "--exec-path"
 #define CMD_PERF_DIR "--perf-dir="
 #define CMD_WORK_TREE "--work-tree="
@@ -18,6 +21,7 @@
 #define DEFAULT_PERF_DIR_ENVIRONMENT ".perf"
 #define PERF_DEBUGFS_ENVIRONMENT "PERF_DEBUGFS_DIR"
 #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR"
+#define PERF_PAGER_ENVIRONMENT "PERF_PAGER"
 
 typedef int (*config_fn_t)(const char *, const char *, void *);
 extern int perf_default_config(const char *, const char *, void *);
@@ -28,11 +32,6 @@ extern int perf_config_bool(const char *, const char *);
 extern int config_error_nonbool(const char *);
 extern const char *perf_config_dirname(const char *, const char *);
 
-/* pager.c */
-extern void setup_pager(void);
-extern int pager_in_use(void);
-extern int pager_use_color;
-
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
 
@@ -71,9 +70,4 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2
 extern char *perf_pathdup(const char *fmt, ...)
         __attribute__((format (printf, 1, 2)));
 
-#ifndef __UCLIBC__
-/* Matches the libc/libbsd function attribute so we declare this unconditionally: */
-extern size_t strlcpy(char *dest, const char *src, size_t size);
-#endif
-
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 735ad48e1858..53c43eb9489e 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -44,6 +44,10 @@ static int parse_callchain_mode(const char *value)
                 callchain_param.mode = CHAIN_GRAPH_REL;
                 return 0;
         }
+        if (!strncmp(value, "folded", strlen(value))) {
+                callchain_param.mode = CHAIN_FOLDED;
+                return 0;
+        }
         return -1;
 }
 
@@ -79,6 +83,23 @@ static int parse_callchain_sort_key(const char *value)
         return -1;
 }
 
+static int parse_callchain_value(const char *value)
+{
+        if (!strncmp(value, "percent", strlen(value))) {
+                callchain_param.value = CCVAL_PERCENT;
+                return 0;
+        }
+        if (!strncmp(value, "period", strlen(value))) {
+                callchain_param.value = CCVAL_PERIOD;
+                return 0;
+        }
+        if (!strncmp(value, "count", strlen(value))) {
+                callchain_param.value = CCVAL_COUNT;
+                return 0;
+        }
+        return -1;
+}
+
 static int
 __parse_callchain_report_opt(const char *arg, bool allow_record_opt)
 {
@@ -102,7 +123,8 @@ __parse_callchain_report_opt(const char *arg, bool allow_record_opt)
 
                 if (!parse_callchain_mode(tok) ||
                     !parse_callchain_order(tok) ||
-                    !parse_callchain_sort_key(tok)) {
+                    !parse_callchain_sort_key(tok) ||
+                    !parse_callchain_value(tok)) {
                         /* parsing ok - move on to the next */
                         try_stack_size = false;
                         goto next;
@@ -218,6 +240,7 @@ rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
 
                 switch (mode) {
                 case CHAIN_FLAT:
+                case CHAIN_FOLDED:
                         if (rnode->hit < chain->hit)
                                 p = &(*p)->rb_left;
                         else
@@ -267,6 +290,7 @@ static void
 sort_chain_flat(struct rb_root *rb_root, struct callchain_root *root,
                 u64 min_hit, struct callchain_param *param __maybe_unused)
 {
+        *rb_root = RB_ROOT;
         __sort_chain_flat(rb_root, &root->node, min_hit);
 }
 
@@ -338,6 +362,7 @@ int callchain_register_param(struct callchain_param *param)
                 param->sort = sort_chain_graph_rel;
                 break;
         case CHAIN_FLAT:
+        case CHAIN_FOLDED:
                 param->sort = sort_chain_flat;
                 break;
         case CHAIN_NONE:
@@ -363,6 +388,7 @@ create_child(struct callchain_node *parent, bool inherit_children)
         }
         new->parent = parent;
         INIT_LIST_HEAD(&new->val);
+        INIT_LIST_HEAD(&new->parent_val);
 
         if (inherit_children) {
                 struct rb_node *n;
@@ -431,6 +457,8 @@ add_child(struct callchain_node *parent,
 
         new->children_hit = 0;
         new->hit = period;
+        new->children_count = 0;
+        new->count = 1;
         return new;
 }
 
@@ -478,6 +506,9 @@ split_add_child(struct callchain_node *parent,
         parent->children_hit = callchain_cumul_hits(new);
         new->val_nr = parent->val_nr - idx_local;
         parent->val_nr = idx_local;
+        new->count = parent->count;
+        new->children_count = parent->children_count;
+        parent->children_count = callchain_cumul_counts(new);
 
         /* create a new child for the new branch if any */
         if (idx_total < cursor->nr) {
@@ -488,6 +519,8 @@ split_add_child(struct callchain_node *parent,
 
                 parent->hit = 0;
                 parent->children_hit += period;
+                parent->count = 0;
+                parent->children_count += 1;
 
                 node = callchain_cursor_current(cursor);
                 new = add_child(parent, cursor, period);
@@ -510,6 +543,7 @@ split_add_child(struct callchain_node *parent,
                 rb_insert_color(&new->rb_node_in, &parent->rb_root_in);
         } else {
                 parent->hit = period;
+                parent->count = 1;
         }
 }
 
@@ -556,6 +590,7 @@ append_chain_children(struct callchain_node *root,
 
 inc_children_hit:
         root->children_hit += period;
+        root->children_count++;
 }
 
 static int
@@ -608,6 +643,7 @@ append_chain(struct callchain_node *root,
         /* we match 100% of the path, increment the hit */
         if (matches == root->val_nr && cursor->pos == cursor->nr) {
                 root->hit += period;
+                root->count++;
                 return 0;
         }
 
@@ -799,12 +835,72 @@ char *callchain_list__sym_name(struct callchain_list *cl,
         return bf;
 }
 
+char *callchain_node__scnprintf_value(struct callchain_node *node,
+                                      char *bf, size_t bfsize, u64 total)
+{
+        double percent = 0.0;
+        u64 period = callchain_cumul_hits(node);
+        unsigned count = callchain_cumul_counts(node);
+
+        if (callchain_param.mode == CHAIN_FOLDED) {
+                period = node->hit;
+                count = node->count;
+        }
+
+        switch (callchain_param.value) {
+        case CCVAL_PERIOD:
+                scnprintf(bf, bfsize, "%"PRIu64, period);
+                break;
+        case CCVAL_COUNT:
+                scnprintf(bf, bfsize, "%u", count);
+                break;
+        case CCVAL_PERCENT:
+        default:
+                if (total)
+                        percent = period * 100.0 / total;
+                scnprintf(bf, bfsize, "%.2f%%", percent);
+                break;
+        }
+        return bf;
+}
+
+int callchain_node__fprintf_value(struct callchain_node *node,
+                                 FILE *fp, u64 total)
+{
+        double percent = 0.0;
+        u64 period = callchain_cumul_hits(node);
+        unsigned count = callchain_cumul_counts(node);
+
+        if (callchain_param.mode == CHAIN_FOLDED) {
+                period = node->hit;
+                count = node->count;
+        }
+
+        switch (callchain_param.value) {
+        case CCVAL_PERIOD:
+                return fprintf(fp, "%"PRIu64, period);
+        case CCVAL_COUNT:
+                return fprintf(fp, "%u", count);
+        case CCVAL_PERCENT:
+        default:
+                if (total)
+                        percent = period * 100.0 / total;
+                return percent_color_fprintf(fp, "%.2f%%", percent);
+        }
+        return 0;
+}
+
 static void free_callchain_node(struct callchain_node *node)
 {
         struct callchain_list *list, *tmp;
         struct callchain_node *child;
         struct rb_node *n;
 
+        list_for_each_entry_safe(list, tmp, &node->parent_val, list) {
+                list_del(&list->list);
+                free(list);
+        }
+
         list_for_each_entry_safe(list, tmp, &node->val, list) {
                 list_del(&list->list);
                 free(list);
@@ -828,3 +924,69 @@ void free_callchain(struct callchain_root *root)
 
         free_callchain_node(&root->node);
 }
+
+static u64 decay_callchain_node(struct callchain_node *node)
+{
+        struct callchain_node *child;
+        struct rb_node *n;
+        u64 child_hits = 0;
+
+        n = rb_first(&node->rb_root_in);
+        while (n) {
+                child = container_of(n, struct callchain_node, rb_node_in);
+
+                child_hits += decay_callchain_node(child);
+                n = rb_next(n);
+        }
+
+        node->hit = (node->hit * 7) / 8;
+        node->children_hit = child_hits;
+
+        return node->hit;
+}
+
+void decay_callchain(struct callchain_root *root)
+{
+        if (!symbol_conf.use_callchain)
+                return;
+
+        decay_callchain_node(&root->node);
+}
+
+int callchain_node__make_parent_list(struct callchain_node *node)
+{
+        struct callchain_node *parent = node->parent;
+        struct callchain_list *chain, *new;
+        LIST_HEAD(head);
+
+        while (parent) {
+                list_for_each_entry_reverse(chain, &parent->val, list) {
+                        new = malloc(sizeof(*new));
+                        if (new == NULL)
+                                goto out;
+                        *new = *chain;
+                        new->has_children = false;
+                        list_add_tail(&new->list, &head);
+                }
+                parent = parent->parent;
+        }
+
+        list_for_each_entry_safe_reverse(chain, new, &head, list)
+                list_move_tail(&chain->list, &node->parent_val);
+
+        if (!list_empty(&node->parent_val)) {
+                chain = list_first_entry(&node->parent_val, struct callchain_list, list);
+                chain->has_children = rb_prev(&node->rb_node) || rb_next(&node->rb_node);
+
+                chain = list_first_entry(&node->val, struct callchain_list, list);
+                chain->has_children = false;
+        }
+        return 0;
+
+out:
+        list_for_each_entry_safe(chain, new, &head, list) {
+                list_del(&chain->list);
+                free(chain);
+        }
+        return -ENOMEM;
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index fce8161e54db..18dd22269764 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -24,12 +24,13 @@
 #define CALLCHAIN_RECORD_HELP  CALLCHAIN_HELP RECORD_MODE_HELP RECORD_SIZE_HELP
 
 #define CALLCHAIN_REPORT_HELP                                           \
-        HELP_PAD "print_type:\tcall graph printing style (graph|flat|fractal|none)\n" \
+        HELP_PAD "print_type:\tcall graph printing style (graph|flat|fractal|folded|none)\n" \
         HELP_PAD "threshold:\tminimum call graph inclusion threshold (<percent>)\n" \
         HELP_PAD "print_limit:\tmaximum number of call graph entry (<number>)\n" \
         HELP_PAD "order:\t\tcall graph order (caller|callee)\n" \
         HELP_PAD "sort_key:\tcall graph sort key (function|address)\n"  \
-        HELP_PAD "branch:\t\tinclude last branch info to call graph (branch)\n"
+        HELP_PAD "branch:\t\tinclude last branch info to call graph (branch)\n" \
+        HELP_PAD "value:\t\tcall graph value (percent|period|count)\n"
 
 enum perf_call_graph_mode {
         CALLCHAIN_NONE,
@@ -43,7 +44,8 @@ enum chain_mode {
         CHAIN_NONE,
         CHAIN_FLAT,
         CHAIN_GRAPH_ABS,
-        CHAIN_GRAPH_REL
+        CHAIN_GRAPH_REL,
+        CHAIN_FOLDED,
 };
 
 enum chain_order {
@@ -54,11 +56,14 @@ enum chain_order {
 struct callchain_node {
         struct callchain_node   *parent;
         struct list_head        val;
+        struct list_head        parent_val;
         struct rb_node          rb_node_in; /* to insert nodes in an rbtree */
         struct rb_node          rb_node;    /* to sort nodes in an output tree */
         struct rb_root          rb_root_in; /* input tree of children */
         struct rb_root          rb_root;    /* sorted output tree of children */
         unsigned int            val_nr;
+        unsigned int            count;
+        unsigned int            children_count;
         u64                     hit;
         u64                     children_hit;
 };
@@ -78,6 +83,12 @@ enum chain_key {
         CCKEY_ADDRESS
 };
 
+enum chain_value {
+        CCVAL_PERCENT,
+        CCVAL_PERIOD,
+        CCVAL_COUNT,
+};
+
 struct callchain_param {
         bool                    enabled;
         enum perf_call_graph_mode record_mode;
@@ -90,6 +101,7 @@ struct callchain_param {
         bool                    order_set;
         enum chain_key          key;
         bool                    branch_callstack;
+        enum chain_value        value;
 };
 
 extern struct callchain_param callchain_param;
@@ -131,6 +143,7 @@ extern __thread struct callchain_cursor callchain_cursor;
 static inline void callchain_init(struct callchain_root *root)
 {
         INIT_LIST_HEAD(&root->node.val);
+        INIT_LIST_HEAD(&root->node.parent_val);
 
         root->node.parent = NULL;
         root->node.hit = 0;
@@ -144,6 +157,11 @@ static inline u64 callchain_cumul_hits(struct callchain_node *node)
         return node->hit + node->children_hit;
 }
 
+static inline unsigned callchain_cumul_counts(struct callchain_node *node)
+{
+        return node->count + node->children_count;
+}
+
 int callchain_register_param(struct callchain_param *param);
 int callchain_append(struct callchain_root *root,
                      struct callchain_cursor *cursor,
@@ -229,7 +247,13 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
 
 char *callchain_list__sym_name(struct callchain_list *cl,
                                char *bf, size_t bfsize, bool show_dso);
+char *callchain_node__scnprintf_value(struct callchain_node *node,
+                                      char *bf, size_t bfsize, u64 total);
+int callchain_node__fprintf_value(struct callchain_node *node,
+                                  FILE *fp, u64 total);
 
 void free_callchain(struct callchain_root *root);
+void decay_callchain(struct callchain_root *root);
+int callchain_node__make_parent_list(struct callchain_node *node);
 
 #endif  /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 32e12ecfe9c5..90aa1b46b2e5 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -1,6 +1,6 @@
 #include "util.h"
 #include "../perf.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 #include "evsel.h"
 #include "cgroup.h"
 #include "evlist.h"
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 9b9565416f90..e5fb88bab9e1 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -24,7 +24,7 @@ int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty)
  auto_color:
         if (stdout_is_tty < 0)
                 stdout_is_tty = isatty(1);
-        if (stdout_is_tty || (pager_in_use() && pager_use_color)) {
+        if (stdout_is_tty || pager_in_use()) {
                 char *term = getenv("TERM");
                 if (term && strcmp(term, "dumb"))
                         return 1;
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 2e452ac1353d..d3e12e30e1d5 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -10,7 +10,7 @@
  */
 #include "util.h"
 #include "cache.h"
-#include "exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "util/hist.h"  /* perf_hist_config */
 #include "util/llvm-utils.h"   /* perf_llvm_config */
 
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 10af1e7524fb..fa935093a599 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -5,6 +5,7 @@
 #include <assert.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <linux/bitmap.h>
 #include "asm/bug.h"
 
 static struct cpu_map *cpu_map__default_new(void)
@@ -179,6 +180,56 @@ out:
         return cpus;
 }
 
+static struct cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
+{
+        struct cpu_map *map;
+
+        map = cpu_map__empty_new(cpus->nr);
+        if (map) {
+                unsigned i;
+
+                for (i = 0; i < cpus->nr; i++) {
+                        /*
+                         * Special treatment for -1, which is not real cpu number,
+                         * and we need to use (int) -1 to initialize map[i],
+                         * otherwise it would become 65535.
+                         */
+                        if (cpus->cpu[i] == (u16) -1)
+                                map->map[i] = -1;
+                        else
+                                map->map[i] = (int) cpus->cpu[i];
+                }
+        }
+
+        return map;
+}
+
+static struct cpu_map *cpu_map__from_mask(struct cpu_map_mask *mask)
+{
+        struct cpu_map *map;
+        int nr, nbits = mask->nr * mask->long_size * BITS_PER_BYTE;
+
+        nr = bitmap_weight(mask->mask, nbits);
+
+        map = cpu_map__empty_new(nr);
+        if (map) {
+                int cpu, i = 0;
+
+                for_each_set_bit(cpu, mask->mask, nbits)
+                        map->map[i++] = cpu;
+        }
+        return map;
+
+}
+
+struct cpu_map *cpu_map__new_data(struct cpu_map_data *data)
+{
+        if (data->type == PERF_CPU_MAP__CPUS)
+                return cpu_map__from_entries((struct cpu_map_entries *)data->data);
+        else
+                return cpu_map__from_mask((struct cpu_map_mask *)data->data);
+}
+
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp)
 {
         int i;
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 85f7772457fa..71c41b9efabb 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -17,6 +17,7 @@ struct cpu_map {
 struct cpu_map *cpu_map__new(const char *cpu_list);
 struct cpu_map *cpu_map__empty_new(int nr);
 struct cpu_map *cpu_map__dummy_new(void);
+struct cpu_map *cpu_map__new_data(struct cpu_map_data *data);
 struct cpu_map *cpu_map__read(FILE *file);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
 int cpu_map__get_socket_id(int cpu);
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 5bfc1198ab46..34cd1e4039d3 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -63,6 +63,7 @@ struct ctf_writer {
                         struct bt_ctf_field_type        *s32;
                         struct bt_ctf_field_type        *u32;
                         struct bt_ctf_field_type        *string;
+                        struct bt_ctf_field_type        *u32_hex;
                         struct bt_ctf_field_type        *u64_hex;
                 };
                 struct bt_ctf_field_type *array[6];
@@ -982,6 +983,7 @@ do {							\
         CREATE_INT_TYPE(cw->data.u64, 64, false, false);
         CREATE_INT_TYPE(cw->data.s32, 32, true,  false);
         CREATE_INT_TYPE(cw->data.u32, 32, false, false);
+        CREATE_INT_TYPE(cw->data.u32_hex, 32, false, true);
         CREATE_INT_TYPE(cw->data.u64_hex, 64, false, true);
 
         cw->data.string  = bt_ctf_field_type_string_create();
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 425df5c86c9c..e8e9a9dbf5e3 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1243,6 +1243,8 @@ struct dso *__dsos__addnew(struct dsos *dsos, const char *name)
         if (dso != NULL) {
                 __dsos__add(dsos, dso);
                 dso__set_basename(dso);
+                /* Put dso here because __dsos_add already got it */
+                dso__put(dso);
         }
         return dso;
 }
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 6af4f7c36820..7dd5939dea2e 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -25,15 +25,6 @@ int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
 {
         int i;
 
-        /*
-         * If env->cmdline_argv has already been set, do not override it.  This allows
-         * a command to set the cmdline, parse args and then call another
-         * builtin function that implements a command -- e.g, cmd_kvm calling
-         * cmd_record.
-         */
-        if (env->cmdline_argv != NULL)
-                return 0;
-
         /* do not include NULL termination */
         env->cmdline_argv = calloc(argc, sizeof(char *));
         if (env->cmdline_argv == NULL)
diff --git a/tools/perf/util/environment.c b/tools/perf/util/environment.c
deleted file mode 100644
index 7405123692f1..000000000000
--- a/tools/perf/util/environment.c
+++ /dev/null
@@ -1,8 +0,0 @@
-/*
- * We put all the perf config variables in this same object
- * file, so that programs can link against the config parser
- * without having to link against all the rest of perf.
- */
-#include "cache.h"
-
-int pager_use_color = 1;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 8b10621b415c..cd61bb1f3917 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -10,6 +10,8 @@
 #include "thread.h"
 #include "thread_map.h"
 #include "symbol/kallsyms.h"
+#include "asm/bug.h"
+#include "stat.h"
 
 static const char *perf_event__names[] = {
         [0]                                     = "TOTAL",
@@ -37,6 +39,12 @@ static const char *perf_event__names[] = {
         [PERF_RECORD_AUXTRACE_INFO]             = "AUXTRACE_INFO",
         [PERF_RECORD_AUXTRACE]                  = "AUXTRACE",
         [PERF_RECORD_AUXTRACE_ERROR]            = "AUXTRACE_ERROR",
+        [PERF_RECORD_THREAD_MAP]                = "THREAD_MAP",
+        [PERF_RECORD_CPU_MAP]                   = "CPU_MAP",
+        [PERF_RECORD_STAT_CONFIG]               = "STAT_CONFIG",
+        [PERF_RECORD_STAT]                      = "STAT",
+        [PERF_RECORD_STAT_ROUND]                = "STAT_ROUND",
+        [PERF_RECORD_EVENT_UPDATE]              = "EVENT_UPDATE",
 };
 
 const char *perf_event__name(unsigned int id)
@@ -699,6 +707,274 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
         return err;
 }
 
+int perf_event__synthesize_thread_map2(struct perf_tool *tool,
+                                      struct thread_map *threads,
+                                      perf_event__handler_t process,
+                                      struct machine *machine)
+{
+        union perf_event *event;
+        int i, err, size;
+
+        size  = sizeof(event->thread_map);
+        size += threads->nr * sizeof(event->thread_map.entries[0]);
+
+        event = zalloc(size);
+        if (!event)
+                return -ENOMEM;
+
+        event->header.type = PERF_RECORD_THREAD_MAP;
+        event->header.size = size;
+        event->thread_map.nr = threads->nr;
+
+        for (i = 0; i < threads->nr; i++) {
+                struct thread_map_event_entry *entry = &event->thread_map.entries[i];
+                char *comm = thread_map__comm(threads, i);
+
+                if (!comm)
+                        comm = (char *) "";
+
+                entry->pid = thread_map__pid(threads, i);
+                strncpy((char *) &entry->comm, comm, sizeof(entry->comm));
+        }
+
+        err = process(tool, event, NULL, machine);
+
+        free(event);
+        return err;
+}
+
+static void synthesize_cpus(struct cpu_map_entries *cpus,
+                            struct cpu_map *map)
+{
+        int i;
+
+        cpus->nr = map->nr;
+
+        for (i = 0; i < map->nr; i++)
+                cpus->cpu[i] = map->map[i];
+}
+
+static void synthesize_mask(struct cpu_map_mask *mask,
+                            struct cpu_map *map, int max)
+{
+        int i;
+
+        mask->nr = BITS_TO_LONGS(max);
+        mask->long_size = sizeof(long);
+
+        for (i = 0; i < map->nr; i++)
+                set_bit(map->map[i], mask->mask);
+}
+
+static size_t cpus_size(struct cpu_map *map)
+{
+        return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16);
+}
+
+static size_t mask_size(struct cpu_map *map, int *max)
+{
+        int i;
+
+        *max = 0;
+
+        for (i = 0; i < map->nr; i++) {
+                /* bit possition of the cpu is + 1 */
+                int bit = map->map[i] + 1;
+
+                if (bit > *max)
+                        *max = bit;
+        }
+
+        return sizeof(struct cpu_map_mask) + BITS_TO_LONGS(*max) * sizeof(long);
+}
+
+void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max)
+{
+        size_t size_cpus, size_mask;
+        bool is_dummy = cpu_map__empty(map);
+
+        /*
+         * Both array and mask data have variable size based
+         * on the number of cpus and their actual values.
+         * The size of the 'struct cpu_map_data' is:
+         *
+         *   array = size of 'struct cpu_map_entries' +
+         *           number of cpus * sizeof(u64)
+         *
+         *   mask  = size of 'struct cpu_map_mask' +
+         *           maximum cpu bit converted to size of longs
+         *
+         * and finaly + the size of 'struct cpu_map_data'.
+         */
+        size_cpus = cpus_size(map);
+        size_mask = mask_size(map, max);
+
+        if (is_dummy || (size_cpus < size_mask)) {
+                *size += size_cpus;
+                *type  = PERF_CPU_MAP__CPUS;
+        } else {
+                *size += size_mask;
+                *type  = PERF_CPU_MAP__MASK;
+        }
+
+        *size += sizeof(struct cpu_map_data);
+        return zalloc(*size);
+}
+
+void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map,
+                              u16 type, int max)
+{
+        data->type = type;
+
+        switch (type) {
+        case PERF_CPU_MAP__CPUS:
+                synthesize_cpus((struct cpu_map_entries *) data->data, map);
+                break;
+        case PERF_CPU_MAP__MASK:
+                synthesize_mask((struct cpu_map_mask *) data->data, map, max);
+        default:
+                break;
+        };
+}
+
+static struct cpu_map_event* cpu_map_event__new(struct cpu_map *map)
+{
+        size_t size = sizeof(struct cpu_map_event);
+        struct cpu_map_event *event;
+        int max;
+        u16 type;
+
+        event = cpu_map_data__alloc(map, &size, &type, &max);
+        if (!event)
+                return NULL;
+
+        event->header.type = PERF_RECORD_CPU_MAP;
+        event->header.size = size;
+        event->data.type   = type;
+
+        cpu_map_data__synthesize(&event->data, map, type, max);
+        return event;
+}
+
+int perf_event__synthesize_cpu_map(struct perf_tool *tool,
+                                   struct cpu_map *map,
+                                   perf_event__handler_t process,
+                                   struct machine *machine)
+{
+        struct cpu_map_event *event;
+        int err;
+
+        event = cpu_map_event__new(map);
+        if (!event)
+                return -ENOMEM;
+
+        err = process(tool, (union perf_event *) event, NULL, machine);
+
+        free(event);
+        return err;
+}
+
+int perf_event__synthesize_stat_config(struct perf_tool *tool,
+                                       struct perf_stat_config *config,
+                                       perf_event__handler_t process,
+                                       struct machine *machine)
+{
+        struct stat_config_event *event;
+        int size, i = 0, err;
+
+        size  = sizeof(*event);
+        size += (PERF_STAT_CONFIG_TERM__MAX * sizeof(event->data[0]));
+
+        event = zalloc(size);
+        if (!event)
+                return -ENOMEM;
+
+        event->header.type = PERF_RECORD_STAT_CONFIG;
+        event->header.size = size;
+        event->nr          = PERF_STAT_CONFIG_TERM__MAX;
+
+#define ADD(__term, __val)                                      \
+        event->data[i].tag = PERF_STAT_CONFIG_TERM__##__term;   \
+        event->data[i].val = __val;                             \
+        i++;
+
+        ADD(AGGR_MODE,  config->aggr_mode)
+        ADD(INTERVAL,   config->interval)
+        ADD(SCALE,      config->scale)
+
+        WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX,
+                  "stat config terms unbalanced\n");
+#undef ADD
+
+        err = process(tool, (union perf_event *) event, NULL, machine);
+
+        free(event);
+        return err;
+}
+
+int perf_event__synthesize_stat(struct perf_tool *tool,
+                                u32 cpu, u32 thread, u64 id,
+                                struct perf_counts_values *count,
+                                perf_event__handler_t process,
+                                struct machine *machine)
+{
+        struct stat_event event;
+
+        event.header.type = PERF_RECORD_STAT;
+        event.header.size = sizeof(event);
+        event.header.misc = 0;
+
+        event.id        = id;
+        event.cpu       = cpu;
+        event.thread    = thread;
+        event.val       = count->val;
+        event.ena       = count->ena;
+        event.run       = count->run;
+
+        return process(tool, (union perf_event *) &event, NULL, machine);
+}
+
+int perf_event__synthesize_stat_round(struct perf_tool *tool,
+                                      u64 evtime, u64 type,
+                                      perf_event__handler_t process,
+                                      struct machine *machine)
+{
+        struct stat_round_event event;
+
+        event.header.type = PERF_RECORD_STAT_ROUND;
+        event.header.size = sizeof(event);
+        event.header.misc = 0;
+
+        event.time = evtime;
+        event.type = type;
+
+        return process(tool, (union perf_event *) &event, NULL, machine);
+}
+
+void perf_event__read_stat_config(struct perf_stat_config *config,
+                                  struct stat_config_event *event)
+{
+        unsigned i;
+
+        for (i = 0; i < event->nr; i++) {
+
+                switch (event->data[i].tag) {
+#define CASE(__term, __val)                                     \
+                case PERF_STAT_CONFIG_TERM__##__term:           \
+                        config->__val = event->data[i].val;     \
+                        break;
+
+                CASE(AGGR_MODE, aggr_mode)
+                CASE(SCALE,     scale)
+                CASE(INTERVAL,  interval)
+#undef CASE
+                default:
+                        pr_warning("unknown stat config term %" PRIu64 "\n",
+                                   event->data[i].tag);
+                }
+        }
+}
+
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
 {
         const char *s;
@@ -783,6 +1059,38 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
                        event->mmap2.filename);
 }
 
+size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp)
+{
+        struct thread_map *threads = thread_map__new_event(&event->thread_map);
+        size_t ret;
+
+        ret = fprintf(fp, " nr: ");
+
+        if (threads)
+                ret += thread_map__fprintf(threads, fp);
+        else
+                ret += fprintf(fp, "failed to get threads from event\n");
+
+        thread_map__put(threads);
+        return ret;
+}
+
+size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp)
+{
+        struct cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data);
+        size_t ret;
+
+        ret = fprintf(fp, " nr: ");
+
+        if (cpus)
+                ret += cpu_map__fprintf(cpus, fp);
+        else
+                ret += fprintf(fp, "failed to get cpumap from event\n");
+
+        cpu_map__put(cpus);
+        return ret;
+}
+
 int perf_event__process_mmap(struct perf_tool *tool __maybe_unused,
                              union perf_event *event,
                              struct perf_sample *sample,
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index a0dbcbd4f6d8..b7ffb7ee9971 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -226,6 +226,12 @@ enum perf_user_event_type { /* above any possible kernel type */
         PERF_RECORD_AUXTRACE_INFO               = 70,
         PERF_RECORD_AUXTRACE                    = 71,
         PERF_RECORD_AUXTRACE_ERROR              = 72,
+        PERF_RECORD_THREAD_MAP                  = 73,
+        PERF_RECORD_CPU_MAP                     = 74,
+        PERF_RECORD_STAT_CONFIG                 = 75,
+        PERF_RECORD_STAT                        = 76,
+        PERF_RECORD_STAT_ROUND                  = 77,
+        PERF_RECORD_EVENT_UPDATE                = 78,
         PERF_RECORD_HEADER_MAX
 };
 
@@ -270,12 +276,61 @@ struct events_stats {
         u32 nr_proc_map_timeout;
 };
 
+enum {
+        PERF_CPU_MAP__CPUS = 0,
+        PERF_CPU_MAP__MASK = 1,
+};
+
+struct cpu_map_entries {
+        u16     nr;
+        u16     cpu[];
+};
+
+struct cpu_map_mask {
+        u16     nr;
+        u16     long_size;
+        unsigned long mask[];
+};
+
+struct cpu_map_data {
+        u16     type;
+        char    data[];
+};
+
+struct cpu_map_event {
+        struct perf_event_header        header;
+        struct cpu_map_data             data;
+};
+
 struct attr_event {
         struct perf_event_header header;
         struct perf_event_attr attr;
         u64 id[];
 };
 
+enum {
+        PERF_EVENT_UPDATE__UNIT  = 0,
+        PERF_EVENT_UPDATE__SCALE = 1,
+        PERF_EVENT_UPDATE__NAME  = 2,
+        PERF_EVENT_UPDATE__CPUS  = 3,
+};
+
+struct event_update_event_cpus {
+        struct cpu_map_data cpus;
+};
+
+struct event_update_event_scale {
+        double scale;
+};
+
+struct event_update_event {
+        struct perf_event_header header;
+        u64 type;
+        u64 id;
+
+        char data[];
+};
+
 #define MAX_EVENT_NAME 64
 
 struct perf_trace_event_type {
@@ -356,6 +411,63 @@ struct context_switch_event {
         u32 next_prev_tid;
 };
 
+struct thread_map_event_entry {
+        u64     pid;
+        char    comm[16];
+};
+
+struct thread_map_event {
+        struct perf_event_header        header;
+        u64                             nr;
+        struct thread_map_event_entry   entries[];
+};
+
+enum {
+        PERF_STAT_CONFIG_TERM__AGGR_MODE        = 0,
+        PERF_STAT_CONFIG_TERM__INTERVAL         = 1,
+        PERF_STAT_CONFIG_TERM__SCALE            = 2,
+        PERF_STAT_CONFIG_TERM__MAX              = 3,
+};
+
+struct stat_config_event_entry {
+        u64     tag;
+        u64     val;
+};
+
+struct stat_config_event {
+        struct perf_event_header        header;
+        u64                             nr;
+        struct stat_config_event_entry  data[];
+};
+
+struct stat_event {
+        struct perf_event_header        header;
+
+        u64     id;
+        u32     cpu;
+        u32     thread;
+
+        union {
+                struct {
+                        u64 val;
+                        u64 ena;
+                        u64 run;
+                };
+                u64 values[3];
+        };
+};
+
+enum {
+        PERF_STAT_ROUND_TYPE__INTERVAL  = 0,
+        PERF_STAT_ROUND_TYPE__FINAL     = 1,
+};
+
+struct stat_round_event {
+        struct perf_event_header        header;
+        u64                             type;
+        u64                             time;
+};
+
 union perf_event {
         struct perf_event_header        header;
         struct mmap_event               mmap;
@@ -368,6 +480,7 @@ union perf_event {
         struct throttle_event           throttle;
         struct sample_event             sample;
         struct attr_event               attr;
+        struct event_update_event       event_update;
         struct event_type_event         event_type;
         struct tracing_data_event       tracing_data;
         struct build_id_event           build_id;
@@ -378,12 +491,20 @@ union perf_event {
         struct aux_event                aux;
         struct itrace_start_event       itrace_start;
         struct context_switch_event     context_switch;
+        struct thread_map_event         thread_map;
+        struct cpu_map_event            cpu_map;
+        struct stat_config_event        stat_config;
+        struct stat_event               stat;
+        struct stat_round_event         stat_round;
 };
 
 void perf_event__print_totals(void);
 
 struct perf_tool;
 struct thread_map;
+struct cpu_map;
+struct perf_stat_config;
+struct perf_counts_values;
 
 typedef int (*perf_event__handler_t)(struct perf_tool *tool,
                                      union perf_event *event,
@@ -395,6 +516,14 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
                                       perf_event__handler_t process,
                                       struct machine *machine, bool mmap_data,
                                       unsigned int proc_map_timeout);
+int perf_event__synthesize_thread_map2(struct perf_tool *tool,
+                                      struct thread_map *threads,
+                                      perf_event__handler_t process,
+                                      struct machine *machine);
+int perf_event__synthesize_cpu_map(struct perf_tool *tool,
+                                   struct cpu_map *cpus,
+                                   perf_event__handler_t process,
+                                   struct machine *machine);
 int perf_event__synthesize_threads(struct perf_tool *tool,
                                    perf_event__handler_t process,
                                    struct machine *machine, bool mmap_data,
@@ -402,7 +531,21 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
                                        perf_event__handler_t process,
                                        struct machine *machine);
-
+int perf_event__synthesize_stat_config(struct perf_tool *tool,
+                                       struct perf_stat_config *config,
+                                       perf_event__handler_t process,
+                                       struct machine *machine);
+void perf_event__read_stat_config(struct perf_stat_config *config,
+                                  struct stat_config_event *event);
+int perf_event__synthesize_stat(struct perf_tool *tool,
+                                u32 cpu, u32 thread, u64 id,
+                                struct perf_counts_values *count,
+                                perf_event__handler_t process,
+                                struct machine *machine);
+int perf_event__synthesize_stat_round(struct perf_tool *tool,
+                                      u64 time, u64 type,
+                                      perf_event__handler_t process,
+                                      struct machine *machine);
 int perf_event__synthesize_modules(struct perf_tool *tool,
                                    perf_event__handler_t process,
                                    struct machine *machine);
@@ -499,9 +642,14 @@ size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 u64 kallsyms__get_function_start(const char *kallsyms_filename,
                                  const char *symbol_name);
 
+void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max);
+void  cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map,
+                               u16 type, int max);
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d1392194a9a9..d81f13de2476 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -18,7 +18,7 @@
 #include <unistd.h>
 
 #include "parse-events.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 
 #include <sys/mman.h>
 
@@ -68,6 +68,18 @@ struct perf_evlist *perf_evlist__new_default(void)
         return evlist;
 }
 
+struct perf_evlist *perf_evlist__new_dummy(void)
+{
+        struct perf_evlist *evlist = perf_evlist__new();
+
+        if (evlist && perf_evlist__add_dummy(evlist)) {
+                perf_evlist__delete(evlist);
+                evlist = NULL;
+        }
+
+        return evlist;
+}
+
 /**
  * perf_evlist__set_id_pos - set the positions of event ids.
  * @evlist: selected event list
@@ -248,6 +260,22 @@ error:
         return -ENOMEM;
 }
 
+int perf_evlist__add_dummy(struct perf_evlist *evlist)
+{
+        struct perf_event_attr attr = {
+                .type   = PERF_TYPE_SOFTWARE,
+                .config = PERF_COUNT_SW_DUMMY,
+                .size   = sizeof(attr), /* to capture ABI version */
+        };
+        struct perf_evsel *evsel = perf_evsel__new(&attr);
+
+        if (evsel == NULL)
+                return -ENOMEM;
+
+        perf_evlist__add(evlist, evsel);
+        return 0;
+}
+
 static int perf_evlist__add_attrs(struct perf_evlist *evlist,
                                   struct perf_event_attr *attrs, size_t nr_attrs)
 {
@@ -336,20 +364,12 @@ static int perf_evlist__nr_threads(struct perf_evlist *evlist,
 
 void perf_evlist__disable(struct perf_evlist *evlist)
 {
-        int cpu, thread;
         struct perf_evsel *pos;
-        int nr_cpus = cpu_map__nr(evlist->cpus);
-        int nr_threads;
 
-        for (cpu = 0; cpu < nr_cpus; cpu++) {
-                evlist__for_each(evlist, pos) {
-                        if (!perf_evsel__is_group_leader(pos) || !pos->fd)
-                                continue;
-                        nr_threads = perf_evlist__nr_threads(evlist, pos);
-                        for (thread = 0; thread < nr_threads; thread++)
-                                ioctl(FD(pos, cpu, thread),
-                                      PERF_EVENT_IOC_DISABLE, 0);
-                }
+        evlist__for_each(evlist, pos) {
+                if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+                        continue;
+                perf_evsel__disable(pos);
         }
 
         evlist->enabled = false;
@@ -357,20 +377,12 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 
 void perf_evlist__enable(struct perf_evlist *evlist)
 {
-        int cpu, thread;
         struct perf_evsel *pos;
-        int nr_cpus = cpu_map__nr(evlist->cpus);
-        int nr_threads;
 
-        for (cpu = 0; cpu < nr_cpus; cpu++) {
-                evlist__for_each(evlist, pos) {
-                        if (!perf_evsel__is_group_leader(pos) || !pos->fd)
-                                continue;
-                        nr_threads = perf_evlist__nr_threads(evlist, pos);
-                        for (thread = 0; thread < nr_threads; thread++)
-                                ioctl(FD(pos, cpu, thread),
-                                      PERF_EVENT_IOC_ENABLE, 0);
-                }
+        evlist__for_each(evlist, pos) {
+                if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+                        continue;
+                perf_evsel__enable(pos);
         }
 
         evlist->enabled = true;
@@ -381,48 +393,6 @@ void perf_evlist__toggle_enable(struct perf_evlist *evlist)
         (evlist->enabled ? perf_evlist__disable : perf_evlist__enable)(evlist);
 }
 
-int perf_evlist__disable_event(struct perf_evlist *evlist,
-                               struct perf_evsel *evsel)
-{
-        int cpu, thread, err;
-        int nr_cpus = cpu_map__nr(evlist->cpus);
-        int nr_threads = perf_evlist__nr_threads(evlist, evsel);
-
-        if (!evsel->fd)
-                return 0;
-
-        for (cpu = 0; cpu < nr_cpus; cpu++) {
-                for (thread = 0; thread < nr_threads; thread++) {
-                        err = ioctl(FD(evsel, cpu, thread),
-                                    PERF_EVENT_IOC_DISABLE, 0);
-                        if (err)
-                                return err;
-                }
-        }
-        return 0;
-}
-
-int perf_evlist__enable_event(struct perf_evlist *evlist,
-                              struct perf_evsel *evsel)
-{
-        int cpu, thread, err;
-        int nr_cpus = cpu_map__nr(evlist->cpus);
-        int nr_threads = perf_evlist__nr_threads(evlist, evsel);
-
-        if (!evsel->fd)
-                return -EINVAL;
-
-        for (cpu = 0; cpu < nr_cpus; cpu++) {
-                for (thread = 0; thread < nr_threads; thread++) {
-                        err = ioctl(FD(evsel, cpu, thread),
-                                    PERF_EVENT_IOC_ENABLE, 0);
-                        if (err)
-                                return err;
-                }
-        }
-        return 0;
-}
-
 static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist,
                                          struct perf_evsel *evsel, int cpu)
 {
@@ -550,9 +520,9 @@ void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
         evsel->id[evsel->ids++] = id;
 }
 
-static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
-                                  struct perf_evsel *evsel,
-                                  int cpu, int thread, int fd)
+int perf_evlist__id_add_fd(struct perf_evlist *evlist,
+                           struct perf_evsel *evsel,
+                           int cpu, int thread, int fd)
 {
         u64 read_data[4] = { 0, };
         int id_idx = 1; /* The first entry is the counter value */
@@ -1486,7 +1456,7 @@ int perf_evlist__open(struct perf_evlist *evlist)
         perf_evlist__update_id_pos(evlist);
 
         evlist__for_each(evlist, evsel) {
-                err = perf_evsel__open(evsel, evlist->cpus, evlist->threads);
+                err = perf_evsel__open(evsel, evsel->cpus, evsel->threads);
                 if (err < 0)
                         goto out_err;
         }
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index a459fe71b452..7c4d9a206776 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -67,6 +67,7 @@ struct perf_evsel_str_handler {
 
 struct perf_evlist *perf_evlist__new(void);
 struct perf_evlist *perf_evlist__new_default(void);
+struct perf_evlist *perf_evlist__new_dummy(void);
 void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
                        struct thread_map *threads);
 void perf_evlist__exit(struct perf_evlist *evlist);
@@ -81,6 +82,8 @@ int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
 #define perf_evlist__add_default_attrs(evlist, array) \
         __perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
 
+int perf_evlist__add_dummy(struct perf_evlist *evlist);
+
 int perf_evlist__add_newtp(struct perf_evlist *evlist,
                            const char *sys, const char *name, void *handler);
 
@@ -97,6 +100,9 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
 
 void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
                          int cpu, int thread, u64 id);
+int perf_evlist__id_add_fd(struct perf_evlist *evlist,
+                           struct perf_evsel *evsel,
+                           int cpu, int thread, int fd);
 
 int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
 int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);
@@ -149,10 +155,6 @@ void perf_evlist__disable(struct perf_evlist *evlist);
 void perf_evlist__enable(struct perf_evlist *evlist);
 void perf_evlist__toggle_enable(struct perf_evlist *evlist);
 
-int perf_evlist__disable_event(struct perf_evlist *evlist,
-                               struct perf_evsel *evsel);
-int perf_evlist__enable_event(struct perf_evlist *evlist,
-                              struct perf_evsel *evsel);
 int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
                                   struct perf_evsel *evsel, int idx);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 397fb4ed3c97..cdbaf9b51e42 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -36,6 +36,7 @@ static struct {
         bool cloexec;
         bool clockid;
         bool clockid_wrong;
+        bool lbr_flags;
 } perf_missing_features;
 
 static clockid_t clockid;
@@ -574,7 +575,9 @@ perf_evsel__config_callgraph(struct perf_evsel *evsel,
                         } else {
                                 perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
                                 attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER |
-                                                        PERF_SAMPLE_BRANCH_CALL_STACK;
+                                                        PERF_SAMPLE_BRANCH_CALL_STACK |
+                                                        PERF_SAMPLE_BRANCH_NO_CYCLES |
+                                                        PERF_SAMPLE_BRANCH_NO_FLAGS;
                         }
                 } else
                          pr_warning("Cannot use LBR callstack with branch stack. "
@@ -981,13 +984,26 @@ int perf_evsel__append_filter(struct perf_evsel *evsel,
         return -1;
 }
 
-int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads)
+int perf_evsel__enable(struct perf_evsel *evsel)
 {
+        int nthreads = thread_map__nr(evsel->threads);
+        int ncpus = cpu_map__nr(evsel->cpus);
+
         return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
                                      PERF_EVENT_IOC_ENABLE,
                                      0);
 }
 
+int perf_evsel__disable(struct perf_evsel *evsel)
+{
+        int nthreads = thread_map__nr(evsel->threads);
+        int ncpus = cpu_map__nr(evsel->cpus);
+
+        return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
+                                     PERF_EVENT_IOC_DISABLE,
+                                     0);
+}
+
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
         if (ncpus == 0 || nthreads == 0)
@@ -1192,6 +1208,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)
                 bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
                 bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
                 bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
+                bit_name(WEIGHT),
                 { .name = NULL, }
         };
 #undef bit_name
@@ -1323,6 +1340,9 @@ fallback_missing_features:
                 evsel->attr.mmap2 = 0;
         if (perf_missing_features.exclude_guest)
                 evsel->attr.exclude_guest = evsel->attr.exclude_host = 0;
+        if (perf_missing_features.lbr_flags)
+                evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
+                                     PERF_SAMPLE_BRANCH_NO_CYCLES);
 retry_sample_id:
         if (perf_missing_features.sample_id_all)
                 evsel->attr.sample_id_all = 0;
@@ -1441,6 +1461,12 @@ try_fallback:
         } else if (!perf_missing_features.sample_id_all) {
                 perf_missing_features.sample_id_all = true;
                 goto retry_sample_id;
+        } else if (!perf_missing_features.lbr_flags &&
+                        (evsel->attr.branch_sample_type &
+                         (PERF_SAMPLE_BRANCH_NO_CYCLES |
+                          PERF_SAMPLE_BRANCH_NO_FLAGS))) {
+                perf_missing_features.lbr_flags = true;
+                goto fallback_missing_features;
         }
 
 out_close:
@@ -2272,6 +2298,29 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
                 printed += comma_fprintf(fp, &first, " %s=%" PRIu64,
                                          term, (u64)evsel->attr.sample_freq);
         }
+
+        if (details->trace_fields) {
+                struct format_field *field;
+
+                if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+                        printed += comma_fprintf(fp, &first, " (not a tracepoint)");
+                        goto out;
+                }
+
+                field = evsel->tp_format->format.fields;
+                if (field == NULL) {
+                        printed += comma_fprintf(fp, &first, " (no trace field)");
+                        goto out;
+                }
+
+                printed += comma_fprintf(fp, &first, " trace_fields: %s", field->name);
+
+                field = field->next;
+                while (field) {
+                        printed += comma_fprintf(fp, &first, "%s", field->name);
+                        field = field->next;
+                }
+        }
 out:
         fputc('\n', fp);
         return ++printed;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 0e49bd742c63..8e75434bd01c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -227,7 +227,8 @@ int perf_evsel__append_filter(struct perf_evsel *evsel,
                               const char *op, const char *filter);
 int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
                              const char *filter);
-int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads);
+int perf_evsel__enable(struct perf_evsel *evsel);
+int perf_evsel__disable(struct perf_evsel *evsel);
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
                              struct cpu_map *cpus);
@@ -368,6 +369,7 @@ struct perf_attr_details {
         bool verbose;
         bool event_group;
         bool force;
+        bool trace_fields;
 };
 
 int perf_evsel__fprintf(struct perf_evsel *evsel,
diff --git a/tools/perf/util/exec_cmd.c b/tools/perf/util/exec_cmd.c
deleted file mode 100644
index 7adf4ad15d8f..000000000000
--- a/tools/perf/util/exec_cmd.c
+++ /dev/null
@@ -1,148 +0,0 @@
-#include "cache.h"
-#include "exec_cmd.h"
-#include "quote.h"
-
-#include <string.h>
-
-#define MAX_ARGS        32
-
-static const char *argv_exec_path;
-static const char *argv0_path;
-
-const char *system_path(const char *path)
-{
-        static const char *prefix = PREFIX;
-        struct strbuf d = STRBUF_INIT;
-
-        if (is_absolute_path(path))
-                return path;
-
-        strbuf_addf(&d, "%s/%s", prefix, path);
-        path = strbuf_detach(&d, NULL);
-        return path;
-}
-
-const char *perf_extract_argv0_path(const char *argv0)
-{
-        const char *slash;
-
-        if (!argv0 || !*argv0)
-                return NULL;
-        slash = argv0 + strlen(argv0);
-
-        while (argv0 <= slash && !is_dir_sep(*slash))
-                slash--;
-
-        if (slash >= argv0) {
-                argv0_path = strndup(argv0, slash - argv0);
-                return argv0_path ? slash + 1 : NULL;
-        }
-
-        return argv0;
-}
-
-void perf_set_argv_exec_path(const char *exec_path)
-{
-        argv_exec_path = exec_path;
-        /*
-         * Propagate this setting to external programs.
-         */
-        setenv(EXEC_PATH_ENVIRONMENT, exec_path, 1);
-}
-
-
-/* Returns the highest-priority, location to look for perf programs. */
-const char *perf_exec_path(void)
-{
-        const char *env;
-
-        if (argv_exec_path)
-                return argv_exec_path;
-
-        env = getenv(EXEC_PATH_ENVIRONMENT);
-        if (env && *env) {
-                return env;
-        }
-
-        return system_path(PERF_EXEC_PATH);
-}
-
-static void add_path(struct strbuf *out, const char *path)
-{
-        if (path && *path) {
-                if (is_absolute_path(path))
-                        strbuf_addstr(out, path);
-                else
-                        strbuf_addstr(out, make_nonrelative_path(path));
-
-                strbuf_addch(out, PATH_SEP);
-        }
-}
-
-void setup_path(void)
-{
-        const char *old_path = getenv("PATH");
-        struct strbuf new_path = STRBUF_INIT;
-
-        add_path(&new_path, perf_exec_path());
-        add_path(&new_path, argv0_path);
-
-        if (old_path)
-                strbuf_addstr(&new_path, old_path);
-        else
-                strbuf_addstr(&new_path, "/usr/local/bin:/usr/bin:/bin");
-
-        setenv("PATH", new_path.buf, 1);
-
-        strbuf_release(&new_path);
-}
-
-static const char **prepare_perf_cmd(const char **argv)
-{
-        int argc;
-        const char **nargv;
-
-        for (argc = 0; argv[argc]; argc++)
-                ; /* just counting */
-        nargv = malloc(sizeof(*nargv) * (argc + 2));
-
-        nargv[0] = "perf";
-        for (argc = 0; argv[argc]; argc++)
-                nargv[argc + 1] = argv[argc];
-        nargv[argc + 1] = NULL;
-        return nargv;
-}
-
-int execv_perf_cmd(const char **argv) {
-        const char **nargv = prepare_perf_cmd(argv);
-
-        /* execvp() can only ever return if it fails */
-        execvp("perf", (char **)nargv);
-
-        free(nargv);
-        return -1;
-}
-
-
-int execl_perf_cmd(const char *cmd,...)
-{
-        int argc;
-        const char *argv[MAX_ARGS + 1];
-        const char *arg;
-        va_list param;
-
-        va_start(param, cmd);
-        argv[0] = cmd;
-        argc = 1;
-        while (argc < MAX_ARGS) {
-                arg = argv[argc++] = va_arg(param, char *);
-                if (!arg)
-                        break;
-        }
-        va_end(param);
-        if (MAX_ARGS <= argc)
-                return error("too many args to run %s", cmd);
-
-        argv[argc] = NULL;
-        return execv_perf_cmd(argv);
-}
diff --git a/tools/perf/util/exec_cmd.h b/tools/perf/util/exec_cmd.h
deleted file mode 100644
index bc4b915963f5..000000000000
--- a/tools/perf/util/exec_cmd.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef __PERF_EXEC_CMD_H
-#define __PERF_EXEC_CMD_H
-
-extern void perf_set_argv_exec_path(const char *exec_path);
-extern const char *perf_extract_argv0_path(const char *path);
-extern const char *perf_exec_path(void);
-extern void setup_path(void);
-extern int execv_perf_cmd(const char **argv); /* NULL terminated */
-extern int execl_perf_cmd(const char *cmd, ...);
-extern const char *system_path(const char *path);
-
-#endif /* __PERF_EXEC_CMD_H */
diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh
index 36a885d2cd22..0ac2037c970c 100755
--- a/tools/perf/util/generate-cmdlist.sh
+++ b/tools/perf/util/generate-cmdlist.sh
@@ -36,4 +36,19 @@ do
      }' "Documentation/perf-$cmd.txt"
 done
 echo "#endif /* HAVE_LIBELF_SUPPORT */"
+
+echo "#ifdef HAVE_LIBAUDIT_SUPPORT"
+sed -n -e 's/^perf-\([^         ]*\)[   ].* audit*/\1/p' command-list.txt |
+sort |
+while read cmd
+do
+     sed -n '
+     /^NAME/,/perf-'"$cmd"'/H
+     ${
+            x
+            s/.*perf-'"$cmd"' - \(.*\)/  {"'"$cmd"'", "\1"},/
+            p
+     }' "Documentation/perf-$cmd.txt"
+done
+echo "#endif /* HAVE_LIBELF_SUPPORT */"
 echo "};"
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 43838003c1a1..f50b7235ecb6 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -724,7 +724,7 @@ static int write_numa_topology(int fd, struct perf_header *h __maybe_unused,
 done:
         free(buf);
         fclose(fp);
-        free(node_map);
+        cpu_map__put(node_map);
         return ret;
 }
 
@@ -868,6 +868,13 @@ static int write_auxtrace(int fd, struct perf_header *h,
         return err;
 }
 
+static int write_stat(int fd __maybe_unused,
+                      struct perf_header *h __maybe_unused,
+                      struct perf_evlist *evlist __maybe_unused)
+{
+        return 0;
+}
+
 static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
                            FILE *fp)
 {
@@ -1159,6 +1166,12 @@ static void print_auxtrace(struct perf_header *ph __maybe_unused,
         fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n");
 }
 
+static void print_stat(struct perf_header *ph __maybe_unused,
+                       int fd __maybe_unused, FILE *fp)
+{
+        fprintf(fp, "# contains stat data\n");
+}
+
 static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
                                FILE *fp)
 {
@@ -1948,6 +1961,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
         FEAT_OPP(HEADER_PMU_MAPPINGS,   pmu_mappings),
         FEAT_OPP(HEADER_GROUP_DESC,     group_desc),
         FEAT_OPP(HEADER_AUXTRACE,       auxtrace),
+        FEAT_OPA(HEADER_STAT,           stat),
 };
 
 struct header_print_data {
@@ -2686,6 +2700,152 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
         return err;
 }
 
+static struct event_update_event *
+event_update_event__new(size_t size, u64 type, u64 id)
+{
+        struct event_update_event *ev;
+
+        size += sizeof(*ev);
+        size  = PERF_ALIGN(size, sizeof(u64));
+
+        ev = zalloc(size);
+        if (ev) {
+                ev->header.type = PERF_RECORD_EVENT_UPDATE;
+                ev->header.size = (u16)size;
+                ev->type = type;
+                ev->id = id;
+        }
+        return ev;
+}
+
+int
+perf_event__synthesize_event_update_unit(struct perf_tool *tool,
+                                         struct perf_evsel *evsel,
+                                         perf_event__handler_t process)
+{
+        struct event_update_event *ev;
+        size_t size = strlen(evsel->unit);
+        int err;
+
+        ev = event_update_event__new(size + 1, PERF_EVENT_UPDATE__UNIT, evsel->id[0]);
+        if (ev == NULL)
+                return -ENOMEM;
+
+        strncpy(ev->data, evsel->unit, size);
+        err = process(tool, (union perf_event *)ev, NULL, NULL);
+        free(ev);
+        return err;
+}
+
+int
+perf_event__synthesize_event_update_scale(struct perf_tool *tool,
+                                          struct perf_evsel *evsel,
+                                          perf_event__handler_t process)
+{
+        struct event_update_event *ev;
+        struct event_update_event_scale *ev_data;
+        int err;
+
+        ev = event_update_event__new(sizeof(*ev_data), PERF_EVENT_UPDATE__SCALE, evsel->id[0]);
+        if (ev == NULL)
+                return -ENOMEM;
+
+        ev_data = (struct event_update_event_scale *) ev->data;
+        ev_data->scale = evsel->scale;
+        err = process(tool, (union perf_event*) ev, NULL, NULL);
+        free(ev);
+        return err;
+}
+
+int
+perf_event__synthesize_event_update_name(struct perf_tool *tool,
+                                         struct perf_evsel *evsel,
+                                         perf_event__handler_t process)
+{
+        struct event_update_event *ev;
+        size_t len = strlen(evsel->name);
+        int err;
+
+        ev = event_update_event__new(len + 1, PERF_EVENT_UPDATE__NAME, evsel->id[0]);
+        if (ev == NULL)
+                return -ENOMEM;
+
+        strncpy(ev->data, evsel->name, len);
+        err = process(tool, (union perf_event*) ev, NULL, NULL);
+        free(ev);
+        return err;
+}
+
+int
+perf_event__synthesize_event_update_cpus(struct perf_tool *tool,
+                                        struct perf_evsel *evsel,
+                                        perf_event__handler_t process)
+{
+        size_t size = sizeof(struct event_update_event);
+        struct event_update_event *ev;
+        int max, err;
+        u16 type;
+
+        if (!evsel->own_cpus)
+                return 0;
+
+        ev = cpu_map_data__alloc(evsel->own_cpus, &size, &type, &max);
+        if (!ev)
+                return -ENOMEM;
+
+        ev->header.type = PERF_RECORD_EVENT_UPDATE;
+        ev->header.size = (u16)size;
+        ev->type = PERF_EVENT_UPDATE__CPUS;
+        ev->id   = evsel->id[0];
+
+        cpu_map_data__synthesize((struct cpu_map_data *) ev->data,
+                                 evsel->own_cpus,
+                                 type, max);
+
+        err = process(tool, (union perf_event*) ev, NULL, NULL);
+        free(ev);
+        return err;
+}
+
+size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
+{
+        struct event_update_event *ev = &event->event_update;
+        struct event_update_event_scale *ev_scale;
+        struct event_update_event_cpus *ev_cpus;
+        struct cpu_map *map;
+        size_t ret;
+
+        ret = fprintf(fp, "\n... id:    %" PRIu64 "\n", ev->id);
+
+        switch (ev->type) {
+        case PERF_EVENT_UPDATE__SCALE:
+                ev_scale = (struct event_update_event_scale *) ev->data;
+                ret += fprintf(fp, "... scale: %f\n", ev_scale->scale);
+                break;
+        case PERF_EVENT_UPDATE__UNIT:
+                ret += fprintf(fp, "... unit:  %s\n", ev->data);
+                break;
+        case PERF_EVENT_UPDATE__NAME:
+                ret += fprintf(fp, "... name:  %s\n", ev->data);
+                break;
+        case PERF_EVENT_UPDATE__CPUS:
+                ev_cpus = (struct event_update_event_cpus *) ev->data;
+                ret += fprintf(fp, "... ");
+
+                map = cpu_map__new_data(&ev_cpus->cpus);
+                if (map)
+                        ret += cpu_map__fprintf(map, fp);
+                else
+                        ret += fprintf(fp, "failed to get cpus\n");
+                break;
+        default:
+                ret += fprintf(fp, "... unknown type\n");
+                break;
+        }
+
+        return ret;
+}
+
 int perf_event__synthesize_attrs(struct perf_tool *tool,
                                    struct perf_session *session,
                                    perf_event__handler_t process)
@@ -2745,6 +2905,51 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
+int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
+                                     union perf_event *event,
+                                     struct perf_evlist **pevlist)
+{
+        struct event_update_event *ev = &event->event_update;
+        struct event_update_event_scale *ev_scale;
+        struct event_update_event_cpus *ev_cpus;
+        struct perf_evlist *evlist;
+        struct perf_evsel *evsel;
+        struct cpu_map *map;
+
+        if (!pevlist || *pevlist == NULL)
+                return -EINVAL;
+
+        evlist = *pevlist;
+
+        evsel = perf_evlist__id2evsel(evlist, ev->id);
+        if (evsel == NULL)
+                return -EINVAL;
+
+        switch (ev->type) {
+        case PERF_EVENT_UPDATE__UNIT:
+                evsel->unit = strdup(ev->data);
+                break;
+        case PERF_EVENT_UPDATE__NAME:
+                evsel->name = strdup(ev->data);
+                break;
+        case PERF_EVENT_UPDATE__SCALE:
+                ev_scale = (struct event_update_event_scale *) ev->data;
+                evsel->scale = ev_scale->scale;
+        case PERF_EVENT_UPDATE__CPUS:
+                ev_cpus = (struct event_update_event_cpus *) ev->data;
+
+                map = cpu_map__new_data(&ev_cpus->cpus);
+                if (map)
+                        evsel->own_cpus = map;
+                else
+                        pr_err("failed to get event_update cpus\n");
+        default:
+                break;
+        }
+
+        return 0;
+}
+
 int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
                                         struct perf_evlist *evlist,
                                         perf_event__handler_t process)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 05f27cb6b7e3..cff9892452ee 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -31,6 +31,7 @@ enum {
         HEADER_PMU_MAPPINGS,
         HEADER_GROUP_DESC,
         HEADER_AUXTRACE,
+        HEADER_STAT,
         HEADER_LAST_FEATURE,
         HEADER_FEAT_BITS        = 256,
 };
@@ -105,8 +106,24 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
 int perf_event__synthesize_attrs(struct perf_tool *tool,
                                  struct perf_session *session,
                                  perf_event__handler_t process);
+int perf_event__synthesize_event_update_unit(struct perf_tool *tool,
+                                             struct perf_evsel *evsel,
+                                             perf_event__handler_t process);
+int perf_event__synthesize_event_update_scale(struct perf_tool *tool,
+                                              struct perf_evsel *evsel,
+                                              perf_event__handler_t process);
+int perf_event__synthesize_event_update_name(struct perf_tool *tool,
+                                             struct perf_evsel *evsel,
+                                             perf_event__handler_t process);
+int perf_event__synthesize_event_update_cpus(struct perf_tool *tool,
+                                             struct perf_evsel *evsel,
+                                             perf_event__handler_t process);
 int perf_event__process_attr(struct perf_tool *tool, union perf_event *event,
                              struct perf_evlist **pevlist);
+int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
+                                     union perf_event *event,
+                                     struct perf_evlist **pevlist);
+size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp);
 
 int perf_event__synthesize_tracing_data(struct perf_tool *tool,
                                         int fd, struct perf_evlist *evlist,
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
new file mode 100644
index 000000000000..dc1e41c9b054
--- /dev/null
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -0,0 +1,103 @@
+#include "cache.h"
+#include <subcmd/help.h>
+#include "../builtin.h"
+#include "levenshtein.h"
+
+static int autocorrect;
+static struct cmdnames aliases;
+
+static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
+{
+        if (!strcmp(var, "help.autocorrect"))
+                autocorrect = perf_config_int(var,value);
+        /* Also use aliases for command lookup */
+        if (!prefixcmp(var, "alias."))
+                add_cmdname(&aliases, var + 6, strlen(var + 6));
+
+        return perf_default_config(var, value, cb);
+}
+
+static int levenshtein_compare(const void *p1, const void *p2)
+{
+        const struct cmdname *const *c1 = p1, *const *c2 = p2;
+        const char *s1 = (*c1)->name, *s2 = (*c2)->name;
+        int l1 = (*c1)->len;
+        int l2 = (*c2)->len;
+        return l1 != l2 ? l1 - l2 : strcmp(s1, s2);
+}
+
+static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
+{
+        unsigned int i;
+
+        ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc);
+
+        for (i = 0; i < old->cnt; i++)
+                cmds->names[cmds->cnt++] = old->names[i];
+        zfree(&old->names);
+        old->cnt = 0;
+}
+
+const char *help_unknown_cmd(const char *cmd)
+{
+        unsigned int i, n = 0, best_similarity = 0;
+        struct cmdnames main_cmds, other_cmds;
+
+        memset(&main_cmds, 0, sizeof(main_cmds));
+        memset(&other_cmds, 0, sizeof(main_cmds));
+        memset(&aliases, 0, sizeof(aliases));
+
+        perf_config(perf_unknown_cmd_config, NULL);
+
+        load_command_list("perf-", &main_cmds, &other_cmds);
+
+        add_cmd_list(&main_cmds, &aliases);
+        add_cmd_list(&main_cmds, &other_cmds);
+        qsort(main_cmds.names, main_cmds.cnt,
+              sizeof(main_cmds.names), cmdname_compare);
+        uniq(&main_cmds);
+
+        if (main_cmds.cnt) {
+                /* This reuses cmdname->len for similarity index */
+                for (i = 0; i < main_cmds.cnt; ++i)
+                        main_cmds.names[i]->len =
+                                levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4);
+
+                qsort(main_cmds.names, main_cmds.cnt,
+                      sizeof(*main_cmds.names), levenshtein_compare);
+
+                best_similarity = main_cmds.names[0]->len;
+                n = 1;
+                while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len)
+                        ++n;
+        }
+
+        if (autocorrect && n == 1) {
+                const char *assumed = main_cmds.names[0]->name;
+
+                main_cmds.names[0] = NULL;
+                clean_cmdnames(&main_cmds);
+                fprintf(stderr, "WARNING: You called a perf program named '%s', "
+                        "which does not exist.\n"
+                        "Continuing under the assumption that you meant '%s'\n",
+                        cmd, assumed);
+                if (autocorrect > 0) {
+                        fprintf(stderr, "in %0.1f seconds automatically...\n",
+                                (float)autocorrect/10.0);
+                        poll(NULL, 0, autocorrect * 100);
+                }
+                return assumed;
+        }
+
+        fprintf(stderr, "perf: '%s' is not a perf-command. See 'perf --help'.\n", cmd);
+
+        if (main_cmds.cnt && best_similarity < 6) {
+                fprintf(stderr, "\nDid you mean %s?\n",
+                        n < 2 ? "this": "one of these");
+
+                for (i = 0; i < n; i++)
+                        fprintf(stderr, "\t%s\n", main_cmds.names[i]->name);
+        }
+
+        exit(1);
+}
diff --git a/tools/perf/util/help-unknown-cmd.h b/tools/perf/util/help-unknown-cmd.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/perf/util/help-unknown-cmd.h
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 4fd37d6708cb..c226303e3da0 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -254,6 +254,7 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
         he_stat__decay(&he->stat);
         if (symbol_conf.cumulate_callchain)
                 he_stat__decay(he->stat_acc);
+        decay_callchain(he->callchain);
 
         diff = prev_period - he->stat.period;
 
@@ -270,6 +271,8 @@ static void hists__delete_entry(struct hists *hists, struct hist_entry *he)
 
         if (sort__need_collapse)
                 rb_erase(&he->rb_node_in, &hists->entries_collapsed);
+        else
+                rb_erase(&he->rb_node_in, hists->entries_in);
 
         --hists->nr_entries;
         if (!he->filtered)
@@ -367,6 +370,25 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
                 if (symbol_conf.use_callchain)
                         callchain_init(he->callchain);
 
+                if (he->raw_data) {
+                        he->raw_data = memdup(he->raw_data, he->raw_size);
+
+                        if (he->raw_data == NULL) {
+                                map__put(he->ms.map);
+                                if (he->branch_info) {
+                                        map__put(he->branch_info->from.map);
+                                        map__put(he->branch_info->to.map);
+                                        free(he->branch_info);
+                                }
+                                if (he->mem_info) {
+                                        map__put(he->mem_info->iaddr.map);
+                                        map__put(he->mem_info->daddr.map);
+                                }
+                                free(he->stat_acc);
+                                free(he);
+                                return NULL;
+                        }
+                }
                 INIT_LIST_HEAD(&he->pairs.node);
                 thread__get(he->thread);
         }
@@ -459,7 +481,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
                                       struct symbol *sym_parent,
                                       struct branch_info *bi,
                                       struct mem_info *mi,
-                                      u64 period, u64 weight, u64 transaction,
+                                      struct perf_sample *sample,
                                       bool sample_self)
 {
         struct hist_entry entry = {
@@ -476,15 +498,17 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
                 .level   = al->level,
                 .stat = {
                         .nr_events = 1,
-                        .period = period,
-                        .weight = weight,
+                        .period = sample->period,
+                        .weight = sample->weight,
                 },
                 .parent = sym_parent,
                 .filtered = symbol__parent_filter(sym_parent) | al->filtered,
                 .hists  = hists,
                 .branch_info = bi,
                 .mem_info = mi,
-                .transaction = transaction,
+                .transaction = sample->transaction,
+                .raw_data = sample->raw_data,
+                .raw_size = sample->raw_size,
         };
 
         return hists__findnew_entry(hists, &entry, al, sample_self);
@@ -524,12 +548,13 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al
         u64 cost;
         struct mem_info *mi = iter->priv;
         struct hists *hists = evsel__hists(iter->evsel);
+        struct perf_sample *sample = iter->sample;
         struct hist_entry *he;
 
         if (mi == NULL)
                 return -EINVAL;
 
-        cost = iter->sample->weight;
+        cost = sample->weight;
         if (!cost)
                 cost = 1;
 
@@ -540,8 +565,10 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al
          * and this is indirectly achieved by passing period=weight here
          * and the he_stat__add_period() function.
          */
+        sample->period = cost;
+
         he = __hists__add_entry(hists, al, iter->parent, NULL, mi,
-                                cost, cost, 0, true);
+                                sample, true);
         if (!he)
                 return -ENOMEM;
 
@@ -628,6 +655,7 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
         struct branch_info *bi;
         struct perf_evsel *evsel = iter->evsel;
         struct hists *hists = evsel__hists(evsel);
+        struct perf_sample *sample = iter->sample;
         struct hist_entry *he = NULL;
         int i = iter->curr;
         int err = 0;
@@ -641,9 +669,11 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
          * The report shows the percentage of total branches captured
          * and not events sampled. Thus we use a pseudo period of 1.
          */
+        sample->period = 1;
+        sample->weight = bi->flags.cycles ? bi->flags.cycles : 1;
+
         he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL,
-                                1, bi->flags.cycles ? bi->flags.cycles : 1,
-                                0, true);
+                                sample, true);
         if (he == NULL)
                 return -ENOMEM;
 
@@ -680,8 +710,7 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location
         struct hist_entry *he;
 
         he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
-                                sample->period, sample->weight,
-                                sample->transaction, true);
+                                sample, true);
         if (he == NULL)
                 return -ENOMEM;
 
@@ -742,8 +771,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
         int err = 0;
 
         he = __hists__add_entry(hists, al, iter->parent, NULL, NULL,
-                                sample->period, sample->weight,
-                                sample->transaction, true);
+                                sample, true);
         if (he == NULL)
                 return -ENOMEM;
 
@@ -795,6 +823,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
                         .sym = al->sym,
                 },
                 .parent = iter->parent,
+                .raw_data = sample->raw_data,
+                .raw_size = sample->raw_size,
         };
         int i;
         struct callchain_cursor cursor;
@@ -816,8 +846,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
         }
 
         he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
-                                sample->period, sample->weight,
-                                sample->transaction, false);
+                                sample, false);
         if (he == NULL)
                 return -ENOMEM;
 
@@ -924,9 +953,6 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
         int64_t cmp = 0;
 
         perf_hpp__for_each_sort_list(fmt) {
-                if (perf_hpp__should_skip(fmt))
-                        continue;
-
                 cmp = fmt->cmp(fmt, left, right);
                 if (cmp)
                         break;
@@ -942,9 +968,6 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
         int64_t cmp = 0;
 
         perf_hpp__for_each_sort_list(fmt) {
-                if (perf_hpp__should_skip(fmt))
-                        continue;
-
                 cmp = fmt->collapse(fmt, left, right);
                 if (cmp)
                         break;
@@ -975,6 +998,8 @@ void hist_entry__delete(struct hist_entry *he)
         if (he->srcfile && he->srcfile[0])
                 free(he->srcfile);
         free_callchain(he->callchain);
+        free(he->trace_output);
+        free(he->raw_data);
         free(he);
 }
 
@@ -982,9 +1007,8 @@ void hist_entry__delete(struct hist_entry *he)
  * collapse the histogram
  */
 
-static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
-                                         struct rb_root *root,
-                                         struct hist_entry *he)
+bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
+                                  struct rb_root *root, struct hist_entry *he)
 {
         struct rb_node **p = &root->rb_node;
         struct rb_node *parent = NULL;
@@ -1024,7 +1048,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
         return true;
 }
 
-static struct rb_root *hists__get_rotate_entries_in(struct hists *hists)
+struct rb_root *hists__get_rotate_entries_in(struct hists *hists)
 {
         struct rb_root *root;
 
@@ -1088,7 +1112,7 @@ static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
         int64_t cmp = 0;
 
         perf_hpp__for_each_sort_list(fmt) {
-                if (perf_hpp__should_skip(fmt))
+                if (perf_hpp__should_skip(fmt, a->hists))
                         continue;
 
                 cmp = fmt->sort(fmt, a, b);
@@ -1559,10 +1583,8 @@ int perf_hist_config(const char *var, const char *value)
         return 0;
 }
 
-static int hists_evsel__init(struct perf_evsel *evsel)
+int __hists__init(struct hists *hists)
 {
-        struct hists *hists = evsel__hists(evsel);
-
         memset(hists, 0, sizeof(*hists));
         hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
         hists->entries_in = &hists->entries_in_array[0];
@@ -1573,6 +1595,43 @@ static int hists_evsel__init(struct perf_evsel *evsel)
         return 0;
 }
 
+static void hists__delete_remaining_entries(struct rb_root *root)
+{
+        struct rb_node *node;
+        struct hist_entry *he;
+
+        while (!RB_EMPTY_ROOT(root)) {
+                node = rb_first(root);
+                rb_erase(node, root);
+
+                he = rb_entry(node, struct hist_entry, rb_node_in);
+                hist_entry__delete(he);
+        }
+}
+
+static void hists__delete_all_entries(struct hists *hists)
+{
+        hists__delete_entries(hists);
+        hists__delete_remaining_entries(&hists->entries_in_array[0]);
+        hists__delete_remaining_entries(&hists->entries_in_array[1]);
+        hists__delete_remaining_entries(&hists->entries_collapsed);
+}
+
+static void hists_evsel__exit(struct perf_evsel *evsel)
+{
+        struct hists *hists = evsel__hists(evsel);
+
+        hists__delete_all_entries(hists);
+}
+
+static int hists_evsel__init(struct perf_evsel *evsel)
+{
+        struct hists *hists = evsel__hists(evsel);
+
+        __hists__init(hists);
+        return 0;
+}
+
 /*
  * XXX We probably need a hists_evsel__exit() to free the hist_entries
  * stored in the rbtree...
@@ -1581,7 +1640,8 @@ static int hists_evsel__init(struct perf_evsel *evsel)
 int hists__init(void)
 {
         int err = perf_evsel__object_config(sizeof(struct hists_evsel),
-                                            hists_evsel__init, NULL);
+                                            hists_evsel__init,
+                                            hists_evsel__exit);
         if (err)
                 fputs("FATAL ERROR: Couldn't setup hists class\n", stderr);
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index a48a2078d288..d4ec4822a103 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -52,6 +52,7 @@ enum hist_column {
         HISTC_MEM_IADDR_SYMBOL,
         HISTC_TRANSACTION,
         HISTC_CYCLES,
+        HISTC_TRACE,
         HISTC_NR_COLS, /* Last entry */
 };
 
@@ -114,8 +115,8 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
                                       struct addr_location *al,
                                       struct symbol *parent,
                                       struct branch_info *bi,
-                                      struct mem_info *mi, u64 period,
-                                      u64 weight, u64 transaction,
+                                      struct mem_info *mi,
+                                      struct perf_sample *sample,
                                       bool sample_self);
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
                          int max_stack_depth, void *arg);
@@ -184,6 +185,11 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel)
 }
 
 int hists__init(void);
+int __hists__init(struct hists *hists);
+
+struct rb_root *hists__get_rotate_entries_in(struct hists *hists);
+bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
+                                  struct rb_root *root, struct hist_entry *he);
 
 struct perf_hpp {
         char *buf;
@@ -261,10 +267,20 @@ void perf_hpp__append_sort_keys(void);
 
 bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
 bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
+bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *format);
+bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists);
 
-static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
+static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format,
+                                         struct hists *hists)
 {
-        return format->elide;
+        if (format->elide)
+                return true;
+
+        if (perf_hpp__is_dynamic_entry(format) &&
+            !perf_hpp__defined_dynamic_entry(format, hists))
+                return true;
+
+        return false;
 }
 
 void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h
deleted file mode 100644
index 6f19c548ecc0..000000000000
--- a/tools/perf/util/include/linux/string.h
+++ /dev/null
@@ -1,3 +0,0 @@
-#include <string.h>
-
-void *memdup(const void *src, size_t len);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 97f963a3dcb9..81a2eb77ba7f 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1744,7 +1744,7 @@ static void intel_pt_free(struct perf_session *session)
         auxtrace_heap__free(&pt->heap);
         intel_pt_free_events(session);
         session->auxtrace = NULL;
-        thread__delete(pt->unknown_thread);
+        thread__put(pt->unknown_thread);
         free(pt);
 }
 
@@ -2153,7 +2153,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
         return 0;
 
 err_delete_thread:
-        thread__delete(pt->unknown_thread);
+        thread__zput(pt->unknown_thread);
 err_free_queues:
         intel_pt_log_disable();
         auxtrace_queues__free(&pt->queues);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 8b303ff20289..ad79297c76c8 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -25,6 +25,7 @@ static void dsos__init(struct dsos *dsos)
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
+        memset(machine, 0, sizeof(*machine));
         map_groups__init(&machine->kmaps, machine);
         RB_CLEAR_NODE(&machine->rb_node);
         dsos__init(&machine->dsos);
@@ -44,6 +45,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
         machine->comm_exec = false;
         machine->kernel_start = 0;
 
+        memset(machine->vmlinux_maps, 0, sizeof(machine->vmlinux_maps));
+
         machine->root_dir = strdup(root_dir);
         if (machine->root_dir == NULL)
                 return -ENOMEM;
@@ -122,6 +125,7 @@ void machine__delete_threads(struct machine *machine)
 
 void machine__exit(struct machine *machine)
 {
+        machine__destroy_kernel_maps(machine);
         map_groups__exit(&machine->kmaps);
         dsos__exit(&machine->dsos);
         machine__exit_vdso(machine);
@@ -348,13 +352,18 @@ static void machine__update_thread_pid(struct machine *machine,
         }
 
         th->mg = map_groups__get(leader->mg);
-
+out_put:
+        thread__put(leader);
         return;
-
 out_err:
         pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid);
+        goto out_put;
 }
 
+/*
+ * Caller must eventually drop thread->refcnt returned with a successfull
+ * lookup/new thread inserted.
+ */
 static struct thread *____machine__findnew_thread(struct machine *machine,
                                                   pid_t pid, pid_t tid,
                                                   bool create)
@@ -372,7 +381,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
         if (th != NULL) {
                 if (th->tid == tid) {
                         machine__update_thread_pid(machine, th, pid);
-                        return th;
+                        return thread__get(th);
                 }
 
                 machine->last_match = NULL;
@@ -385,7 +394,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
                 if (th->tid == tid) {
                         machine->last_match = th;
                         machine__update_thread_pid(machine, th, pid);
-                        return th;
+                        return thread__get(th);
                 }
 
                 if (tid < th->tid)
@@ -413,7 +422,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
                 if (thread__init_map_groups(th, machine)) {
                         rb_erase_init(&th->rb_node, &machine->threads);
                         RB_CLEAR_NODE(&th->rb_node);
-                        thread__delete(th);
+                        thread__put(th);
                         return NULL;
                 }
                 /*
@@ -437,7 +446,7 @@ struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
         struct thread *th;
 
         pthread_rwlock_wrlock(&machine->threads_lock);
-        th = thread__get(__machine__findnew_thread(machine, pid, tid));
+        th = __machine__findnew_thread(machine, pid, tid);
         pthread_rwlock_unlock(&machine->threads_lock);
         return th;
 }
@@ -447,7 +456,7 @@ struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 {
         struct thread *th;
         pthread_rwlock_rdlock(&machine->threads_lock);
-        th =  thread__get(____machine__findnew_thread(machine, pid, tid, false));
+        th =  ____machine__findnew_thread(machine, pid, tid, false);
         pthread_rwlock_unlock(&machine->threads_lock);
         return th;
 }
@@ -560,11 +569,29 @@ int machine__process_switch_event(struct machine *machine __maybe_unused,
         return 0;
 }
 
+static void dso__adjust_kmod_long_name(struct dso *dso, const char *filename)
+{
+        const char *dup_filename;
+
+        if (!filename || !dso || !dso->long_name)
+                return;
+        if (dso->long_name[0] != '[')
+                return;
+        if (!strchr(filename, '/'))
+                return;
+
+        dup_filename = strdup(filename);
+        if (!dup_filename)
+                return;
+
+        dso__set_long_name(dso, dup_filename, true);
+}
+
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
                                         const char *filename)
 {
         struct map *map = NULL;
-        struct dso *dso;
+        struct dso *dso = NULL;
         struct kmod_path m;
 
         if (kmod_path__parse_name(&m, filename))
@@ -572,8 +599,15 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 
         map = map_groups__find_by_name(&machine->kmaps, MAP__FUNCTION,
                                        m.name);
-        if (map)
+        if (map) {
+                /*
+                 * If the map's dso is an offline module, give dso__load()
+                 * a chance to find the file path of that module by fixing
+                 * long_name.
+                 */
+                dso__adjust_kmod_long_name(map->dso, filename);
                 goto out;
+        }
 
         dso = machine__findnew_module_dso(machine, &m, filename);
         if (dso == NULL)
@@ -585,7 +619,11 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 
         map_groups__insert(&machine->kmaps, map);
 
+        /* Put the map here because map_groups__insert alread got it */
+        map__put(map);
 out:
+        /* put the dso here, corresponding to  machine__findnew_module_dso */
+        dso__put(dso);
         free(m.name);
         return map;
 }
@@ -740,6 +778,9 @@ int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
         enum map_type type;
         u64 start = machine__get_running_kernel_start(machine, NULL);
 
+        /* In case of renewal the kernel map, destroy previous one */
+        machine__destroy_kernel_maps(machine);
+
         for (type = 0; type < MAP__NR_TYPES; ++type) {
                 struct kmap *kmap;
                 struct map *map;
@@ -788,6 +829,7 @@ void machine__destroy_kernel_maps(struct machine *machine)
                                 kmap->ref_reloc_sym = NULL;
                 }
 
+                map__put(machine->vmlinux_maps[type]);
                 machine->vmlinux_maps[type] = NULL;
         }
 }
@@ -1084,11 +1126,14 @@ int machine__create_kernel_maps(struct machine *machine)
         struct dso *kernel = machine__get_kernel(machine);
         const char *name;
         u64 addr = machine__get_running_kernel_start(machine, &name);
-        if (!addr)
+        int ret;
+
+        if (!addr || kernel == NULL)
                 return -1;
 
-        if (kernel == NULL ||
-            __machine__create_kernel_maps(machine, kernel) < 0)
+        ret = __machine__create_kernel_maps(machine, kernel);
+        dso__put(kernel);
+        if (ret < 0)
                 return -1;
 
         if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
@@ -1609,6 +1654,8 @@ static int add_callchain_ip(struct thread *thread,
                 }
         }
 
+        if (symbol_conf.hide_unresolved && al.sym == NULL)
+                return 0;
         return callchain_cursor_append(&callchain_cursor, al.addr, al.map, al.sym);
 }
 
@@ -1863,6 +1910,9 @@ check_calls:
 static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
         struct callchain_cursor *cursor = arg;
+
+        if (symbol_conf.hide_unresolved && entry->sym == NULL)
+                return 0;
         return callchain_cursor_append(cursor, entry->ip,
                                        entry->map, entry->sym);
 }
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index afc6b56cf749..171b6d10a04b 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -26,8 +26,8 @@ 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)");
+               !strncmp(filename, "/dev/zero", sizeof("/dev/zero") - 1) ||
+               !strncmp(filename, "/anon_hugepage", sizeof("/anon_hugepage") - 1);
 }
 
 static inline int is_no_dso_memory(const char *filename)
@@ -691,6 +691,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
                         __map_groups__insert(pos->groups, before);
                         if (verbose >= 2)
                                 map__fprintf(before, fp);
+                        map__put(before);
                 }
 
                 if (map->end < pos->end) {
@@ -705,6 +706,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
                         __map_groups__insert(pos->groups, after);
                         if (verbose >= 2)
                                 map__fprintf(after, fp);
+                        map__put(after);
                 }
 put_map:
                 map__put(pos);
@@ -742,6 +744,7 @@ int map_groups__clone(struct map_groups *mg,
                 if (new == NULL)
                         goto out_unlock;
                 map_groups__insert(mg, new);
+                map__put(new);
         }
 
         err = 0;
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
index 355eecf6bf59..afc088dd7d20 100644
--- a/tools/perf/util/parse-branch-options.c
+++ b/tools/perf/util/parse-branch-options.c
@@ -1,7 +1,7 @@
 #include "perf.h"
 #include "util/util.h"
 #include "util/debug.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-branch-options.h"
 
 #define BRANCH_OPT(n, m) \
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 6fc8cd753e1a..4f7b0efdde2f 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -4,9 +4,9 @@
 #include "../perf.h"
 #include "evlist.h"
 #include "evsel.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 #include "parse-events.h"
-#include "exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "string.h"
 #include "symbol.h"
 #include "cache.h"
diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c
index 4f2c1c255d81..646ecf736aad 100644
--- a/tools/perf/util/parse-regs-options.c
+++ b/tools/perf/util/parse-regs-options.c
@@ -1,7 +1,7 @@
 #include "perf.h"
 #include "util/util.h"
 #include "util/debug.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-regs-options.h"
 
 int
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index 5d13cb45b317..3654d964e49d 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -22,24 +22,6 @@ static const char *get_perf_dir(void)
         return ".";
 }
 
-/*
- * If libc has strlcpy() then that version will override this
- * implementation:
- */
-size_t __weak strlcpy(char *dest, const char *src, size_t size)
-{
-        size_t ret = strlen(src);
-
-        if (size) {
-                size_t len = (ret >= size) ? size - 1 : ret;
-
-                memcpy(dest, src, len);
-                dest[len] = '\0';
-        }
-
-        return ret;
-}
-
 static char *get_pathname(void)
 {
         static char pathname_array[4][PATH_MAX];
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index e4b173dec4b9..b597bcc8fc78 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -220,6 +220,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
         alias->scale = 1.0;
         alias->unit[0] = '\0';
         alias->per_pkg = false;
+        alias->snapshot = false;
 
         ret = parse_events_terms(&alias->terms, val);
         if (ret) {
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 03875f9154e7..93996ec4bbe3 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2326,8 +2326,11 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
                 goto out;
 
         if (!allow_suffix) {
-                pr_warning("Error: event \"%s\" already exists. "
-                           "(Use -f to force duplicates.)\n", buf);
+                pr_warning("Error: event \"%s\" already exists.\n"
+                           " Hint: Remove existing event by 'perf probe -d'\n"
+                           "       or force duplicates by 'perf probe -f'\n"
+                           "       or set 'force=yes' in BPF source.\n",
+                           buf);
                 ret = -EEXIST;
                 goto out;
         }
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 05012bb178d7..2be10fb27172 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -654,6 +654,7 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
 static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 {
         Dwarf_Attribute fb_attr;
+        Dwarf_Frame *frame = NULL;
         size_t nops;
         int ret;
 
@@ -686,11 +687,11 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 #if _ELFUTILS_PREREQ(0, 142)
         } else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
                    pf->cfi != NULL) {
-                Dwarf_Frame *frame;
                 if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 ||
                     dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) {
                         pr_warning("Failed to get call frame on 0x%jx\n",
                                    (uintmax_t)pf->addr);
+                        free(frame);
                         return -ENOENT;
                 }
 #endif
@@ -699,7 +700,8 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
         /* Call finder's callback handler */
         ret = pf->callback(sc_die, pf);
 
-        /* *pf->fb_ops will be cached in libdw. Don't free it. */
+        /* Since *pf->fb_ops can be a part of frame. we should free it here. */
+        free(frame);
         pf->fb_ops = NULL;
 
         return ret;
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 51be28b1bca2..8162ba0e2e57 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,6 +10,8 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
+../lib/bitmap.c
+../lib/find_bit.c
 ../lib/hweight.c
 util/thread_map.c
 util/util.c
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index a8e825fca42a..d72fafc1c800 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -41,6 +41,9 @@
 #include "../thread-stack.h"
 #include "../trace-event.h"
 #include "../machine.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "stat.h"
 
 PyMODINIT_FUNC initperf_trace_context(void);
 
@@ -859,6 +862,104 @@ static void python_process_event(union perf_event *event,
         }
 }
 
+static void get_handler_name(char *str, size_t size,
+                             struct perf_evsel *evsel)
+{
+        char *p = str;
+
+        scnprintf(str, size, "stat__%s", perf_evsel__name(evsel));
+
+        while ((p = strchr(p, ':'))) {
+                *p = '_';
+                p++;
+        }
+}
+
+static void
+process_stat(struct perf_evsel *counter, int cpu, int thread, u64 tstamp,
+             struct perf_counts_values *count)
+{
+        PyObject *handler, *t;
+        static char handler_name[256];
+        int n = 0;
+
+        t = PyTuple_New(MAX_FIELDS);
+        if (!t)
+                Py_FatalError("couldn't create Python tuple");
+
+        get_handler_name(handler_name, sizeof(handler_name),
+                         counter);
+
+        handler = get_handler(handler_name);
+        if (!handler) {
+                pr_debug("can't find python handler %s\n", handler_name);
+                return;
+        }
+
+        PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
+        PyTuple_SetItem(t, n++, PyInt_FromLong(thread));
+
+        tuple_set_u64(t, n++, tstamp);
+        tuple_set_u64(t, n++, count->val);
+        tuple_set_u64(t, n++, count->ena);
+        tuple_set_u64(t, n++, count->run);
+
+        if (_PyTuple_Resize(&t, n) == -1)
+                Py_FatalError("error resizing Python tuple");
+
+        call_object(handler, t, handler_name);
+
+        Py_DECREF(t);
+}
+
+static void python_process_stat(struct perf_stat_config *config,
+                                struct perf_evsel *counter, u64 tstamp)
+{
+        struct thread_map *threads = counter->threads;
+        struct cpu_map *cpus = counter->cpus;
+        int cpu, thread;
+
+        if (config->aggr_mode == AGGR_GLOBAL) {
+                process_stat(counter, -1, -1, tstamp,
+                             &counter->counts->aggr);
+                return;
+        }
+
+        for (thread = 0; thread < threads->nr; thread++) {
+                for (cpu = 0; cpu < cpus->nr; cpu++) {
+                        process_stat(counter, cpus->map[cpu],
+                                     thread_map__pid(threads, thread), tstamp,
+                                     perf_counts(counter->counts, cpu, thread));
+                }
+        }
+}
+
+static void python_process_stat_interval(u64 tstamp)
+{
+        PyObject *handler, *t;
+        static const char handler_name[] = "stat__interval";
+        int n = 0;
+
+        t = PyTuple_New(MAX_FIELDS);
+        if (!t)
+                Py_FatalError("couldn't create Python tuple");
+
+        handler = get_handler(handler_name);
+        if (!handler) {
+                pr_debug("can't find python handler %s\n", handler_name);
+                return;
+        }
+
+        tuple_set_u64(t, n++, tstamp);
+
+        if (_PyTuple_Resize(&t, n) == -1)
+                Py_FatalError("error resizing Python tuple");
+
+        call_object(handler, t, handler_name);
+
+        Py_DECREF(t);
+}
+
 static int run_start_sub(void)
 {
         main_module = PyImport_AddModule("__main__");
@@ -1201,10 +1302,12 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 }
 
 struct scripting_ops python_scripting_ops = {
-        .name = "Python",
-        .start_script = python_start_script,
-        .flush_script = python_flush_script,
-        .stop_script = python_stop_script,
-        .process_event = python_process_event,
-        .generate_script = python_generate_script,
+        .name                   = "Python",
+        .start_script           = python_start_script,
+        .flush_script           = python_flush_script,
+        .stop_script            = python_stop_script,
+        .process_event          = python_process_event,
+        .process_stat           = python_process_stat,
+        .process_stat_interval  = python_process_stat_interval,
+        .generate_script        = python_generate_script,
 };
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index c35ffdd360fe..d5636ba94b20 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -17,6 +17,7 @@
 #include "asm/bug.h"
 #include "auxtrace.h"
 #include "thread-stack.h"
+#include "stat.h"
 
 static int perf_session__deliver_event(struct perf_session *session,
                                        union perf_event *event,
@@ -36,6 +37,9 @@ static int perf_session__open(struct perf_session *session)
         if (perf_data_file__is_pipe(file))
                 return 0;
 
+        if (perf_header__has_feat(&session->header, HEADER_STAT))
+                return 0;
+
         if (!perf_evlist__valid_sample_type(session->evlist)) {
                 pr_err("non matching sample_type\n");
                 return -1;
@@ -205,6 +209,18 @@ static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
+static int process_event_synth_event_update_stub(struct perf_tool *tool __maybe_unused,
+                                                 union perf_event *event __maybe_unused,
+                                                 struct perf_evlist **pevlist
+                                                 __maybe_unused)
+{
+        if (dump_trace)
+                perf_event__fprintf_event_update(event, stdout);
+
+        dump_printf(": unhandled!\n");
+        return 0;
+}
+
 static int process_event_sample_stub(struct perf_tool *tool __maybe_unused,
                                      union perf_event *event __maybe_unused,
                                      struct perf_sample *sample __maybe_unused,
@@ -296,6 +312,67 @@ int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
+
+static
+int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused,
+                                  union perf_event *event __maybe_unused,
+                                  struct perf_session *session __maybe_unused)
+{
+        if (dump_trace)
+                perf_event__fprintf_thread_map(event, stdout);
+
+        dump_printf(": unhandled!\n");
+        return 0;
+}
+
+static
+int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused,
+                               union perf_event *event __maybe_unused,
+                               struct perf_session *session __maybe_unused)
+{
+        if (dump_trace)
+                perf_event__fprintf_cpu_map(event, stdout);
+
+        dump_printf(": unhandled!\n");
+        return 0;
+}
+
+static
+int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused,
+                                   union perf_event *event __maybe_unused,
+                                   struct perf_session *session __maybe_unused)
+{
+        if (dump_trace)
+                perf_event__fprintf_stat_config(event, stdout);
+
+        dump_printf(": unhandled!\n");
+        return 0;
+}
+
+static int process_stat_stub(struct perf_tool *tool __maybe_unused,
+                             union perf_event *event __maybe_unused,
+                             struct perf_session *perf_session
+                             __maybe_unused)
+{
+        if (dump_trace)
+                perf_event__fprintf_stat(event, stdout);
+
+        dump_printf(": unhandled!\n");
+        return 0;
+}
+
+static int process_stat_round_stub(struct perf_tool *tool __maybe_unused,
+                                   union perf_event *event __maybe_unused,
+                                   struct perf_session *perf_session
+                                   __maybe_unused)
+{
+        if (dump_trace)
+                perf_event__fprintf_stat_round(event, stdout);
+
+        dump_printf(": unhandled!\n");
+        return 0;
+}
+
 void perf_tool__fill_defaults(struct perf_tool *tool)
 {
         if (tool->sample == NULL)
@@ -328,6 +405,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
                 tool->unthrottle = process_event_stub;
         if (tool->attr == NULL)
                 tool->attr = process_event_synth_attr_stub;
+        if (tool->event_update == NULL)
+                tool->event_update = process_event_synth_event_update_stub;
         if (tool->tracing_data == NULL)
                 tool->tracing_data = process_event_synth_tracing_data_stub;
         if (tool->build_id == NULL)
@@ -346,6 +425,16 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
                 tool->auxtrace = process_event_auxtrace_stub;
         if (tool->auxtrace_error == NULL)
                 tool->auxtrace_error = process_event_auxtrace_error_stub;
+        if (tool->thread_map == NULL)
+                tool->thread_map = process_event_thread_map_stub;
+        if (tool->cpu_map == NULL)
+                tool->cpu_map = process_event_cpu_map_stub;
+        if (tool->stat_config == NULL)
+                tool->stat_config = process_event_stat_config_stub;
+        if (tool->stat == NULL)
+                tool->stat = process_stat_stub;
+        if (tool->stat_round == NULL)
+                tool->stat_round = process_stat_round_stub;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -569,6 +658,13 @@ static void perf_event__hdr_attr_swap(union perf_event *event,
         mem_bswap_64(event->attr.id, size);
 }
 
+static void perf_event__event_update_swap(union perf_event *event,
+                                          bool sample_id_all __maybe_unused)
+{
+        event->event_update.type = bswap_64(event->event_update.type);
+        event->event_update.id   = bswap_64(event->event_update.id);
+}
+
 static void perf_event__event_type_swap(union perf_event *event,
                                         bool sample_id_all __maybe_unused)
 {
@@ -616,6 +712,81 @@ static void perf_event__auxtrace_error_swap(union perf_event *event,
         event->auxtrace_error.ip   = bswap_64(event->auxtrace_error.ip);
 }
 
+static void perf_event__thread_map_swap(union perf_event *event,
+                                        bool sample_id_all __maybe_unused)
+{
+        unsigned i;
+
+        event->thread_map.nr = bswap_64(event->thread_map.nr);
+
+        for (i = 0; i < event->thread_map.nr; i++)
+                event->thread_map.entries[i].pid = bswap_64(event->thread_map.entries[i].pid);
+}
+
+static void perf_event__cpu_map_swap(union perf_event *event,
+                                     bool sample_id_all __maybe_unused)
+{
+        struct cpu_map_data *data = &event->cpu_map.data;
+        struct cpu_map_entries *cpus;
+        struct cpu_map_mask *mask;
+        unsigned i;
+
+        data->type = bswap_64(data->type);
+
+        switch (data->type) {
+        case PERF_CPU_MAP__CPUS:
+                cpus = (struct cpu_map_entries *)data->data;
+
+                cpus->nr = bswap_16(cpus->nr);
+
+                for (i = 0; i < cpus->nr; i++)
+                        cpus->cpu[i] = bswap_16(cpus->cpu[i]);
+                break;
+        case PERF_CPU_MAP__MASK:
+                mask = (struct cpu_map_mask *) data->data;
+
+                mask->nr = bswap_16(mask->nr);
+                mask->long_size = bswap_16(mask->long_size);
+
+                switch (mask->long_size) {
+                case 4: mem_bswap_32(&mask->mask, mask->nr); break;
+                case 8: mem_bswap_64(&mask->mask, mask->nr); break;
+                default:
+                        pr_err("cpu_map swap: unsupported long size\n");
+                }
+        default:
+                break;
+        }
+}
+
+static void perf_event__stat_config_swap(union perf_event *event,
+                                         bool sample_id_all __maybe_unused)
+{
+        u64 size;
+
+        size  = event->stat_config.nr * sizeof(event->stat_config.data[0]);
+        size += 1; /* nr item itself */
+        mem_bswap_64(&event->stat_config.nr, size);
+}
+
+static void perf_event__stat_swap(union perf_event *event,
+                                  bool sample_id_all __maybe_unused)
+{
+        event->stat.id     = bswap_64(event->stat.id);
+        event->stat.thread = bswap_32(event->stat.thread);
+        event->stat.cpu    = bswap_32(event->stat.cpu);
+        event->stat.val    = bswap_64(event->stat.val);
+        event->stat.ena    = bswap_64(event->stat.ena);
+        event->stat.run    = bswap_64(event->stat.run);
+}
+
+static void perf_event__stat_round_swap(union perf_event *event,
+                                        bool sample_id_all __maybe_unused)
+{
+        event->stat_round.type = bswap_64(event->stat_round.type);
+        event->stat_round.time = bswap_64(event->stat_round.time);
+}
+
 typedef void (*perf_event__swap_op)(union perf_event *event,
                                     bool sample_id_all);
 
@@ -643,6 +814,12 @@ static perf_event__swap_op perf_event__swap_ops[] = {
         [PERF_RECORD_AUXTRACE_INFO]       = perf_event__auxtrace_info_swap,
         [PERF_RECORD_AUXTRACE]            = perf_event__auxtrace_swap,
         [PERF_RECORD_AUXTRACE_ERROR]      = perf_event__auxtrace_error_swap,
+        [PERF_RECORD_THREAD_MAP]          = perf_event__thread_map_swap,
+        [PERF_RECORD_CPU_MAP]             = perf_event__cpu_map_swap,
+        [PERF_RECORD_STAT_CONFIG]         = perf_event__stat_config_swap,
+        [PERF_RECORD_STAT]                = perf_event__stat_swap,
+        [PERF_RECORD_STAT_ROUND]          = perf_event__stat_round_swap,
+        [PERF_RECORD_EVENT_UPDATE]        = perf_event__event_update_swap,
         [PERF_RECORD_HEADER_MAX]          = NULL,
 };
 
@@ -1154,6 +1331,8 @@ static s64 perf_session__process_user_event(struct perf_session *session,
                         perf_session__set_comm_exec(session);
                 }
                 return err;
+        case PERF_RECORD_EVENT_UPDATE:
+                return tool->event_update(tool, event, &session->evlist);
         case PERF_RECORD_HEADER_EVENT_TYPE:
                 /*
                  * Depreceated, but we need to handle it for sake
@@ -1179,6 +1358,16 @@ static s64 perf_session__process_user_event(struct perf_session *session,
         case PERF_RECORD_AUXTRACE_ERROR:
                 perf_session__auxtrace_error_inc(session, event);
                 return tool->auxtrace_error(tool, event, session);
+        case PERF_RECORD_THREAD_MAP:
+                return tool->thread_map(tool, event, session);
+        case PERF_RECORD_CPU_MAP:
+                return tool->cpu_map(tool, event, session);
+        case PERF_RECORD_STAT_CONFIG:
+                return tool->stat_config(tool, event, session);
+        case PERF_RECORD_STAT:
+                return tool->stat(tool, event, session);
+        case PERF_RECORD_STAT_ROUND:
+                return tool->stat_round(tool, event, session);
         default:
                 return -EINVAL;
         }
@@ -1311,17 +1500,20 @@ struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
         return machine__findnew_thread(&session->machines.host, -1, pid);
 }
 
-struct thread *perf_session__register_idle_thread(struct perf_session *session)
+int perf_session__register_idle_thread(struct perf_session *session)
 {
         struct thread *thread;
+        int err = 0;
 
         thread = machine__findnew_thread(&session->machines.host, 0, 0);
         if (thread == NULL || thread__set_comm(thread, "swapper", 0)) {
                 pr_err("problem inserting idle task.\n");
-                thread = NULL;
+                err = -1;
         }
 
-        return thread;
+        /* machine__findnew_thread() got the thread, so put it */
+        thread__put(thread);
+        return err;
 }
 
 static void perf_session__warn_about_errors(const struct perf_session *session)
@@ -1676,7 +1868,7 @@ int perf_session__process_events(struct perf_session *session)
         u64 size = perf_data_file__size(session->file);
         int err;
 
-        if (perf_session__register_idle_thread(session) == NULL)
+        if (perf_session__register_idle_thread(session) < 0)
                 return -ENOMEM;
 
         if (!perf_data_file__is_pipe(session->file))
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 3e900c0efc73..5f792e35d4c1 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -89,7 +89,7 @@ struct machine *perf_session__findnew_machine(struct perf_session *session, pid_
 }
 
 struct thread *perf_session__findnew(struct perf_session *session, pid_t pid);
-struct thread *perf_session__register_idle_thread(struct perf_session *session);
+int perf_session__register_idle_thread(struct perf_session *session);
 
 size_t perf_session__fprintf(struct perf_session *session, FILE *fp);
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 2d8ccd4d9e1b..ec722346e6ff 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -4,6 +4,8 @@
 #include "comm.h"
 #include "symbol.h"
 #include "evsel.h"
+#include "evlist.h"
+#include <traceevent/event-parse.h>
 
 regex_t         parent_regex;
 const char      default_parent_pattern[] = "^sys_|^do_page_fault";
@@ -13,6 +15,7 @@ const char	default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cy
 const char      default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
 const char      default_top_sort_order[] = "dso,symbol";
 const char      default_diff_sort_order[] = "dso,symbol";
+const char      default_tracepoint_sort_order[] = "trace";
 const char      *sort_order;
 const char      *field_order;
 regex_t         ignore_callees_regex;
@@ -443,6 +446,70 @@ struct sort_entry sort_socket = {
         .se_width_idx   = HISTC_SOCKET,
 };
 
+/* --sort trace */
+
+static char *get_trace_output(struct hist_entry *he)
+{
+        struct trace_seq seq;
+        struct perf_evsel *evsel;
+        struct pevent_record rec = {
+                .data = he->raw_data,
+                .size = he->raw_size,
+        };
+
+        evsel = hists_to_evsel(he->hists);
+
+        trace_seq_init(&seq);
+        if (symbol_conf.raw_trace) {
+                pevent_print_fields(&seq, he->raw_data, he->raw_size,
+                                    evsel->tp_format);
+        } else {
+                pevent_event_info(&seq, evsel->tp_format, &rec);
+        }
+        return seq.buffer;
+}
+
+static int64_t
+sort__trace_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+        struct perf_evsel *evsel;
+
+        evsel = hists_to_evsel(left->hists);
+        if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+                return 0;
+
+        if (left->trace_output == NULL)
+                left->trace_output = get_trace_output(left);
+        if (right->trace_output == NULL)
+                right->trace_output = get_trace_output(right);
+
+        hists__new_col_len(left->hists, HISTC_TRACE, strlen(left->trace_output));
+        hists__new_col_len(right->hists, HISTC_TRACE, strlen(right->trace_output));
+
+        return strcmp(right->trace_output, left->trace_output);
+}
+
+static int hist_entry__trace_snprintf(struct hist_entry *he, char *bf,
+                                    size_t size, unsigned int width)
+{
+        struct perf_evsel *evsel;
+
+        evsel = hists_to_evsel(he->hists);
+        if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+                return scnprintf(bf, size, "%-*.*s", width, width, "N/A");
+
+        if (he->trace_output == NULL)
+                he->trace_output = get_trace_output(he);
+        return repsep_snprintf(bf, size, "%-*.*s", width, width, he->trace_output);
+}
+
+struct sort_entry sort_trace = {
+        .se_header      = "Trace output",
+        .se_cmp         = sort__trace_cmp,
+        .se_snprintf    = hist_entry__trace_snprintf,
+        .se_width_idx   = HISTC_TRACE,
+};
+
 /* sort keys for branch stacks */
 
 static int64_t
@@ -1312,6 +1379,7 @@ static struct sort_dimension common_sort_dimensions[] = {
         DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
         DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
         DIM(SORT_TRANSACTION, "transaction", sort_transaction),
+        DIM(SORT_TRACE, "trace", sort_trace),
 };
 
 #undef DIM
@@ -1529,6 +1597,455 @@ static int __sort_dimension__add_hpp_output(struct sort_dimension *sd)
         return 0;
 }
 
+struct hpp_dynamic_entry {
+        struct perf_hpp_fmt hpp;
+        struct perf_evsel *evsel;
+        struct format_field *field;
+        unsigned dynamic_len;
+        bool raw_trace;
+};
+
+static int hde_width(struct hpp_dynamic_entry *hde)
+{
+        if (!hde->hpp.len) {
+                int len = hde->dynamic_len;
+                int namelen = strlen(hde->field->name);
+                int fieldlen = hde->field->size;
+
+                if (namelen > len)
+                        len = namelen;
+
+                if (!(hde->field->flags & FIELD_IS_STRING)) {
+                        /* length for print hex numbers */
+                        fieldlen = hde->field->size * 2 + 2;
+                }
+                if (fieldlen > len)
+                        len = fieldlen;
+
+                hde->hpp.len = len;
+        }
+        return hde->hpp.len;
+}
+
+static void update_dynamic_len(struct hpp_dynamic_entry *hde,
+                               struct hist_entry *he)
+{
+        char *str, *pos;
+        struct format_field *field = hde->field;
+        size_t namelen;
+        bool last = false;
+
+        if (hde->raw_trace)
+                return;
+
+        /* parse pretty print result and update max length */
+        if (!he->trace_output)
+                he->trace_output = get_trace_output(he);
+
+        namelen = strlen(field->name);
+        str = he->trace_output;
+
+        while (str) {
+                pos = strchr(str, ' ');
+                if (pos == NULL) {
+                        last = true;
+                        pos = str + strlen(str);
+                }
+
+                if (!strncmp(str, field->name, namelen)) {
+                        size_t len;
+
+                        str += namelen + 1;
+                        len = pos - str;
+
+                        if (len > hde->dynamic_len)
+                                hde->dynamic_len = len;
+                        break;
+                }
+
+                if (last)
+                        str = NULL;
+                else
+                        str = pos + 1;
+        }
+}
+
+static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+                              struct perf_evsel *evsel __maybe_unused)
+{
+        struct hpp_dynamic_entry *hde;
+        size_t len = fmt->user_len;
+
+        hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+
+        if (!len)
+                len = hde_width(hde);
+
+        return scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, hde->field->name);
+}
+
+static int __sort__hde_width(struct perf_hpp_fmt *fmt,
+                             struct perf_hpp *hpp __maybe_unused,
+                             struct perf_evsel *evsel __maybe_unused)
+{
+        struct hpp_dynamic_entry *hde;
+        size_t len = fmt->user_len;
+
+        hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+
+        if (!len)
+                len = hde_width(hde);
+
+        return len;
+}
+
+bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists)
+{
+        struct hpp_dynamic_entry *hde;
+
+        hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+
+        return hists_to_evsel(hists) == hde->evsel;
+}
+
+static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+                             struct hist_entry *he)
+{
+        struct hpp_dynamic_entry *hde;
+        size_t len = fmt->user_len;
+        char *str, *pos;
+        struct format_field *field;
+        size_t namelen;
+        bool last = false;
+        int ret;
+
+        hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+
+        if (!len)
+                len = hde_width(hde);
+
+        if (hde->raw_trace)
+                goto raw_field;
+
+        field = hde->field;
+        namelen = strlen(field->name);
+        str = he->trace_output;
+
+        while (str) {
+                pos = strchr(str, ' ');
+                if (pos == NULL) {
+                        last = true;
+                        pos = str + strlen(str);
+                }
+
+                if (!strncmp(str, field->name, namelen)) {
+                        str += namelen + 1;
+                        str = strndup(str, pos - str);
+
+                        if (str == NULL)
+                                return scnprintf(hpp->buf, hpp->size,
+                                                 "%*.*s", len, len, "ERROR");
+                        break;
+                }
+
+                if (last)
+                        str = NULL;
+                else
+                        str = pos + 1;
+        }
+
+        if (str == NULL) {
+                struct trace_seq seq;
+raw_field:
+                trace_seq_init(&seq);
+                pevent_print_field(&seq, he->raw_data, hde->field);
+                str = seq.buffer;
+        }
+
+        ret = scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, str);
+        free(str);
+        return ret;
+}
+
+static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
+                               struct hist_entry *a, struct hist_entry *b)
+{
+        struct hpp_dynamic_entry *hde;
+        struct format_field *field;
+        unsigned offset, size;
+
+        hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+
+        field = hde->field;
+        if (field->flags & FIELD_IS_DYNAMIC) {
+                unsigned long long dyn;
+
+                pevent_read_number_field(field, a->raw_data, &dyn);
+                offset = dyn & 0xffff;
+                size = (dyn >> 16) & 0xffff;
+
+                /* record max width for output */
+                if (size > hde->dynamic_len)
+                        hde->dynamic_len = size;
+        } else {
+                offset = field->offset;
+                size = field->size;
+
+                update_dynamic_len(hde, a);
+                update_dynamic_len(hde, b);
+        }
+
+        return memcmp(a->raw_data + offset, b->raw_data + offset, size);
+}
+
+bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *fmt)
+{
+        return fmt->cmp == __sort__hde_cmp;
+}
+
+static struct hpp_dynamic_entry *
+__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field)
+{
+        struct hpp_dynamic_entry *hde;
+
+        hde = malloc(sizeof(*hde));
+        if (hde == NULL) {
+                pr_debug("Memory allocation failed\n");
+                return NULL;
+        }
+
+        hde->evsel = evsel;
+        hde->field = field;
+        hde->dynamic_len = 0;
+
+        hde->hpp.name = field->name;
+        hde->hpp.header = __sort__hde_header;
+        hde->hpp.width  = __sort__hde_width;
+        hde->hpp.entry  = __sort__hde_entry;
+        hde->hpp.color  = NULL;
+
+        hde->hpp.cmp = __sort__hde_cmp;
+        hde->hpp.collapse = __sort__hde_cmp;
+        hde->hpp.sort = __sort__hde_cmp;
+
+        INIT_LIST_HEAD(&hde->hpp.list);
+        INIT_LIST_HEAD(&hde->hpp.sort_list);
+        hde->hpp.elide = false;
+        hde->hpp.len = 0;
+        hde->hpp.user_len = 0;
+
+        return hde;
+}
+
+static int parse_field_name(char *str, char **event, char **field, char **opt)
+{
+        char *event_name, *field_name, *opt_name;
+
+        event_name = str;
+        field_name = strchr(str, '.');
+
+        if (field_name) {
+                *field_name++ = '\0';
+        } else {
+                event_name = NULL;
+                field_name = str;
+        }
+
+        opt_name = strchr(field_name, '/');
+        if (opt_name)
+                *opt_name++ = '\0';
+
+        *event = event_name;
+        *field = field_name;
+        *opt   = opt_name;
+
+        return 0;
+}
+
+/* find match evsel using a given event name.  The event name can be:
+ *   1. '%' + event index (e.g. '%1' for first event)
+ *   2. full event name (e.g. sched:sched_switch)
+ *   3. partial event name (should not contain ':')
+ */
+static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_name)
+{
+        struct perf_evsel *evsel = NULL;
+        struct perf_evsel *pos;
+        bool full_name;
+
+        /* case 1 */
+        if (event_name[0] == '%') {
+                int nr = strtol(event_name+1, NULL, 0);
+
+                if (nr > evlist->nr_entries)
+                        return NULL;
+
+                evsel = perf_evlist__first(evlist);
+                while (--nr > 0)
+                        evsel = perf_evsel__next(evsel);
+
+                return evsel;
+        }
+
+        full_name = !!strchr(event_name, ':');
+        evlist__for_each(evlist, pos) {
+                /* case 2 */
+                if (full_name && !strcmp(pos->name, event_name))
+                        return pos;
+                /* case 3 */
+                if (!full_name && strstr(pos->name, event_name)) {
+                        if (evsel) {
+                                pr_debug("'%s' event is ambiguous: it can be %s or %s\n",
+                                         event_name, evsel->name, pos->name);
+                                return NULL;
+                        }
+                        evsel = pos;
+                }
+        }
+
+        return evsel;
+}
+
+static int __dynamic_dimension__add(struct perf_evsel *evsel,
+                                    struct format_field *field,
+                                    bool raw_trace)
+{
+        struct hpp_dynamic_entry *hde;
+
+        hde = __alloc_dynamic_entry(evsel, field);
+        if (hde == NULL)
+                return -ENOMEM;
+
+        hde->raw_trace = raw_trace;
+
+        perf_hpp__register_sort_field(&hde->hpp);
+        return 0;
+}
+
+static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace)
+{
+        int ret;
+        struct format_field *field;
+
+        field = evsel->tp_format->format.fields;
+        while (field) {
+                ret = __dynamic_dimension__add(evsel, field, raw_trace);
+                if (ret < 0)
+                        return ret;
+
+                field = field->next;
+        }
+        return 0;
+}
+
+static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
+{
+        int ret;
+        struct perf_evsel *evsel;
+
+        evlist__for_each(evlist, evsel) {
+                if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+                        continue;
+
+                ret = add_evsel_fields(evsel, raw_trace);
+                if (ret < 0)
+                        return ret;
+        }
+        return 0;
+}
+
+static int add_all_matching_fields(struct perf_evlist *evlist,
+                                   char *field_name, bool raw_trace)
+{
+        int ret = -ESRCH;
+        struct perf_evsel *evsel;
+        struct format_field *field;
+
+        evlist__for_each(evlist, evsel) {
+                if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+                        continue;
+
+                field = pevent_find_any_field(evsel->tp_format, field_name);
+                if (field == NULL)
+                        continue;
+
+                ret = __dynamic_dimension__add(evsel, field, raw_trace);
+                if (ret < 0)
+                        break;
+        }
+        return ret;
+}
+
+static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
+{
+        char *str, *event_name, *field_name, *opt_name;
+        struct perf_evsel *evsel;
+        struct format_field *field;
+        bool raw_trace = symbol_conf.raw_trace;
+        int ret = 0;
+
+        if (evlist == NULL)
+                return -ENOENT;
+
+        str = strdup(tok);
+        if (str == NULL)
+                return -ENOMEM;
+
+        if (parse_field_name(str, &event_name, &field_name, &opt_name) < 0) {
+                ret = -EINVAL;
+                goto out;
+        }
+
+        if (opt_name) {
+                if (strcmp(opt_name, "raw")) {
+                        pr_debug("unsupported field option %s\n", opt_name);
+                        ret = -EINVAL;
+                        goto out;
+                }
+                raw_trace = true;
+        }
+
+        if (!strcmp(field_name, "trace_fields")) {
+                ret = add_all_dynamic_fields(evlist, raw_trace);
+                goto out;
+        }
+
+        if (event_name == NULL) {
+                ret = add_all_matching_fields(evlist, field_name, raw_trace);
+                goto out;
+        }
+
+        evsel = find_evsel(evlist, event_name);
+        if (evsel == NULL) {
+                pr_debug("Cannot find event: %s\n", event_name);
+                ret = -ENOENT;
+                goto out;
+        }
+
+        if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+                pr_debug("%s is not a tracepoint event\n", event_name);
+                ret = -EINVAL;
+                goto out;
+        }
+
+        if (!strcmp(field_name, "*")) {
+                ret = add_evsel_fields(evsel, raw_trace);
+        } else {
+                field = pevent_find_any_field(evsel->tp_format, field_name);
+                if (field == NULL) {
+                        pr_debug("Cannot find event field for %s.%s\n",
+                                 event_name, field_name);
+                        return -ENOENT;
+                }
+
+                ret = __dynamic_dimension__add(evsel, field, raw_trace);
+        }
+
+out:
+        free(str);
+        return ret;
+}
+
 static int __sort_dimension__add(struct sort_dimension *sd)
 {
         if (sd->taken)
@@ -1583,7 +2100,8 @@ int hpp_dimension__add_output(unsigned col)
         return __hpp_dimension__add_output(&hpp_sort_dimensions[col]);
 }
 
-int sort_dimension__add(const char *tok)
+static int sort_dimension__add(const char *tok,
+                               struct perf_evlist *evlist __maybe_unused)
 {
         unsigned int i;
 
@@ -1664,10 +2182,13 @@ int sort_dimension__add(const char *tok)
                 return 0;
         }
 
+        if (!add_dynamic_entry(evlist, tok))
+                return 0;
+
         return -ESRCH;
 }
 
-static const char *get_default_sort_order(void)
+static const char *get_default_sort_order(struct perf_evlist *evlist)
 {
         const char *default_sort_orders[] = {
                 default_sort_order,
@@ -1675,14 +2196,33 @@ static const char *get_default_sort_order(void)
                 default_mem_sort_order,
                 default_top_sort_order,
                 default_diff_sort_order,
+                default_tracepoint_sort_order,
         };
+        bool use_trace = true;
+        struct perf_evsel *evsel;
 
         BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders));
 
+        if (evlist == NULL)
+                goto out_no_evlist;
+
+        evlist__for_each(evlist, evsel) {
+                if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+                        use_trace = false;
+                        break;
+                }
+        }
+
+        if (use_trace) {
+                sort__mode = SORT_MODE__TRACEPOINT;
+                if (symbol_conf.raw_trace)
+                        return "trace_fields";
+        }
+out_no_evlist:
         return default_sort_orders[sort__mode];
 }
 
-static int setup_sort_order(void)
+static int setup_sort_order(struct perf_evlist *evlist)
 {
         char *new_sort_order;
 
@@ -1703,7 +2243,7 @@ static int setup_sort_order(void)
          * because it's checked over the rest of the code.
          */
         if (asprintf(&new_sort_order, "%s,%s",
-                     get_default_sort_order(), sort_order + 1) < 0) {
+                     get_default_sort_order(evlist), sort_order + 1) < 0) {
                 error("Not enough memory to set up --sort");
                 return -ENOMEM;
         }
@@ -1712,13 +2252,41 @@ static int setup_sort_order(void)
         return 0;
 }
 
-static int __setup_sorting(void)
+/*
+ * Adds 'pre,' prefix into 'str' is 'pre' is
+ * not already part of 'str'.
+ */
+static char *prefix_if_not_in(const char *pre, char *str)
+{
+        char *n;
+
+        if (!str || strstr(str, pre))
+                return str;
+
+        if (asprintf(&n, "%s,%s", pre, str) < 0)
+                return NULL;
+
+        free(str);
+        return n;
+}
+
+static char *setup_overhead(char *keys)
+{
+        keys = prefix_if_not_in("overhead", keys);
+
+        if (symbol_conf.cumulate_callchain)
+                keys = prefix_if_not_in("overhead_children", keys);
+
+        return keys;
+}
+
+static int __setup_sorting(struct perf_evlist *evlist)
 {
         char *tmp, *tok, *str;
         const char *sort_keys;
         int ret = 0;
 
-        ret = setup_sort_order();
+        ret = setup_sort_order(evlist);
         if (ret)
                 return ret;
 
@@ -1732,7 +2300,7 @@ static int __setup_sorting(void)
                         return 0;
                 }
 
-                sort_keys = get_default_sort_order();
+                sort_keys = get_default_sort_order(evlist);
         }
 
         str = strdup(sort_keys);
@@ -1741,9 +2309,20 @@ static int __setup_sorting(void)
                 return -ENOMEM;
         }
 
+        /*
+         * Prepend overhead fields for backward compatibility.
+         */
+        if (!is_strict_order(field_order)) {
+                str = setup_overhead(str);
+                if (str == NULL) {
+                        error("Not enough memory to setup overhead keys");
+                        return -ENOMEM;
+                }
+        }
+
         for (tok = strtok_r(str, ", ", &tmp);
                         tok; tok = strtok_r(NULL, ", ", &tmp)) {
-                ret = sort_dimension__add(tok);
+                ret = sort_dimension__add(tok, evlist);
                 if (ret == -EINVAL) {
                         error("Invalid --sort key: `%s'", tok);
                         break;
@@ -1954,16 +2533,16 @@ out:
         return ret;
 }
 
-int setup_sorting(void)
+int setup_sorting(struct perf_evlist *evlist)
 {
         int err;
 
-        err = __setup_sorting();
+        err = __setup_sorting(evlist);
         if (err < 0)
                 return err;
 
         if (parent_pattern != default_parent_pattern) {
-                err = sort_dimension__add("parent");
+                err = sort_dimension__add("parent", evlist);
                 if (err < 0)
                         return err;
         }
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 31228851e397..687bbb124428 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -18,7 +18,7 @@
 #include "debug.h"
 #include "header.h"
 
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 #include "parse-events.h"
 #include "hist.h"
 #include "thread.h"
@@ -122,6 +122,9 @@ struct hist_entry {
         struct branch_info      *branch_info;
         struct hists            *hists;
         struct mem_info         *mem_info;
+        void                    *raw_data;
+        u32                     raw_size;
+        void                    *trace_output;
         struct callchain_root   callchain[0]; /* must be last member */
 };
 
@@ -164,6 +167,7 @@ enum sort_mode {
         SORT_MODE__MEMORY,
         SORT_MODE__TOP,
         SORT_MODE__DIFF,
+        SORT_MODE__TRACEPOINT,
 };
 
 enum sort_type {
@@ -180,6 +184,7 @@ enum sort_type {
         SORT_LOCAL_WEIGHT,
         SORT_GLOBAL_WEIGHT,
         SORT_TRANSACTION,
+        SORT_TRACE,
 
         /* branch stack specific sort keys */
         __SORT_BRANCH_STACK,
@@ -209,8 +214,6 @@ enum sort_type {
  */
 
 struct sort_entry {
-        struct list_head list;
-
         const char *se_header;
 
         int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *);
@@ -224,10 +227,11 @@ struct sort_entry {
 extern struct sort_entry sort_thread;
 extern struct list_head hist_entry__sort_list;
 
-int setup_sorting(void);
+struct perf_evlist;
+struct pevent;
+int setup_sorting(struct perf_evlist *evlist);
 int setup_output_field(void);
 void reset_output_field(void);
-extern int sort_dimension__add(const char *);
 void sort__setup_elide(FILE *fp);
 void perf_hpp__set_elide(int idx, bool elide);
 
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 2d9d8306dbd3..2f901d15e063 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -341,3 +341,65 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 
         return 0;
 }
+
+int perf_event__process_stat_event(struct perf_tool *tool __maybe_unused,
+                                   union perf_event *event,
+                                   struct perf_session *session)
+{
+        struct perf_counts_values count;
+        struct stat_event *st = &event->stat;
+        struct perf_evsel *counter;
+
+        count.val = st->val;
+        count.ena = st->ena;
+        count.run = st->run;
+
+        counter = perf_evlist__id2evsel(session->evlist, st->id);
+        if (!counter) {
+                pr_err("Failed to resolve counter for stat event.\n");
+                return -EINVAL;
+        }
+
+        *perf_counts(counter->counts, st->cpu, st->thread) = count;
+        counter->supported = true;
+        return 0;
+}
+
+size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp)
+{
+        struct stat_event *st = (struct stat_event *) event;
+        size_t ret;
+
+        ret  = fprintf(fp, "\n... id %" PRIu64 ", cpu %d, thread %d\n",
+                       st->id, st->cpu, st->thread);
+        ret += fprintf(fp, "... value %" PRIu64 ", enabled %" PRIu64 ", running %" PRIu64 "\n",
+                       st->val, st->ena, st->run);
+
+        return ret;
+}
+
+size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp)
+{
+        struct stat_round_event *rd = (struct stat_round_event *)event;
+        size_t ret;
+
+        ret = fprintf(fp, "\n... time %" PRIu64 ", type %s\n", rd->time,
+                      rd->type == PERF_STAT_ROUND_TYPE__FINAL ? "FINAL" : "INTERVAL");
+
+        return ret;
+}
+
+size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
+{
+        struct perf_stat_config sc;
+        size_t ret;
+
+        perf_event__read_stat_config(&sc, &event->stat_config);
+
+        ret  = fprintf(fp, "\n");
+        ret += fprintf(fp, "... aggr_mode %d\n", sc.aggr_mode);
+        ret += fprintf(fp, "... scale     %d\n", sc.scale);
+        ret += fprintf(fp, "... interval  %u\n", sc.interval);
+
+        return ret;
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index da1d11c4f8c1..086f4e128d63 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -90,4 +90,14 @@ void perf_evlist__reset_stats(struct perf_evlist *evlist);
 
 int perf_stat_process_counter(struct perf_stat_config *config,
                               struct perf_evsel *counter);
+struct perf_tool;
+union perf_event;
+struct perf_session;
+int perf_event__process_stat_event(struct perf_tool *tool,
+                                   union perf_event *event,
+                                   struct perf_session *session);
+
+size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
 #endif
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index fc8781de62db..7f7e072be746 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -342,22 +342,6 @@ char *rtrim(char *s)
         return s;
 }
 
-/**
- * memdup - duplicate region of memory
- * @src: memory region to duplicate
- * @len: memory region length
- */
-void *memdup(const void *src, size_t len)
-{
-        void *p;
-
-        p = malloc(len);
-        if (p)
-                memcpy(p, src, len);
-
-        return p;
-}
-
 char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints)
 {
         /*
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 475d88d0a1c9..562b8ebeae5b 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1026,8 +1026,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
                                 curr_dso->long_name_len = dso->long_name_len;
                                 curr_map = map__new2(start, curr_dso,
                                                      map->type);
+                                dso__put(curr_dso);
                                 if (curr_map == NULL) {
-                                        dso__put(curr_dso);
                                         goto out_elf_end;
                                 }
                                 if (adjust_kernel_syms) {
@@ -1042,7 +1042,14 @@ int dso__load_sym(struct dso *dso, struct map *map,
                                 }
                                 curr_dso->symtab_type = dso->symtab_type;
                                 map_groups__insert(kmaps, curr_map);
+                                /*
+                                 * Add it before we drop the referece to curr_map,
+                                 * i.e. while we still are sure to have a reference
+                                 * to this DSO via curr_map->dso.
+                                 */
                                 dsos__add(&map->groups->machine->dsos, curr_dso);
+                                /* kmaps already got it */
+                                map__put(curr_map);
                                 dso__set_loaded(curr_dso, map->type);
                         } else
                                 curr_dso = curr_map->dso;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index cd08027a6d2c..3b2de6eb3376 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -39,6 +39,7 @@ struct symbol_conf symbol_conf = {
         .cumulate_callchain     = true,
         .show_hist_headers      = true,
         .symfs                  = "",
+        .event_group            = true,
 };
 
 static enum dso_binary_type binary_type_symtab[] = {
@@ -1860,24 +1861,44 @@ static void vmlinux_path__exit(void)
         zfree(&vmlinux_path);
 }
 
+static const char * const vmlinux_paths[] = {
+        "vmlinux",
+        "/boot/vmlinux"
+};
+
+static const char * const vmlinux_paths_upd[] = {
+        "/boot/vmlinux-%s",
+        "/usr/lib/debug/boot/vmlinux-%s",
+        "/lib/modules/%s/build/vmlinux",
+        "/usr/lib/debug/lib/modules/%s/vmlinux",
+        "/usr/lib/debug/boot/vmlinux-%s.debug"
+};
+
+static int vmlinux_path__add(const char *new_entry)
+{
+        vmlinux_path[vmlinux_path__nr_entries] = strdup(new_entry);
+        if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
+                return -1;
+        ++vmlinux_path__nr_entries;
+
+        return 0;
+}
+
 static int vmlinux_path__init(struct perf_env *env)
 {
         struct utsname uts;
         char bf[PATH_MAX];
         char *kernel_version;
+        unsigned int i;
 
-        vmlinux_path = malloc(sizeof(char *) * 6);
+        vmlinux_path = malloc(sizeof(char *) * (ARRAY_SIZE(vmlinux_paths) +
+                              ARRAY_SIZE(vmlinux_paths_upd)));
         if (vmlinux_path == NULL)
                 return -1;
 
-        vmlinux_path[vmlinux_path__nr_entries] = strdup("vmlinux");
-        if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-                goto out_fail;
-        ++vmlinux_path__nr_entries;
-        vmlinux_path[vmlinux_path__nr_entries] = strdup("/boot/vmlinux");
-        if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-                goto out_fail;
-        ++vmlinux_path__nr_entries;
+        for (i = 0; i < ARRAY_SIZE(vmlinux_paths); i++)
+                if (vmlinux_path__add(vmlinux_paths[i]) < 0)
+                        goto out_fail;
 
         /* only try kernel version if no symfs was given */
         if (symbol_conf.symfs[0] != 0)
@@ -1892,28 +1913,11 @@ static int vmlinux_path__init(struct perf_env *env)
                 kernel_version = uts.release;
         }
 
-        snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", kernel_version);
-        vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
-        if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-                goto out_fail;
-        ++vmlinux_path__nr_entries;
-        snprintf(bf, sizeof(bf), "/usr/lib/debug/boot/vmlinux-%s",
-                 kernel_version);
-        vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
-        if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-                goto out_fail;
-        ++vmlinux_path__nr_entries;
-        snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", kernel_version);
-        vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
-        if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-                goto out_fail;
-        ++vmlinux_path__nr_entries;
-        snprintf(bf, sizeof(bf), "/usr/lib/debug/lib/modules/%s/vmlinux",
-                 kernel_version);
-        vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
-        if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-                goto out_fail;
-        ++vmlinux_path__nr_entries;
+        for (i = 0; i < ARRAY_SIZE(vmlinux_paths_upd); i++) {
+                snprintf(bf, sizeof(bf), vmlinux_paths_upd[i], kernel_version);
+                if (vmlinux_path__add(bf) < 0)
+                        goto out_fail;
+        }
 
         return 0;
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index dcd786e364f2..ccd1caa40e11 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -108,7 +108,9 @@ struct symbol_conf {
                         show_hist_headers,
                         branch_callstack,
                         has_filter,
-                        show_ref_callgraph;
+                        show_ref_callgraph,
+                        hide_unresolved,
+                        raw_trace;
         const char      *vmlinux_name,
                         *kallsyms_name,
                         *source_prefix,
diff --git a/tools/perf/util/term.c b/tools/perf/util/term.c
new file mode 100644
index 000000000000..90b47d8aa19c
--- /dev/null
+++ b/tools/perf/util/term.c
@@ -0,0 +1,35 @@
+#include "util.h"
+
+void get_term_dimensions(struct winsize *ws)
+{
+        char *s = getenv("LINES");
+
+        if (s != NULL) {
+                ws->ws_row = atoi(s);
+                s = getenv("COLUMNS");
+                if (s != NULL) {
+                        ws->ws_col = atoi(s);
+                        if (ws->ws_row && ws->ws_col)
+                                return;
+                }
+        }
+#ifdef TIOCGWINSZ
+        if (ioctl(1, TIOCGWINSZ, ws) == 0 &&
+            ws->ws_row && ws->ws_col)
+                return;
+#endif
+        ws->ws_row = 25;
+        ws->ws_col = 80;
+}
+
+void set_term_quiet_input(struct termios *old)
+{
+        struct termios tc;
+
+        tcgetattr(0, old);
+        tc = *old;
+        tc.c_lflag &= ~(ICANON | ECHO);
+        tc.c_cc[VMIN] = 0;
+        tc.c_cc[VTIME] = 0;
+        tcsetattr(0, TCSANOW, &tc);
+}
diff --git a/tools/perf/util/term.h b/tools/perf/util/term.h
new file mode 100644
index 000000000000..2c06a61846a1
--- /dev/null
+++ b/tools/perf/util/term.h
@@ -0,0 +1,10 @@
+#ifndef __PERF_TERM_H
+#define __PERF_TERM_H
+
+struct termios;
+struct winsize;
+
+void get_term_dimensions(struct winsize *ws);
+void set_term_quiet_input(struct termios *old);
+
+#endif /* __PERF_TERM_H */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 0a9ae8014729..dfd00c6dad6e 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -19,8 +19,10 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine)
                 thread->mg = map_groups__new(machine);
         } else {
                 leader = __machine__findnew_thread(machine, pid, pid);
-                if (leader)
+                if (leader) {
                         thread->mg = map_groups__get(leader->mg);
+                        thread__put(leader);
+                }
         }
 
         return thread->mg ? 0 : -1;
@@ -53,7 +55,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
                         goto err_thread;
 
                 list_add(&comm->list, &thread->comm_list);
-                atomic_set(&thread->refcnt, 0);
+                atomic_set(&thread->refcnt, 1);
                 RB_CLEAR_NODE(&thread->rb_node);
         }
 
@@ -95,6 +97,10 @@ struct thread *thread__get(struct thread *thread)
 void thread__put(struct thread *thread)
 {
         if (thread && atomic_dec_and_test(&thread->refcnt)) {
+                /*
+                 * Remove it from the dead_threads list, as last reference
+                 * is gone.
+                 */
                 list_del_init(&thread->node);
                 thread__delete(thread);
         }
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 6ec3c5ca438f..08afc6909953 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -13,6 +13,7 @@
 #include "thread_map.h"
 #include "util.h"
 #include "debug.h"
+#include "event.h"
 
 /* Skip "." and ".." directories */
 static int filter(const struct dirent *dir)
@@ -304,6 +305,7 @@ out:
 
 out_free_threads:
         zfree(&threads);
+        strlist__delete(slist);
         goto out;
 }
 
@@ -408,3 +410,29 @@ void thread_map__read_comms(struct thread_map *threads)
         for (i = 0; i < threads->nr; ++i)
                 comm_init(threads, i);
 }
+
+static void thread_map__copy_event(struct thread_map *threads,
+                                   struct thread_map_event *event)
+{
+        unsigned i;
+
+        threads->nr = (int) event->nr;
+
+        for (i = 0; i < event->nr; i++) {
+                thread_map__set_pid(threads, i, (pid_t) event->entries[i].pid);
+                threads->map[i].comm = strndup(event->entries[i].comm, 16);
+        }
+
+        atomic_set(&threads->refcnt, 1);
+}
+
+struct thread_map *thread_map__new_event(struct thread_map_event *event)
+{
+        struct thread_map *threads;
+
+        threads = thread_map__alloc(event->nr);
+        if (threads)
+                thread_map__copy_event(threads, event);
+
+        return threads;
+}
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index af679d8a50f8..85e4c7c4fbde 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -16,11 +16,14 @@ struct thread_map {
         struct thread_map_data map[];
 };
 
+struct thread_map_event;
+
 struct thread_map *thread_map__new_dummy(void);
 struct thread_map *thread_map__new_by_pid(pid_t pid);
 struct thread_map *thread_map__new_by_tid(pid_t tid);
 struct thread_map *thread_map__new_by_uid(uid_t uid);
 struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
+struct thread_map *thread_map__new_event(struct thread_map_event *event);
 
 struct thread_map *thread_map__get(struct thread_map *map);
 void thread_map__put(struct thread_map *map);
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index cab8cc24831b..55de4cffcd4e 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -50,12 +50,18 @@ struct perf_tool {
                         throttle,
                         unthrottle;
         event_attr_op   attr;
+        event_attr_op   event_update;
         event_op2       tracing_data;
         event_oe        finished_round;
         event_op2       build_id,
                         id_index,
                         auxtrace_info,
-                        auxtrace_error;
+                        auxtrace_error,
+                        thread_map,
+                        cpu_map,
+                        stat_config,
+                        stat,
+                        stat_round;
         event_op3       auxtrace;
         bool            ordered_events;
         bool            ordering_requires_timestamps;
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index b85ee55cca0c..bce5b1dac268 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -65,6 +65,7 @@ int tracing_data_put(struct tracing_data *tdata);
 struct addr_location;
 
 struct perf_session;
+struct perf_stat_config;
 
 struct scripting_ops {
         const char *name;
@@ -75,6 +76,9 @@ struct scripting_ops {
                                struct perf_sample *sample,
                                struct perf_evsel *evsel,
                                struct addr_location *al);
+        void (*process_stat)(struct perf_stat_config *config,
+                             struct perf_evsel *evsel, u64 tstamp);
+        void (*process_stat_interval)(u64 tstamp);
         int (*generate_script) (struct pevent *pevent, const char *outfile);
 };
 
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 2dcfe9a7c8d0..cf5e250bc78e 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include "event.h"
 #include "perf_regs.h"
+#include "callchain.h"
 
 static char *debuginfo_path;
 
@@ -52,25 +53,28 @@ static int report_module(u64 ip, struct unwind_info *ui)
         return __report_module(&al, ip, ui);
 }
 
+/*
+ * Store all entries within entries array,
+ * we will process it after we finish unwind.
+ */
 static int entry(u64 ip, struct unwind_info *ui)
 
 {
-        struct unwind_entry e;
+        struct unwind_entry *e = &ui->entries[ui->idx++];
         struct addr_location al;
 
         if (__report_module(&al, ip, ui))
                 return -1;
 
-        e.ip  = ip;
-        e.map = al.map;
-        e.sym = al.sym;
+        e->ip  = ip;
+        e->map = al.map;
+        e->sym = al.sym;
 
         pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
                  al.sym ? al.sym->name : "''",
                  ip,
                  al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
-
-        return ui->cb(&e, ui->arg);
+        return 0;
 }
 
 static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
@@ -92,6 +96,16 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
         thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
                               MAP__FUNCTION, addr, &al);
         if (!al.map) {
+                /*
+                 * We've seen cases (softice) where DWARF unwinder went
+                 * through non executable mmaps, which we need to lookup
+                 * in MAP__VARIABLE tree.
+                 */
+                thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
+                                      MAP__VARIABLE, addr, &al);
+        }
+
+        if (!al.map) {
                 pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
                 return -1;
         }
@@ -168,7 +182,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
                         struct perf_sample *data,
                         int max_stack)
 {
-        struct unwind_info ui = {
+        struct unwind_info *ui, ui_buf = {
                 .sample         = data,
                 .thread         = thread,
                 .machine        = thread->mg->machine,
@@ -177,35 +191,54 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
                 .max_stack      = max_stack,
         };
         Dwarf_Word ip;
-        int err = -EINVAL;
+        int err = -EINVAL, i;
 
         if (!data->user_regs.regs)
                 return -EINVAL;
 
-        ui.dwfl = dwfl_begin(&offline_callbacks);
-        if (!ui.dwfl)
+        ui = zalloc(sizeof(ui_buf) + sizeof(ui_buf.entries[0]) * max_stack);
+        if (!ui)
+                return -ENOMEM;
+
+        *ui = ui_buf;
+
+        ui->dwfl = dwfl_begin(&offline_callbacks);
+        if (!ui->dwfl)
                 goto out;
 
         err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
         if (err)
                 goto out;
 
-        err = report_module(ip, &ui);
+        err = report_module(ip, ui);
         if (err)
                 goto out;
 
-        if (!dwfl_attach_state(ui.dwfl, EM_NONE, thread->tid, &callbacks, &ui))
+        if (!dwfl_attach_state(ui->dwfl, EM_NONE, thread->tid, &callbacks, ui))
                 goto out;
 
-        err = dwfl_getthread_frames(ui.dwfl, thread->tid, frame_callback, &ui);
+        err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui);
 
-        if (err && !ui.max_stack)
+        if (err && !ui->max_stack)
                 err = 0;
 
+        /*
+         * Display what we got based on the order setup.
+         */
+        for (i = 0; i < ui->idx && !err; i++) {
+                int j = i;
+
+                if (callchain_param.order == ORDER_CALLER)
+                        j = ui->idx - i - 1;
+
+                err = ui->entries[j].ip ? ui->cb(&ui->entries[j], ui->arg) : 0;
+        }
+
  out:
         if (err)
                 pr_debug("unwind: failed with '%s'\n", dwfl_errmsg(-1));
 
-        dwfl_end(ui.dwfl);
+        dwfl_end(ui->dwfl);
+        free(ui);
         return 0;
 }
diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h
index 417a1426f3ad..58328669ed16 100644
--- a/tools/perf/util/unwind-libdw.h
+++ b/tools/perf/util/unwind-libdw.h
@@ -16,6 +16,8 @@ struct unwind_info {
         unwind_entry_cb_t       cb;
         void                    *arg;
         int                     max_stack;
+        int                     idx;
+        struct unwind_entry     entries[];
 };
 
 #endif /* __PERF_UNWIND_LIBDW_H */
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index c83832b555e5..ee7e372297e5 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -319,6 +319,15 @@ static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
 
         thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
                               MAP__FUNCTION, ip, &al);
+        if (!al.map) {
+                /*
+                 * We've seen cases (softice) where DWARF unwinder went
+                 * through non executable mmaps, which we need to lookup
+                 * in MAP__VARIABLE tree.
+                 */
+                thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
+                                      MAP__VARIABLE, ip, &al);
+        }
         return al.map;
 }
 
@@ -416,20 +425,19 @@ get_proc_name(unw_addr_space_t __maybe_unused as,
 static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
                           unw_word_t *data)
 {
-        struct addr_location al;
+        struct map *map;
         ssize_t size;
 
-        thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
-                              MAP__FUNCTION, addr, &al);
-        if (!al.map) {
+        map = find_map(addr, ui);
+        if (!map) {
                 pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
                 return -1;
         }
 
-        if (!al.map->dso)
+        if (!map->dso)
                 return -1;
 
-        size = dso__data_read_addr(al.map->dso, al.map, ui->machine,
+        size = dso__data_read_addr(map->dso, map, ui->machine,
                                    addr, (u8 *) data, sizeof(*data));
 
         return !(size == sizeof(*data));
@@ -614,23 +622,48 @@ void unwind__finish_access(struct thread *thread)
 static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
                        void *arg, int max_stack)
 {
+        u64 val;
+        unw_word_t ips[max_stack];
         unw_addr_space_t addr_space;
         unw_cursor_t c;
-        int ret;
-
-        addr_space = thread__priv(ui->thread);
-        if (addr_space == NULL)
-                return -1;
+        int ret, i = 0;
 
-        ret = unw_init_remote(&c, addr_space, ui);
+        ret = perf_reg_value(&val, &ui->sample->user_regs, PERF_REG_IP);
         if (ret)
-                display_error(ret);
+                return ret;
 
-        while (!ret && (unw_step(&c) > 0) && max_stack--) {
-                unw_word_t ip;
+        ips[i++] = (unw_word_t) val;
 
-                unw_get_reg(&c, UNW_REG_IP, &ip);
-                ret = ip ? entry(ip, ui->thread, cb, arg) : 0;
+        /*
+         * If we need more than one entry, do the DWARF
+         * unwind itself.
+         */
+        if (max_stack - 1 > 0) {
+                addr_space = thread__priv(ui->thread);
+                if (addr_space == NULL)
+                        return -1;
+
+                ret = unw_init_remote(&c, addr_space, ui);
+                if (ret)
+                        display_error(ret);
+
+                while (!ret && (unw_step(&c) > 0) && i < max_stack) {
+                        unw_get_reg(&c, UNW_REG_IP, &ips[i]);
+                        ++i;
+                }
+
+                max_stack = i;
+        }
+
+        /*
+         * Display what we got based on the order setup.
+         */
+        for (i = 0; i < max_stack && !ret; i++) {
+                int j = i;
+
+                if (callchain_param.order == ORDER_CALLER)
+                        j = max_stack - i - 1;
+                ret = ips[j] ? entry(ips[j], ui->thread, cb, arg) : 0;
         }
 
         return ret;
@@ -640,24 +673,17 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
                         struct thread *thread,
                         struct perf_sample *data, int max_stack)
 {
-        u64 ip;
         struct unwind_info ui = {
                 .sample       = data,
                 .thread       = thread,
                 .machine      = thread->mg->machine,
         };
-        int ret;
 
         if (!data->user_regs.regs)
                 return -EINVAL;
 
-        ret = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
-        if (ret)
-                return ret;
-
-        ret = entry(ip, thread, cb, arg);
-        if (ret)
-                return -ENOMEM;
+        if (max_stack <= 0)
+                return -EINVAL;
 
-        return --max_stack > 0 ? get_entries(&ui, cb, arg, max_stack) : 0;
+        return get_entries(&ui, cb, arg, max_stack);
 }
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 47b1e36c7ea0..88b8f8d21f58 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -16,12 +16,15 @@
 #include <linux/kernel.h>
 #include <unistd.h>
 #include "callchain.h"
+#include "strlist.h"
+#include <subcmd/exec-cmd.h>
 
 struct callchain_param  callchain_param = {
         .mode   = CHAIN_GRAPH_ABS,
         .min_percent = 0.5,
         .order  = ORDER_CALLEE,
-        .key    = CCKEY_FUNCTION
+        .key    = CCKEY_FUNCTION,
+        .value  = CCVAL_PERCENT,
 };
 
 /*
@@ -351,41 +354,8 @@ void sighandler_dump_stack(int sig)
 {
         psignal(sig, "perf");
         dump_stack();
-        exit(sig);
-}
-
-void get_term_dimensions(struct winsize *ws)
-{
-        char *s = getenv("LINES");
-
-        if (s != NULL) {
-                ws->ws_row = atoi(s);
-                s = getenv("COLUMNS");
-                if (s != NULL) {
-                        ws->ws_col = atoi(s);
-                        if (ws->ws_row && ws->ws_col)
-                                return;
-                }
-        }
-#ifdef TIOCGWINSZ
-        if (ioctl(1, TIOCGWINSZ, ws) == 0 &&
-            ws->ws_row && ws->ws_col)
-                return;
-#endif
-        ws->ws_row = 25;
-        ws->ws_col = 80;
-}
-
-void set_term_quiet_input(struct termios *old)
-{
-        struct termios tc;
-
-        tcgetattr(0, old);
-        tc = *old;
-        tc.c_lflag &= ~(ICANON | ECHO);
-        tc.c_cc[VMIN] = 0;
-        tc.c_cc[VTIME] = 0;
-        tcsetattr(0, TCSANOW, &tc);
+        signal(sig, SIG_DFL);
+        raise(sig);
 }
 
 int parse_nsec_time(const char *str, u64 *ptime)
@@ -695,3 +665,28 @@ fetch_kernel_version(unsigned int *puint, char *str,
                 *puint = (version << 16) + (patchlevel << 8) + sublevel;
         return 0;
 }
+
+const char *perf_tip(const char *dirpath)
+{
+        struct strlist *tips;
+        struct str_node *node;
+        char *tip = NULL;
+        struct strlist_config conf = {
+                .dirname = system_path(dirpath) ,
+        };
+
+        tips = strlist__new("tips.txt", &conf);
+        if (tips == NULL || strlist__nr_entries(tips) == 1) {
+                tip = (char *)"Cannot find tips.txt file";
+                goto out;
+        }
+
+        node = strlist__entry(tips, random() % strlist__nr_entries(tips));
+        if (asprintf(&tip, "Tip: %s", node->s) < 0)
+                tip = (char *)"Tip: get more memory! ;-)";
+
+out:
+        strlist__delete(tips);
+
+        return tip;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index dcc659017976..fe915e616f9b 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -53,6 +53,7 @@
 #include <stdlib.h>
 #include <stdarg.h>
 #include <string.h>
+#include <term.h>
 #include <errno.h>
 #include <limits.h>
 #include <sys/param.h>
@@ -150,12 +151,6 @@ extern void set_warning_routine(void (*routine)(const char *err, va_list params)
 extern int prefixcmp(const char *str, const char *prefix);
 extern void set_buildid_dir(const char *dir);
 
-static inline const char *skip_prefix(const char *str, const char *prefix)
-{
-        size_t len = strlen(prefix);
-        return strncmp(str, prefix, len) ? NULL : str + len;
-}
-
 #ifdef __GLIBC_PREREQ
 #if __GLIBC_PREREQ(2, 1)
 #define HAVE_STRCHRNUL
@@ -186,14 +181,6 @@ static inline void *zalloc(size_t size)
 
 #define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
 
-static inline int has_extension(const char *filename, const char *ext)
-{
-        size_t len = strlen(filename);
-        size_t extlen = strlen(ext);
-
-        return len > extlen && !memcmp(filename + len - extlen, ext, extlen);
-}
-
 /* Sane ctype - no locale, and works with signed chars */
 #undef isascii
 #undef isspace
@@ -282,9 +269,6 @@ void sighandler_dump_stack(int sig);
 extern unsigned int page_size;
 extern int cacheline_size;
 
-void get_term_dimensions(struct winsize *ws);
-void set_term_quiet_input(struct termios *old);
-
 struct parse_tag {
         char tag;
         int mult;
@@ -358,4 +342,6 @@ int fetch_kernel_version(unsigned int *puint,
 #define KVER_FMT        "%d.%d.%d"
 #define KVER_PARAM(x)   KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
 
+const char *perf_tip(const char *dirpath);
+
 #endif /* GIT_COMPAT_UTIL_H */