Merge tag 'perf-tools-for-v6.4-3-2023-05-06' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tool updates from Arnaldo Carvalho de Melo:
 "Third version of perf tool updates, with the build problems with with
  using a 'vmlinux.h' generated from the main build fixed, and the bpf
  skeleton build disabled by default.

  Build:

   - Require libtraceevent to build, one can disable it using
     NO_LIBTRACEEVENT=1.

     It is required for tools like 'perf sched', 'perf kvm', 'perf
     trace', etc.

     libtraceevent is available in most distros so installing
     'libtraceevent-devel' should be a one-time event to continue
     building perf as usual.

     Using NO_LIBTRACEEVENT=1 produces tooling that is functional and
     sufficient for lots of users not interested in those libtraceevent
     dependent features.

   - Allow Python support in 'perf script' when libtraceevent isn't
     linked, as not all features requires it, for instance Intel PT does
     not use tracepoints.

   - Error if the python interpreter needed for jevents to work isn't
     available and NO_JEVENTS=1 isn't set, preventing a build without
     support for JSON vendor events, which is a rare but possible
     condition. The two check error messages:

        $(error ERROR: No python interpreter needed for jevents generation. Install python or build with NO_JEVENTS=1.)
        $(error ERROR: Python interpreter needed for jevents generation too old (older than 3.6). Install a newer python or build with NO_JEVENTS=1.)

   - Make libbpf 1.0 the minimum required when building with out of
     tree, distro provided libbpf.

   - Use libsdtc++'s and LLVM's libcxx's __cxa_demangle, a portable C++
     demangler, add 'perf test' entry for it.

   - Make binutils libraries opt in, as distros disable building with it
     due to licensing, they were used for C++ demangling, for instance.

   - Switch libpfm4 to opt-out rather than opt-in, if libpfm-devel (or
     equivalent) isn't installed, we'll just have a build warning:

       Makefile.config:1144: libpfm4 not found, disables libpfm4 support. Please install libpfm4-dev

   - Add a feature test for scandirat(), that is not implemented so far
     in musl and uclibc, disabling features that need it, such as
     scanning for tracepoints in /sys/kernel/tracing/events.

  perf BPF filters:

   - New feature where BPF can be used to filter samples, for instance:

      $ sudo ./perf record -e cycles --filter 'period > 1000' true
      $ sudo ./perf script
           perf-exec 2273949 546850.708501:       5029 cycles:  ffffffff826f9e25 finish_wait+0x5 ([kernel.kallsyms])
           perf-exec 2273949 546850.708508:      32409 cycles:  ffffffff826f9e25 finish_wait+0x5 ([kernel.kallsyms])
           perf-exec 2273949 546850.708526:     143369 cycles:  ffffffff82b4cdbf xas_start+0x5f ([kernel.kallsyms])
           perf-exec 2273949 546850.708600:     372650 cycles:  ffffffff8286b8f7 __pagevec_lru_add+0x117 ([kernel.kallsyms])
           perf-exec 2273949 546850.708791:     482953 cycles:  ffffffff829190de __mod_memcg_lruvec_state+0x4e ([kernel.kallsyms])
                true 2273949 546850.709036:     501985 cycles:  ffffffff828add7c tlb_gather_mmu+0x4c ([kernel.kallsyms])
                true 2273949 546850.709292:     503065 cycles:      7f2446d97c03 _dl_map_object_deps+0x973 (/usr/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2)

   - In addition to 'period' (PERF_SAMPLE_PERIOD), the other
     PERF_SAMPLE_ can be used for filtering, and also some other sample
     accessible values, from tools/perf/Documentation/perf-record.txt:

        Essentially the BPF filter expression is:

        <term> <operator> <value> (("," | "||") <term> <operator> <value>)*

     The <term> can be one of:
        ip, id, tid, pid, cpu, time, addr, period, txn, weight, phys_addr,
        code_pgsz, data_pgsz, weight1, weight2, weight3, ins_lat, retire_lat,
        p_stage_cyc, mem_op, mem_lvl, mem_snoop, mem_remote, mem_lock,
        mem_dtlb, mem_blk, mem_hops

     The <operator> can be one of:
        ==, !=, >, >=, <, <=, &

     The <value> can be one of:
        <number> (for any term)
        na, load, store, pfetch, exec (for mem_op)
        l1, l2, l3, l4, cxl, io, any_cache, lfb, ram, pmem (for mem_lvl)
        na, none, hit, miss, hitm, fwd, peer (for mem_snoop)
        remote (for mem_remote)
        na, locked (for mem_locked)
        na, l1_hit, l1_miss, l2_hit, l2_miss, any_hit, any_miss, walk, fault (for mem_dtlb)
        na, by_data, by_addr (for mem_blk)
        hops0, hops1, hops2, hops3 (for mem_hops)

  perf lock contention:

   - Show lock type with address.

   - Track and show mmap_lock, siglock and per-cpu rq_lock with address.
     This is done for mmap_lock by following the current->mm pointer:

      $ sudo ./perf lock con -abl -- sleep 10
       contended   total wait     max wait     avg wait            address   symbol
       ...
           16344    312.30 ms      2.22 ms     19.11 us   ffff8cc702595640
           17686    310.08 ms      1.49 ms     17.53 us   ffff8cc7025952c0
               3     84.14 ms     45.79 ms     28.05 ms   ffff8cc78114c478   mmap_lock
            3557     76.80 ms     68.75 us     21.59 us   ffff8cc77ca3af58
               1     68.27 ms     68.27 ms     68.27 ms   ffff8cda745dfd70
               9     54.53 ms      7.96 ms      6.06 ms   ffff8cc7642a48b8   mmap_lock
           14629     44.01 ms     60.00 us      3.01 us   ffff8cc7625f9ca0
            3481     42.63 ms    140.71 us     12.24 us   ffffffff937906ac   vmap_area_lock
           16194     38.73 ms     42.15 us      2.39 us   ffff8cd397cbc560
              11     38.44 ms     10.39 ms      3.49 ms   ffff8ccd6d12fbb8   mmap_lock
               1      5.43 ms      5.43 ms      5.43 ms   ffff8cd70018f0d8
            1674      5.38 ms    422.93 us      3.21 us   ffffffff92e06080   tasklist_lock
             581      4.51 ms    130.68 us      7.75 us   ffff8cc9b1259058
               5      3.52 ms      1.27 ms    703.23 us   ffff8cc754510070
             112      3.47 ms     56.47 us     31.02 us   ffff8ccee38b3120
             381      3.31 ms     73.44 us      8.69 us   ffffffff93790690   purge_vmap_area_lock
             255      3.19 ms     36.35 us     12.49 us   ffff8d053ce30c80

   - Update default map size to 16384.

   - Allocate single letter option -M for --map-nr-entries, as it is
     proving being frequently used.

   - Fix struct rq lock access for older kernels with BPF's CO-RE
     (Compile once, run everywhere).

   - Fix problems found with MSAn.

  perf report/top:

   - Add inline information when using --call-graph=fp or lbr, as was
     already done to the --call-graph=dwarf callchain mode.

   - Improve the 'srcfile' sort key performance by really using an
     optimization introduced in 6.2 for the 'srcline' sort key that
     avoids calling addr2line for comparision with each sample.

  perf sched:

   - Make 'perf sched latency/map/replay' to use "sched:sched_waking"
     instead of "sched:sched_waking", consistent with 'perf record'
     since d566a9c2d482 ("perf sched: Prefer sched_waking event when it
     exists").

  perf ftrace:

   - Make system wide the default target for latency subcommand, run the
     following command then generate some network traffic and press
     control+C:

       # perf ftrace latency -T __kfree_skb
     ^C
         DURATION     |      COUNT | GRAPH                                          |
          0 - 1    us |         27 | #############                                  |
          1 - 2    us |         22 | ###########                                    |
          2 - 4    us |          8 | ####                                           |
          4 - 8    us |          5 | ##                                             |
          8 - 16   us |         24 | ############                                   |
         16 - 32   us |          2 | #                                              |
         32 - 64   us |          1 |                                                |
         64 - 128  us |          0 |                                                |
        128 - 256  us |          0 |                                                |
        256 - 512  us |          0 |                                                |
        512 - 1024 us |          0 |                                                |
          1 - 2    ms |          0 |                                                |
          2 - 4    ms |          0 |                                                |
          4 - 8    ms |          0 |                                                |
          8 - 16   ms |          0 |                                                |
         16 - 32   ms |          0 |                                                |
         32 - 64   ms |          0 |                                                |
         64 - 128  ms |          0 |                                                |
        128 - 256  ms |          0 |                                                |
        256 - 512  ms |          0 |                                                |
        512 - 1024 ms |          0 |                                                |
          1 - ...   s |          0 |                                                |
       #

  perf top:

   - Add --branch-history (LBR: Last Branch Record) option, just like
     already available for 'perf record'.

   - Fix segfault in thread__comm_len() where thread->comm was being
     used outside thread->comm_lock.

  perf annotate:

   - Allow configuring objdump and addr2line in ~/.perfconfig., so that
     you can use alternative binaries, such as llvm's.

  perf kvm:

   - Add TUI mode for 'perf kvm stat report'.

  Reference counting:

   - Add reference count checking infrastructure to check for use after
     free, done to the 'cpumap', 'namespaces', 'maps' and 'map' structs,
     more to come.

     To build with it use -DREFCNT_CHECKING=1 in the make command line
     to build tools/perf. Documented at:

       https://perf.wiki.kernel.org/index.php/Reference_Count_Checking

   - The above caught, for instance, fix, present in this series:

        - Fix maps use after put in 'perf test "Share thread maps"':

          'maps' is copied from leader, but the leader is put on line 79
          and then 'maps' is used to read the reference count below - so
          a use after put, with the put of maps happening within
          thread__put.

     Fixed by reversing the order of puts so that the leader is put
     last.

   - Also several fixes were made to places where reference counts were
     not being held.

   - Make this one of the tests in 'make -C tools/perf build-test' to
     regularly build test it and to make sure no direct access to the
     reference counted structs are made, doing that via accessors to
     check the validity of the struct pointer.

  ARM64:

   - Fix 'perf report' segfault when filtering coresight traces by
     sparse lists of CPUs.

   - Add support for 'simd' as a sort field for 'perf report', to show
     ARM's NEON SIMD's predicate flags: "partial" and "empty".

  arm64 vendor events:

   - Add N1 metrics.

  Intel vendor events:

   - Add graniterapids, grandridge and sierraforrest events.

   - Refresh events for: alderlake, aldernaken, broadwell, broadwellde,
     broadwellx, cascadelakx, haswell, haswellx, icelake, icelakex,
     jaketown, meteorlake, knightslanding, sandybridge, sapphirerapids,
     silvermont, skylake, tigerlake and westmereep-dp

   - Refresh metrics for alderlake-n, broadwell, broadwellde,
     broadwellx, haswell, haswellx, icelakex, ivybridge, ivytown and
     skylakex.

  perf stat:

   - Implement --topdown using JSON metrics.

   - Add TopdownL1 JSON metric as a default if present, but disable it
     for now for some Intel hybrid architectures, a series of patches
     addressing this is being reviewed and will be submitted for v6.5.

   - Use metrics for --smi-cost.

   - Update topdown documentation.

  Vendor events (JSON) infrastructure:

   - Add support for computing and printing metric threshold values. For
     instance, here is one found in thesapphirerapids json file:

       {
           "BriefDescription": "Percentage of cycles spent in System Management Interrupts.",
           "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)",
           "MetricGroup": "smi",
           "MetricName": "smi_cycles",
           "MetricThreshold": "smi_cycles > 0.1",
           "ScaleUnit": "100%"
       },

   - Test parsing metric thresholds with the fake PMU in 'perf test
     pmu-events'.

   - Support for printing metric thresholds in 'perf list'.

   - Add --metric-no-threshold option to 'perf stat'.

   - Add rand (reverse and) and has_pmem (optane memory) support to
     metrics.

   - Sort list of input files to avoid depending on the order from
     readdir() helping in obtaining reproducible builds.

  S/390:

   - Add common metrics: - CPI (cycles per instruction), prbstate (ratio
     of instructions executed in problem state compared to total number
     of instructions), l1mp (Level one instruction and data cache misses
     per 100 instructions).

   - Add cache metrics for z13, z14, z15 and z16.

   - Add metric for TLB and cache.

  ARM:

   - Add raw decoding for SPE (Statistical Profiling Extension) v1.3 MTE
     (Memory Tagging Extension) and MOPS (Memory Operations) load/store.

  Intel PT hardware tracing:

   - Add event type names UINTR (User interrupt delivered) and UIRET
     (Exiting from user interrupt routine), documented in table 32-50
     "CFE Packet Type and Vector Fields Details" in the Intel Processor
     Trace chapter of The Intel SDM Volume 3 version 078.

   - Add support for new branch instructions ERETS and ERETU.

   - Fix CYC timestamps after standalone CBR

  ARM CoreSight hardware tracing:

   - Allow user to override timestamp and contextid settings.

   - Fix segfault in dso lookup.

   - Fix timeless decode mode detection.

   - Add separate decode paths for timeless and per-thread modes.

  auxtrace:

   - Fix address filter entire kernel size.

  Miscellaneous:

   - Fix use-after-free and unaligned bugs in the PLT handling routines.

   - Use zfree() to reduce chances of use after free.

   - Add missing 0x prefix for addresses printed in hexadecimal in 'perf
     probe'.

   - Suppress massive unsupported target platform errors in the unwind
     code.

   - Fix return incorrect build_id size in elf_read_build_id().

   - Fix 'perf scripts intel-pt-events.py' IPC output for Python 2 .

   - Add missing new parameter in kfree_skb tracepoint to the python
     scripts using it.

   - Add 'perf bench syscall fork' benchmark.

   - Add support for printing PERF_MEM_LVLNUM_UNC (Uncached access) in
     'perf mem'.

   - Fix wrong size expectation for perf test 'Setup struct
     perf_event_attr' caused by the patch adding
     perf_event_attr::config3.

   - Fix some spelling mistakes"

* tag 'perf-tools-for-v6.4-3-2023-05-06' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (365 commits)
  Revert "perf build: Make BUILD_BPF_SKEL default, rename to NO_BPF_SKEL"
  Revert "perf build: Warn for BPF skeletons if endian mismatches"
  perf metrics: Fix SEGV with --for-each-cgroup
  perf bpf skels: Stop using vmlinux.h generated from BTF, use subset of used structs + CO-RE
  perf stat: Separate bperf from bpf_profiler
  perf test record+probe_libc_inet_pton: Fix call chain match on x86_64
  perf test record+probe_libc_inet_pton: Fix call chain match on s390
  perf tracepoint: Fix memory leak in is_valid_tracepoint()
  perf cs-etm: Add fix for coresight trace for any range of CPUs
  perf build: Fix unescaped # in perf build-test
  perf unwind: Suppress massive unsupported target platform errors
  perf script: Add new parameter in kfree_skb tracepoint to the python scripts using it
  perf script: Print raw ip instead of binary offset for callchain
  perf symbols: Fix return incorrect build_id size in elf_read_build_id()
  perf list: Modify the warning message about scandirat(3)
  perf list: Fix memory leaks in print_tracepoint_events()
  perf lock contention: Rework offset calculation with BPF CO-RE
  perf lock contention: Fix struct rq lock access
  perf stat: Disable TopdownL1 on hybrid
  perf stat: Avoid SEGV on counter->name
  ...

1 files changed, 703 insertions, 167 deletions

diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 641e739c717c..71165036e4ca 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -23,6 +23,9 @@
 #include "util/data.h"
 #include "util/ordered-events.h"
 #include "util/kvm-stat.h"
+#include "util/util.h"
+#include "ui/browsers/hists.h"
+#include "ui/progress.h"
 #include "ui/ui.h"
 #include "util/string2.h"
 
@@ -49,6 +52,553 @@
 #include <math.h>
 #include <perf/mmap.h>
 
+#if defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT)
+#define GET_EVENT_KEY(func, field)					\
+static u64 get_event_ ##func(struct kvm_event *event, int vcpu)		\
+{									\
+	if (vcpu == -1)							\
+		return event->total.field;				\
+									\
+	if (vcpu >= event->max_vcpu)					\
+		return 0;						\
+									\
+	return event->vcpu[vcpu].field;					\
+}
+
+#define COMPARE_EVENT_KEY(func, field)					\
+GET_EVENT_KEY(func, field)						\
+static int64_t cmp_event_ ## func(struct kvm_event *one,		\
+			      struct kvm_event *two, int vcpu)		\
+{									\
+	return get_event_ ##func(one, vcpu) -				\
+	       get_event_ ##func(two, vcpu);				\
+}
+
+COMPARE_EVENT_KEY(time, time);
+COMPARE_EVENT_KEY(max, stats.max);
+COMPARE_EVENT_KEY(min, stats.min);
+COMPARE_EVENT_KEY(count, stats.n);
+COMPARE_EVENT_KEY(mean, stats.mean);
+
+struct kvm_hists {
+	struct hists		hists;
+	struct perf_hpp_list	list;
+};
+
+struct kvm_dimension {
+	const char *name;
+	const char *header;
+	int width;
+	int64_t (*cmp)(struct perf_hpp_fmt *fmt, struct hist_entry *left,
+		       struct hist_entry *right);
+	int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		     struct hist_entry *he);
+};
+
+struct kvm_fmt {
+	struct perf_hpp_fmt	fmt;
+	struct kvm_dimension	*dim;
+};
+
+static struct kvm_hists kvm_hists;
+
+static int64_t ev_name_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+			   struct hist_entry *left,
+			   struct hist_entry *right)
+{
+	/* Return opposite number for sorting in alphabetical order */
+	return -strcmp(left->kvm_info->name, right->kvm_info->name);
+}
+
+static int fmt_width(struct perf_hpp_fmt *fmt,
+		     struct perf_hpp *hpp __maybe_unused,
+		     struct hists *hists __maybe_unused);
+
+static int ev_name_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			 struct hist_entry *he)
+{
+	int width = fmt_width(fmt, hpp, he->hists);
+
+	return scnprintf(hpp->buf, hpp->size, "%*s", width, he->kvm_info->name);
+}
+
+static struct kvm_dimension dim_event = {
+	.header		= "Event name",
+	.name		= "ev_name",
+	.cmp		= ev_name_cmp,
+	.entry		= ev_name_entry,
+	.width		= 40,
+};
+
+#define EV_METRIC_CMP(metric)						\
+static int64_t ev_cmp_##metric(struct perf_hpp_fmt *fmt __maybe_unused,	\
+			       struct hist_entry *left,			\
+			       struct hist_entry *right)		\
+{									\
+	struct kvm_event *event_left;					\
+	struct kvm_event *event_right;					\
+	struct perf_kvm_stat *perf_kvm;					\
+									\
+	event_left  = container_of(left, struct kvm_event, he);		\
+	event_right = container_of(right, struct kvm_event, he);	\
+									\
+	perf_kvm = event_left->perf_kvm;				\
+	return cmp_event_##metric(event_left, event_right,		\
+				  perf_kvm->trace_vcpu);		\
+}
+
+EV_METRIC_CMP(time)
+EV_METRIC_CMP(count)
+EV_METRIC_CMP(max)
+EV_METRIC_CMP(min)
+EV_METRIC_CMP(mean)
+
+#define EV_METRIC_ENTRY(metric)						\
+static int ev_entry_##metric(struct perf_hpp_fmt *fmt,			\
+			     struct perf_hpp *hpp,			\
+			     struct hist_entry *he)			\
+{									\
+	struct kvm_event *event;					\
+	int width = fmt_width(fmt, hpp, he->hists);			\
+	struct perf_kvm_stat *perf_kvm;					\
+									\
+	event = container_of(he, struct kvm_event, he);			\
+	perf_kvm = event->perf_kvm;					\
+	return scnprintf(hpp->buf, hpp->size, "%*lu", width,		\
+		get_event_##metric(event, perf_kvm->trace_vcpu));	\
+}
+
+EV_METRIC_ENTRY(time)
+EV_METRIC_ENTRY(count)
+EV_METRIC_ENTRY(max)
+EV_METRIC_ENTRY(min)
+
+static struct kvm_dimension dim_time = {
+	.header		= "Time (ns)",
+	.name		= "time",
+	.cmp		= ev_cmp_time,
+	.entry		= ev_entry_time,
+	.width		= 12,
+};
+
+static struct kvm_dimension dim_count = {
+	.header		= "Samples",
+	.name		= "sample",
+	.cmp		= ev_cmp_count,
+	.entry		= ev_entry_count,
+	.width		= 12,
+};
+
+static struct kvm_dimension dim_max_time = {
+	.header		= "Max Time (ns)",
+	.name		= "max_t",
+	.cmp		= ev_cmp_max,
+	.entry		= ev_entry_max,
+	.width		= 14,
+};
+
+static struct kvm_dimension dim_min_time = {
+	.header		= "Min Time (ns)",
+	.name		= "min_t",
+	.cmp		= ev_cmp_min,
+	.entry		= ev_entry_min,
+	.width		= 14,
+};
+
+static int ev_entry_mean(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			 struct hist_entry *he)
+{
+	struct kvm_event *event;
+	int width = fmt_width(fmt, hpp, he->hists);
+	struct perf_kvm_stat *perf_kvm;
+
+	event = container_of(he, struct kvm_event, he);
+	perf_kvm = event->perf_kvm;
+	return scnprintf(hpp->buf, hpp->size, "%*lu", width,
+			 get_event_mean(event, perf_kvm->trace_vcpu));
+}
+
+static struct kvm_dimension dim_mean_time = {
+	.header		= "Mean Time (ns)",
+	.name		= "mean_t",
+	.cmp		= ev_cmp_mean,
+	.entry		= ev_entry_mean,
+	.width		= 14,
+};
+
+#define PERC_STR(__s, __v)				\
+({							\
+	scnprintf(__s, sizeof(__s), "%.2F%%", __v);	\
+	__s;						\
+})
+
+static double percent(u64 st, u64 tot)
+{
+	return tot ? 100. * (double) st / (double) tot : 0;
+}
+
+#define EV_METRIC_PERCENT(metric)					\
+static int ev_percent_##metric(struct hist_entry *he)			\
+{									\
+	struct kvm_event *event;					\
+	struct perf_kvm_stat *perf_kvm;					\
+									\
+	event = container_of(he, struct kvm_event, he);			\
+	perf_kvm = event->perf_kvm;					\
+									\
+	return percent(get_event_##metric(event, perf_kvm->trace_vcpu),	\
+		       perf_kvm->total_##metric);			\
+}
+
+EV_METRIC_PERCENT(time)
+EV_METRIC_PERCENT(count)
+
+static int ev_entry_time_precent(struct perf_hpp_fmt *fmt,
+				 struct perf_hpp *hpp,
+				 struct hist_entry *he)
+{
+	int width = fmt_width(fmt, hpp, he->hists);
+	double per;
+	char buf[10];
+
+	per = ev_percent_time(he);
+	return scnprintf(hpp->buf, hpp->size, "%*s", width, PERC_STR(buf, per));
+}
+
+static int64_t
+ev_cmp_time_precent(struct perf_hpp_fmt *fmt __maybe_unused,
+		    struct hist_entry *left, struct hist_entry *right)
+{
+	double per_left;
+	double per_right;
+
+	per_left  = ev_percent_time(left);
+	per_right = ev_percent_time(right);
+
+	return per_left - per_right;
+}
+
+static struct kvm_dimension dim_time_percent = {
+	.header		= "Time%",
+	.name		= "percent_time",
+	.cmp		= ev_cmp_time_precent,
+	.entry		= ev_entry_time_precent,
+	.width		= 12,
+};
+
+static int ev_entry_count_precent(struct perf_hpp_fmt *fmt,
+				  struct perf_hpp *hpp,
+				  struct hist_entry *he)
+{
+	int width = fmt_width(fmt, hpp, he->hists);
+	double per;
+	char buf[10];
+
+	per = ev_percent_count(he);
+	return scnprintf(hpp->buf, hpp->size, "%*s", width, PERC_STR(buf, per));
+}
+
+static int64_t
+ev_cmp_count_precent(struct perf_hpp_fmt *fmt __maybe_unused,
+		     struct hist_entry *left, struct hist_entry *right)
+{
+	double per_left;
+	double per_right;
+
+	per_left  = ev_percent_count(left);
+	per_right = ev_percent_count(right);
+
+	return per_left - per_right;
+}
+
+static struct kvm_dimension dim_count_percent = {
+	.header		= "Sample%",
+	.name		= "percent_sample",
+	.cmp		= ev_cmp_count_precent,
+	.entry		= ev_entry_count_precent,
+	.width		= 12,
+};
+
+static struct kvm_dimension *dimensions[] = {
+	&dim_event,
+	&dim_time,
+	&dim_time_percent,
+	&dim_count,
+	&dim_count_percent,
+	&dim_max_time,
+	&dim_min_time,
+	&dim_mean_time,
+	NULL,
+};
+
+static int fmt_width(struct perf_hpp_fmt *fmt,
+		     struct perf_hpp *hpp __maybe_unused,
+		     struct hists *hists __maybe_unused)
+{
+	struct kvm_fmt *kvm_fmt;
+
+	kvm_fmt = container_of(fmt, struct kvm_fmt, fmt);
+	return kvm_fmt->dim->width;
+}
+
+static int fmt_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		      struct hists *hists, int line __maybe_unused,
+		      int *span __maybe_unused)
+{
+	struct kvm_fmt *kvm_fmt;
+	struct kvm_dimension *dim;
+	int width = fmt_width(fmt, hpp, hists);
+
+	kvm_fmt = container_of(fmt, struct kvm_fmt, fmt);
+	dim = kvm_fmt->dim;
+
+	return scnprintf(hpp->buf, hpp->size, "%*s", width, dim->header);
+}
+
+static bool fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	struct kvm_fmt *kvm_fmt_a = container_of(a, struct kvm_fmt, fmt);
+	struct kvm_fmt *kvm_fmt_b = container_of(b, struct kvm_fmt, fmt);
+
+	return kvm_fmt_a->dim == kvm_fmt_b->dim;
+}
+
+static void fmt_free(struct perf_hpp_fmt *fmt)
+{
+	struct kvm_fmt *kvm_fmt;
+
+	kvm_fmt = container_of(fmt, struct kvm_fmt, fmt);
+	free(kvm_fmt);
+}
+
+static struct kvm_dimension *get_dimension(const char *name)
+{
+	unsigned int i;
+
+	for (i = 0; dimensions[i] != NULL; i++) {
+		if (!strcmp(dimensions[i]->name, name))
+			return dimensions[i];
+	}
+
+	return NULL;
+}
+
+static struct kvm_fmt *get_format(const char *name)
+{
+	struct kvm_dimension *dim = get_dimension(name);
+	struct kvm_fmt *kvm_fmt;
+	struct perf_hpp_fmt *fmt;
+
+	if (!dim)
+		return NULL;
+
+	kvm_fmt = zalloc(sizeof(*kvm_fmt));
+	if (!kvm_fmt)
+		return NULL;
+
+	kvm_fmt->dim = dim;
+
+	fmt = &kvm_fmt->fmt;
+	INIT_LIST_HEAD(&fmt->list);
+	INIT_LIST_HEAD(&fmt->sort_list);
+	fmt->cmp	= dim->cmp;
+	fmt->sort	= dim->cmp;
+	fmt->color	= NULL;
+	fmt->entry	= dim->entry;
+	fmt->header	= fmt_header;
+	fmt->width	= fmt_width;
+	fmt->collapse	= dim->cmp;
+	fmt->equal	= fmt_equal;
+	fmt->free	= fmt_free;
+
+	return kvm_fmt;
+}
+
+static int kvm_hists__init_output(struct perf_hpp_list *hpp_list, char *name)
+{
+	struct kvm_fmt *kvm_fmt = get_format(name);
+
+	if (!kvm_fmt) {
+		pr_warning("Fail to find format for output field %s.\n", name);
+		return -EINVAL;
+	}
+
+	perf_hpp_list__column_register(hpp_list, &kvm_fmt->fmt);
+	return 0;
+}
+
+static int kvm_hists__init_sort(struct perf_hpp_list *hpp_list, char *name)
+{
+	struct kvm_fmt *kvm_fmt = get_format(name);
+
+	if (!kvm_fmt) {
+		pr_warning("Fail to find format for sorting %s.\n", name);
+		return -EINVAL;
+	}
+
+	perf_hpp_list__register_sort_field(hpp_list, &kvm_fmt->fmt);
+	return 0;
+}
+
+static int kvm_hpp_list__init(char *list,
+			      struct perf_hpp_list *hpp_list,
+			      int (*fn)(struct perf_hpp_list *hpp_list,
+					char *name))
+{
+	char *tmp, *tok;
+	int ret;
+
+	if (!list || !fn)
+		return 0;
+
+	for (tok = strtok_r(list, ", ", &tmp); tok;
+	     tok = strtok_r(NULL, ", ", &tmp)) {
+		ret = fn(hpp_list, tok);
+		if (!ret)
+			continue;
+
+		/* Handle errors */
+		if (ret == -EINVAL)
+			pr_err("Invalid field key: '%s'", tok);
+		else if (ret == -ESRCH)
+			pr_err("Unknown field key: '%s'", tok);
+		else
+			pr_err("Fail to initialize for field key: '%s'", tok);
+
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_hpp_list__parse(struct perf_hpp_list *hpp_list,
+			       const char *output_, const char *sort_)
+{
+	char *output = output_ ? strdup(output_) : NULL;
+	char *sort = sort_ ? strdup(sort_) : NULL;
+	int ret;
+
+	ret = kvm_hpp_list__init(output, hpp_list, kvm_hists__init_output);
+	if (ret)
+		goto out;
+
+	ret = kvm_hpp_list__init(sort, hpp_list, kvm_hists__init_sort);
+	if (ret)
+		goto out;
+
+	/* Copy sort keys to output fields */
+	perf_hpp__setup_output_field(hpp_list);
+
+	/* and then copy output fields to sort keys */
+	perf_hpp__append_sort_keys(hpp_list);
+out:
+	free(output);
+	free(sort);
+	return ret;
+}
+
+static int kvm_hists__init(void)
+{
+	kvm_hists.list.nr_header_lines = 1;
+	__hists__init(&kvm_hists.hists, &kvm_hists.list);
+	perf_hpp_list__init(&kvm_hists.list);
+	return kvm_hpp_list__parse(&kvm_hists.list, NULL, "ev_name");
+}
+
+static int kvm_hists__reinit(const char *output, const char *sort)
+{
+	perf_hpp__reset_output_field(&kvm_hists.list);
+	return kvm_hpp_list__parse(&kvm_hists.list, output, sort);
+}
+static void print_result(struct perf_kvm_stat *kvm);
+
+#ifdef HAVE_SLANG_SUPPORT
+static void kvm_browser__update_nr_entries(struct hist_browser *hb)
+{
+	struct rb_node *nd = rb_first_cached(&hb->hists->entries);
+	u64 nr_entries = 0;
+
+	for (; nd; nd = rb_next(nd)) {
+		struct hist_entry *he = rb_entry(nd, struct hist_entry,
+						 rb_node);
+
+		if (!he->filtered)
+			nr_entries++;
+	}
+
+	hb->nr_non_filtered_entries = nr_entries;
+}
+
+static int kvm_browser__title(struct hist_browser *browser,
+			      char *buf, size_t size)
+{
+	scnprintf(buf, size, "KVM event statistics (%lu entries)",
+		  browser->nr_non_filtered_entries);
+	return 0;
+}
+
+static struct hist_browser*
+perf_kvm_browser__new(struct hists *hists)
+{
+	struct hist_browser *browser = hist_browser__new(hists);
+
+	if (browser)
+		browser->title = kvm_browser__title;
+
+	return browser;
+}
+
+static int kvm__hists_browse(struct hists *hists)
+{
+	struct hist_browser *browser;
+	int key = -1;
+
+	browser = perf_kvm_browser__new(hists);
+	if (browser == NULL)
+		return -1;
+
+	/* reset abort key so that it can get Ctrl-C as a key */
+	SLang_reset_tty();
+	SLang_init_tty(0, 0, 0);
+
+	kvm_browser__update_nr_entries(browser);
+
+	while (1) {
+		key = hist_browser__run(browser, "? - help", true, 0);
+
+		switch (key) {
+		case 'q':
+			goto out;
+		default:
+			break;
+		}
+	}
+
+out:
+	hist_browser__delete(browser);
+	return 0;
+}
+
+static void kvm_display(struct perf_kvm_stat *kvm)
+{
+	if (!use_browser)
+		print_result(kvm);
+	else
+		kvm__hists_browse(&kvm_hists.hists);
+}
+
+#else
+
+static void kvm_display(struct perf_kvm_stat *kvm)
+{
+	use_browser = 0;
+	print_result(kvm);
+}
+
+#endif /* HAVE_SLANG_SUPPORT */
+
+#endif // defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT)
+
 static const char *get_filename_for_perf_kvm(void)
 {
 	const char *filename;
@@ -75,7 +625,7 @@ void exit_event_get_key(struct evsel *evsel,
 
 bool kvm_exit_event(struct evsel *evsel)
 {
-	return !strcmp(evsel->name, kvm_exit_trace);
+	return evsel__name_is(evsel, kvm_exit_trace);
 }
 
 bool exit_event_begin(struct evsel *evsel,
@@ -91,7 +641,7 @@ bool exit_event_begin(struct evsel *evsel,
 
 bool kvm_entry_event(struct evsel *evsel)
 {
-	return !strcmp(evsel->name, kvm_entry_trace);
+	return evsel__name_is(evsel, kvm_entry_trace);
 }
 
 bool exit_event_end(struct evsel *evsel,
@@ -123,7 +673,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm,
 	const char *exit_reason = get_exit_reason(kvm, key->exit_reasons,
 						  key->key);
 
-	scnprintf(decode, decode_str_len, "%s", exit_reason);
+	scnprintf(decode, KVM_EVENT_NAME_LEN, "%s", exit_reason);
 }
 
 static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
@@ -146,44 +696,37 @@ struct vcpu_event_record {
 	struct kvm_event *last_event;
 };
 
-
-static void init_kvm_event_record(struct perf_kvm_stat *kvm)
-{
-	unsigned int i;
-
-	for (i = 0; i < EVENTS_CACHE_SIZE; i++)
-		INIT_LIST_HEAD(&kvm->kvm_events_cache[i]);
-}
-
 #ifdef HAVE_TIMERFD_SUPPORT
-static void clear_events_cache_stats(struct list_head *kvm_events_cache)
+static void clear_events_cache_stats(void)
 {
-	struct list_head *head;
+	struct rb_root_cached *root;
+	struct rb_node *nd;
 	struct kvm_event *event;
-	unsigned int i;
-	int j;
-
-	for (i = 0; i < EVENTS_CACHE_SIZE; i++) {
-		head = &kvm_events_cache[i];
-		list_for_each_entry(event, head, hash_entry) {
-			/* reset stats for event */
-			event->total.time = 0;
-			init_stats(&event->total.stats);
-
-			for (j = 0; j < event->max_vcpu; ++j) {
-				event->vcpu[j].time = 0;
-				init_stats(&event->vcpu[j].stats);
-			}
+	int i;
+
+	if (hists__has(&kvm_hists.hists, need_collapse))
+		root = &kvm_hists.hists.entries_collapsed;
+	else
+		root = kvm_hists.hists.entries_in;
+
+	for (nd = rb_first_cached(root); nd; nd = rb_next(nd)) {
+		struct hist_entry *he;
+
+		he = rb_entry(nd, struct hist_entry, rb_node_in);
+		event = container_of(he, struct kvm_event, he);
+
+		/* reset stats for event */
+		event->total.time = 0;
+		init_stats(&event->total.stats);
+
+		for (i = 0; i < event->max_vcpu; ++i) {
+			event->vcpu[i].time = 0;
+			init_stats(&event->vcpu[i].stats);
 		}
 	}
 }
 #endif
 
-static int kvm_events_hash_fn(u64 key)
-{
-	return key & (EVENTS_CACHE_SIZE - 1);
-}
-
 static bool kvm_event_expand(struct kvm_event *event, int vcpu_id)
 {
 	int old_max_vcpu = event->max_vcpu;
@@ -209,54 +752,78 @@ static bool kvm_event_expand(struct kvm_event *event, int vcpu_id)
 	return true;
 }
 
-static struct kvm_event *kvm_alloc_init_event(struct event_key *key)
+static void *kvm_he_zalloc(size_t size)
 {
-	struct kvm_event *event;
+	struct kvm_event *kvm_ev;
 
-	event = zalloc(sizeof(*event));
-	if (!event) {
-		pr_err("Not enough memory\n");
+	kvm_ev = zalloc(size + sizeof(*kvm_ev));
+	if (!kvm_ev)
 		return NULL;
-	}
 
-	event->key = *key;
-	init_stats(&event->total.stats);
-	return event;
+	init_stats(&kvm_ev->total.stats);
+	hists__inc_nr_samples(&kvm_hists.hists, 0);
+	return &kvm_ev->he;
+}
+
+static void kvm_he_free(void *he)
+{
+	struct kvm_event *kvm_ev;
+
+	kvm_ev = container_of(he, struct kvm_event, he);
+	free(kvm_ev);
 }
 
+static struct hist_entry_ops kvm_ev_entry_ops = {
+	.new	= kvm_he_zalloc,
+	.free	= kvm_he_free,
+};
+
 static struct kvm_event *find_create_kvm_event(struct perf_kvm_stat *kvm,
-					       struct event_key *key)
+					       struct event_key *key,
+					       struct perf_sample *sample)
 {
 	struct kvm_event *event;
-	struct list_head *head;
+	struct hist_entry *he;
+	struct kvm_info *ki;
 
 	BUG_ON(key->key == INVALID_KEY);
 
-	head = &kvm->kvm_events_cache[kvm_events_hash_fn(key->key)];
-	list_for_each_entry(event, head, hash_entry) {
-		if (event->key.key == key->key && event->key.info == key->info)
-			return event;
+	ki = kvm_info__new();
+	if (!ki) {
+		pr_err("Failed to allocate kvm info\n");
+		return NULL;
 	}
 
-	event = kvm_alloc_init_event(key);
-	if (!event)
+	kvm->events_ops->decode_key(kvm, key, ki->name);
+	he = hists__add_entry_ops(&kvm_hists.hists, &kvm_ev_entry_ops,
+				  &kvm->al, NULL, NULL, NULL, ki, sample, true);
+	if (he == NULL) {
+		pr_err("Failed to allocate hist entry\n");
+		free(ki);
 		return NULL;
+	}
+
+	event = container_of(he, struct kvm_event, he);
+	if (!event->perf_kvm) {
+		event->perf_kvm = kvm;
+		event->key = *key;
+	}
 
-	list_add(&event->hash_entry, head);
 	return event;
 }
 
 static bool handle_begin_event(struct perf_kvm_stat *kvm,
 			       struct vcpu_event_record *vcpu_record,
-			       struct event_key *key, u64 timestamp)
+			       struct event_key *key,
+			       struct perf_sample *sample)
 {
 	struct kvm_event *event = NULL;
 
 	if (key->key != INVALID_KEY)
-		event = find_create_kvm_event(kvm, key);
+		event = find_create_kvm_event(kvm, key, sample);
 
 	vcpu_record->last_event = event;
-	vcpu_record->start_time = timestamp;
+	vcpu_record->start_time = sample->time;
 	return true;
 }
 
@@ -278,9 +845,14 @@ static double kvm_event_rel_stddev(int vcpu_id, struct kvm_event *event)
 				avg_stats(&kvm_stats->stats));
 }
 
-static bool update_kvm_event(struct kvm_event *event, int vcpu_id,
+static bool update_kvm_event(struct perf_kvm_stat *kvm,
+			     struct kvm_event *event, int vcpu_id,
 			     u64 time_diff)
 {
+	/* Update overall statistics */
+	kvm->total_count++;
+	kvm->total_time += time_diff;
+
 	if (vcpu_id == -1) {
 		kvm_update_event_stats(&event->total, time_diff);
 		return true;
@@ -306,7 +878,7 @@ static bool is_child_event(struct perf_kvm_stat *kvm,
 		return false;
 
 	for (; child_ops->name; child_ops++) {
-		if (!strcmp(evsel->name, child_ops->name)) {
+		if (evsel__name_is(evsel, child_ops->name)) {
 			child_ops->get_key(evsel, sample, key);
 			return true;
 		}
@@ -318,12 +890,12 @@ static bool is_child_event(struct perf_kvm_stat *kvm,
 static bool handle_child_event(struct perf_kvm_stat *kvm,
 			       struct vcpu_event_record *vcpu_record,
 			       struct event_key *key,
-			       struct perf_sample *sample __maybe_unused)
+			       struct perf_sample *sample)
 {
 	struct kvm_event *event = NULL;
 
 	if (key->key != INVALID_KEY)
-		event = find_create_kvm_event(kvm, key);
+		event = find_create_kvm_event(kvm, key, sample);
 
 	vcpu_record->last_event = event;
 
@@ -372,7 +944,7 @@ static bool handle_end_event(struct perf_kvm_stat *kvm,
 		return true;
 
 	if (!event)
-		event = find_create_kvm_event(kvm, key);
+		event = find_create_kvm_event(kvm, key, sample);
 
 	if (!event)
 		return false;
@@ -389,7 +961,7 @@ static bool handle_end_event(struct perf_kvm_stat *kvm,
 	time_diff = sample->time - time_begin;
 
 	if (kvm->duration && time_diff > kvm->duration) {
-		char decode[decode_str_len];
+		char decode[KVM_EVENT_NAME_LEN];
 
 		kvm->events_ops->decode_key(kvm, &event->key, decode);
 		if (!skip_event(decode)) {
@@ -399,7 +971,7 @@ static bool handle_end_event(struct perf_kvm_stat *kvm,
 		}
 	}
 
-	return update_kvm_event(event, vcpu, time_diff);
+	return update_kvm_event(kvm, event, vcpu, time_diff);
 }
 
 static
@@ -443,7 +1015,7 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm,
 		return true;
 
 	if (kvm->events_ops->is_begin_event(evsel, sample, &key))
-		return handle_begin_event(kvm, vcpu_record, &key, sample->time);
+		return handle_begin_event(kvm, vcpu_record, &key, sample);
 
 	if (is_child_event(kvm, evsel, sample, &key))
 		return handle_child_event(kvm, vcpu_record, &key, sample);
@@ -454,119 +1026,51 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm,
 	return true;
 }
 
-#define GET_EVENT_KEY(func, field)					\
-static u64 get_event_ ##func(struct kvm_event *event, int vcpu)		\
-{									\
-	if (vcpu == -1)							\
-		return event->total.field;				\
-									\
-	if (vcpu >= event->max_vcpu)					\
-		return 0;						\
-									\
-	return event->vcpu[vcpu].field;					\
-}
-
-#define COMPARE_EVENT_KEY(func, field)					\
-GET_EVENT_KEY(func, field)						\
-static int compare_kvm_event_ ## func(struct kvm_event *one,		\
-					struct kvm_event *two, int vcpu)\
-{									\
-	return get_event_ ##func(one, vcpu) >				\
-				get_event_ ##func(two, vcpu);		\
-}
-
-GET_EVENT_KEY(time, time);
-COMPARE_EVENT_KEY(count, stats.n);
-COMPARE_EVENT_KEY(mean, stats.mean);
-GET_EVENT_KEY(max, stats.max);
-GET_EVENT_KEY(min, stats.min);
-
-#define DEF_SORT_NAME_KEY(name, compare_key)				\
-	{ #name, compare_kvm_event_ ## compare_key }
-
-static struct kvm_event_key keys[] = {
-	DEF_SORT_NAME_KEY(sample, count),
-	DEF_SORT_NAME_KEY(time, mean),
-	{ NULL, NULL }
-};
-
-static bool select_key(struct perf_kvm_stat *kvm)
+static bool is_valid_key(struct perf_kvm_stat *kvm)
 {
-	int i;
+	static const char *key_array[] = {
+		"ev_name", "sample", "time", "max_t", "min_t", "mean_t",
+	};
+	unsigned int i;
 
-	for (i = 0; keys[i].name; i++) {
-		if (!strcmp(keys[i].name, kvm->sort_key)) {
-			kvm->compare = keys[i].key;
+	for (i = 0; i < ARRAY_SIZE(key_array); i++)
+		if (!strcmp(key_array[i], kvm->sort_key))
 			return true;
-		}
-	}
 
-	pr_err("Unknown compare key:%s\n", kvm->sort_key);
+	pr_err("Unsupported sort key: %s\n", kvm->sort_key);
 	return false;
 }
 
-static void insert_to_result(struct rb_root *result, struct kvm_event *event,
-			     key_cmp_fun bigger, int vcpu)
-{
-	struct rb_node **rb = &result->rb_node;
-	struct rb_node *parent = NULL;
-	struct kvm_event *p;
-
-	while (*rb) {
-		p = container_of(*rb, struct kvm_event, rb);
-		parent = *rb;
-
-		if (bigger(event, p, vcpu))
-			rb = &(*rb)->rb_left;
-		else
-			rb = &(*rb)->rb_right;
-	}
-
-	rb_link_node(&event->rb, parent, rb);
-	rb_insert_color(&event->rb, result);
-}
-
-static void
-update_total_count(struct perf_kvm_stat *kvm, struct kvm_event *event)
-{
-	int vcpu = kvm->trace_vcpu;
-
-	kvm->total_count += get_event_count(event, vcpu);
-	kvm->total_time += get_event_time(event, vcpu);
-}
-
 static bool event_is_valid(struct kvm_event *event, int vcpu)
 {
 	return !!get_event_count(event, vcpu);
 }
 
-static void sort_result(struct perf_kvm_stat *kvm)
+static int filter_cb(struct hist_entry *he, void *arg __maybe_unused)
 {
-	unsigned int i;
-	int vcpu = kvm->trace_vcpu;
 	struct kvm_event *event;
+	struct perf_kvm_stat *perf_kvm;
 
-	for (i = 0; i < EVENTS_CACHE_SIZE; i++) {
-		list_for_each_entry(event, &kvm->kvm_events_cache[i], hash_entry) {
-			if (event_is_valid(event, vcpu)) {
-				update_total_count(kvm, event);
-				insert_to_result(&kvm->result, event,
-						 kvm->compare, vcpu);
-			}
-		}
-	}
+	event = container_of(he, struct kvm_event, he);
+	perf_kvm = event->perf_kvm;
+	if (!event_is_valid(event, perf_kvm->trace_vcpu))
+		he->filtered = 1;
+	else
+		he->filtered = 0;
+	return 0;
 }
 
-/* returns left most element of result, and erase it */
-static struct kvm_event *pop_from_result(struct rb_root *result)
+static void sort_result(struct perf_kvm_stat *kvm)
 {
-	struct rb_node *node = rb_first(result);
+	struct ui_progress prog;
+	const char *output_columns = "ev_name,sample,percent_sample,"
+				     "time,percent_time,max_t,min_t,mean_t";
 
-	if (!node)
-		return NULL;
-
-	rb_erase(node, result);
-	return container_of(node, struct kvm_event, rb);
+	kvm_hists__reinit(output_columns, kvm->sort_key);
+	ui_progress__init(&prog, kvm_hists.hists.nr_entries, "Sorting...");
+	hists__collapse_resort(&kvm_hists.hists, NULL);
+	hists__output_resort_cb(&kvm_hists.hists, NULL, filter_cb);
+	ui_progress__finish();
 }
 
 static void print_vcpu_info(struct perf_kvm_stat *kvm)
@@ -606,9 +1110,10 @@ static void show_timeofday(void)
 
 static void print_result(struct perf_kvm_stat *kvm)
 {
-	char decode[decode_str_len];
+	char decode[KVM_EVENT_NAME_LEN];
 	struct kvm_event *event;
 	int vcpu = kvm->trace_vcpu;
+	struct rb_node *nd;
 
 	if (kvm->live) {
 		puts(CONSOLE_CLEAR);
@@ -617,7 +1122,7 @@ static void print_result(struct perf_kvm_stat *kvm)
 
 	pr_info("\n\n");
 	print_vcpu_info(kvm);
-	pr_info("%*s ", decode_str_len, kvm->events_ops->name);
+	pr_info("%*s ", KVM_EVENT_NAME_LEN, kvm->events_ops->name);
 	pr_info("%10s ", "Samples");
 	pr_info("%9s ", "Samples%");
 
@@ -627,16 +1132,22 @@ static void print_result(struct perf_kvm_stat *kvm)
 	pr_info("%16s ", "Avg time");
 	pr_info("\n\n");
 
-	while ((event = pop_from_result(&kvm->result))) {
+	for (nd = rb_first_cached(&kvm_hists.hists.entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *he;
 		u64 ecount, etime, max, min;
 
+		he = rb_entry(nd, struct hist_entry, rb_node);
+		if (he->filtered)
+			continue;
+
+		event = container_of(he, struct kvm_event, he);
 		ecount = get_event_count(event, vcpu);
 		etime = get_event_time(event, vcpu);
 		max = get_event_max(event, vcpu);
 		min = get_event_min(event, vcpu);
 
 		kvm->events_ops->decode_key(kvm, &event->key, decode);
-		pr_info("%*s ", decode_str_len, decode);
+		pr_info("%*s ", KVM_EVENT_NAME_LEN, decode);
 		pr_info("%10llu ", (unsigned long long)ecount);
 		pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
 		pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
@@ -690,6 +1201,11 @@ static int process_sample_event(struct perf_tool *tool,
 	if (skip_sample(kvm, sample))
 		return 0;
 
+	if (machine__resolve(machine, &kvm->al, sample) < 0) {
+		pr_warning("Fail to resolve address location, skip sample.\n");
+		return 0;
+	}
+
 	thread = machine__findnew_thread(machine, sample->pid, sample->tid);
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
@@ -901,8 +1417,11 @@ static int perf_kvm__handle_timerfd(struct perf_kvm_stat *kvm)
 	sort_result(kvm);
 	print_result(kvm);
 
+	/* Reset sort list to "ev_name" */
+	kvm_hists__reinit(NULL, "ev_name");
+
 	/* reset counts */
-	clear_events_cache_stats(kvm->kvm_events_cache);
+	clear_events_cache_stats();
 	kvm->total_count = 0;
 	kvm->total_time = 0;
 	kvm->lost_events = 0;
@@ -952,13 +1471,14 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
 		return ret;
 
 	if (!verify_vcpu(kvm->trace_vcpu) ||
-	    !select_key(kvm) ||
+	    !is_valid_key(kvm) ||
 	    !register_kvm_events_ops(kvm)) {
 		goto out;
 	}
 
 	set_term_quiet_input(&save);
-	init_kvm_event_record(kvm);
+
+	kvm_hists__init();
 
 	signal(SIGINT, sig_handler);
 	signal(SIGTERM, sig_handler);
@@ -1009,6 +1529,8 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
 	}
 
 out:
+	hists__delete_entries(&kvm_hists.hists);
+
 	if (kvm->timerfd >= 0)
 		close(kvm->timerfd);
 
@@ -1146,23 +1668,32 @@ static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm)
 	if (!verify_vcpu(vcpu))
 		goto exit;
 
-	if (!select_key(kvm))
+	if (!is_valid_key(kvm))
 		goto exit;
 
 	if (!register_kvm_events_ops(kvm))
 		goto exit;
 
-	init_kvm_event_record(kvm);
-	setup_pager();
+	if (kvm->use_stdio) {
+		use_browser = 0;
+		setup_pager();
+	} else {
+		use_browser = 1;
+	}
+
+	setup_browser(false);
+
+	kvm_hists__init();
 
 	ret = read_events(kvm);
 	if (ret)
 		goto exit;
 
 	sort_result(kvm);
-	print_result(kvm);
+	kvm_display(kvm);
 
 exit:
+	hists__delete_entries(&kvm_hists.hists);
 	return ret;
 }
 
@@ -1267,6 +1798,7 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
 		OPT_STRING('p', "pid", &kvm->opts.target.pid, "pid",
 			   "analyze events only for given process id(s)"),
 		OPT_BOOLEAN('f', "force", &kvm->force, "don't complain, do it"),
+		OPT_BOOLEAN(0, "stdio", &kvm->use_stdio, "use the stdio interface"),
 		OPT_END()
 	};
 
@@ -1284,6 +1816,10 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
 					   kvm_events_report_options);
 	}
 
+#ifndef HAVE_SLANG_SUPPORT
+	kvm->use_stdio = true;
+#endif
+
 	if (!kvm->opts.target.pid)
 		kvm->opts.target.system_wide = true;