62 files changed, 1645 insertions, 805 deletions

diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 86f9301903c8..5f2fc4441b11 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_X86_NMI_H
 #define _ASM_X86_NMI_H
 
+#include <linux/irq_work.h>
 #include <linux/pm.h>
 #include <asm/irq.h>
 #include <asm/io.h>
@@ -38,6 +39,8 @@ typedef int (*nmi_handler_t)(unsigned int, struct pt_regs *);
 struct nmiaction {
         struct list_head        list;
         nmi_handler_t           handler;
+        u64                     max_duration;
+        struct irq_work         irq_work;
         unsigned long           flags;
         const char              *name;
 };
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index c88f7f4b03ee..b262c6124cf3 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -66,6 +66,47 @@ DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4");
 DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31");
 DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63");
 
+static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
+static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
+static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event);
+static void uncore_pmu_event_read(struct perf_event *event);
+
+static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
+{
+        return container_of(event->pmu, struct intel_uncore_pmu, pmu);
+}
+
+static struct intel_uncore_box *
+uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
+{
+        struct intel_uncore_box *box;
+
+        box = *per_cpu_ptr(pmu->box, cpu);
+        if (box)
+                return box;
+
+        raw_spin_lock(&uncore_box_lock);
+        list_for_each_entry(box, &pmu->box_list, list) {
+                if (box->phys_id == topology_physical_package_id(cpu)) {
+                        atomic_inc(&box->refcnt);
+                        *per_cpu_ptr(pmu->box, cpu) = box;
+                        break;
+                }
+        }
+        raw_spin_unlock(&uncore_box_lock);
+
+        return *per_cpu_ptr(pmu->box, cpu);
+}
+
+static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
+{
+        /*
+         * perf core schedules event on the basis of cpu, uncore events are
+         * collected by one of the cpus inside a physical package.
+         */
+        return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
+}
+
 static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
 {
         u64 count;
@@ -1639,6 +1680,345 @@ static struct intel_uncore_type *snb_msr_uncores[] = {
         &snb_uncore_cbox,
         NULL,
 };
+
+enum {
+        SNB_PCI_UNCORE_IMC,
+};
+
+static struct uncore_event_desc snb_uncore_imc_events[] = {
+        INTEL_UNCORE_EVENT_DESC(data_reads,  "event=0x01"),
+        INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"),
+        INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"),
+
+        INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"),
+        INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"),
+        INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"),
+
+        { /* end: all zeroes */ },
+};
+
+#define SNB_UNCORE_PCI_IMC_EVENT_MASK           0xff
+#define SNB_UNCORE_PCI_IMC_BAR_OFFSET           0x48
+
+/* page size multiple covering all config regs */
+#define SNB_UNCORE_PCI_IMC_MAP_SIZE             0x6000
+
+#define SNB_UNCORE_PCI_IMC_DATA_READS           0x1
+#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE      0x5050
+#define SNB_UNCORE_PCI_IMC_DATA_WRITES          0x2
+#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE     0x5054
+#define SNB_UNCORE_PCI_IMC_CTR_BASE             SNB_UNCORE_PCI_IMC_DATA_READS_BASE
+
+static struct attribute *snb_uncore_imc_formats_attr[] = {
+        &format_attr_event.attr,
+        NULL,
+};
+
+static struct attribute_group snb_uncore_imc_format_group = {
+        .name = "format",
+        .attrs = snb_uncore_imc_formats_attr,
+};
+
+static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
+{
+        struct pci_dev *pdev = box->pci_dev;
+        u32 addr_lo, addr_hi;
+        resource_size_t addr;
+
+        pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET, &addr_lo);
+        addr = addr_lo;
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+        pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET+4, &addr_hi);
+        addr = ((resource_size_t)addr_hi << 32) | addr_lo;
+#endif
+
+        addr &= ~(PAGE_SIZE - 1);
+
+        box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
+        box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
+}
+
+static void snb_uncore_imc_enable_box(struct intel_uncore_box *box)
+{}
+
+static void snb_uncore_imc_disable_box(struct intel_uncore_box *box)
+{}
+
+static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{}
+
+static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{}
+
+static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+        struct hw_perf_event *hwc = &event->hw;
+
+        return (u64)*(unsigned int *)(box->io_addr + hwc->event_base);
+}
+
+/*
+ * custom event_init() function because we define our own fixed, free
+ * running counters, so we do not want to conflict with generic uncore
+ * logic. Also simplifies processing
+ */
+static int snb_uncore_imc_event_init(struct perf_event *event)
+{
+        struct intel_uncore_pmu *pmu;
+        struct intel_uncore_box *box;
+        struct hw_perf_event *hwc = &event->hw;
+        u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK;
+        int idx, base;
+
+        if (event->attr.type != event->pmu->type)
+                return -ENOENT;
+
+        pmu = uncore_event_to_pmu(event);
+        /* no device found for this pmu */
+        if (pmu->func_id < 0)
+                return -ENOENT;
+
+        /* Sampling not supported yet */
+        if (hwc->sample_period)
+                return -EINVAL;
+
+        /* unsupported modes and filters */
+        if (event->attr.exclude_user   ||
+            event->attr.exclude_kernel ||
+            event->attr.exclude_hv     ||
+            event->attr.exclude_idle   ||
+            event->attr.exclude_host   ||
+            event->attr.exclude_guest  ||
+            event->attr.sample_period) /* no sampling */
+                return -EINVAL;
+
+        /*
+         * Place all uncore events for a particular physical package
+         * onto a single cpu
+         */
+        if (event->cpu < 0)
+                return -EINVAL;
+
+        /* check only supported bits are set */
+        if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK)
+                return -EINVAL;
+
+        box = uncore_pmu_to_box(pmu, event->cpu);
+        if (!box || box->cpu < 0)
+                return -EINVAL;
+
+        event->cpu = box->cpu;
+
+        event->hw.idx = -1;
+        event->hw.last_tag = ~0ULL;
+        event->hw.extra_reg.idx = EXTRA_REG_NONE;
+        event->hw.branch_reg.idx = EXTRA_REG_NONE;
+        /*
+         * check event is known (whitelist, determines counter)
+         */
+        switch (cfg) {
+        case SNB_UNCORE_PCI_IMC_DATA_READS:
+                base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE;
+                idx = UNCORE_PMC_IDX_FIXED;
+                break;
+        case SNB_UNCORE_PCI_IMC_DATA_WRITES:
+                base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE;
+                idx = UNCORE_PMC_IDX_FIXED + 1;
+                break;
+        default:
+                return -EINVAL;
+        }
+
+        /* must be done before validate_group */
+        event->hw.event_base = base;
+        event->hw.config = cfg;
+        event->hw.idx = idx;
+
+        /* no group validation needed, we have free running counters */
+
+        return 0;
+}
+
+static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+        return 0;
+}
+
+static void snb_uncore_imc_event_start(struct perf_event *event, int flags)
+{
+        struct intel_uncore_box *box = uncore_event_to_box(event);
+        u64 count;
+
+        if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+                return;
+
+        event->hw.state = 0;
+        box->n_active++;
+
+        list_add_tail(&event->active_entry, &box->active_list);
+
+        count = snb_uncore_imc_read_counter(box, event);
+        local64_set(&event->hw.prev_count, count);
+
+        if (box->n_active == 1)
+                uncore_pmu_start_hrtimer(box);
+}
+
+static void snb_uncore_imc_event_stop(struct perf_event *event, int flags)
+{
+        struct intel_uncore_box *box = uncore_event_to_box(event);
+        struct hw_perf_event *hwc = &event->hw;
+
+        if (!(hwc->state & PERF_HES_STOPPED)) {
+                box->n_active--;
+
+                WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+                hwc->state |= PERF_HES_STOPPED;
+
+                list_del(&event->active_entry);
+
+                if (box->n_active == 0)
+                        uncore_pmu_cancel_hrtimer(box);
+        }
+
+        if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+                /*
+                 * Drain the remaining delta count out of a event
+                 * that we are disabling:
+                 */
+                uncore_perf_event_update(box, event);
+                hwc->state |= PERF_HES_UPTODATE;
+        }
+}
+
+static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
+{
+        struct intel_uncore_box *box = uncore_event_to_box(event);
+        struct hw_perf_event *hwc = &event->hw;
+
+        if (!box)
+                return -ENODEV;
+
+        hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+        if (!(flags & PERF_EF_START))
+                hwc->state |= PERF_HES_ARCH;
+
+        snb_uncore_imc_event_start(event, 0);
+
+        box->n_events++;
+
+        return 0;
+}
+
+static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
+{
+        struct intel_uncore_box *box = uncore_event_to_box(event);
+        int i;
+
+        snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
+
+        for (i = 0; i < box->n_events; i++) {
+                if (event == box->event_list[i]) {
+                        --box->n_events;
+                        break;
+                }
+        }
+}
+
+static int snb_pci2phy_map_init(int devid)
+{
+        struct pci_dev *dev = NULL;
+        int bus;
+
+        dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev);
+        if (!dev)
+                return -ENOTTY;
+
+        bus = dev->bus->number;
+
+        pcibus_to_physid[bus] = 0;
+
+        pci_dev_put(dev);
+
+        return 0;
+}
+
+static struct pmu snb_uncore_imc_pmu = {
+        .task_ctx_nr    = perf_invalid_context,
+        .event_init     = snb_uncore_imc_event_init,
+        .add            = snb_uncore_imc_event_add,
+        .del            = snb_uncore_imc_event_del,
+        .start          = snb_uncore_imc_event_start,
+        .stop           = snb_uncore_imc_event_stop,
+        .read           = uncore_pmu_event_read,
+};
+
+static struct intel_uncore_ops snb_uncore_imc_ops = {
+        .init_box       = snb_uncore_imc_init_box,
+        .enable_box     = snb_uncore_imc_enable_box,
+        .disable_box    = snb_uncore_imc_disable_box,
+        .disable_event  = snb_uncore_imc_disable_event,
+        .enable_event   = snb_uncore_imc_enable_event,
+        .hw_config      = snb_uncore_imc_hw_config,
+        .read_counter   = snb_uncore_imc_read_counter,
+};
+
+static struct intel_uncore_type snb_uncore_imc = {
+        .name           = "imc",
+        .num_counters   = 2,
+        .num_boxes      = 1,
+        .fixed_ctr_bits = 32,
+        .fixed_ctr      = SNB_UNCORE_PCI_IMC_CTR_BASE,
+        .event_descs    = snb_uncore_imc_events,
+        .format_group   = &snb_uncore_imc_format_group,
+        .perf_ctr       = SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
+        .event_mask     = SNB_UNCORE_PCI_IMC_EVENT_MASK,
+        .ops            = &snb_uncore_imc_ops,
+        .pmu            = &snb_uncore_imc_pmu,
+};
+
+static struct intel_uncore_type *snb_pci_uncores[] = {
+        [SNB_PCI_UNCORE_IMC]    = &snb_uncore_imc,
+        NULL,
+};
+
+static DEFINE_PCI_DEVICE_TABLE(snb_uncore_pci_ids) = {
+        { /* IMC */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC),
+                .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+        },
+};
+
+static DEFINE_PCI_DEVICE_TABLE(ivb_uncore_pci_ids) = {
+        { /* IMC */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC),
+                .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+        },
+};
+
+static DEFINE_PCI_DEVICE_TABLE(hsw_uncore_pci_ids) = {
+        { /* IMC */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
+                .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+        },
+};
+
+static struct pci_driver snb_uncore_pci_driver = {
+        .name           = "snb_uncore",
+        .id_table       = snb_uncore_pci_ids,
+};
+
+static struct pci_driver ivb_uncore_pci_driver = {
+        .name           = "ivb_uncore",
+        .id_table       = ivb_uncore_pci_ids,
+};
+
+static struct pci_driver hsw_uncore_pci_driver = {
+        .name           = "hsw_uncore",
+        .id_table       = hsw_uncore_pci_ids,
+};
+
 /* end of Sandy Bridge uncore support */
 
 /* Nehalem uncore support */
@@ -2789,6 +3169,7 @@ again:
 static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
 {
         struct intel_uncore_box *box;
+        struct perf_event *event;
         unsigned long flags;
         int bit;
 
@@ -2801,19 +3182,27 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
          */
         local_irq_save(flags);
 
+        /*
+         * handle boxes with an active event list as opposed to active
+         * counters
+         */
+        list_for_each_entry(event, &box->active_list, active_entry) {
+                uncore_perf_event_update(box, event);
+        }
+
         for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX)
                 uncore_perf_event_update(box, box->events[bit]);
 
         local_irq_restore(flags);
 
-        hrtimer_forward_now(hrtimer, ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL));
+        hrtimer_forward_now(hrtimer, ns_to_ktime(box->hrtimer_duration));
         return HRTIMER_RESTART;
 }
 
 static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
 {
         __hrtimer_start_range_ns(&box->hrtimer,
-                        ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL), 0,
+                        ns_to_ktime(box->hrtimer_duration), 0,
                         HRTIMER_MODE_REL_PINNED, 0);
 }
 
@@ -2847,43 +3236,12 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
         box->cpu = -1;
         box->phys_id = -1;
 
-        return box;
-}
+        /* set default hrtimer timeout */
+        box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL;
 
-static struct intel_uncore_box *
-uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
-{
-        struct intel_uncore_box *box;
+        INIT_LIST_HEAD(&box->active_list);
 
-        box = *per_cpu_ptr(pmu->box, cpu);
-        if (box)
-                return box;
-
-        raw_spin_lock(&uncore_box_lock);
-        list_for_each_entry(box, &pmu->box_list, list) {
-                if (box->phys_id == topology_physical_package_id(cpu)) {
-                        atomic_inc(&box->refcnt);
-                        *per_cpu_ptr(pmu->box, cpu) = box;
-                        break;
-                }
-        }
-        raw_spin_unlock(&uncore_box_lock);
-
-        return *per_cpu_ptr(pmu->box, cpu);
-}
-
-static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
-{
-        return container_of(event->pmu, struct intel_uncore_pmu, pmu);
-}
-
-static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
-{
-        /*
-         * perf core schedules event on the basis of cpu, uncore events are
-         * collected by one of the cpus inside a physical package.
-         */
-        return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
+        return box;
 }
 
 static int
@@ -3279,16 +3637,21 @@ static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu)
 {
         int ret;
 
-        pmu->pmu = (struct pmu) {
-                .attr_groups    = pmu->type->attr_groups,
-                .task_ctx_nr    = perf_invalid_context,
-                .event_init     = uncore_pmu_event_init,
-                .add            = uncore_pmu_event_add,
-                .del            = uncore_pmu_event_del,
-                .start          = uncore_pmu_event_start,
-                .stop           = uncore_pmu_event_stop,
-                .read           = uncore_pmu_event_read,
-        };
+        if (!pmu->type->pmu) {
+                pmu->pmu = (struct pmu) {
+                        .attr_groups    = pmu->type->attr_groups,
+                        .task_ctx_nr    = perf_invalid_context,
+                        .event_init     = uncore_pmu_event_init,
+                        .add            = uncore_pmu_event_add,
+                        .del            = uncore_pmu_event_del,
+                        .start          = uncore_pmu_event_start,
+                        .stop           = uncore_pmu_event_stop,
+                        .read           = uncore_pmu_event_read,
+                };
+        } else {
+                pmu->pmu = *pmu->type->pmu;
+                pmu->pmu.attr_groups = pmu->type->attr_groups;
+        }
 
         if (pmu->type->num_boxes == 1) {
                 if (strlen(pmu->type->name) > 0)
@@ -3501,6 +3864,28 @@ static int __init uncore_pci_init(void)
                 pci_uncores = ivt_pci_uncores;
                 uncore_pci_driver = &ivt_uncore_pci_driver;
                 break;
+        case 42: /* Sandy Bridge */
+                ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_SNB_IMC);
+                if (ret)
+                        return ret;
+                pci_uncores = snb_pci_uncores;
+                uncore_pci_driver = &snb_uncore_pci_driver;
+                break;
+        case 58: /* Ivy Bridge */
+                ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_IVB_IMC);
+                if (ret)
+                        return ret;
+                pci_uncores = snb_pci_uncores;
+                uncore_pci_driver = &ivb_uncore_pci_driver;
+                break;
+        case 60: /* Haswell */
+        case 69: /* Haswell Celeron */
+                ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_HSW_IMC);
+                if (ret)
+                        return ret;
+                pci_uncores = snb_pci_uncores;
+                uncore_pci_driver = &hsw_uncore_pci_driver;
+                break;
         default:
                 return 0;
         }
@@ -3772,7 +4157,7 @@ static void __init uncore_cpu_setup(void *dummy)
 
 static int __init uncore_cpu_init(void)
 {
-        int ret, cpu, max_cores;
+        int ret, max_cores;
 
         max_cores = boot_cpu_data.x86_max_cores;
         switch (boot_cpu_data.x86_model) {
@@ -3816,29 +4201,6 @@ static int __init uncore_cpu_init(void)
         if (ret)
                 return ret;
 
-        get_online_cpus();
-
-        for_each_online_cpu(cpu) {
-                int i, phys_id = topology_physical_package_id(cpu);
-
-                for_each_cpu(i, &uncore_cpu_mask) {
-                        if (phys_id == topology_physical_package_id(i)) {
-                                phys_id = -1;
-                                break;
-                        }
-                }
-                if (phys_id < 0)
-                        continue;
-
-                uncore_cpu_prepare(cpu, phys_id);
-                uncore_event_init_cpu(cpu);
-        }
-        on_each_cpu(uncore_cpu_setup, NULL, 1);
-
-        register_cpu_notifier(&uncore_cpu_nb);
-
-        put_online_cpus();
-
         return 0;
 }
 
@@ -3867,6 +4229,41 @@ static int __init uncore_pmus_register(void)
         return 0;
 }
 
+static void uncore_cpumask_init(void)
+{
+        int cpu;
+
+        /*
+         * ony invoke once from msr or pci init code
+         */
+        if (!cpumask_empty(&uncore_cpu_mask))
+                return;
+
+        get_online_cpus();
+
+        for_each_online_cpu(cpu) {
+                int i, phys_id = topology_physical_package_id(cpu);
+
+                for_each_cpu(i, &uncore_cpu_mask) {
+                        if (phys_id == topology_physical_package_id(i)) {
+                                phys_id = -1;
+                                break;
+                        }
+                }
+                if (phys_id < 0)
+                        continue;
+
+                uncore_cpu_prepare(cpu, phys_id);
+                uncore_event_init_cpu(cpu);
+        }
+        on_each_cpu(uncore_cpu_setup, NULL, 1);
+
+        register_cpu_notifier(&uncore_cpu_nb);
+
+        put_online_cpus();
+}
+
+
 static int __init intel_uncore_init(void)
 {
         int ret;
@@ -3885,6 +4282,7 @@ static int __init intel_uncore_init(void)
                 uncore_pci_exit();
                 goto fail;
         }
+        uncore_cpumask_init();
 
         uncore_pmus_register();
         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 a80ab71a883d..90236f0c94a9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -6,6 +6,7 @@
 
 #define UNCORE_PMU_NAME_LEN             32
 #define UNCORE_PMU_HRTIMER_INTERVAL     (60LL * NSEC_PER_SEC)
+#define UNCORE_SNB_IMC_HRTIMER_INTERVAL (5ULL * NSEC_PER_SEC)
 
 #define UNCORE_FIXED_EVENT              0xff
 #define UNCORE_PMC_IDX_MAX_GENERIC      8
@@ -440,6 +441,7 @@ struct intel_uncore_type {
         struct intel_uncore_ops *ops;
         struct uncore_event_desc *event_descs;
         const struct attribute_group *attr_groups[4];
+        struct pmu *pmu; /* for custom pmu ops */
 };
 
 #define pmu_group attr_groups[0]
@@ -488,8 +490,11 @@ struct intel_uncore_box {
         u64 tags[UNCORE_PMC_IDX_MAX];
         struct pci_dev *pci_dev;
         struct intel_uncore_pmu *pmu;
+        u64 hrtimer_duration; /* hrtimer timeout for this box */
         struct hrtimer hrtimer;
         struct list_head list;
+        struct list_head active_list;
+        void *io_addr;
         struct intel_uncore_extra_reg shared_regs[0];
 };
 
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 3486e6660357..5d466b7d8609 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1257,7 +1257,24 @@ again:
                         pass++;
                         goto again;
                 }
-
+                /*
+                 * Perf does test runs to see if a whole group can be assigned
+                 * together succesfully.  There can be multiple rounds of this.
+                 * Unfortunately, p4_pmu_swap_config_ts touches the hwc->config
+                 * bits, such that the next round of group assignments will
+                 * cause the above p4_should_swap_ts to pass instead of fail.
+                 * This leads to counters exclusive to thread0 being used by
+                 * thread1.
+                 *
+                 * Solve this with a cheap hack, reset the idx back to -1 to
+                 * force a new lookup (p4_next_cntr) to get the right counter
+                 * for the right thread.
+                 *
+                 * This probably doesn't comply with the general spirit of how
+                 * perf wants to work, but P4 is special. :-(
+                 */
+                if (p4_should_swap_ts(hwc->config, cpu))
+                        hwc->idx = -1;
                 p4_pmu_swap_config_ts(hwc, cpu);
                 if (assign)
                         assign[i] = cntr_idx;
@@ -1322,6 +1339,7 @@ static __initconst const struct x86_pmu p4_pmu = {
 __init int p4_pmu_init(void)
 {
         unsigned int low, high;
+        int i, reg;
 
         /* If we get stripped -- indexing fails */
         BUILD_BUG_ON(ARCH_P4_MAX_CCCR > INTEL_PMC_MAX_GENERIC);
@@ -1340,5 +1358,19 @@ __init int p4_pmu_init(void)
 
         x86_pmu = p4_pmu;
 
+        /*
+         * Even though the counters are configured to interrupt a particular
+         * logical processor when an overflow happens, testing has shown that
+         * on kdump kernels (which uses a single cpu), thread1's counter
+         * continues to run and will report an NMI on thread0.  Due to the
+         * overflow bug, this leads to a stream of unknown NMIs.
+         *
+         * Solve this by zero'ing out the registers to mimic a reset.
+         */
+        for (i = 0; i < x86_pmu.num_counters; i++) {
+                reg = x86_pmu_config_addr(i);
+                wrmsrl_safe(reg, 0ULL);
+        }
+
         return 0;
 }
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 6fcb49ce50a1..b4872b999a71 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -87,6 +87,7 @@ __setup("unknown_nmi_panic", setup_unknown_nmi_panic);
 #define nmi_to_desc(type) (&nmi_desc[type])
 
 static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC;
+
 static int __init nmi_warning_debugfs(void)
 {
         debugfs_create_u64("nmi_longest_ns", 0644,
@@ -95,6 +96,20 @@ static int __init nmi_warning_debugfs(void)
 }
 fs_initcall(nmi_warning_debugfs);
 
+static void nmi_max_handler(struct irq_work *w)
+{
+        struct nmiaction *a = container_of(w, struct nmiaction, irq_work);
+        int remainder_ns, decimal_msecs;
+        u64 whole_msecs = ACCESS_ONCE(a->max_duration);
+
+        remainder_ns = do_div(whole_msecs, (1000 * 1000));
+        decimal_msecs = remainder_ns / 1000;
+
+        printk_ratelimited(KERN_INFO
+                "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n",
+                a->handler, whole_msecs, decimal_msecs);
+}
+
 static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
 {
         struct nmi_desc *desc = nmi_to_desc(type);
@@ -110,26 +125,20 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
          * to handle those situations.
          */
         list_for_each_entry_rcu(a, &desc->head, list) {
-                u64 before, delta, whole_msecs;
-                int remainder_ns, decimal_msecs, thishandled;
+                int thishandled;
+                u64 delta;
 
-                before = sched_clock();
+                delta = sched_clock();
                 thishandled = a->handler(type, regs);
                 handled += thishandled;
-                delta = sched_clock() - before;
+                delta = sched_clock() - delta;
                 trace_nmi_handler(a->handler, (int)delta, thishandled);
 
-                if (delta < nmi_longest_ns)
+                if (delta < nmi_longest_ns || delta < a->max_duration)
                         continue;
 
-                nmi_longest_ns = delta;
-                whole_msecs = delta;
-                remainder_ns = do_div(whole_msecs, (1000 * 1000));
-                decimal_msecs = remainder_ns / 1000;
-                printk_ratelimited(KERN_INFO
-                        "INFO: NMI handler (%ps) took too long to run: "
-                        "%lld.%03d msecs\n", a->handler, whole_msecs,
-                        decimal_msecs);
+                a->max_duration = delta;
+                irq_work_queue(&a->irq_work);
         }
 
         rcu_read_unlock();
@@ -146,6 +155,8 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action)
         if (!action->handler)
                 return -EINVAL;
 
+        init_irq_work(&action->irq_work, nmi_max_handler);
+
         spin_lock_irqsave(&desc->lock, flags);
 
         /*
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 66017028dcb3..19ae05d4b8ec 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -30,7 +30,9 @@ void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *))
         work->func = func;
 }
 
-void irq_work_queue(struct irq_work *work);
+#define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { .func = (_f), }
+
+bool irq_work_queue(struct irq_work *work);
 void irq_work_run(void);
 void irq_work_sync(struct irq_work *work);
 
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 97fbecdd7a40..7399e6a3e9a0 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2531,6 +2531,9 @@
 
 #define PCI_VENDOR_ID_INTEL             0x8086
 #define PCI_DEVICE_ID_INTEL_EESSC       0x0008
+#define PCI_DEVICE_ID_INTEL_SNB_IMC     0x0100
+#define PCI_DEVICE_ID_INTEL_IVB_IMC     0x0154
+#define PCI_DEVICE_ID_INTEL_HSW_IMC     0x0c00
 #define PCI_DEVICE_ID_INTEL_PXHD_0      0x0320
 #define PCI_DEVICE_ID_INTEL_PXHD_1      0x0321
 #define PCI_DEVICE_ID_INTEL_PXH_0       0x0329
diff --git a/kernel/events/core.c b/kernel/events/core.c
index fa0b2d4ad83c..fa990061aa6c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -231,11 +231,29 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
 #define NR_ACCUMULATED_SAMPLES 128
 static DEFINE_PER_CPU(u64, running_sample_length);
 
-void perf_sample_event_took(u64 sample_len_ns)
+static void perf_duration_warn(struct irq_work *w)
 {
+        u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
         u64 avg_local_sample_len;
         u64 local_samples_len;
+
+        local_samples_len = __get_cpu_var(running_sample_length);
+        avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES;
+
+        printk_ratelimited(KERN_WARNING
+                        "perf interrupt took too long (%lld > %lld), lowering "
+                        "kernel.perf_event_max_sample_rate to %d\n",
+                        avg_local_sample_len, allowed_ns >> 1,
+                        sysctl_perf_event_sample_rate);
+}
+
+static DEFINE_IRQ_WORK(perf_duration_work, perf_duration_warn);
+
+void perf_sample_event_took(u64 sample_len_ns)
+{
         u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
+        u64 avg_local_sample_len;
+        u64 local_samples_len;
 
         if (allowed_ns == 0)
                 return;
@@ -263,13 +281,14 @@ void perf_sample_event_took(u64 sample_len_ns)
         sysctl_perf_event_sample_rate = max_samples_per_tick * HZ;
         perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
 
-        printk_ratelimited(KERN_WARNING
-                        "perf samples too long (%lld > %lld), lowering "
-                        "kernel.perf_event_max_sample_rate to %d\n",
-                        avg_local_sample_len, allowed_ns,
-                        sysctl_perf_event_sample_rate);
-
         update_perf_cpu_limits();
+
+        if (!irq_work_queue(&perf_duration_work)) {
+                early_printk("perf interrupt took too long (%lld > %lld), lowering "
+                             "kernel.perf_event_max_sample_rate to %d\n",
+                             avg_local_sample_len, allowed_ns >> 1,
+                             sysctl_perf_event_sample_rate);
+        }
 }
 
 static atomic64_t perf_event_id;
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 55fcce6065cf..a82170e2fa78 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -61,11 +61,11 @@ void __weak arch_irq_work_raise(void)
  *
  * Can be re-enqueued while the callback is still in progress.
  */
-void irq_work_queue(struct irq_work *work)
+bool irq_work_queue(struct irq_work *work)
 {
         /* Only queue if not already pending */
         if (!irq_work_claim(work))
-                return;
+                return false;
 
         /* Queue the entry and raise the IPI if needed. */
         preempt_disable();
@@ -83,6 +83,8 @@ void irq_work_queue(struct irq_work *work)
         }
 
         preempt_enable();
+
+        return true;
 }
 EXPORT_SYMBOL_GPL(irq_work_queue);
 
diff --git a/tools/include/linux/hash.h b/tools/include/linux/hash.h
new file mode 100644
index 000000000000..d026c6573018
--- /dev/null
+++ b/tools/include/linux/hash.h
@@ -0,0 +1,5 @@
+#include "../../../include/linux/hash.h"
+
+#ifndef _TOOLS_LINUX_HASH_H
+#define _TOOLS_LINUX_HASH_H
+#endif
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index ed2f51e11b80..ce00f7ee6455 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -9,8 +9,10 @@ LIB_H=
 LIB_OBJS=
 
 LIB_H += fs/debugfs.h
+LIB_H += fs/fs.h
 
 LIB_OBJS += $(OUTPUT)fs/debugfs.o
+LIB_OBJS += $(OUTPUT)fs/fs.o
 
 LIBFILE = libapikfs.a
 
diff --git a/tools/perf/util/fs.c b/tools/lib/api/fs/fs.c
index f5be1f26e724..5b5eb788996e 100644
--- a/tools/perf/util/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -1,8 +1,13 @@
+/* TODO merge/factor in debugfs.c here */
 
-/* TODO merge/factor into tools/lib/lk/debugfs.c */
+#include <errno.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/vfs.h>
 
-#include "util.h"
-#include "util/fs.h"
+#include "debugfs.h"
+#include "fs.h"
 
 static const char * const sysfs__fs_known_mountpoints[] = {
         "/sys",
diff --git a/tools/perf/util/include/linux/magic.h b/tools/lib/api/fs/fs.h
index 07d63cf3e0f6..cb7049551f33 100644
--- a/tools/perf/util/include/linux/magic.h
+++ b/tools/lib/api/fs/fs.h
@@ -1,9 +1,5 @@
-#ifndef _PERF_LINUX_MAGIC_H_
-#define _PERF_LINUX_MAGIC_H_
-
-#ifndef DEBUGFS_MAGIC
-#define DEBUGFS_MAGIC          0x64626720
-#endif
+#ifndef __API_FS__
+#define __API_FS__
 
 #ifndef SYSFS_MAGIC
 #define SYSFS_MAGIC            0x62656572
@@ -13,4 +9,6 @@
 #define PROC_SUPER_MAGIC       0x9fa0
 #endif
 
-#endif
+const char *sysfs__mountpoint(void);
+const char *procfs__mountpoint(void);
+#endif /* __API_FS__ */
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index f41572d0dd76..c0c87c87b60f 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -6,6 +6,7 @@ tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/include/asm/bug.h
 tools/include/linux/compiler.h
+tools/include/linux/hash.h
 include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 7257e7e9e38a..77b153fa23a5 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -208,7 +208,7 @@ LIB_H += ../../include/uapi/linux/perf_event.h
 LIB_H += ../../include/linux/rbtree.h
 LIB_H += ../../include/linux/list.h
 LIB_H += ../../include/uapi/linux/const.h
-LIB_H += ../../include/linux/hash.h
+LIB_H += ../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
 LIB_H += util/include/linux/bitops.h
@@ -218,9 +218,7 @@ LIB_H += util/include/linux/ctype.h
 LIB_H += util/include/linux/kernel.h
 LIB_H += util/include/linux/list.h
 LIB_H += util/include/linux/export.h
-LIB_H += util/include/linux/magic.h
 LIB_H += util/include/linux/poison.h
-LIB_H += util/include/linux/prefetch.h
 LIB_H += util/include/linux/rbtree.h
 LIB_H += util/include/linux/rbtree_augmented.h
 LIB_H += util/include/linux/string.h
@@ -244,7 +242,6 @@ LIB_H += util/cache.h
 LIB_H += util/callchain.h
 LIB_H += util/build-id.h
 LIB_H += util/debug.h
-LIB_H += util/fs.h
 LIB_H += util/pmu.h
 LIB_H += util/event.h
 LIB_H += util/evsel.h
@@ -306,7 +303,6 @@ LIB_OBJS += $(OUTPUT)util/annotate.o
 LIB_OBJS += $(OUTPUT)util/build-id.o
 LIB_OBJS += $(OUTPUT)util/config.o
 LIB_OBJS += $(OUTPUT)util/ctype.o
-LIB_OBJS += $(OUTPUT)util/fs.o
 LIB_OBJS += $(OUTPUT)util/pmu.o
 LIB_OBJS += $(OUTPUT)util/environment.o
 LIB_OBJS += $(OUTPUT)util/event.o
@@ -408,6 +404,11 @@ endif
 LIB_OBJS += $(OUTPUT)tests/code-reading.o
 LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
 LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o
+ifndef NO_LIBUNWIND
+ifeq ($(ARCH),x86)
+LIB_OBJS += $(OUTPUT)tests/dwarf-unwind.o
+endif
+endif
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
@@ -476,7 +477,7 @@ endif # NO_DWARF
 endif # NO_LIBELF
 
 ifndef NO_LIBUNWIND
-  LIB_OBJS += $(OUTPUT)util/unwind.o
+  LIB_OBJS += $(OUTPUT)util/unwind-libunwind.o
 endif
 LIB_OBJS += $(OUTPUT)tests/keep-tracking.o
 
@@ -533,6 +534,7 @@ ifeq ($(NO_PERF_REGS),0)
   ifeq ($(ARCH),x86)
     LIB_H += arch/x86/include/perf_regs.h
   endif
+  LIB_OBJS += $(OUTPUT)util/perf_regs.o
 endif
 
 ifndef NO_LIBNUMA
@@ -655,6 +657,9 @@ $(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS
                 -DPYTHON='"$(PYTHON_WORD)"' \
                 $<
 
+$(OUTPUT)tests/dwarf-unwind.o: tests/dwarf-unwind.c
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -fno-optimize-sibling-calls $<
+
 $(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile
index fe9b61e322a5..67e9b3d38e89 100644
--- a/tools/perf/arch/arm/Makefile
+++ b/tools/perf/arch/arm/Makefile
@@ -3,5 +3,5 @@ PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
 ifndef NO_LIBUNWIND
-LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
 endif
diff --git a/tools/perf/arch/arm/util/unwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c
index da3dc950550c..729ed69a6664 100644
--- a/tools/perf/arch/arm/util/unwind.c
+++ b/tools/perf/arch/arm/util/unwind-libunwind.c
@@ -4,7 +4,7 @@
 #include "perf_regs.h"
 #include "../../util/unwind.h"
 
-int unwind__arch_reg_id(int regnum)
+int libunwind__arch_reg_id(int regnum)
 {
         switch (regnum) {
         case UNW_ARM_R0:
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 8801fe02f206..4fa9be983ad1 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -3,7 +3,9 @@ PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
 ifndef NO_LIBUNWIND
-LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/dwarf-unwind.o
 endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index e84ca76aae77..fc819ca34a7e 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -5,14 +5,20 @@
 #include "../../util/types.h"
 #include <asm/perf_regs.h>
 
+void perf_regs_load(u64 *regs);
+
 #ifndef HAVE_ARCH_X86_64_SUPPORT
 #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
+#define PERF_REGS_MAX PERF_REG_X86_32_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32
 #else
 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
                        (1ULL << PERF_REG_X86_ES) | \
                        (1ULL << PERF_REG_X86_FS) | \
                        (1ULL << PERF_REG_X86_GS))
 #define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT)
+#define PERF_REGS_MAX PERF_REG_X86_64_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64
 #endif
 #define PERF_REG_IP PERF_REG_X86_IP
 #define PERF_REG_SP PERF_REG_X86_SP
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
new file mode 100644
index 000000000000..b602ad93ce63
--- /dev/null
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -0,0 +1,59 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "tests/tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+                         struct thread *thread, u64 *regs)
+{
+        struct stack_dump *stack = &sample->user_stack;
+        struct map *map;
+        unsigned long sp;
+        u64 stack_size, *buf;
+
+        buf = malloc(STACK_SIZE);
+        if (!buf) {
+                pr_debug("failed to allocate sample uregs data\n");
+                return -1;
+        }
+
+        sp = (unsigned long) regs[PERF_REG_X86_SP];
+
+        map = map_groups__find(&thread->mg, MAP__FUNCTION, (u64) sp);
+        if (!map) {
+                pr_debug("failed to get stack map\n");
+                return -1;
+        }
+
+        stack_size = map->end - sp;
+        stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+        memcpy(buf, (void *) sp, stack_size);
+        stack->data = (char *) buf;
+        stack->size = stack_size;
+        return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+                             struct thread *thread)
+{
+        struct regs_dump *regs = &sample->user_regs;
+        u64 *buf;
+
+        buf = malloc(sizeof(u64) * PERF_REGS_MAX);
+        if (!buf) {
+                pr_debug("failed to allocate sample uregs data\n");
+                return -1;
+        }
+
+        perf_regs_load(buf);
+        regs->abi  = PERF_SAMPLE_REGS_ABI;
+        regs->regs = buf;
+        regs->mask = PERF_REGS_MASK;
+
+        return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S
new file mode 100644
index 000000000000..99167bf644ea
--- /dev/null
+++ b/tools/perf/arch/x86/tests/regs_load.S
@@ -0,0 +1,92 @@
+
+#include <linux/linkage.h>
+
+#define AX       0
+#define BX       1 * 8
+#define CX       2 * 8
+#define DX       3 * 8
+#define SI       4 * 8
+#define DI       5 * 8
+#define BP       6 * 8
+#define SP       7 * 8
+#define IP       8 * 8
+#define FLAGS    9 * 8
+#define CS      10 * 8
+#define SS      11 * 8
+#define DS      12 * 8
+#define ES      13 * 8
+#define FS      14 * 8
+#define GS      15 * 8
+#define R8      16 * 8
+#define R9      17 * 8
+#define R10     18 * 8
+#define R11     19 * 8
+#define R12     20 * 8
+#define R13     21 * 8
+#define R14     22 * 8
+#define R15     23 * 8
+
+.text
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+ENTRY(perf_regs_load)
+        movq %rax, AX(%rdi)
+        movq %rbx, BX(%rdi)
+        movq %rcx, CX(%rdi)
+        movq %rdx, DX(%rdi)
+        movq %rsi, SI(%rdi)
+        movq %rdi, DI(%rdi)
+        movq %rbp, BP(%rdi)
+
+        leaq 8(%rsp), %rax /* exclude this call.  */
+        movq %rax, SP(%rdi)
+
+        movq 0(%rsp), %rax
+        movq %rax, IP(%rdi)
+
+        movq $0, FLAGS(%rdi)
+        movq $0, CS(%rdi)
+        movq $0, SS(%rdi)
+        movq $0, DS(%rdi)
+        movq $0, ES(%rdi)
+        movq $0, FS(%rdi)
+        movq $0, GS(%rdi)
+
+        movq %r8,  R8(%rdi)
+        movq %r9,  R9(%rdi)
+        movq %r10, R10(%rdi)
+        movq %r11, R11(%rdi)
+        movq %r12, R12(%rdi)
+        movq %r13, R13(%rdi)
+        movq %r14, R14(%rdi)
+        movq %r15, R15(%rdi)
+        ret
+ENDPROC(perf_regs_load)
+#else
+ENTRY(perf_regs_load)
+        push %edi
+        movl 8(%esp), %edi
+        movl %eax, AX(%edi)
+        movl %ebx, BX(%edi)
+        movl %ecx, CX(%edi)
+        movl %edx, DX(%edi)
+        movl %esi, SI(%edi)
+        pop %eax
+        movl %eax, DI(%edi)
+        movl %ebp, BP(%edi)
+
+        leal 4(%esp), %eax /* exclude this call.  */
+        movl %eax, SP(%edi)
+
+        movl 0(%esp), %eax
+        movl %eax, IP(%edi)
+
+        movl $0, FLAGS(%edi)
+        movl $0, CS(%edi)
+        movl $0, SS(%edi)
+        movl $0, DS(%edi)
+        movl $0, ES(%edi)
+        movl $0, FS(%edi)
+        movl $0, GS(%edi)
+        ret
+ENDPROC(perf_regs_load)
+#endif
diff --git a/tools/perf/arch/x86/util/unwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
index 456a88cf5b37..3261f68c6a7c 100644
--- a/tools/perf/arch/x86/util/unwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -5,7 +5,7 @@
 #include "../../util/unwind.h"
 
 #ifdef HAVE_ARCH_X86_64_SUPPORT
-int unwind__arch_reg_id(int regnum)
+int libunwind__arch_reg_id(int regnum)
 {
         int id;
 
@@ -69,7 +69,7 @@ int unwind__arch_reg_id(int regnum)
         return id;
 }
 #else
-int unwind__arch_reg_id(int regnum)
+int libunwind__arch_reg_id(int regnum)
 {
         int id;
 
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index b3466018bbd7..3a7387551369 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -312,7 +312,6 @@ found:
         sample_sw.period = sample->period;
         sample_sw.time   = sample->time;
         perf_event__synthesize_sample(event_sw, evsel->attr.sample_type,
-                                      evsel->attr.sample_regs_user,
                                       evsel->attr.read_format, &sample_sw,
                                       false);
         build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine);
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 78948882e3de..cdcd4eb3a57d 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -268,9 +268,9 @@ static int opt_set_filter(const struct option *opt __maybe_unused,
         return 0;
 }
 
-static void init_params(void)
+static int init_params(void)
 {
-        line_range__init(&params.line_range);
+        return line_range__init(&params.line_range);
 }
 
 static void cleanup_params(void)
@@ -515,9 +515,11 @@ int cmd_probe(int argc, const char **argv, const char *prefix)
 {
         int ret;
 
-        init_params();
-        ret = __cmd_probe(argc, argv, prefix);
-        cleanup_params();
+        ret = init_params();
+        if (!ret) {
+                ret = __cmd_probe(argc, argv, prefix);
+                cleanup_params();
+        }
 
         return ret;
 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index af47531b82ec..eb524f91bffe 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -649,7 +649,7 @@ error:
         return ret;
 }
 
-#ifdef HAVE_LIBUNWIND_SUPPORT
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
 static int get_stack_size(char *str, unsigned long *_size)
 {
         char *endptr;
@@ -675,7 +675,7 @@ static int get_stack_size(char *str, unsigned long *_size)
                max_size, str);
         return -1;
 }
-#endif /* HAVE_LIBUNWIND_SUPPORT */
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
 
 int record_parse_callchain(const char *arg, struct record_opts *opts)
 {
@@ -704,7 +704,7 @@ int record_parse_callchain(const char *arg, struct record_opts *opts)
                                        "needed for -g fp\n");
                         break;
 
-#ifdef HAVE_LIBUNWIND_SUPPORT
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
                 /* Dwarf style */
                 } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
                         const unsigned long default_stack_dump_size = 8192;
@@ -720,7 +720,7 @@ int record_parse_callchain(const char *arg, struct record_opts *opts)
                                 ret = get_stack_size(tok, &size);
                                 opts->stack_dump_size = size;
                         }
-#endif /* HAVE_LIBUNWIND_SUPPORT */
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
                 } else {
                         pr_err("callchain: Unknown --call-graph option "
                                "value: %s\n", arg);
@@ -735,7 +735,9 @@ int record_parse_callchain(const char *arg, struct record_opts *opts)
 
 static void callchain_debug(struct record_opts *opts)
 {
-        pr_debug("callchain: type %d\n", opts->call_graph);
+        static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF" };
+
+        pr_debug("callchain: type %s\n", str[opts->call_graph]);
 
         if (opts->call_graph == CALLCHAIN_DWARF)
                 pr_debug("callchain: stack dump size %d\n",
@@ -749,6 +751,8 @@ int record_parse_callchain_opt(const struct option *opt,
         struct record_opts *opts = opt->value;
         int ret;
 
+        opts->call_graph_enabled = !unset;
+
         /* --no-call-graph */
         if (unset) {
                 opts->call_graph = CALLCHAIN_NONE;
@@ -769,6 +773,8 @@ int record_callchain_opt(const struct option *opt,
 {
         struct record_opts *opts = opt->value;
 
+        opts->call_graph_enabled = !unset;
+
         if (opts->call_graph == CALLCHAIN_NONE)
                 opts->call_graph = CALLCHAIN_FP;
 
@@ -776,6 +782,16 @@ int record_callchain_opt(const struct option *opt,
         return 0;
 }
 
+static int perf_record_config(const char *var, const char *value, void *cb)
+{
+        struct record *rec = cb;
+
+        if (!strcmp(var, "record.call-graph"))
+                return record_parse_callchain(value, &rec->opts);
+
+        return perf_default_config(var, value, cb);
+}
+
 static const char * const record_usage[] = {
         "perf record [<options>] [<command>]",
         "perf record [<options>] -- <command> [<options>]",
@@ -807,7 +823,7 @@ static struct record record = {
 
 #define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: "
 
-#ifdef HAVE_LIBUNWIND_SUPPORT
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
 const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf";
 #else
 const char record_callchain_help[] = CALLCHAIN_HELP "fp";
@@ -907,6 +923,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
         if (rec->evlist == NULL)
                 return -ENOMEM;
 
+        perf_config(perf_record_config, rec);
+
         argc = parse_options(argc, argv, record_options, record_usage,
                             PARSE_OPT_STOP_AT_NON_OPTION);
         if (!argc && target__none(&rec->opts.target))
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 3c53ec268fbc..d882b6f96411 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -75,13 +75,10 @@ static int report__config(const char *var, const char *value, void *cb)
         return perf_default_config(var, value, cb);
 }
 
-static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_location *al,
-                                      struct perf_sample *sample, struct perf_evsel *evsel,
-                                      union perf_event *event)
+static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al,
+                                      struct perf_sample *sample, struct perf_evsel *evsel)
 {
-        struct report *rep = container_of(tool, struct report, tool);
         struct symbol *parent = NULL;
-        u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
         struct hist_entry *he;
         struct mem_info *mi, *mx;
         uint64_t cost;
@@ -90,7 +87,7 @@ static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_locati
         if (err)
                 return err;
 
-        mi = machine__resolve_mem(al->machine, al->thread, sample, cpumode);
+        mi = sample__resolve_mem(sample, al);
         if (!mi)
                 return -ENOMEM;
 
@@ -129,10 +126,9 @@ out:
         return err;
 }
 
-static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_location *al,
+static int report__add_branch_hist_entry(struct report *rep, struct addr_location *al,
                                          struct perf_sample *sample, struct perf_evsel *evsel)
 {
-        struct report *rep = container_of(tool, struct report, tool);
         struct symbol *parent = NULL;
         unsigned i;
         struct hist_entry *he;
@@ -142,8 +138,7 @@ static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_loc
         if (err)
                 return err;
 
-        bi = machine__resolve_bstack(al->machine, al->thread,
-                                     sample->branch_stack);
+        bi = sample__resolve_bstack(sample, al);
         if (!bi)
                 return -ENOMEM;
 
@@ -184,10 +179,9 @@ out:
         return err;
 }
 
-static int report__add_hist_entry(struct perf_tool *tool, struct perf_evsel *evsel,
+static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel,
                                   struct addr_location *al, struct perf_sample *sample)
 {
-        struct report *rep = container_of(tool, struct report, tool);
         struct symbol *parent = NULL;
         struct hist_entry *he;
         int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
@@ -236,18 +230,18 @@ static int process_sample_event(struct perf_tool *tool,
                 return 0;
 
         if (sort__mode == SORT_MODE__BRANCH) {
-                ret = report__add_branch_hist_entry(tool, &al, sample, evsel);
+                ret = report__add_branch_hist_entry(rep, &al, sample, evsel);
                 if (ret < 0)
                         pr_debug("problem adding lbr entry, skipping event\n");
         } else if (rep->mem_mode == 1) {
-                ret = report__add_mem_hist_entry(tool, &al, sample, evsel, event);
+                ret = report__add_mem_hist_entry(rep, &al, sample, evsel);
                 if (ret < 0)
                         pr_debug("problem adding mem entry, skipping event\n");
         } else {
                 if (al.map != NULL)
                         al.map->dso->hit = 1;
 
-                ret = report__add_hist_entry(tool, evsel, &al, sample);
+                ret = report__add_hist_entry(rep, evsel, &al, sample);
                 if (ret < 0)
                         pr_debug("problem incrementing symbol period, skipping event\n");
         }
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 76cd510d34d0..ed99ec4a309f 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -991,6 +991,16 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
         return record_parse_callchain_opt(opt, arg, unset);
 }
 
+static int perf_top_config(const char *var, const char *value, void *cb)
+{
+        struct perf_top *top = cb;
+
+        if (!strcmp(var, "top.call-graph"))
+                return record_parse_callchain(value, &top->record_opts);
+
+        return perf_default_config(var, value, cb);
+}
+
 static int
 parse_percent_limit(const struct option *opt, const char *arg,
                     int unset __maybe_unused)
@@ -1115,6 +1125,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
         if (top.evlist == NULL)
                 return -ENOMEM;
 
+        perf_config(perf_top_config, &top);
+
         argc = parse_options(argc, argv, options, top_usage, 0);
         if (argc)
                 usage_with_options(top_usage, options);
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index c48d44958172..1686583ff7fc 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -338,7 +338,7 @@ ifndef NO_LIBUNWIND
       CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME
     endif
 
-    CFLAGS += -DHAVE_LIBUNWIND_SUPPORT
+    CFLAGS += -DHAVE_DWARF_UNWIND_SUPPORT -DHAVE_LIBUNWIND_SUPPORT
     EXTLIBS += $(LIBUNWIND_LIBS)
     CFLAGS += $(LIBUNWIND_CFLAGS)
     LDFLAGS += $(LIBUNWIND_LDFLAGS)
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index e84fa26bc1be..6898ad0e199f 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -251,12 +251,14 @@ void pthread__unblock_sigwinch(void);
 enum perf_call_graph_mode {
         CALLCHAIN_NONE,
         CALLCHAIN_FP,
-        CALLCHAIN_DWARF
+        CALLCHAIN_DWARF,
+        CALLCHAIN_MAX
 };
 
 struct record_opts {
         struct target target;
         int          call_graph;
+        bool         call_graph_enabled;
         bool         group;
         bool         inherit_stat;
         bool         no_buffering;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 1e67437fb4ca..b11bf8a08430 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -115,6 +115,14 @@ static struct test {
                 .desc = "Test parsing with no sample_id_all bit set",
                 .func = test__parse_no_sample_id_all,
         },
+#if defined(__x86_64__) || defined(__i386__)
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+        {
+                .desc = "Test dwarf unwind",
+                .func = test__dwarf_unwind,
+        },
+#endif
+#endif
         {
                 .func = NULL,
         },
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
new file mode 100644
index 000000000000..f16ea2808a75
--- /dev/null
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -0,0 +1,144 @@
+#include <linux/compiler.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include "tests.h"
+#include "debug.h"
+#include "machine.h"
+#include "event.h"
+#include "unwind.h"
+#include "perf_regs.h"
+#include "map.h"
+#include "thread.h"
+
+static int mmap_handler(struct perf_tool *tool __maybe_unused,
+                        union perf_event *event,
+                        struct perf_sample *sample __maybe_unused,
+                        struct machine *machine)
+{
+        return machine__process_mmap_event(machine, event, NULL);
+}
+
+static int init_live_machine(struct machine *machine)
+{
+        union perf_event event;
+        pid_t pid = getpid();
+
+        return perf_event__synthesize_mmap_events(NULL, &event, pid, pid,
+                                                  mmap_handler, machine, true);
+}
+
+#define MAX_STACK 6
+
+static int unwind_entry(struct unwind_entry *entry, void *arg)
+{
+        unsigned long *cnt = (unsigned long *) arg;
+        char *symbol = entry->sym ? entry->sym->name : NULL;
+        static const char *funcs[MAX_STACK] = {
+                "test__arch_unwind_sample",
+                "unwind_thread",
+                "krava_3",
+                "krava_2",
+                "krava_1",
+                "test__dwarf_unwind"
+        };
+
+        if (*cnt >= MAX_STACK) {
+                pr_debug("failed: crossed the max stack value %d\n", MAX_STACK);
+                return -1;
+        }
+
+        if (!symbol) {
+                pr_debug("failed: got unresolved address 0x%" PRIx64 "\n",
+                         entry->ip);
+                return -1;
+        }
+
+        pr_debug("got: %s 0x%" PRIx64 "\n", symbol, entry->ip);
+        return strcmp((const char *) symbol, funcs[(*cnt)++]);
+}
+
+__attribute__ ((noinline))
+static int unwind_thread(struct thread *thread, struct machine *machine)
+{
+        struct perf_sample sample;
+        unsigned long cnt = 0;
+        int err = -1;
+
+        memset(&sample, 0, sizeof(sample));
+
+        if (test__arch_unwind_sample(&sample, thread)) {
+                pr_debug("failed to get unwind sample\n");
+                goto out;
+        }
+
+        err = unwind__get_entries(unwind_entry, &cnt, machine, thread,
+                                  &sample, MAX_STACK);
+        if (err)
+                pr_debug("unwind failed\n");
+        else if (cnt != MAX_STACK) {
+                pr_debug("got wrong number of stack entries %lu != %d\n",
+                         cnt, MAX_STACK);
+                err = -1;
+        }
+
+ out:
+        free(sample.user_stack.data);
+        free(sample.user_regs.regs);
+        return err;
+}
+
+__attribute__ ((noinline))
+static int krava_3(struct thread *thread, struct machine *machine)
+{
+        return unwind_thread(thread, machine);
+}
+
+__attribute__ ((noinline))
+static int krava_2(struct thread *thread, struct machine *machine)
+{
+        return krava_3(thread, machine);
+}
+
+__attribute__ ((noinline))
+static int krava_1(struct thread *thread, struct machine *machine)
+{
+        return krava_2(thread, machine);
+}
+
+int test__dwarf_unwind(void)
+{
+        struct machines machines;
+        struct machine *machine;
+        struct thread *thread;
+        int err = -1;
+
+        machines__init(&machines);
+
+        machine = machines__find(&machines, HOST_KERNEL_ID);
+        if (!machine) {
+                pr_err("Could not get machine\n");
+                return -1;
+        }
+
+        if (init_live_machine(machine)) {
+                pr_err("Could not init machine\n");
+                goto out;
+        }
+
+        if (verbose > 1)
+                machine__fprintf(machine, stderr);
+
+        thread = machine__find_thread(machine, getpid());
+        if (!thread) {
+                pr_err("Could not get thread\n");
+                goto out;
+        }
+
+        err = krava_1(thread, machine);
+
+ out:
+        machine__delete_threads(machine);
+        machine__exit(machine);
+        machines__exit(&machines);
+        return err;
+}
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 4db0ae617d70..8605ff5572ae 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -2,7 +2,7 @@
 #include "parse-events.h"
 #include "evsel.h"
 #include "evlist.h"
-#include "fs.h"
+#include <api/fs/fs.h>
 #include <api/fs/debugfs.h>
 #include "tests.h"
 #include <linux/hw_breakpoint.h>
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 1b677202638d..0014d3c8c21c 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -22,8 +22,8 @@
 } while (0)
 
 static bool samples_same(const struct perf_sample *s1,
-                         const struct perf_sample *s2, u64 type, u64 regs_user,
-                         u64 read_format)
+                         const struct perf_sample *s2,
+                         u64 type, u64 read_format)
 {
         size_t i;
 
@@ -95,8 +95,9 @@ static bool samples_same(const struct perf_sample *s1,
         }
 
         if (type & PERF_SAMPLE_REGS_USER) {
-                size_t sz = hweight_long(regs_user) * sizeof(u64);
+                size_t sz = hweight_long(s1->user_regs.mask) * sizeof(u64);
 
+                COMP(user_regs.mask);
                 COMP(user_regs.abi);
                 if (s1->user_regs.abi &&
                     (!s1->user_regs.regs || !s2->user_regs.regs ||
@@ -174,6 +175,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
                 .branch_stack   = &branch_stack.branch_stack,
                 .user_regs      = {
                         .abi    = PERF_SAMPLE_REGS_ABI_64,
+                        .mask   = sample_regs_user,
                         .regs   = user_regs,
                 },
                 .user_stack     = {
@@ -201,8 +203,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
                 sample.read.one.id    = 99;
         }
 
-        sz = perf_event__sample_event_size(&sample, sample_type,
-                                           sample_regs_user, read_format);
+        sz = perf_event__sample_event_size(&sample, sample_type, read_format);
         bufsz = sz + 4096; /* Add a bit for overrun checking */
         event = malloc(bufsz);
         if (!event) {
@@ -215,8 +216,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
         event->header.misc = 0;
         event->header.size = sz;
 
-        err = perf_event__synthesize_sample(event, sample_type,
-                                            sample_regs_user, read_format,
+        err = perf_event__synthesize_sample(event, sample_type, read_format,
                                             &sample, false);
         if (err) {
                 pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
@@ -244,8 +244,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
                 goto out_free;
         }
 
-        if (!samples_same(&sample, &sample_out, sample_type,
-                          sample_regs_user, read_format)) {
+        if (!samples_same(&sample, &sample_out, sample_type, read_format)) {
                 pr_debug("parsing failed for sample_type %#"PRIx64"\n",
                          sample_type);
                 goto out_free;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index e0ac713857ba..a24795ca002d 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -40,5 +40,14 @@ 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);
 
+#if defined(__x86_64__) || defined(__i386__)
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+int test__arch_unwind_sample(struct perf_sample *sample,
+                             struct thread *thread);
+#endif
+#endif
 #endif /* TESTS_H */
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index a9b48c42e81e..7fe4994eeb63 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -1,5 +1,5 @@
 #include "util.h"
-#include "fs.h"
+#include <api/fs/fs.h>
 #include "../perf.h"
 #include "cpumap.h"
 #include <assert.h>
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index cd7d6f078cdd..ab06f1c03655 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -102,6 +102,16 @@ struct dso {
         char             name[0];
 };
 
+/* dso__for_each_symbol - iterate over the symbols of given type
+ *
+ * @dso: the 'struct dso *' in which symbols itereated
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @n: the 'struct rb_node *' to use as a temporary storage
+ * @type: the 'enum map_type' type of symbols
+ */
+#define dso__for_each_symbol(dso, pos, n, type) \
+        symbols__for_each_entry(&(dso)->symbols[(type)], pos, n)
+
 static inline void dso__set_loaded(struct dso *dso, enum map_type type)
 {
         dso->loaded |= (1 << type);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 851fa06f4a42..38457d447a13 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -85,6 +85,7 @@ struct sample_event {
 
 struct regs_dump {
         u64 abi;
+        u64 mask;
         u64 *regs;
 };
 
@@ -259,9 +260,9 @@ int perf_event__preprocess_sample(const union perf_event *event,
 const char *perf_event__name(unsigned int id);
 
 size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
-                                     u64 sample_regs_user, u64 read_format);
+                                     u64 read_format);
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
-                                  u64 sample_regs_user, u64 read_format,
+                                  u64 read_format,
                                   const struct perf_sample *sample,
                                   bool swapped);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 55407c594b87..adc94dd1794d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -595,7 +595,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
                 attr->mmap_data = track;
         }
 
-        if (opts->call_graph) {
+        if (opts->call_graph_enabled) {
                 perf_evsel__set_sample_bit(evsel, CALLCHAIN);
 
                 if (opts->call_graph == CALLCHAIN_DWARF) {
@@ -1220,7 +1220,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
         memset(data, 0, sizeof(*data));
         data->cpu = data->pid = data->tid = -1;
         data->stream_id = data->id = data->time = -1ULL;
-        data->period = 1;
+        data->period = evsel->attr.sample_period;
         data->weight = 0;
 
         if (event->header.type != PERF_RECORD_SAMPLE) {
@@ -1396,10 +1396,11 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                 array++;
 
                 if (data->user_regs.abi) {
-                        u64 regs_user = evsel->attr.sample_regs_user;
+                        u64 mask = evsel->attr.sample_regs_user;
 
-                        sz = hweight_long(regs_user) * sizeof(u64);
+                        sz = hweight_long(mask) * sizeof(u64);
                         OVERFLOW_CHECK(array, sz, max_size);
+                        data->user_regs.mask = mask;
                         data->user_regs.regs = (u64 *)array;
                         array = (void *)array + sz;
                 }
@@ -1451,7 +1452,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 }
 
 size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
-                                     u64 sample_regs_user, u64 read_format)
+                                     u64 read_format)
 {
         size_t sz, result = sizeof(struct sample_event);
 
@@ -1517,7 +1518,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
         if (type & PERF_SAMPLE_REGS_USER) {
                 if (sample->user_regs.abi) {
                         result += sizeof(u64);
-                        sz = hweight_long(sample_regs_user) * sizeof(u64);
+                        sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
                         result += sz;
                 } else {
                         result += sizeof(u64);
@@ -1546,7 +1547,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 }
 
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
-                                  u64 sample_regs_user, u64 read_format,
+                                  u64 read_format,
                                   const struct perf_sample *sample,
                                   bool swapped)
 {
@@ -1687,7 +1688,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
         if (type & PERF_SAMPLE_REGS_USER) {
                 if (sample->user_regs.abi) {
                         *array++ = sample->user_regs.abi;
-                        sz = hweight_long(sample_regs_user) * sizeof(u64);
+                        sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
                         memcpy(array, sample->user_regs.regs, sz);
                         array = (void *)array + sz;
                 } else {
diff --git a/tools/perf/util/fs.h b/tools/perf/util/fs.h
deleted file mode 100644
index 5e09ce1bab0e..000000000000
--- a/tools/perf/util/fs.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __PERF_FS
-#define __PERF_FS
-
-const char *sysfs__mountpoint(void);
-const char *procfs__mountpoint(void);
-
-#endif /* __PERF_FS */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index e4e6249b87d4..0466efa71140 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -290,7 +290,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template)
                 if (he->branch_info) {
                         /*
                          * This branch info is (a part of) allocated from
-                         * machine__resolve_bstack() and will be freed after
+                         * sample__resolve_bstack() and will be freed after
                          * adding new entries.  So we need to save a copy.
                          */
                         he->branch_info = malloc(sizeof(*he->branch_info));
@@ -369,7 +369,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
                         he_stat__add_period(&he->stat, period, weight);
 
                         /*
-                         * This mem info was allocated from machine__resolve_mem
+                         * This mem info was allocated from sample__resolve_mem
                          * and will not be used anymore.
                          */
                         zfree(&entry->mem_info);
diff --git a/tools/perf/util/include/linux/hash.h b/tools/perf/util/include/linux/hash.h
deleted file mode 100644
index 201f57397997..000000000000
--- a/tools/perf/util/include/linux/hash.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#include "../../../../include/linux/hash.h"
-
-#ifndef PERF_HASH_H
-#define PERF_HASH_H
-#endif
diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h
index 1d928a0ce997..bfe0a2afd0d2 100644
--- a/tools/perf/util/include/linux/list.h
+++ b/tools/perf/util/include/linux/list.h
@@ -1,5 +1,4 @@
 #include <linux/kernel.h>
-#include <linux/prefetch.h>
 
 #include "../../../../include/linux/list.h"
 
diff --git a/tools/perf/util/include/linux/prefetch.h b/tools/perf/util/include/linux/prefetch.h
deleted file mode 100644
index 7841e485d8c3..000000000000
--- a/tools/perf/util/include/linux/prefetch.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef PERF_LINUX_PREFETCH_H
-#define PERF_LINUX_PREFETCH_H
-
-static inline void prefetch(void *a __attribute__((unused))) { }
-
-#endif
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c872991e0f65..ac37d788b5cb 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1238,37 +1238,35 @@ static void ip__resolve_data(struct machine *machine, struct thread *thread,
         ams->map = al.map;
 }
 
-struct mem_info *machine__resolve_mem(struct machine *machine,
-                                      struct thread *thr,
-                                      struct perf_sample *sample,
-                                      u8 cpumode)
+struct mem_info *sample__resolve_mem(struct perf_sample *sample,
+                                     struct addr_location *al)
 {
         struct mem_info *mi = zalloc(sizeof(*mi));
 
         if (!mi)
                 return NULL;
 
-        ip__resolve_ams(machine, thr, &mi->iaddr, sample->ip);
-        ip__resolve_data(machine, thr, cpumode, &mi->daddr, sample->addr);
+        ip__resolve_ams(al->machine, al->thread, &mi->iaddr, sample->ip);
+        ip__resolve_data(al->machine, al->thread, al->cpumode,
+                         &mi->daddr, sample->addr);
         mi->data_src.val = sample->data_src;
 
         return mi;
 }
 
-struct branch_info *machine__resolve_bstack(struct machine *machine,
-                                            struct thread *thr,
-                                            struct branch_stack *bs)
+struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
+                                           struct addr_location *al)
 {
-        struct branch_info *bi;
         unsigned int i;
+        const struct branch_stack *bs = sample->branch_stack;
+        struct branch_info *bi = calloc(bs->nr, sizeof(struct branch_info));
 
-        bi = calloc(bs->nr, sizeof(struct branch_info));
         if (!bi)
                 return NULL;
 
         for (i = 0; i < bs->nr; i++) {
-                ip__resolve_ams(machine, thr, &bi[i].to, bs->entries[i].to);
-                ip__resolve_ams(machine, thr, &bi[i].from, bs->entries[i].from);
+                ip__resolve_ams(al->machine, al->thread, &bi[i].to, bs->entries[i].to);
+                ip__resolve_ams(al->machine, al->thread, &bi[i].from, bs->entries[i].from);
                 bi[i].flags = bs->entries[i].flags;
         }
         return bi;
@@ -1385,8 +1383,7 @@ int machine__resolve_callchain(struct machine *machine,
                 return 0;
 
         return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
-                                   thread, evsel->attr.sample_regs_user,
-                                   sample, max_stack);
+                                   thread, sample, max_stack);
 
 }
 
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index f77e91e483dc..2e6c248c870f 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -91,12 +91,10 @@ void machine__delete_dead_threads(struct machine *machine);
 void machine__delete_threads(struct machine *machine);
 void machine__delete(struct machine *machine);
 
-struct branch_info *machine__resolve_bstack(struct machine *machine,
-                                            struct thread *thread,
-                                            struct branch_stack *bs);
-struct mem_info *machine__resolve_mem(struct machine *machine,
-                                      struct thread *thread,
-                                      struct perf_sample *sample, u8 cpumode);
+struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
+                                           struct addr_location *al);
+struct mem_info *sample__resolve_mem(struct perf_sample *sample,
+                                     struct addr_location *al);
 int machine__resolve_callchain(struct machine *machine,
                                struct perf_evsel *evsel,
                                struct thread *thread,
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 257e513205ce..f00f058afb3b 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -90,6 +90,16 @@ u64 map__objdump_2mem(struct map *map, u64 ip);
 
 struct symbol;
 
+/* map__for_each_symbol - iterate over the symbols in the given map
+ *
+ * @map: the 'struct map *' in which symbols itereated
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @n: the 'struct rb_node *' to use as a temporary storage
+ * Note: caller must ensure map->dso is not NULL (map is loaded).
+ */
+#define map__for_each_symbol(map, pos, n)       \
+        dso__for_each_symbol(map->dso, pos, n, map->type)
+
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
 void map__init(struct map *map, enum map_type type,
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
new file mode 100644
index 000000000000..a3539ef30b15
--- /dev/null
+++ b/tools/perf/util/perf_regs.c
@@ -0,0 +1,19 @@
+#include <errno.h>
+#include "perf_regs.h"
+
+int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
+{
+        int i, idx = 0;
+        u64 mask = regs->mask;
+
+        if (!(mask & (1 << id)))
+                return -EINVAL;
+
+        for (i = 0; i < id; i++) {
+                if (mask & (1 << i))
+                        idx++;
+        }
+
+        *valp = regs->regs[idx];
+        return 0;
+}
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index a3d42cd74919..d6e8b6a8d7f3 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -1,8 +1,14 @@
 #ifndef __PERF_REGS_H
 #define __PERF_REGS_H
 
+#include "types.h"
+#include "event.h"
+
 #ifdef HAVE_PERF_REGS_SUPPORT
 #include <perf_regs.h>
+
+int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
+
 #else
 #define PERF_REGS_MASK  0
 
@@ -10,5 +16,12 @@ static inline const char *perf_reg_name(int id __maybe_unused)
 {
         return NULL;
 }
+
+static inline int perf_reg_value(u64 *valp __maybe_unused,
+                                 struct regs_dump *regs __maybe_unused,
+                                 int id __maybe_unused)
+{
+        return 0;
+}
 #endif /* HAVE_PERF_REGS_SUPPORT */
 #endif /* __PERF_REGS_H */
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index b752ecb40d86..00a7dcb2f55c 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -3,7 +3,7 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <dirent.h>
-#include "fs.h"
+#include <api/fs/fs.h>
 #include <locale.h>
 #include "util.h"
 #include "pmu.h"
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d8b048c20cde..0d1542f33d87 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -70,34 +70,32 @@ static int e_snprintf(char *str, size_t size, const char *format, ...)
 }
 
 static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
-static int convert_name_to_addr(struct perf_probe_event *pev,
-                                const char *exec);
 static void clear_probe_trace_event(struct probe_trace_event *tev);
-static struct machine machine;
+static struct machine *host_machine;
 
 /* Initialize symbol maps and path of vmlinux/modules */
-static int init_vmlinux(void)
+static int init_symbol_maps(bool user_only)
 {
         int ret;
 
         symbol_conf.sort_by_name = true;
-        if (symbol_conf.vmlinux_name == NULL)
-                symbol_conf.try_vmlinux_path = true;
-        else
-                pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name);
         ret = symbol__init();
         if (ret < 0) {
                 pr_debug("Failed to init symbol map.\n");
                 goto out;
         }
 
-        ret = machine__init(&machine, "", HOST_KERNEL_ID);
-        if (ret < 0)
-                goto out;
+        if (host_machine || user_only)  /* already initialized */
+                return 0;
 
-        if (machine__create_kernel_maps(&machine) < 0) {
-                pr_debug("machine__create_kernel_maps() failed.\n");
-                goto out;
+        if (symbol_conf.vmlinux_name)
+                pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name);
+
+        host_machine = machine__new_host();
+        if (!host_machine) {
+                pr_debug("machine__new_host() failed.\n");
+                symbol__exit();
+                ret = -1;
         }
 out:
         if (ret < 0)
@@ -105,21 +103,66 @@ out:
         return ret;
 }
 
+static void exit_symbol_maps(void)
+{
+        if (host_machine) {
+                machine__delete(host_machine);
+                host_machine = NULL;
+        }
+        symbol__exit();
+}
+
 static struct symbol *__find_kernel_function_by_name(const char *name,
                                                      struct map **mapp)
 {
-        return machine__find_kernel_function_by_name(&machine, name, mapp,
+        return machine__find_kernel_function_by_name(host_machine, name, mapp,
                                                      NULL);
 }
 
+static struct symbol *__find_kernel_function(u64 addr, struct map **mapp)
+{
+        return machine__find_kernel_function(host_machine, addr, mapp, NULL);
+}
+
+static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
+{
+        /* kmap->ref_reloc_sym should be set if host_machine is initialized */
+        struct kmap *kmap;
+
+        if (map__load(host_machine->vmlinux_maps[MAP__FUNCTION], NULL) < 0)
+                return NULL;
+
+        kmap = map__kmap(host_machine->vmlinux_maps[MAP__FUNCTION]);
+        return kmap->ref_reloc_sym;
+}
+
+static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc)
+{
+        struct ref_reloc_sym *reloc_sym;
+        struct symbol *sym;
+        struct map *map;
+
+        /* ref_reloc_sym is just a label. Need a special fix*/
+        reloc_sym = kernel_get_ref_reloc_sym();
+        if (reloc_sym && strcmp(name, reloc_sym->name) == 0)
+                return (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr;
+        else {
+                sym = __find_kernel_function_by_name(name, &map);
+                if (sym)
+                        return map->unmap_ip(map, sym->start) -
+                                (reloc) ? 0 : map->reloc;
+        }
+        return 0;
+}
+
 static struct map *kernel_get_module_map(const char *module)
 {
         struct rb_node *nd;
-        struct map_groups *grp = &machine.kmaps;
+        struct map_groups *grp = &host_machine->kmaps;
 
         /* A file path -- this is an offline module */
         if (module && strchr(module, '/'))
-                return machine__new_module(&machine, 0, module);
+                return machine__new_module(host_machine, 0, module);
 
         if (!module)
                 module = "kernel";
@@ -141,7 +184,7 @@ static struct dso *kernel_get_module_dso(const char *module)
         const char *vmlinux_name;
 
         if (module) {
-                list_for_each_entry(dso, &machine.kernel_dsos, node) {
+                list_for_each_entry(dso, &host_machine->kernel_dsos, node) {
                         if (strncmp(dso->short_name + 1, module,
                                     dso->short_name_len - 2) == 0)
                                 goto found;
@@ -150,7 +193,7 @@ static struct dso *kernel_get_module_dso(const char *module)
                 return NULL;
         }
 
-        map = machine.vmlinux_maps[MAP__FUNCTION];
+        map = host_machine->vmlinux_maps[MAP__FUNCTION];
         dso = map->dso;
 
         vmlinux_name = symbol_conf.vmlinux_name;
@@ -173,20 +216,6 @@ const char *kernel_get_module_path(const char *module)
         return (dso) ? dso->long_name : NULL;
 }
 
-static int init_user_exec(void)
-{
-        int ret = 0;
-
-        symbol_conf.try_vmlinux_path = false;
-        symbol_conf.sort_by_name = true;
-        ret = symbol__init();
-
-        if (ret < 0)
-                pr_debug("Failed to init symbol map.\n");
-
-        return ret;
-}
-
 static int convert_exec_to_group(const char *exec, char **result)
 {
         char *ptr1, *ptr2, *exec_copy;
@@ -218,32 +247,23 @@ out:
         return ret;
 }
 
-static int convert_to_perf_probe_point(struct probe_trace_point *tp,
-                                        struct perf_probe_point *pp)
+static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 {
-        pp->function = strdup(tp->symbol);
-
-        if (pp->function == NULL)
-                return -ENOMEM;
-
-        pp->offset = tp->offset;
-        pp->retprobe = tp->retprobe;
+        int i;
 
-        return 0;
+        for (i = 0; i < ntevs; i++)
+                clear_probe_trace_event(tevs + i);
 }
 
 #ifdef HAVE_DWARF_SUPPORT
+
 /* Open new debuginfo of given module */
 static struct debuginfo *open_debuginfo(const char *module)
 {
-        const char *path;
+        const char *path = module;
 
-        /* A file path -- this is an offline module */
-        if (module && strchr(module, '/'))
-                path = module;
-        else {
+        if (!module || !strchr(module, '/')) {
                 path = kernel_get_module_path(module);
-
                 if (!path) {
                         pr_err("Failed to find path of %s module.\n",
                                module ?: "kernel");
@@ -253,46 +273,6 @@ static struct debuginfo *open_debuginfo(const char *module)
         return debuginfo__new(path);
 }
 
-/*
- * Convert trace point to probe point with debuginfo
- * Currently only handles kprobes.
- */
-static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
-                                        struct perf_probe_point *pp)
-{
-        struct symbol *sym;
-        struct map *map;
-        u64 addr;
-        int ret = -ENOENT;
-        struct debuginfo *dinfo;
-
-        sym = __find_kernel_function_by_name(tp->symbol, &map);
-        if (sym) {
-                addr = map->unmap_ip(map, sym->start + tp->offset);
-                pr_debug("try to find %s+%ld@%" PRIx64 "\n", tp->symbol,
-                         tp->offset, addr);
-
-                dinfo = debuginfo__new_online_kernel(addr);
-                if (dinfo) {
-                        ret = debuginfo__find_probe_point(dinfo,
-                                                 (unsigned long)addr, pp);
-                        debuginfo__delete(dinfo);
-                } else {
-                        pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n",
-                                 addr);
-                        ret = -ENOENT;
-                }
-        }
-        if (ret <= 0) {
-                pr_debug("Failed to find corresponding probes from "
-                         "debuginfo. Use kprobe event information.\n");
-                return convert_to_perf_probe_point(tp, pp);
-        }
-        pp->retprobe = tp->retprobe;
-
-        return 0;
-}
-
 static int get_text_start_address(const char *exec, unsigned long *address)
 {
         Elf *elf;
@@ -321,12 +301,62 @@ out:
         return ret;
 }
 
+/*
+ * Convert trace point to probe point with debuginfo
+ */
+static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
+                                            struct perf_probe_point *pp,
+                                            bool is_kprobe)
+{
+        struct debuginfo *dinfo = NULL;
+        unsigned long stext = 0;
+        u64 addr = tp->address;
+        int ret = -ENOENT;
+
+        /* convert the address to dwarf address */
+        if (!is_kprobe) {
+                if (!addr) {
+                        ret = -EINVAL;
+                        goto error;
+                }
+                ret = get_text_start_address(tp->module, &stext);
+                if (ret < 0)
+                        goto error;
+                addr += stext;
+        } else {
+                addr = kernel_get_symbol_address_by_name(tp->symbol, false);
+                if (addr == 0)
+                        goto error;
+                addr += tp->offset;
+        }
+
+        pr_debug("try to find information at %" PRIx64 " in %s\n", addr,
+                 tp->module ? : "kernel");
+
+        dinfo = open_debuginfo(tp->module);
+        if (dinfo) {
+                ret = debuginfo__find_probe_point(dinfo,
+                                                 (unsigned long)addr, pp);
+                debuginfo__delete(dinfo);
+        } else {
+                pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n", addr);
+                ret = -ENOENT;
+        }
+
+        if (ret > 0) {
+                pp->retprobe = tp->retprobe;
+                return 0;
+        }
+error:
+        pr_debug("Failed to find corresponding probes from debuginfo.\n");
+        return ret ? : -ENOENT;
+}
+
 static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
                                           int ntevs, const char *exec)
 {
         int i, ret = 0;
-        unsigned long offset, stext = 0;
-        char buf[32];
+        unsigned long stext = 0;
 
         if (!exec)
                 return 0;
@@ -337,15 +367,9 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
 
         for (i = 0; i < ntevs && ret >= 0; i++) {
                 /* point.address is the addres of point.symbol + point.offset */
-                offset = tevs[i].point.address - stext;
-                tevs[i].point.offset = 0;
-                zfree(&tevs[i].point.symbol);
-                ret = e_snprintf(buf, 32, "0x%lx", offset);
-                if (ret < 0)
-                        break;
+                tevs[i].point.address -= stext;
                 tevs[i].point.module = strdup(exec);
-                tevs[i].point.symbol = strdup(buf);
-                if (!tevs[i].point.symbol || !tevs[i].point.module) {
+                if (!tevs[i].point.module) {
                         ret = -ENOMEM;
                         break;
                 }
@@ -388,12 +412,40 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
         return ret;
 }
 
-static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
+/* Post processing the probe events */
+static int post_process_probe_trace_events(struct probe_trace_event *tevs,
+                                           int ntevs, const char *module,
+                                           bool uprobe)
 {
+        struct ref_reloc_sym *reloc_sym;
+        char *tmp;
         int i;
 
-        for (i = 0; i < ntevs; i++)
-                clear_probe_trace_event(tevs + i);
+        if (uprobe)
+                return add_exec_to_probe_trace_events(tevs, ntevs, module);
+
+        /* Note that currently ref_reloc_sym based probe is not for drivers */
+        if (module)
+                return add_module_to_probe_trace_events(tevs, ntevs, module);
+
+        reloc_sym = kernel_get_ref_reloc_sym();
+        if (!reloc_sym) {
+                pr_warning("Relocated base symbol is not found!\n");
+                return -EINVAL;
+        }
+
+        for (i = 0; i < ntevs; i++) {
+                if (tevs[i].point.address) {
+                        tmp = strdup(reloc_sym->name);
+                        if (!tmp)
+                                return -ENOMEM;
+                        free(tevs[i].point.symbol);
+                        tevs[i].point.symbol = tmp;
+                        tevs[i].point.offset = tevs[i].point.address -
+                                               reloc_sym->unrelocated_addr;
+                }
+        }
+        return 0;
 }
 
 /* Try to find perf_probe_event with debuginfo */
@@ -416,21 +468,16 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
                 return 0;
         }
 
+        pr_debug("Try to find probe point from debuginfo.\n");
         /* Searching trace events corresponding to a probe event */
         ntevs = debuginfo__find_trace_events(dinfo, pev, tevs, max_tevs);
 
         debuginfo__delete(dinfo);
 
         if (ntevs > 0) {        /* Succeeded to find trace events */
-                pr_debug("find %d probe_trace_events.\n", ntevs);
-                if (target) {
-                        if (pev->uprobes)
-                                ret = add_exec_to_probe_trace_events(*tevs,
-                                                 ntevs, target);
-                        else
-                                ret = add_module_to_probe_trace_events(*tevs,
-                                                 ntevs, target);
-                }
+                pr_debug("Found %d probe_trace_events.\n", ntevs);
+                ret = post_process_probe_trace_events(*tevs, ntevs,
+                                                        target, pev->uprobes);
                 if (ret < 0) {
                         clear_probe_trace_events(*tevs, ntevs);
                         zfree(tevs);
@@ -563,20 +610,16 @@ static int _show_one_line(FILE *fp, int l, bool skip, bool show_num)
  * Show line-range always requires debuginfo to find source file and
  * line number.
  */
-int show_line_range(struct line_range *lr, const char *module)
+static int __show_line_range(struct line_range *lr, const char *module)
 {
         int l = 1;
-        struct line_node *ln;
+        struct int_node *ln;
         struct debuginfo *dinfo;
         FILE *fp;
         int ret;
         char *tmp;
 
         /* Search a line range */
-        ret = init_vmlinux();
-        if (ret < 0)
-                return ret;
-
         dinfo = open_debuginfo(module);
         if (!dinfo) {
                 pr_warning("Failed to open debuginfo file.\n");
@@ -623,8 +666,8 @@ int show_line_range(struct line_range *lr, const char *module)
                         goto end;
         }
 
-        list_for_each_entry(ln, &lr->line_list, list) {
-                for (; ln->line > l; l++) {
+        intlist__for_each(ln, lr->line_list) {
+                for (; ln->i > l; l++) {
                         ret = show_one_line(fp, l - lr->offset);
                         if (ret < 0)
                                 goto end;
@@ -646,6 +689,19 @@ end:
         return ret;
 }
 
+int show_line_range(struct line_range *lr, const char *module)
+{
+        int ret;
+
+        ret = init_symbol_maps(false);
+        if (ret < 0)
+                return ret;
+        ret = __show_line_range(lr, module);
+        exit_symbol_maps();
+
+        return ret;
+}
+
 static int show_available_vars_at(struct debuginfo *dinfo,
                                   struct perf_probe_event *pev,
                                   int max_vls, struct strfilter *_filter,
@@ -707,14 +763,15 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
         int i, ret = 0;
         struct debuginfo *dinfo;
 
-        ret = init_vmlinux();
+        ret = init_symbol_maps(false);
         if (ret < 0)
                 return ret;
 
         dinfo = open_debuginfo(module);
         if (!dinfo) {
                 pr_warning("Failed to open debuginfo file.\n");
-                return -ENOENT;
+                ret = -ENOENT;
+                goto out;
         }
 
         setup_pager();
@@ -724,23 +781,19 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
                                              externs);
 
         debuginfo__delete(dinfo);
+out:
+        exit_symbol_maps();
         return ret;
 }
 
 #else   /* !HAVE_DWARF_SUPPORT */
 
-static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
-                                        struct perf_probe_point *pp)
+static int
+find_perf_probe_point_from_dwarf(struct probe_trace_point *tp __maybe_unused,
+                                 struct perf_probe_point *pp __maybe_unused,
+                                 bool is_kprobe __maybe_unused)
 {
-        struct symbol *sym;
-
-        sym = __find_kernel_function_by_name(tp->symbol, NULL);
-        if (!sym) {
-                pr_err("Failed to find symbol %s in kernel.\n", tp->symbol);
-                return -ENOENT;
-        }
-
-        return convert_to_perf_probe_point(tp, pp);
+        return -ENOSYS;
 }
 
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
@@ -776,24 +829,22 @@ int show_available_vars(struct perf_probe_event *pevs __maybe_unused,
 
 void line_range__clear(struct line_range *lr)
 {
-        struct line_node *ln;
-
         free(lr->function);
         free(lr->file);
         free(lr->path);
         free(lr->comp_dir);
-        while (!list_empty(&lr->line_list)) {
-                ln = list_first_entry(&lr->line_list, struct line_node, list);
-                list_del(&ln->list);
-                free(ln);
-        }
+        intlist__delete(lr->line_list);
         memset(lr, 0, sizeof(*lr));
 }
 
-void line_range__init(struct line_range *lr)
+int line_range__init(struct line_range *lr)
 {
         memset(lr, 0, sizeof(*lr));
-        INIT_LIST_HEAD(&lr->line_list);
+        lr->line_list = intlist__new(NULL);
+        if (!lr->line_list)
+                return -ENOMEM;
+        else
+                return 0;
 }
 
 static int parse_line_num(char **ptr, int *val, const char *what)
@@ -1267,16 +1318,21 @@ static int parse_probe_trace_command(const char *cmd,
         } else
                 p = argv[1];
         fmt1_str = strtok_r(p, "+", &fmt);
-        tp->symbol = strdup(fmt1_str);
-        if (tp->symbol == NULL) {
-                ret = -ENOMEM;
-                goto out;
+        if (fmt1_str[0] == '0') /* only the address started with 0x */
+                tp->address = strtoul(fmt1_str, NULL, 0);
+        else {
+                /* Only the symbol-based probe has offset */
+                tp->symbol = strdup(fmt1_str);
+                if (tp->symbol == NULL) {
+                        ret = -ENOMEM;
+                        goto out;
+                }
+                fmt2_str = strtok_r(NULL, "", &fmt);
+                if (fmt2_str == NULL)
+                        tp->offset = 0;
+                else
+                        tp->offset = strtoul(fmt2_str, NULL, 10);
         }
-        fmt2_str = strtok_r(NULL, "", &fmt);
-        if (fmt2_str == NULL)
-                tp->offset = 0;
-        else
-                tp->offset = strtoul(fmt2_str, NULL, 10);
 
         tev->nargs = argc - 2;
         tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
@@ -1518,20 +1574,27 @@ char *synthesize_probe_trace_command(struct probe_trace_event *tev)
         if (buf == NULL)
                 return NULL;
 
+        len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s ", tp->retprobe ? 'r' : 'p',
+                         tev->group, tev->event);
+        if (len <= 0)
+                goto error;
+
+        /* Uprobes must have tp->address and tp->module */
+        if (tev->uprobes && (!tp->address || !tp->module))
+                goto error;
+
+        /* Use the tp->address for uprobes */
         if (tev->uprobes)
-                len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s:%s",
-                                 tp->retprobe ? 'r' : 'p',
-                                 tev->group, tev->event,
-                                 tp->module, tp->symbol);
+                ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s:0x%lx",
+                                 tp->module, tp->address);
         else
-                len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s%s%s+%lu",
-                                 tp->retprobe ? 'r' : 'p',
-                                 tev->group, tev->event,
+                ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s%s%s+%lu",
                                  tp->module ?: "", tp->module ? ":" : "",
                                  tp->symbol, tp->offset);
 
-        if (len <= 0)
+        if (ret <= 0)
                 goto error;
+        len += ret;
 
         for (i = 0; i < tev->nargs; i++) {
                 ret = synthesize_probe_trace_arg(&tev->args[i], buf + len,
@@ -1547,6 +1610,79 @@ error:
         return NULL;
 }
 
+static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
+                                          struct perf_probe_point *pp,
+                                          bool is_kprobe)
+{
+        struct symbol *sym = NULL;
+        struct map *map;
+        u64 addr;
+        int ret = -ENOENT;
+
+        if (!is_kprobe) {
+                map = dso__new_map(tp->module);
+                if (!map)
+                        goto out;
+                addr = tp->address;
+                sym = map__find_symbol(map, addr, NULL);
+        } else {
+                addr = kernel_get_symbol_address_by_name(tp->symbol, true);
+                if (addr) {
+                        addr += tp->offset;
+                        sym = __find_kernel_function(addr, &map);
+                }
+        }
+        if (!sym)
+                goto out;
+
+        pp->retprobe = tp->retprobe;
+        pp->offset = addr - map->unmap_ip(map, sym->start);
+        pp->function = strdup(sym->name);
+        ret = pp->function ? 0 : -ENOMEM;
+
+out:
+        if (map && !is_kprobe) {
+                dso__delete(map->dso);
+                map__delete(map);
+        }
+
+        return ret;
+}
+
+static int convert_to_perf_probe_point(struct probe_trace_point *tp,
+                                        struct perf_probe_point *pp,
+                                        bool is_kprobe)
+{
+        char buf[128];
+        int ret;
+
+        ret = find_perf_probe_point_from_dwarf(tp, pp, is_kprobe);
+        if (!ret)
+                return 0;
+        ret = find_perf_probe_point_from_map(tp, pp, is_kprobe);
+        if (!ret)
+                return 0;
+
+        pr_debug("Failed to find probe point from both of dwarf and map.\n");
+
+        if (tp->symbol) {
+                pp->function = strdup(tp->symbol);
+                pp->offset = tp->offset;
+        } else if (!tp->module && !is_kprobe) {
+                ret = e_snprintf(buf, 128, "0x%" PRIx64, (u64)tp->address);
+                if (ret < 0)
+                        return ret;
+                pp->function = strdup(buf);
+                pp->offset = 0;
+        }
+        if (pp->function == NULL)
+                return -ENOMEM;
+
+        pp->retprobe = tp->retprobe;
+
+        return 0;
+}
+
 static int convert_to_perf_probe_event(struct probe_trace_event *tev,
                                struct perf_probe_event *pev, bool is_kprobe)
 {
@@ -1560,11 +1696,7 @@ static int convert_to_perf_probe_event(struct probe_trace_event *tev,
                 return -ENOMEM;
 
         /* Convert trace_point to probe_point */
-        if (is_kprobe)
-                ret = kprobe_convert_to_perf_probe(&tev->point, &pev->point);
-        else
-                ret = convert_to_perf_probe_point(&tev->point, &pev->point);
-
+        ret = convert_to_perf_probe_point(&tev->point, &pev->point, is_kprobe);
         if (ret < 0)
                 return ret;
 
@@ -1731,7 +1863,8 @@ static struct strlist *get_probe_trace_command_rawlist(int fd)
 }
 
 /* Show an event */
-static int show_perf_probe_event(struct perf_probe_event *pev)
+static int show_perf_probe_event(struct perf_probe_event *pev,
+                                 const char *module)
 {
         int i, ret;
         char buf[128];
@@ -1747,6 +1880,8 @@ static int show_perf_probe_event(struct perf_probe_event *pev)
                 return ret;
 
         printf("  %-20s (on %s", buf, place);
+        if (module)
+                printf(" in %s", module);
 
         if (pev->nargs > 0) {
                 printf(" with");
@@ -1784,7 +1919,8 @@ static int __show_perf_probe_events(int fd, bool is_kprobe)
                         ret = convert_to_perf_probe_event(&tev, &pev,
                                                                 is_kprobe);
                         if (ret >= 0)
-                                ret = show_perf_probe_event(&pev);
+                                ret = show_perf_probe_event(&pev,
+                                                            tev.point.module);
                 }
                 clear_perf_probe_event(&pev);
                 clear_probe_trace_event(&tev);
@@ -1807,7 +1943,7 @@ int show_perf_probe_events(void)
         if (fd < 0)
                 return fd;
 
-        ret = init_vmlinux();
+        ret = init_symbol_maps(false);
         if (ret < 0)
                 return ret;
 
@@ -1820,6 +1956,7 @@ int show_perf_probe_events(void)
                 close(fd);
         }
 
+        exit_symbol_maps();
         return ret;
 }
 
@@ -1982,7 +2119,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
                 group = pev->group;
                 pev->event = tev->event;
                 pev->group = tev->group;
-                show_perf_probe_event(pev);
+                show_perf_probe_event(pev, tev->point.module);
                 /* Trick here - restore current event/group */
                 pev->event = (char *)event;
                 pev->group = (char *)group;
@@ -2008,113 +2145,175 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
         return ret;
 }
 
-static int convert_to_probe_trace_events(struct perf_probe_event *pev,
-                                          struct probe_trace_event **tevs,
-                                          int max_tevs, const char *target)
+static char *looking_function_name;
+static int num_matched_functions;
+
+static int probe_function_filter(struct map *map __maybe_unused,
+                                      struct symbol *sym)
 {
+        if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) &&
+            strcmp(looking_function_name, sym->name) == 0) {
+                num_matched_functions++;
+                return 0;
+        }
+        return 1;
+}
+
+#define strdup_or_goto(str, label)      \
+        ({ char *__p = strdup(str); if (!__p) goto label; __p; })
+
+/*
+ * Find probe function addresses from map.
+ * Return an error or the number of found probe_trace_event
+ */
+static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
+                                            struct probe_trace_event **tevs,
+                                            int max_tevs, const char *target)
+{
+        struct map *map = NULL;
+        struct kmap *kmap = NULL;
+        struct ref_reloc_sym *reloc_sym = NULL;
         struct symbol *sym;
-        int ret, i;
+        struct rb_node *nd;
         struct probe_trace_event *tev;
+        struct perf_probe_point *pp = &pev->point;
+        struct probe_trace_point *tp;
+        int ret, i;
 
-        if (pev->uprobes && !pev->group) {
-                /* Replace group name if not given */
-                ret = convert_exec_to_group(target, &pev->group);
-                if (ret != 0) {
-                        pr_warning("Failed to make a group name.\n");
-                        return ret;
-                }
+        /* Init maps of given executable or kernel */
+        if (pev->uprobes)
+                map = dso__new_map(target);
+        else
+                map = kernel_get_module_map(target);
+        if (!map) {
+                ret = -EINVAL;
+                goto out;
         }
 
-        /* Convert perf_probe_event with debuginfo */
-        ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target);
-        if (ret != 0)
-                return ret;     /* Found in debuginfo or got an error */
-
-        if (pev->uprobes) {
-                ret = convert_name_to_addr(pev, target);
-                if (ret < 0)
-                        return ret;
+        /*
+         * Load matched symbols: Since the different local symbols may have
+         * same name but different addresses, this lists all the symbols.
+         */
+        num_matched_functions = 0;
+        looking_function_name = pp->function;
+        ret = map__load(map, probe_function_filter);
+        if (ret || num_matched_functions == 0) {
+                pr_err("Failed to find symbol %s in %s\n", pp->function,
+                        target ? : "kernel");
+                ret = -ENOENT;
+                goto out;
+        } else if (num_matched_functions > max_tevs) {
+                pr_err("Too many functions matched in %s\n",
+                        target ? : "kernel");
+                ret = -E2BIG;
+                goto out;
         }
 
-        /* Allocate trace event buffer */
-        tev = *tevs = zalloc(sizeof(struct probe_trace_event));
-        if (tev == NULL)
-                return -ENOMEM;
+        if (!pev->uprobes) {
+                kmap = map__kmap(map);
+                reloc_sym = kmap->ref_reloc_sym;
+                if (!reloc_sym) {
+                        pr_warning("Relocated base symbol is not found!\n");
+                        ret = -EINVAL;
+                        goto out;
+                }
+        }
 
-        /* Copy parameters */
-        tev->point.symbol = strdup(pev->point.function);
-        if (tev->point.symbol == NULL) {
+        /* Setup result trace-probe-events */
+        *tevs = zalloc(sizeof(*tev) * num_matched_functions);
+        if (!*tevs) {
                 ret = -ENOMEM;
-                goto error;
+                goto out;
         }
 
-        if (target) {
-                tev->point.module = strdup(target);
-                if (tev->point.module == NULL) {
-                        ret = -ENOMEM;
-                        goto error;
+        ret = 0;
+        map__for_each_symbol(map, sym, nd) {
+                tev = (*tevs) + ret;
+                tp = &tev->point;
+                if (ret == num_matched_functions) {
+                        pr_warning("Too many symbols are listed. Skip it.\n");
+                        break;
                 }
-        }
-
-        tev->point.offset = pev->point.offset;
-        tev->point.retprobe = pev->point.retprobe;
-        tev->nargs = pev->nargs;
-        tev->uprobes = pev->uprobes;
+                ret++;
 
-        if (tev->nargs) {
-                tev->args = zalloc(sizeof(struct probe_trace_arg)
-                                   * tev->nargs);
-                if (tev->args == NULL) {
-                        ret = -ENOMEM;
-                        goto error;
+                if (pp->offset > sym->end - sym->start) {
+                        pr_warning("Offset %ld is bigger than the size of %s\n",
+                                   pp->offset, sym->name);
+                        ret = -ENOENT;
+                        goto err_out;
+                }
+                /* Add one probe point */
+                tp->address = map->unmap_ip(map, sym->start) + pp->offset;
+                if (reloc_sym) {
+                        tp->symbol = strdup_or_goto(reloc_sym->name, nomem_out);
+                        tp->offset = tp->address - reloc_sym->addr;
+                } else {
+                        tp->symbol = strdup_or_goto(sym->name, nomem_out);
+                        tp->offset = pp->offset;
+                }
+                tp->retprobe = pp->retprobe;
+                if (target)
+                        tev->point.module = strdup_or_goto(target, nomem_out);
+                tev->uprobes = pev->uprobes;
+                tev->nargs = pev->nargs;
+                if (tev->nargs) {
+                        tev->args = zalloc(sizeof(struct probe_trace_arg) *
+                                           tev->nargs);
+                        if (tev->args == NULL)
+                                goto nomem_out;
                 }
                 for (i = 0; i < tev->nargs; i++) {
-                        if (pev->args[i].name) {
-                                tev->args[i].name = strdup(pev->args[i].name);
-                                if (tev->args[i].name == NULL) {
-                                        ret = -ENOMEM;
-                                        goto error;
-                                }
-                        }
-                        tev->args[i].value = strdup(pev->args[i].var);
-                        if (tev->args[i].value == NULL) {
-                                ret = -ENOMEM;
-                                goto error;
-                        }
-                        if (pev->args[i].type) {
-                                tev->args[i].type = strdup(pev->args[i].type);
-                                if (tev->args[i].type == NULL) {
-                                        ret = -ENOMEM;
-                                        goto error;
-                                }
-                        }
+                        if (pev->args[i].name)
+                                tev->args[i].name =
+                                        strdup_or_goto(pev->args[i].name,
+                                                        nomem_out);
+
+                        tev->args[i].value = strdup_or_goto(pev->args[i].var,
+                                                            nomem_out);
+                        if (pev->args[i].type)
+                                tev->args[i].type =
+                                        strdup_or_goto(pev->args[i].type,
+                                                        nomem_out);
                 }
         }
 
-        if (pev->uprobes)
-                return 1;
+out:
+        if (map && pev->uprobes) {
+                /* Only when using uprobe(exec) map needs to be released */
+                dso__delete(map->dso);
+                map__delete(map);
+        }
+        return ret;
 
-        /* Currently just checking function name from symbol map */
-        sym = __find_kernel_function_by_name(tev->point.symbol, NULL);
-        if (!sym) {
-                pr_warning("Kernel symbol \'%s\' not found.\n",
-                           tev->point.symbol);
-                ret = -ENOENT;
-                goto error;
-        } else if (tev->point.offset > sym->end - sym->start) {
-                pr_warning("Offset specified is greater than size of %s\n",
-                           tev->point.symbol);
-                ret = -ENOENT;
-                goto error;
+nomem_out:
+        ret = -ENOMEM;
+err_out:
+        clear_probe_trace_events(*tevs, num_matched_functions);
+        zfree(tevs);
+        goto out;
+}
+
+static int convert_to_probe_trace_events(struct perf_probe_event *pev,
+                                          struct probe_trace_event **tevs,
+                                          int max_tevs, const char *target)
+{
+        int ret;
 
+        if (pev->uprobes && !pev->group) {
+                /* Replace group name if not given */
+                ret = convert_exec_to_group(target, &pev->group);
+                if (ret != 0) {
+                        pr_warning("Failed to make a group name.\n");
+                        return ret;
+                }
         }
 
-        return 1;
-error:
-        clear_probe_trace_event(tev);
-        free(tev);
-        *tevs = NULL;
-        return ret;
+        /* Convert perf_probe_event with debuginfo */
+        ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target);
+        if (ret != 0)
+                return ret;     /* Found in debuginfo or got an error */
+
+        return find_probe_trace_events_from_map(pev, tevs, max_tevs, target);
 }
 
 struct __event_package {
@@ -2135,12 +2334,7 @@ int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
         if (pkgs == NULL)
                 return -ENOMEM;
 
-        if (!pevs->uprobes)
-                /* Init vmlinux path */
-                ret = init_vmlinux();
-        else
-                ret = init_user_exec();
-
+        ret = init_symbol_maps(pevs->uprobes);
         if (ret < 0) {
                 free(pkgs);
                 return ret;
@@ -2174,6 +2368,7 @@ end:
                 zfree(&pkgs[i].tevs);
         }
         free(pkgs);
+        exit_symbol_maps();
 
         return ret;
 }
@@ -2323,159 +2518,51 @@ static struct strfilter *available_func_filter;
 static int filter_available_functions(struct map *map __maybe_unused,
                                       struct symbol *sym)
 {
-        if (sym->binding == STB_GLOBAL &&
+        if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) &&
             strfilter__compare(available_func_filter, sym->name))
                 return 0;
         return 1;
 }
 
-static int __show_available_funcs(struct map *map)
-{
-        if (map__load(map, filter_available_functions)) {
-                pr_err("Failed to load map.\n");
-                return -EINVAL;
-        }
-        if (!dso__sorted_by_name(map->dso, map->type))
-                dso__sort_by_name(map->dso, map->type);
-
-        dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
-        return 0;
-}
-
-static int available_kernel_funcs(const char *module)
+int show_available_funcs(const char *target, struct strfilter *_filter,
+                                        bool user)
 {
         struct map *map;
         int ret;
 
-        ret = init_vmlinux();
+        ret = init_symbol_maps(user);
         if (ret < 0)
                 return ret;
 
-        map = kernel_get_module_map(module);
+        /* Get a symbol map */
+        if (user)
+                map = dso__new_map(target);
+        else
+                map = kernel_get_module_map(target);
         if (!map) {
-                pr_err("Failed to find %s map.\n", (module) ? : "kernel");
+                pr_err("Failed to get a map for %s\n", (target) ? : "kernel");
                 return -EINVAL;
         }
-        return __show_available_funcs(map);
-}
-
-static int available_user_funcs(const char *target)
-{
-        struct map *map;
-        int ret;
-
-        ret = init_user_exec();
-        if (ret < 0)
-                return ret;
-
-        map = dso__new_map(target);
-        ret = __show_available_funcs(map);
-        dso__delete(map->dso);
-        map__delete(map);
-        return ret;
-}
 
-int show_available_funcs(const char *target, struct strfilter *_filter,
-                                        bool user)
-{
-        setup_pager();
+        /* Load symbols with given filter */
         available_func_filter = _filter;
-
-        if (!user)
-                return available_kernel_funcs(target);
-
-        return available_user_funcs(target);
-}
-
-/*
- * uprobe_events only accepts address:
- * Convert function and any offset to address
- */
-static int convert_name_to_addr(struct perf_probe_event *pev, const char *exec)
-{
-        struct perf_probe_point *pp = &pev->point;
-        struct symbol *sym;
-        struct map *map = NULL;
-        char *function = NULL;
-        int ret = -EINVAL;
-        unsigned long long vaddr = 0;
-
-        if (!pp->function) {
-                pr_warning("No function specified for uprobes");
-                goto out;
-        }
-
-        function = strdup(pp->function);
-        if (!function) {
-                pr_warning("Failed to allocate memory by strdup.\n");
-                ret = -ENOMEM;
-                goto out;
-        }
-
-        map = dso__new_map(exec);
-        if (!map) {
-                pr_warning("Cannot find appropriate DSO for %s.\n", exec);
-                goto out;
-        }
-        available_func_filter = strfilter__new(function, NULL);
         if (map__load(map, filter_available_functions)) {
-                pr_err("Failed to load map.\n");
-                goto out;
-        }
-
-        sym = map__find_symbol_by_name(map, function, NULL);
-        if (!sym) {
-                pr_warning("Cannot find %s in DSO %s\n", function, exec);
-                goto out;
-        }
-
-        if (map->start > sym->start)
-                vaddr = map->start;
-        vaddr += sym->start + pp->offset + map->pgoff;
-        pp->offset = 0;
-
-        if (!pev->event) {
-                pev->event = function;
-                function = NULL;
-        }
-        if (!pev->group) {
-                char *ptr1, *ptr2, *exec_copy;
-
-                pev->group = zalloc(sizeof(char *) * 64);
-                exec_copy = strdup(exec);
-                if (!exec_copy) {
-                        ret = -ENOMEM;
-                        pr_warning("Failed to copy exec string.\n");
-                        goto out;
-                }
-
-                ptr1 = strdup(basename(exec_copy));
-                if (ptr1) {
-                        ptr2 = strpbrk(ptr1, "-._");
-                        if (ptr2)
-                                *ptr2 = '\0';
-                        e_snprintf(pev->group, 64, "%s_%s", PERFPROBE_GROUP,
-                                        ptr1);
-                        free(ptr1);
-                }
-                free(exec_copy);
-        }
-        free(pp->function);
-        pp->function = zalloc(sizeof(char *) * MAX_PROBE_ARGS);
-        if (!pp->function) {
-                ret = -ENOMEM;
-                pr_warning("Failed to allocate memory by zalloc.\n");
-                goto out;
+                pr_err("Failed to load symbols in %s\n", (target) ? : "kernel");
+                goto end;
         }
-        e_snprintf(pp->function, MAX_PROBE_ARGS, "0x%llx", vaddr);
-        ret = 0;
+        if (!dso__sorted_by_name(map->dso, map->type))
+                dso__sort_by_name(map->dso, map->type);
 
-out:
-        if (map) {
+        /* Show all (filtered) symbols */
+        setup_pager();
+        dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
+end:
+        if (user) {
                 dso__delete(map->dso);
                 map__delete(map);
         }
-        if (function)
-                free(function);
+        exit_symbol_maps();
+
         return ret;
 }
+
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index fcaf7273e85a..776c9347a3b6 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -2,6 +2,7 @@
 #define _PROBE_EVENT_H
 
 #include <stdbool.h>
+#include "intlist.h"
 #include "strlist.h"
 #include "strfilter.h"
 
@@ -76,13 +77,6 @@ struct perf_probe_event {
         struct perf_probe_arg   *args;  /* Arguments */
 };
 
-
-/* Line number container */
-struct line_node {
-        struct list_head        list;
-        int                     line;
-};
-
 /* Line range */
 struct line_range {
         char                    *file;          /* File name */
@@ -92,7 +86,7 @@ struct line_range {
         int                     offset;         /* Start line offset */
         char                    *path;          /* Real path name */
         char                    *comp_dir;      /* Compile directory */
-        struct list_head        line_list;      /* Visible lines */
+        struct intlist          *line_list;     /* Visible lines */
 };
 
 /* List of variables */
@@ -124,7 +118,7 @@ extern int parse_line_range_desc(const char *cmd, struct line_range *lr);
 extern void line_range__clear(struct line_range *lr);
 
 /* Initialize line range */
-extern void line_range__init(struct line_range *lr);
+extern int line_range__init(struct line_range *lr);
 
 /* Internal use: Return kernel/module path */
 extern const char *kernel_get_module_path(const char *module);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 061edb162b5b..df0238654698 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -34,7 +34,9 @@
 
 #include <linux/bitops.h>
 #include "event.h"
+#include "dso.h"
 #include "debug.h"
+#include "intlist.h"
 #include "util.h"
 #include "symbol.h"
 #include "probe-finder.h"
@@ -42,65 +44,6 @@
 /* Kprobe tracer basic type is up to u64 */
 #define MAX_BASIC_TYPE_BITS     64
 
-/* Line number list operations */
-
-/* Add a line to line number list */
-static int line_list__add_line(struct list_head *head, int line)
-{
-        struct line_node *ln;
-        struct list_head *p;
-
-        /* Reverse search, because new line will be the last one */
-        list_for_each_entry_reverse(ln, head, list) {
-                if (ln->line < line) {
-                        p = &ln->list;
-                        goto found;
-                } else if (ln->line == line)    /* Already exist */
-                        return 1;
-        }
-        /* List is empty, or the smallest entry */
-        p = head;
-found:
-        pr_debug("line list: add a line %u\n", line);
-        ln = zalloc(sizeof(struct line_node));
-        if (ln == NULL)
-                return -ENOMEM;
-        ln->line = line;
-        INIT_LIST_HEAD(&ln->list);
-        list_add(&ln->list, p);
-        return 0;
-}
-
-/* Check if the line in line number list */
-static int line_list__has_line(struct list_head *head, int line)
-{
-        struct line_node *ln;
-
-        /* Reverse search, because new line will be the last one */
-        list_for_each_entry(ln, head, list)
-                if (ln->line == line)
-                        return 1;
-
-        return 0;
-}
-
-/* Init line number list */
-static void line_list__init(struct list_head *head)
-{
-        INIT_LIST_HEAD(head);
-}
-
-/* Free line number list */
-static void line_list__free(struct list_head *head)
-{
-        struct line_node *ln;
-        while (!list_empty(head)) {
-                ln = list_first_entry(head, struct line_node, list);
-                list_del(&ln->list);
-                free(ln);
-        }
-}
-
 /* Dwarf FL wrappers */
 static char *debuginfo_path;    /* Currently dummy */
 
@@ -147,80 +90,7 @@ error:
         return -ENOENT;
 }
 
-#if _ELFUTILS_PREREQ(0, 148)
-/* This method is buggy if elfutils is older than 0.148 */
-static int __linux_kernel_find_elf(Dwfl_Module *mod,
-                                   void **userdata,
-                                   const char *module_name,
-                                   Dwarf_Addr base,
-                                   char **file_name, Elf **elfp)
-{
-        int fd;
-        const char *path = kernel_get_module_path(module_name);
-
-        pr_debug2("Use file %s for %s\n", path, module_name);
-        if (path) {
-                fd = open(path, O_RDONLY);
-                if (fd >= 0) {
-                        *file_name = strdup(path);
-                        return fd;
-                }
-        }
-        /* If failed, try to call standard method */
-        return dwfl_linux_kernel_find_elf(mod, userdata, module_name, base,
-                                          file_name, elfp);
-}
-
-static const Dwfl_Callbacks kernel_callbacks = {
-        .find_debuginfo = dwfl_standard_find_debuginfo,
-        .debuginfo_path = &debuginfo_path,
-
-        .find_elf = __linux_kernel_find_elf,
-        .section_address = dwfl_linux_kernel_module_section_address,
-};
-
-/* Get a Dwarf from live kernel image */
-static int debuginfo__init_online_kernel_dwarf(struct debuginfo *dbg,
-                                               Dwarf_Addr addr)
-{
-        dbg->dwfl = dwfl_begin(&kernel_callbacks);
-        if (!dbg->dwfl)
-                return -EINVAL;
-
-        /* Load the kernel dwarves: Don't care the result here */
-        dwfl_linux_kernel_report_kernel(dbg->dwfl);
-        dwfl_linux_kernel_report_modules(dbg->dwfl);
-
-        dbg->dbg = dwfl_addrdwarf(dbg->dwfl, addr, &dbg->bias);
-        /* Here, check whether we could get a real dwarf */
-        if (!dbg->dbg) {
-                pr_debug("Failed to find kernel dwarf at %lx\n",
-                         (unsigned long)addr);
-                dwfl_end(dbg->dwfl);
-                memset(dbg, 0, sizeof(*dbg));
-                return -ENOENT;
-        }
-
-        return 0;
-}
-#else
-/* With older elfutils, this just support kernel module... */
-static int debuginfo__init_online_kernel_dwarf(struct debuginfo *dbg,
-                                               Dwarf_Addr addr __maybe_unused)
-{
-        const char *path = kernel_get_module_path("kernel");
-
-        if (!path) {
-                pr_err("Failed to find vmlinux path\n");
-                return -ENOENT;
-        }
-
-        pr_debug2("Use file %s for debuginfo\n", path);
-        return debuginfo__init_offline_dwarf(dbg, path);
-}
-#endif
-
-struct debuginfo *debuginfo__new(const char *path)
+static struct debuginfo *__debuginfo__new(const char *path)
 {
         struct debuginfo *dbg = zalloc(sizeof(*dbg));
         if (!dbg)
@@ -228,21 +98,44 @@ struct debuginfo *debuginfo__new(const char *path)
 
         if (debuginfo__init_offline_dwarf(dbg, path) < 0)
                 zfree(&dbg);
-
+        if (dbg)
+                pr_debug("Open Debuginfo file: %s\n", path);
         return dbg;
 }
 
-struct debuginfo *debuginfo__new_online_kernel(unsigned long addr)
-{
-        struct debuginfo *dbg = zalloc(sizeof(*dbg));
+enum dso_binary_type distro_dwarf_types[] = {
+        DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+        DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+        DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
+        DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+        DSO_BINARY_TYPE__NOT_FOUND,
+};
 
-        if (!dbg)
-                return NULL;
+struct debuginfo *debuginfo__new(const char *path)
+{
+        enum dso_binary_type *type;
+        char buf[PATH_MAX], nil = '\0';
+        struct dso *dso;
+        struct debuginfo *dinfo = NULL;
+
+        /* Try to open distro debuginfo files */
+        dso = dso__new(path);
+        if (!dso)
+                goto out;
 
-        if (debuginfo__init_online_kernel_dwarf(dbg, (Dwarf_Addr)addr) < 0)
-                zfree(&dbg);
+        for (type = distro_dwarf_types;
+             !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND;
+             type++) {
+                if (dso__read_binary_type_filename(dso, *type, &nil,
+                                                   buf, PATH_MAX) < 0)
+                        continue;
+                dinfo = __debuginfo__new(buf);
+        }
+        dso__delete(dso);
 
-        return dbg;
+out:
+        /* if failed to open all distro debuginfo, open given binary */
+        return dinfo ? : __debuginfo__new(path);
 }
 
 void debuginfo__delete(struct debuginfo *dbg)
@@ -880,7 +773,7 @@ static int find_probe_point_by_line(struct probe_finder *pf)
 }
 
 /* Find lines which match lazy pattern */
-static int find_lazy_match_lines(struct list_head *head,
+static int find_lazy_match_lines(struct intlist *list,
                                  const char *fname, const char *pat)
 {
         FILE *fp;
@@ -901,7 +794,7 @@ static int find_lazy_match_lines(struct list_head *head,
                         line[len - 1] = '\0';
 
                 if (strlazymatch(line, pat)) {
-                        line_list__add_line(head, linenum);
+                        intlist__add(list, linenum);
                         count++;
                 }
                 linenum++;
@@ -924,7 +817,7 @@ static int probe_point_lazy_walker(const char *fname, int lineno,
         Dwarf_Die *sc_die, die_mem;
         int ret;
 
-        if (!line_list__has_line(&pf->lcache, lineno) ||
+        if (!intlist__has_entry(pf->lcache, lineno) ||
             strtailcmp(fname, pf->fname) != 0)
                 return 0;
 
@@ -952,9 +845,9 @@ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
         int ret = 0;
 
-        if (list_empty(&pf->lcache)) {
+        if (intlist__empty(pf->lcache)) {
                 /* Matching lazy line pattern */
-                ret = find_lazy_match_lines(&pf->lcache, pf->fname,
+                ret = find_lazy_match_lines(pf->lcache, pf->fname,
                                             pf->pev->point.lazy_line);
                 if (ret <= 0)
                         return ret;
@@ -1096,7 +989,9 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 #endif
 
         off = 0;
-        line_list__init(&pf->lcache);
+        pf->lcache = intlist__new(NULL);
+        if (!pf->lcache)
+                return -ENOMEM;
 
         /* Fastpath: lookup by function name from .debug_pubnames section */
         if (pp->function) {
@@ -1149,7 +1044,8 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
         }
 
 found:
-        line_list__free(&pf->lcache);
+        intlist__delete(pf->lcache);
+        pf->lcache = NULL;
 
         return ret;
 }
@@ -1537,7 +1433,7 @@ static int line_range_add_line(const char *src, unsigned int lineno,
                 if (lr->path == NULL)
                         return -ENOMEM;
         }
-        return line_list__add_line(&lr->line_list, lineno);
+        return intlist__add(lr->line_list, lineno);
 }
 
 static int line_range_walk_cb(const char *fname, int lineno,
@@ -1565,7 +1461,7 @@ static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 
         /* Update status */
         if (ret >= 0)
-                if (!list_empty(&lf->lr->line_list))
+                if (!intlist__empty(lf->lr->line_list))
                         ret = lf->found = 1;
                 else
                         ret = 0;        /* Lines are not found */
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index ffc33cdd25cc..92590b2c7e1c 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -3,6 +3,7 @@
 
 #include <stdbool.h>
 #include "util.h"
+#include "intlist.h"
 #include "probe-event.h"
 
 #define MAX_PROBE_BUFFER        1024
@@ -29,8 +30,8 @@ struct debuginfo {
         Dwarf_Addr      bias;
 };
 
+/* This also tries to open distro debuginfo */
 extern struct debuginfo *debuginfo__new(const char *path);
-extern struct debuginfo *debuginfo__new_online_kernel(unsigned long addr);
 extern void debuginfo__delete(struct debuginfo *dbg);
 
 /* Find probe_trace_events specified by perf_probe_event from debuginfo */
@@ -66,7 +67,7 @@ struct probe_finder {
         const char              *fname;         /* Real file name */
         Dwarf_Die               cu_die;         /* Current CU */
         Dwarf_Die               sp_die;
-        struct list_head        lcache;         /* Line cache for lazy match */
+        struct intlist          *lcache;        /* Line cache for lazy match */
 
         /* For variable searching */
 #if _ELFUTILS_PREREQ(0, 142)
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 595bfc73d2ed..16a475a7d492 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -17,6 +17,6 @@ util/xyarray.c
 util/cgroup.c
 util/rblist.c
 util/strlist.c
-util/fs.c
+../lib/api/fs/fs.c
 util/trace-event.c
 ../../lib/rbtree.c
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 373762501dad..049e0a09ccd3 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -2,7 +2,7 @@
 #include "evsel.h"
 #include "cpumap.h"
 #include "parse-events.h"
-#include "fs.h"
+#include <api/fs/fs.h>
 #include "util.h"
 
 typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 5da6ce74c676..1d555d652f58 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -702,11 +702,12 @@ static void regs_dump__printf(u64 mask, u64 *regs)
         }
 }
 
-static void regs_user__printf(struct perf_sample *sample, u64 mask)
+static void regs_user__printf(struct perf_sample *sample)
 {
         struct regs_dump *user_regs = &sample->user_regs;
 
         if (user_regs->regs) {
+                u64 mask = user_regs->mask;
                 printf("... user regs: mask 0x%" PRIx64 "\n", mask);
                 regs_dump__printf(mask, user_regs->regs);
         }
@@ -806,7 +807,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
                 branch_stack__printf(sample);
 
         if (sample_type & PERF_SAMPLE_REGS_USER)
-                regs_user__printf(sample, evsel->attr.sample_regs_user);
+                regs_user__printf(sample);
 
         if (sample_type & PERF_SAMPLE_STACK_USER)
                 stack_user__printf(&sample->user_stack);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index a9d758a3b371..46e2ede12c51 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -410,7 +410,7 @@ struct symbol *dso__find_symbol(struct dso *dso,
         return symbols__find(&dso->symbols[type], addr);
 }
 
-struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
+static struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
 {
         return symbols__first(&dso->symbols[type]);
 }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index fffe2888a1c7..2553ae04b788 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -79,6 +79,17 @@ struct symbol {
 void symbol__delete(struct symbol *sym);
 void symbols__delete(struct rb_root *symbols);
 
+/* symbols__for_each_entry - iterate over symbols (rb_root)
+ *
+ * @symbols: the rb_root of symbols
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @nd: the 'struct rb_node *' to use as a temporary storage
+ */
+#define symbols__for_each_entry(symbols, pos, nd)                       \
+        for (nd = rb_first(symbols);                                    \
+             nd && (pos = rb_entry(nd, struct symbol, rb_node));        \
+             nd = rb_next(nd))
+
 static inline size_t symbol__size(const struct symbol *sym)
 {
         return sym->end - sym->start + 1;
@@ -223,7 +234,6 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
                                 u64 addr);
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
                                         const char *name);
-struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
 
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index e0d6d07f6848..c36636fd825b 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -126,6 +126,7 @@ void event_format__print(struct event_format *event,
         trace_seq_init(&s);
         pevent_event_info(&s, event, &record);
         trace_seq_do_printf(&s);
+        trace_seq_destroy(&s);
 }
 
 void parse_proc_kallsyms(struct pevent *pevent,
diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind-libunwind.c
index 742f23bf35ff..bd5768d74f01 100644
--- a/tools/perf/util/unwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -86,7 +86,6 @@ struct unwind_info {
         struct perf_sample      *sample;
         struct machine          *machine;
         struct thread           *thread;
-        u64                     sample_uregs;
 };
 
 #define dw_read(ptr, type, end) ({      \
@@ -391,30 +390,13 @@ static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
         return !(size == sizeof(*data));
 }
 
-static int reg_value(unw_word_t *valp, struct regs_dump *regs, int id,
-                     u64 sample_regs)
-{
-        int i, idx = 0;
-
-        if (!(sample_regs & (1 << id)))
-                return -EINVAL;
-
-        for (i = 0; i < id; i++) {
-                if (sample_regs & (1 << i))
-                        idx++;
-        }
-
-        *valp = regs->regs[idx];
-        return 0;
-}
-
 static int access_mem(unw_addr_space_t __maybe_unused as,
                       unw_word_t addr, unw_word_t *valp,
                       int __write, void *arg)
 {
         struct unwind_info *ui = arg;
         struct stack_dump *stack = &ui->sample->user_stack;
-        unw_word_t start, end;
+        u64 start, end;
         int offset;
         int ret;
 
@@ -424,8 +406,7 @@ static int access_mem(unw_addr_space_t __maybe_unused as,
                 return 0;
         }
 
-        ret = reg_value(&start, &ui->sample->user_regs, PERF_REG_SP,
-                        ui->sample_uregs);
+        ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP);
         if (ret)
                 return ret;
 
@@ -438,8 +419,9 @@ static int access_mem(unw_addr_space_t __maybe_unused as,
         if (addr < start || addr + sizeof(unw_word_t) >= end) {
                 ret = access_dso_mem(ui, addr, valp);
                 if (ret) {
-                        pr_debug("unwind: access_mem %p not inside range %p-%p\n",
-                                (void *)addr, (void *)start, (void *)end);
+                        pr_debug("unwind: access_mem %p not inside range"
+                                 " 0x%" PRIx64 "-0x%" PRIx64 "\n",
+                                 (void *) addr, start, end);
                         *valp = 0;
                         return ret;
                 }
@@ -448,8 +430,8 @@ static int access_mem(unw_addr_space_t __maybe_unused as,
 
         offset = addr - start;
         *valp  = *(unw_word_t *)&stack->data[offset];
-        pr_debug("unwind: access_mem addr %p, val %lx, offset %d\n",
-                 (void *)addr, (unsigned long)*valp, offset);
+        pr_debug("unwind: access_mem addr %p val %lx, offset %d\n",
+                 (void *) addr, (unsigned long)*valp, offset);
         return 0;
 }
 
@@ -459,6 +441,7 @@ static int access_reg(unw_addr_space_t __maybe_unused as,
 {
         struct unwind_info *ui = arg;
         int id, ret;
+        u64 val;
 
         /* Don't support write, I suspect we don't need it. */
         if (__write) {
@@ -471,16 +454,17 @@ static int access_reg(unw_addr_space_t __maybe_unused as,
                 return 0;
         }
 
-        id = unwind__arch_reg_id(regnum);
+        id = libunwind__arch_reg_id(regnum);
         if (id < 0)
                 return -EINVAL;
 
-        ret = reg_value(valp, &ui->sample->user_regs, id, ui->sample_uregs);
+        ret = perf_reg_value(&val, &ui->sample->user_regs, id);
         if (ret) {
                 pr_err("unwind: can't read reg %d\n", regnum);
                 return ret;
         }
 
+        *valp = (unw_word_t) val;
         pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp);
         return 0;
 }
@@ -563,7 +547,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
                 unw_word_t ip;
 
                 unw_get_reg(&c, UNW_REG_IP, &ip);
-                ret = entry(ip, ui->thread, ui->machine, cb, arg);
+                ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0;
         }
 
         unw_destroy_addr_space(addr_space);
@@ -572,13 +556,11 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
                         struct machine *machine, struct thread *thread,
-                        u64 sample_uregs, struct perf_sample *data,
-                        int max_stack)
+                        struct perf_sample *data, int max_stack)
 {
-        unw_word_t ip;
+        u64 ip;
         struct unwind_info ui = {
                 .sample       = data,
-                .sample_uregs = sample_uregs,
                 .thread       = thread,
                 .machine      = machine,
         };
@@ -587,7 +569,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
         if (!data->user_regs.regs)
                 return -EINVAL;
 
-        ret = reg_value(&ip, &data->user_regs, PERF_REG_IP, sample_uregs);
+        ret = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
         if (ret)
                 return ret;
 
@@ -595,5 +577,5 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
         if (ret)
                 return -ENOMEM;
 
-        return get_entries(&ui, cb, arg, max_stack);
+        return --max_stack > 0 ? get_entries(&ui, cb, arg, max_stack) : 0;
 }
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index d5966f49e22c..b031316f221a 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -13,24 +13,25 @@ struct unwind_entry {
 
 typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
 
-#ifdef HAVE_LIBUNWIND_SUPPORT
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
                         struct machine *machine,
                         struct thread *thread,
-                        u64 sample_uregs,
                         struct perf_sample *data, int max_stack);
-int unwind__arch_reg_id(int regnum);
+/* libunwind specific */
+#ifdef HAVE_LIBUNWIND_SUPPORT
+int libunwind__arch_reg_id(int regnum);
+#endif
 #else
 static inline int
 unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
                     void *arg __maybe_unused,
                     struct machine *machine __maybe_unused,
                     struct thread *thread __maybe_unused,
-                    u64 sample_uregs __maybe_unused,
                     struct perf_sample *data __maybe_unused,
                     int max_stack __maybe_unused)
 {
         return 0;
 }
-#endif /* HAVE_LIBUNWIND_SUPPORT */
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
 #endif /* __UNWIND_H */
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 42ad667bb317..9f66549562bd 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,6 +1,6 @@
 #include "../perf.h"
 #include "util.h"
-#include "fs.h"
+#include <api/fs/fs.h>
 #include <sys/mman.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>