brain-hackers_pepepper-mirror
/
linux-brain
mirror of https://github.com/brain-hackers/linux-brain.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull perf updates from Ingo Molnar:
 "The main changes in this cycle on the kernel side were:

   - CPU PMU and uncore driver updates to Intel Snow Ridge, IceLake,
     KabyLake, AmberLake and WhiskeyLake CPUs.

   - Rework the MSR probing infrastructure to make it more robust, make
     it work better on virtualized systems and to better expose it on
     sysfs.

   - Rework PMU attributes group support based on the feedback from
     Greg. The core sysfs patch that adds sysfs_update_groups() was
     acked by Greg.

  There's a lot of perf tooling changes as well, all around the place:

   - vendor updates to Intel, cs-etm (ARM), ARM64, s390,

   - various enhancements to Intel PT tooling support:
      - Improve CBR (Core to Bus Ratio) packets support.
      - Export power and ptwrite events to sqlite and postgresql.
      - Add support for decoding PEBS via PT packets.
      - Add support for samples to contain IPC ratio, collecting cycles
        information from CYC packets, showing the IPC info periodically
      - Allow using time ranges

   - lots of updates to perf pmu, perf stat, perf trace, eBPF support,
     perf record, perf diff, etc. - please see the shortlog and Git log
     for details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (252 commits)
  tools arch x86: Sync asm/cpufeatures.h with the with the kernel
  tools build: Check if gettid() is available before providing helper
  perf jvmti: Address gcc string overflow warning for strncpy()
  perf python: Remove -fstack-protector-strong if clang doesn't have it
  perf annotate TUI browser: Do not use member from variable within its own initialization
  perf tests: Fix record+probe_libc_inet_pton.sh for powerpc64
  perf evsel: Do not rely on errno values for precise_ip fallback
  perf thread: Allow references to thread objects after machine__exit()
  perf header: Assign proper ff->ph in perf_event__synthesize_features()
  tools arch kvm: Sync kvm headers with the kernel sources
  perf script: Allow specifying the files to process guest samples
  perf tools metric: Don't include duration_time in group
  perf list: Avoid extra : for --raw metrics
  perf vendor events intel: Metric fixes for SKX/CLX
  perf tools: Fix typos / broken sentences
  perf jevents: Add support for Hisi hip08 L3C PMU aliasing
  perf jevents: Add support for Hisi hip08 HHA PMU aliasing
  perf jevents: Add support for Hisi hip08 DDRC PMU aliasing
  perf pmu: Support more complex PMU event aliasing
  perf diff: Documentation -c cycles option
  ...
This commit is contained in:
Linus Torvalds 2019-07-09 11:15:52 -07:00
parent cdc5ffc410 d1d59b8179
commit 608745f124
204 changed files with 8991 additions and 2121 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
arch/x86/events/Makefile
View File

@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0-only
obj-y += core.o
obj-y += core.o probe.o
obj-y += amd/
obj-$(CONFIG_X86_LOCAL_APIC) += msr.o
obj-$(CONFIG_CPU_SUP_INTEL) += intel/

106
arch/x86/events/core.c
View File

@ -1618,68 +1618,6 @@ static struct attribute_group x86_pmu_format_group __ro_after_init = {
.attrs = NULL,
};
/*
* Remove all undefined events (x86_pmu.event_map(id) == 0)
* out of events_attr attributes.
*/
static void __init filter_events(struct attribute **attrs)
{
struct device_attribute *d;
struct perf_pmu_events_attr *pmu_attr;
int offset = 0;
int i, j;
for (i = 0; attrs[i]; i++) {
d = (struct device_attribute *)attrs[i];
pmu_attr = container_of(d, struct perf_pmu_events_attr, attr);
/* str trumps id */
if (pmu_attr->event_str)
continue;
if (x86_pmu.event_map(i + offset))
continue;
for (j = i; attrs[j]; j++)
attrs[j] = attrs[j + 1];
/* Check the shifted attr. */
i--;
/*
* event_map() is index based, the attrs array is organized
* by increasing event index. If we shift the events, then
* we need to compensate for the event_map(), otherwise
* we are looking up the wrong event in the map
*/
offset++;
}
}
/* Merge two pointer arrays */
__init struct attribute **merge_attr(struct attribute **a, struct attribute **b)
{
struct attribute **new;
int j, i;
for (j = 0; a && a[j]; j++)
;
for (i = 0; b && b[i]; i++)
j++;
j++;
new = kmalloc_array(j, sizeof(struct attribute *), GFP_KERNEL);
if (!new)
return NULL;
j = 0;
for (i = 0; a && a[i]; i++)
new[j++] = a[i];
for (i = 0; b && b[i]; i++)
new[j++] = b[i];
new[j] = NULL;
return new;
}
ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page)
{
struct perf_pmu_events_attr *pmu_attr = \
@ -1744,9 +1682,24 @@ static struct attribute *events_attr[] = {
NULL,
};
/*
* Remove all undefined events (x86_pmu.event_map(id) == 0)
* out of events_attr attributes.
*/
static umode_t
is_visible(struct kobject *kobj, struct attribute *attr, int idx)
{
struct perf_pmu_events_attr *pmu_attr;
pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr);
/* str trumps id */
return pmu_attr->event_str || x86_pmu.event_map(idx) ? attr->mode : 0;
}
static struct attribute_group x86_pmu_events_group __ro_after_init = {
.name = "events",
.attrs = events_attr,
.is_visible = is_visible,
};
ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event)
@ -1842,37 +1795,10 @@ static int __init init_hw_perf_events(void)
x86_pmu_format_group.attrs = x86_pmu.format_attrs;
if (x86_pmu.caps_attrs) {
struct attribute **tmp;
tmp = merge_attr(x86_pmu_caps_group.attrs, x86_pmu.caps_attrs);
if (!WARN_ON(!tmp))
x86_pmu_caps_group.attrs = tmp;
}
if (x86_pmu.event_attrs)
x86_pmu_events_group.attrs = x86_pmu.event_attrs;
if (!x86_pmu.events_sysfs_show)
x86_pmu_events_group.attrs = &empty_attrs;
else
filter_events(x86_pmu_events_group.attrs);
if (x86_pmu.cpu_events) {
struct attribute **tmp;
tmp = merge_attr(x86_pmu_events_group.attrs, x86_pmu.cpu_events);
if (!WARN_ON(!tmp))
x86_pmu_events_group.attrs = tmp;
}
if (x86_pmu.attrs) {
struct attribute **tmp;
tmp = merge_attr(x86_pmu_attr_group.attrs, x86_pmu.attrs);
if (!WARN_ON(!tmp))
x86_pmu_attr_group.attrs = tmp;
}
pmu.attr_update = x86_pmu.attr_update;
pr_info("... version: %d\n", x86_pmu.version);
pr_info("... bit width: %d\n", x86_pmu.cntval_bits);

191
arch/x86/events/intel/core.c
View File

@ -20,6 +20,7 @@
#include <asm/intel-family.h>
#include <asm/apic.h>
#include <asm/cpu_device_id.h>
#include <asm/hypervisor.h>
#include "../perf_event.h"
@ -3897,8 +3898,6 @@ static __initconst const struct x86_pmu core_pmu = {
.check_period = intel_pmu_check_period,
};
static struct attribute *intel_pmu_attrs[];
static __initconst const struct x86_pmu intel_pmu = {
.name = "Intel",
.handle_irq = intel_pmu_handle_irq,
@ -3930,8 +3929,6 @@ static __initconst const struct x86_pmu intel_pmu = {
.format_attrs = intel_arch3_formats_attr,
.events_sysfs_show = intel_event_sysfs_show,
.attrs = intel_pmu_attrs,
.cpu_prepare = intel_pmu_cpu_prepare,
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
@ -4054,6 +4051,13 @@ static bool check_msr(unsigned long msr, u64 mask)
{
u64 val_old, val_new, val_tmp;
/*
* Disable the check for real HW, so we don't
* mess with potentionaly enabled registers:
*/
if (hypervisor_is_type(X86_HYPER_NATIVE))
return true;
/*
* Read the current value, change it and read it back to see if it
* matches, this is needed to detect certain hardware emulators
@ -4274,13 +4278,6 @@ static struct attribute *icl_tsx_events_attrs[] = {
NULL,
};
static __init struct attribute **get_icl_events_attrs(void)
{
return boot_cpu_has(X86_FEATURE_RTM) ?
merge_attr(icl_events_attrs, icl_tsx_events_attrs) :
icl_events_attrs;
}
static ssize_t freeze_on_smi_show(struct device *cdev,
struct device_attribute *attr,
char *buf)
@ -4402,43 +4399,111 @@ static DEVICE_ATTR(allow_tsx_force_abort, 0644,
static struct attribute *intel_pmu_attrs[] = {
&dev_attr_freeze_on_smi.attr,
NULL, /* &dev_attr_allow_tsx_force_abort.attr.attr */
&dev_attr_allow_tsx_force_abort.attr,
NULL,
};
static __init struct attribute **
get_events_attrs(struct attribute **base,
struct attribute **mem,
struct attribute **tsx)
static umode_t
tsx_is_visible(struct kobject *kobj, struct attribute *attr, int i)
{
struct attribute **attrs = base;
struct attribute **old;
if (mem && x86_pmu.pebs)
attrs = merge_attr(attrs, mem);
if (tsx && boot_cpu_has(X86_FEATURE_RTM)) {
old = attrs;
attrs = merge_attr(attrs, tsx);
if (old != base)
kfree(old);
}
return attrs;
return boot_cpu_has(X86_FEATURE_RTM) ? attr->mode : 0;
}
static umode_t
pebs_is_visible(struct kobject *kobj, struct attribute *attr, int i)
{
return x86_pmu.pebs ? attr->mode : 0;
}
static umode_t
lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
{
return x86_pmu.lbr_nr ? attr->mode : 0;
}
static umode_t
exra_is_visible(struct kobject *kobj, struct attribute *attr, int i)
{
return x86_pmu.version >= 2 ? attr->mode : 0;
}
static umode_t
default_is_visible(struct kobject *kobj, struct attribute *attr, int i)
{
if (attr == &dev_attr_allow_tsx_force_abort.attr)
return x86_pmu.flags & PMU_FL_TFA ? attr->mode : 0;
return attr->mode;
}
static struct attribute_group group_events_td = {
.name = "events",
};
static struct attribute_group group_events_mem = {
.name = "events",
.is_visible = pebs_is_visible,
};
static struct attribute_group group_events_tsx = {
.name = "events",
.is_visible = tsx_is_visible,
};
static struct attribute_group group_caps_gen = {
.name = "caps",
.attrs = intel_pmu_caps_attrs,
};
static struct attribute_group group_caps_lbr = {
.name = "caps",
.attrs = lbr_attrs,
.is_visible = lbr_is_visible,
};
static struct attribute_group group_format_extra = {
.name = "format",
.is_visible = exra_is_visible,
};
static struct attribute_group group_format_extra_skl = {
.name = "format",
.is_visible = exra_is_visible,
};
static struct attribute_group group_default = {
.attrs = intel_pmu_attrs,
.is_visible = default_is_visible,
};
static const struct attribute_group *attr_update[] = {
&group_events_td,
&group_events_mem,
&group_events_tsx,
&group_caps_gen,
&group_caps_lbr,
&group_format_extra,
&group_format_extra_skl,
&group_default,
NULL,
};
static struct attribute *empty_attrs;
__init int intel_pmu_init(void)
{
struct attribute **extra_attr = NULL;
struct attribute **mem_attr = NULL;
struct attribute **tsx_attr = NULL;
struct attribute **to_free = NULL;
struct attribute **extra_skl_attr = &empty_attrs;
struct attribute **extra_attr = &empty_attrs;
struct attribute **td_attr = &empty_attrs;
struct attribute **mem_attr = &empty_attrs;
struct attribute **tsx_attr = &empty_attrs;
union cpuid10_edx edx;
union cpuid10_eax eax;
union cpuid10_ebx ebx;
struct event_constraint *c;
unsigned int unused;
struct extra_reg *er;
bool pmem = false;
int version, i;
char *name;
@ -4596,7 +4661,7 @@ __init int intel_pmu_init(void)
x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
x86_pmu.extra_regs = intel_slm_extra_regs;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.cpu_events = slm_events_attrs;
td_attr = slm_events_attrs;
extra_attr = slm_format_attr;
pr_cont("Silvermont events, ");
name = "silvermont";
@ -4624,7 +4689,7 @@ __init int intel_pmu_init(void)
x86_pmu.pebs_prec_dist = true;
x86_pmu.lbr_pt_coexist = true;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.cpu_events = glm_events_attrs;
td_attr = glm_events_attrs;
extra_attr = slm_format_attr;
pr_cont("Goldmont events, ");
name = "goldmont";
@ -4651,7 +4716,7 @@ __init int intel_pmu_init(void)
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_PEBS_ALL;
x86_pmu.get_event_constraints = glp_get_event_constraints;
x86_pmu.cpu_events = glm_events_attrs;
td_attr = glm_events_attrs;
/* Goldmont Plus has 4-wide pipeline */
event_attr_td_total_slots_scale_glm.event_str = "4";
extra_attr = slm_format_attr;
@ -4740,7 +4805,7 @@ __init int intel_pmu_init(void)
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
x86_pmu.cpu_events = snb_events_attrs;
td_attr = snb_events_attrs;
mem_attr = snb_mem_events_attrs;
/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
@ -4781,7 +4846,7 @@ __init int intel_pmu_init(void)
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
x86_pmu.cpu_events = snb_events_attrs;
td_attr = snb_events_attrs;
mem_attr = snb_mem_events_attrs;
/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
@ -4818,10 +4883,10 @@ __init int intel_pmu_init(void)
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
x86_pmu.cpu_events = hsw_events_attrs;
x86_pmu.lbr_double_abort = true;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
td_attr = hsw_events_attrs;
mem_attr = hsw_mem_events_attrs;
tsx_attr = hsw_tsx_events_attrs;
pr_cont("Haswell events, ");
@ -4860,10 +4925,10 @@ __init int intel_pmu_init(void)
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
x86_pmu.cpu_events = hsw_events_attrs;
x86_pmu.limit_period = bdw_limit_period;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
td_attr = hsw_events_attrs;
mem_attr = hsw_mem_events_attrs;
tsx_attr = hsw_tsx_events_attrs;
pr_cont("Broadwell events, ");
@ -4890,9 +4955,10 @@ __init int intel_pmu_init(void)
name = "knights-landing";
break;
case INTEL_FAM6_SKYLAKE_X:
pmem = true;
case INTEL_FAM6_SKYLAKE_MOBILE:
case INTEL_FAM6_SKYLAKE_DESKTOP:
case INTEL_FAM6_SKYLAKE_X:
case INTEL_FAM6_KABYLAKE_MOBILE:
case INTEL_FAM6_KABYLAKE_DESKTOP:
x86_add_quirk(intel_pebs_isolation_quirk);
@ -4920,27 +4986,28 @@ __init int intel_pmu_init(void)
x86_pmu.get_event_constraints = hsw_get_event_constraints;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
extra_attr = merge_attr(extra_attr, skl_format_attr);
to_free = extra_attr;
x86_pmu.cpu_events = hsw_events_attrs;
extra_skl_attr = skl_format_attr;
td_attr = hsw_events_attrs;
mem_attr = hsw_mem_events_attrs;
tsx_attr = hsw_tsx_events_attrs;
intel_pmu_pebs_data_source_skl(
boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
intel_pmu_pebs_data_source_skl(pmem);
if (boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) {
x86_pmu.flags |= PMU_FL_TFA;
x86_pmu.get_event_constraints = tfa_get_event_constraints;
x86_pmu.enable_all = intel_tfa_pmu_enable_all;
x86_pmu.commit_scheduling = intel_tfa_commit_scheduling;
intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr;
}
pr_cont("Skylake events, ");
name = "skylake";
break;
case INTEL_FAM6_ICELAKE_X:
case INTEL_FAM6_ICELAKE_XEON_D:
pmem = true;
case INTEL_FAM6_ICELAKE_MOBILE:
case INTEL_FAM6_ICELAKE_DESKTOP:
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@ -4959,11 +5026,12 @@ __init int intel_pmu_init(void)
x86_pmu.get_event_constraints = icl_get_event_constraints;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
extra_attr = merge_attr(extra_attr, skl_format_attr);
x86_pmu.cpu_events = get_icl_events_attrs();
extra_skl_attr = skl_format_attr;
mem_attr = icl_events_attrs;
tsx_attr = icl_tsx_events_attrs;
x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
x86_pmu.lbr_pt_coexist = true;
intel_pmu_pebs_data_source_skl(false);
intel_pmu_pebs_data_source_skl(pmem);
pr_cont("Icelake events, ");
name = "icelake";
break;
@ -4988,14 +5056,14 @@ __init int intel_pmu_init(void)
snprintf(pmu_name_str, sizeof(pmu_name_str), "%s", name);
if (version >= 2 && extra_attr) {
x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr,
extra_attr);
WARN_ON(!x86_pmu.format_attrs);
}
x86_pmu.cpu_events = get_events_attrs(x86_pmu.cpu_events,
mem_attr, tsx_attr);
group_events_td.attrs = td_attr;
group_events_mem.attrs = mem_attr;
group_events_tsx.attrs = tsx_attr;
group_format_extra.attrs = extra_attr;
group_format_extra_skl.attrs = extra_skl_attr;
x86_pmu.attr_update = attr_update;
if (x86_pmu.num_counters > INTEL_PMC_MAX_GENERIC) {
WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
@ -5043,12 +5111,8 @@ __init int intel_pmu_init(void)
x86_pmu.lbr_nr = 0;
}
x86_pmu.caps_attrs = intel_pmu_caps_attrs;
if (x86_pmu.lbr_nr) {
x86_pmu.caps_attrs = merge_attr(x86_pmu.caps_attrs, lbr_attrs);
if (x86_pmu.lbr_nr)
pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr);
}
/*
* Access extra MSR may cause #GP under certain circumstances.
@ -5078,7 +5142,6 @@ __init int intel_pmu_init(void)
if (x86_pmu.counter_freezing)
x86_pmu.handle_irq = intel_pmu_handle_irq_v4;
kfree(to_free);
return 0;
}

149
arch/x86/events/intel/cstate.c
View File

@ -96,6 +96,7 @@
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#include "../perf_event.h"
#include "../probe.h"
MODULE_LICENSE("GPL");
@ -144,25 +145,42 @@ enum perf_cstate_core_events {
PERF_CSTATE_CORE_EVENT_MAX,
};
PMU_EVENT_ATTR_STRING(c1-residency, evattr_cstate_core_c1, "event=0x00");
PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_core_c3, "event=0x01");
PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_core_c6, "event=0x02");
PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_core_c7, "event=0x03");
PMU_EVENT_ATTR_STRING(c1-residency, attr_cstate_core_c1, "event=0x00");
PMU_EVENT_ATTR_STRING(c3-residency, attr_cstate_core_c3, "event=0x01");
PMU_EVENT_ATTR_STRING(c6-residency, attr_cstate_core_c6, "event=0x02");
PMU_EVENT_ATTR_STRING(c7-residency, attr_cstate_core_c7, "event=0x03");
static struct perf_cstate_msr core_msr[] = {
[PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &evattr_cstate_core_c1 },
[PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &evattr_cstate_core_c3 },
[PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &evattr_cstate_core_c6 },
[PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &evattr_cstate_core_c7 },
static unsigned long core_msr_mask;
PMU_EVENT_GROUP(events, cstate_core_c1);
PMU_EVENT_GROUP(events, cstate_core_c3);
PMU_EVENT_GROUP(events, cstate_core_c6);
PMU_EVENT_GROUP(events, cstate_core_c7);
static bool test_msr(int idx, void *data)
{
return test_bit(idx, (unsigned long *) data);
}
static struct perf_msr core_msr[] = {
[PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &group_cstate_core_c1, test_msr },
[PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &group_cstate_core_c3, test_msr },
[PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &group_cstate_core_c6, test_msr },
[PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &group_cstate_core_c7, test_msr },
};
static struct attribute *core_events_attrs[PERF_CSTATE_CORE_EVENT_MAX + 1] = {
static struct attribute *attrs_empty[] = {
NULL,
};
/*
* There are no default events, but we need to create
* "events" group (with empty attrs) before updating
* it with detected events.
*/
static struct attribute_group core_events_attr_group = {
.name = "events",
.attrs = core_events_attrs,
.attrs = attrs_empty,
};
DEFINE_CSTATE_FORMAT_ATTR(core_event, event, "config:0-63");
@ -211,31 +229,37 @@ enum perf_cstate_pkg_events {
PERF_CSTATE_PKG_EVENT_MAX,
};
PMU_EVENT_ATTR_STRING(c2-residency, evattr_cstate_pkg_c2, "event=0x00");
PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_pkg_c3, "event=0x01");
PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_pkg_c6, "event=0x02");
PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_pkg_c7, "event=0x03");
PMU_EVENT_ATTR_STRING(c8-residency, evattr_cstate_pkg_c8, "event=0x04");
PMU_EVENT_ATTR_STRING(c9-residency, evattr_cstate_pkg_c9, "event=0x05");
PMU_EVENT_ATTR_STRING(c10-residency, evattr_cstate_pkg_c10, "event=0x06");
PMU_EVENT_ATTR_STRING(c2-residency, attr_cstate_pkg_c2, "event=0x00");
PMU_EVENT_ATTR_STRING(c3-residency, attr_cstate_pkg_c3, "event=0x01");
PMU_EVENT_ATTR_STRING(c6-residency, attr_cstate_pkg_c6, "event=0x02");
PMU_EVENT_ATTR_STRING(c7-residency, attr_cstate_pkg_c7, "event=0x03");
PMU_EVENT_ATTR_STRING(c8-residency, attr_cstate_pkg_c8, "event=0x04");
PMU_EVENT_ATTR_STRING(c9-residency, attr_cstate_pkg_c9, "event=0x05");
PMU_EVENT_ATTR_STRING(c10-residency, attr_cstate_pkg_c10, "event=0x06");
static struct perf_cstate_msr pkg_msr[] = {
[PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &evattr_cstate_pkg_c2 },
[PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &evattr_cstate_pkg_c3 },
[PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &evattr_cstate_pkg_c6 },
[PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &evattr_cstate_pkg_c7 },
[PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &evattr_cstate_pkg_c8 },
[PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &evattr_cstate_pkg_c9 },
[PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &evattr_cstate_pkg_c10 },
};
static unsigned long pkg_msr_mask;
static struct attribute *pkg_events_attrs[PERF_CSTATE_PKG_EVENT_MAX + 1] = {
NULL,
PMU_EVENT_GROUP(events, cstate_pkg_c2);
PMU_EVENT_GROUP(events, cstate_pkg_c3);
PMU_EVENT_GROUP(events, cstate_pkg_c6);
PMU_EVENT_GROUP(events, cstate_pkg_c7);
PMU_EVENT_GROUP(events, cstate_pkg_c8);
PMU_EVENT_GROUP(events, cstate_pkg_c9);
PMU_EVENT_GROUP(events, cstate_pkg_c10);
static struct perf_msr pkg_msr[] = {
[PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &group_cstate_pkg_c2, test_msr },
[PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &group_cstate_pkg_c3, test_msr },
[PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &group_cstate_pkg_c6, test_msr },
[PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &group_cstate_pkg_c7, test_msr },
[PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &group_cstate_pkg_c8, test_msr },
[PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &group_cstate_pkg_c9, test_msr },
[PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &group_cstate_pkg_c10, test_msr },
};
static struct attribute_group pkg_events_attr_group = {
.name = "events",
.attrs = pkg_events_attrs,
.attrs = attrs_empty,
};
DEFINE_CSTATE_FORMAT_ATTR(pkg_event, event, "config:0-63");
@ -289,7 +313,8 @@ static int cstate_pmu_event_init(struct perf_event *event)
if (event->pmu == &cstate_core_pmu) {
if (cfg >= PERF_CSTATE_CORE_EVENT_MAX)
return -EINVAL;
if (!core_msr[cfg].attr)
cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_CORE_EVENT_MAX);
if (!(core_msr_mask & (1 << cfg)))
return -EINVAL;
event->hw.event_base = core_msr[cfg].msr;
cpu = cpumask_any_and(&cstate_core_cpu_mask,
@ -298,7 +323,7 @@ static int cstate_pmu_event_init(struct perf_event *event)
if (cfg >= PERF_CSTATE_PKG_EVENT_MAX)
return -EINVAL;
cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX);
if (!pkg_msr[cfg].attr)
if (!(pkg_msr_mask & (1 << cfg)))
return -EINVAL;
event->hw.event_base = pkg_msr[cfg].msr;
cpu = cpumask_any_and(&cstate_pkg_cpu_mask,
@ -421,8 +446,28 @@ static int cstate_cpu_init(unsigned int cpu)
return 0;
}
const struct attribute_group *core_attr_update[] = {
&group_cstate_core_c1,
&group_cstate_core_c3,
&group_cstate_core_c6,
&group_cstate_core_c7,
NULL,
};
const struct attribute_group *pkg_attr_update[] = {
&group_cstate_pkg_c2,
&group_cstate_pkg_c3,
&group_cstate_pkg_c6,
&group_cstate_pkg_c7,
&group_cstate_pkg_c8,
&group_cstate_pkg_c9,
&group_cstate_pkg_c10,
NULL,
};
static struct pmu cstate_core_pmu = {
.attr_groups = core_attr_groups,
.attr_update = core_attr_update,
.name = "cstate_core",
.task_ctx_nr = perf_invalid_context,
.event_init = cstate_pmu_event_init,
@ -437,6 +482,7 @@ static struct pmu cstate_core_pmu = {
static struct pmu cstate_pkg_pmu = {
.attr_groups = pkg_attr_groups,
.attr_update = pkg_attr_update,
.name = "cstate_pkg",
.task_ctx_nr = perf_invalid_context,
.event_init = cstate_pmu_event_init,
@ -580,35 +626,11 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_MOBILE, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_DESKTOP, snb_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
/*
* Probe the cstate events and insert the available one into sysfs attrs
* Return false if there are no available events.
*/
static bool __init cstate_probe_msr(const unsigned long evmsk, int max,
struct perf_cstate_msr *msr,
struct attribute **attrs)
{
bool found = false;
unsigned int bit;
u64 val;
for (bit = 0; bit < max; bit++) {
if (test_bit(bit, &evmsk) && !rdmsrl_safe(msr[bit].msr, &val)) {
*attrs++ = &msr[bit].attr->attr.attr;
found = true;
} else {
msr[bit].attr = NULL;
}
}
*attrs = NULL;
return found;
}
static int __init cstate_probe(const struct cstate_model *cm)
{
/* SLM has different MSR for PKG C6 */
@ -620,13 +642,14 @@ static int __init cstate_probe(const struct cstate_model *cm)
pkg_msr[PERF_CSTATE_CORE_C6_RES].msr = MSR_KNL_CORE_C6_RESIDENCY;
has_cstate_core = cstate_probe_msr(cm->core_events,
PERF_CSTATE_CORE_EVENT_MAX,
core_msr, core_events_attrs);
core_msr_mask = perf_msr_probe(core_msr, PERF_CSTATE_CORE_EVENT_MAX,
true, (void *) &cm->core_events);
has_cstate_pkg = cstate_probe_msr(cm->pkg_events,
PERF_CSTATE_PKG_EVENT_MAX,
pkg_msr, pkg_events_attrs);
pkg_msr_mask = perf_msr_probe(pkg_msr, PERF_CSTATE_PKG_EVENT_MAX,
true, (void *) &cm->pkg_events);
has_cstate_core = !!core_msr_mask;
has_cstate_pkg = !!pkg_msr_mask;
return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV;
}

401
arch/x86/events/intel/rapl.c
View File

@ -55,27 +55,28 @@
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/perf_event.h>
#include <linux/nospec.h>
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#include "../perf_event.h"
#include "../probe.h"
MODULE_LICENSE("GPL");
/*
* RAPL energy status counters
*/
#define RAPL_IDX_PP0_NRG_STAT 0 /* all cores */
#define INTEL_RAPL_PP0 0x1 /* pseudo-encoding */
#define RAPL_IDX_PKG_NRG_STAT 1 /* entire package */
#define INTEL_RAPL_PKG 0x2 /* pseudo-encoding */
#define RAPL_IDX_RAM_NRG_STAT 2 /* DRAM */
#define INTEL_RAPL_RAM 0x3 /* pseudo-encoding */
#define RAPL_IDX_PP1_NRG_STAT 3 /* gpu */
#define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */
#define RAPL_IDX_PSYS_NRG_STAT 4 /* psys */
#define INTEL_RAPL_PSYS 0x5 /* pseudo-encoding */
enum perf_rapl_events {
PERF_RAPL_PP0 = 0, /* all cores */
PERF_RAPL_PKG, /* entire package */
PERF_RAPL_RAM, /* DRAM */
PERF_RAPL_PP1, /* gpu */
PERF_RAPL_PSYS, /* psys */
PERF_RAPL_MAX,
NR_RAPL_DOMAINS = PERF_RAPL_MAX,
};
#define NR_RAPL_DOMAINS 0x5
static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
"pp0-core",
"package",
@ -84,33 +85,6 @@ static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
"psys",
};
/* Clients have PP0, PKG */
#define RAPL_IDX_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\
1<<RAPL_IDX_PKG_NRG_STAT|\
1<<RAPL_IDX_PP1_NRG_STAT)
/* Servers have PP0, PKG, RAM */
#define RAPL_IDX_SRV (1<<RAPL_IDX_PP0_NRG_STAT|\
1<<RAPL_IDX_PKG_NRG_STAT|\
1<<RAPL_IDX_RAM_NRG_STAT)
/* Servers have PP0, PKG, RAM, PP1 */
#define RAPL_IDX_HSW (1<<RAPL_IDX_PP0_NRG_STAT|\
1<<RAPL_IDX_PKG_NRG_STAT|\
1<<RAPL_IDX_RAM_NRG_STAT|\
1<<RAPL_IDX_PP1_NRG_STAT)
/* SKL clients have PP0, PKG, RAM, PP1, PSYS */
#define RAPL_IDX_SKL_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\
1<<RAPL_IDX_PKG_NRG_STAT|\
1<<RAPL_IDX_RAM_NRG_STAT|\
1<<RAPL_IDX_PP1_NRG_STAT|\
1<<RAPL_IDX_PSYS_NRG_STAT)
/* Knights Landing has PKG, RAM */
#define RAPL_IDX_KNL (1<<RAPL_IDX_PKG_NRG_STAT|\
1<<RAPL_IDX_RAM_NRG_STAT)
/*
* event code: LSB 8 bits, passed in attr->config
* any other bit is reserved
@ -153,12 +127,18 @@ struct rapl_pmus {
struct rapl_pmu *pmus[];
};
struct rapl_model {
unsigned long events;
bool apply_quirk;
};
/* 1/2^hw_unit Joule */
static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly;
static struct rapl_pmus *rapl_pmus;
static cpumask_t rapl_cpu_mask;
static unsigned int rapl_cntr_mask;
static u64 rapl_timer_ms;
static struct perf_msr rapl_msrs[];
static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
{
@ -350,7 +330,7 @@ static void rapl_pmu_event_del(struct perf_event *event, int flags)
static int rapl_pmu_event_init(struct perf_event *event)
{
u64 cfg = event->attr.config & RAPL_EVENT_MASK;
int bit, msr, ret = 0;
int bit, ret = 0;
struct rapl_pmu *pmu;
/* only look at RAPL events */
@ -366,33 +346,12 @@ static int rapl_pmu_event_init(struct perf_event *event)
event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
/*
* check event is known (determines counter)
*/
switch (cfg) {
case INTEL_RAPL_PP0:
bit = RAPL_IDX_PP0_NRG_STAT;
msr = MSR_PP0_ENERGY_STATUS;
break;
case INTEL_RAPL_PKG:
bit = RAPL_IDX_PKG_NRG_STAT;
msr = MSR_PKG_ENERGY_STATUS;
break;
case INTEL_RAPL_RAM:
bit = RAPL_IDX_RAM_NRG_STAT;
msr = MSR_DRAM_ENERGY_STATUS;
break;
case INTEL_RAPL_PP1:
bit = RAPL_IDX_PP1_NRG_STAT;
msr = MSR_PP1_ENERGY_STATUS;
break;
case INTEL_RAPL_PSYS:
bit = RAPL_IDX_PSYS_NRG_STAT;
msr = MSR_PLATFORM_ENERGY_STATUS;
break;
default:
if (!cfg || cfg >= NR_RAPL_DOMAINS + 1)
return -EINVAL;
}
cfg = array_index_nospec((long)cfg, NR_RAPL_DOMAINS + 1);
bit = cfg - 1;
/* check event supported */
if (!(rapl_cntr_mask & (1 << bit)))
return -EINVAL;
@ -407,7 +366,7 @@ static int rapl_pmu_event_init(struct perf_event *event)
return -EINVAL;
event->cpu = pmu->cpu;
event->pmu_private = pmu;
event->hw.event_base = msr;
event->hw.event_base = rapl_msrs[bit].msr;
event->hw.config = cfg;
event->hw.idx = bit;
@ -457,90 +416,18 @@ RAPL_EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890
RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10");
RAPL_EVENT_ATTR_STR(energy-psys.scale, rapl_psys_scale, "2.3283064365386962890625e-10");
static struct attribute *rapl_events_srv_attr[] = {
EVENT_PTR(rapl_cores),
EVENT_PTR(rapl_pkg),
EVENT_PTR(rapl_ram),
EVENT_PTR(rapl_cores_unit),
EVENT_PTR(rapl_pkg_unit),
EVENT_PTR(rapl_ram_unit),
EVENT_PTR(rapl_cores_scale),
EVENT_PTR(rapl_pkg_scale),
EVENT_PTR(rapl_ram_scale),
NULL,
};
static struct attribute *rapl_events_cln_attr[] = {
EVENT_PTR(rapl_cores),
EVENT_PTR(rapl_pkg),
EVENT_PTR(rapl_gpu),
EVENT_PTR(rapl_cores_unit),
EVENT_PTR(rapl_pkg_unit),
EVENT_PTR(rapl_gpu_unit),
EVENT_PTR(rapl_cores_scale),
EVENT_PTR(rapl_pkg_scale),
EVENT_PTR(rapl_gpu_scale),
NULL,
};
static struct attribute *rapl_events_hsw_attr[] = {
EVENT_PTR(rapl_cores),
EVENT_PTR(rapl_pkg),
EVENT_PTR(rapl_gpu),
EVENT_PTR(rapl_ram),
EVENT_PTR(rapl_cores_unit),
EVENT_PTR(rapl_pkg_unit),
EVENT_PTR(rapl_gpu_unit),
EVENT_PTR(rapl_ram_unit),
EVENT_PTR(rapl_cores_scale),
EVENT_PTR(rapl_pkg_scale),
EVENT_PTR(rapl_gpu_scale),
EVENT_PTR(rapl_ram_scale),
NULL,
};
static struct attribute *rapl_events_skl_attr[] = {
EVENT_PTR(rapl_cores),
EVENT_PTR(rapl_pkg),
EVENT_PTR(rapl_gpu),
EVENT_PTR(rapl_ram),
EVENT_PTR(rapl_psys),
EVENT_PTR(rapl_cores_unit),
EVENT_PTR(rapl_pkg_unit),
EVENT_PTR(rapl_gpu_unit),
EVENT_PTR(rapl_ram_unit),
EVENT_PTR(rapl_psys_unit),
EVENT_PTR(rapl_cores_scale),
EVENT_PTR(rapl_pkg_scale),
EVENT_PTR(rapl_gpu_scale),
EVENT_PTR(rapl_ram_scale),
EVENT_PTR(rapl_psys_scale),
NULL,
};
static struct attribute *rapl_events_knl_attr[] = {
EVENT_PTR(rapl_pkg),
EVENT_PTR(rapl_ram),
EVENT_PTR(rapl_pkg_unit),
EVENT_PTR(rapl_ram_unit),
EVENT_PTR(rapl_pkg_scale),
EVENT_PTR(rapl_ram_scale),
/*
* There are no default events, but we need to create
* "events" group (with empty attrs) before updating
* it with detected events.
*/
static struct attribute *attrs_empty[] = {
NULL,
};
static struct attribute_group rapl_pmu_events_group = {
.name = "events",
.attrs = NULL, /* patched at runtime */
.attrs = attrs_empty,
};
DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7");
@ -561,6 +448,79 @@ static const struct attribute_group *rapl_attr_groups[] = {
NULL,
};
static struct attribute *rapl_events_cores[] = {
EVENT_PTR(rapl_cores),
EVENT_PTR(rapl_cores_unit),
EVENT_PTR(rapl_cores_scale),
NULL,
};
static struct attribute_group rapl_events_cores_group = {
.name = "events",
.attrs = rapl_events_cores,
};
static struct attribute *rapl_events_pkg[] = {
EVENT_PTR(rapl_pkg),
EVENT_PTR(rapl_pkg_unit),
EVENT_PTR(rapl_pkg_scale),
NULL,
};
static struct attribute_group rapl_events_pkg_group = {
.name = "events",
.attrs = rapl_events_pkg,
};
static struct attribute *rapl_events_ram[] = {
EVENT_PTR(rapl_ram),
EVENT_PTR(rapl_ram_unit),
EVENT_PTR(rapl_ram_scale),
NULL,
};
static struct attribute_group rapl_events_ram_group = {
.name = "events",
.attrs = rapl_events_ram,
};
static struct attribute *rapl_events_gpu[] = {
EVENT_PTR(rapl_gpu),
EVENT_PTR(rapl_gpu_unit),
EVENT_PTR(rapl_gpu_scale),
NULL,
};
static struct attribute_group rapl_events_gpu_group = {
.name = "events",
.attrs = rapl_events_gpu,
};
static struct attribute *rapl_events_psys[] = {
EVENT_PTR(rapl_psys),
EVENT_PTR(rapl_psys_unit),
EVENT_PTR(rapl_psys_scale),
NULL,
};
static struct attribute_group rapl_events_psys_group = {
.name = "events",
.attrs = rapl_events_psys,
};
static bool test_msr(int idx, void *data)
{
return test_bit(idx, (unsigned long *) data);
}
static struct perf_msr rapl_msrs[] = {
[PERF_RAPL_PP0] = { MSR_PP0_ENERGY_STATUS, &rapl_events_cores_group, test_msr },
[PERF_RAPL_PKG] = { MSR_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr },
[PERF_RAPL_RAM] = { MSR_DRAM_ENERGY_STATUS, &rapl_events_ram_group, test_msr },
[PERF_RAPL_PP1] = { MSR_PP1_ENERGY_STATUS, &rapl_events_gpu_group, test_msr },
[PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group, test_msr },
};
static int rapl_cpu_offline(unsigned int cpu)
{
struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
@ -633,7 +593,7 @@ static int rapl_check_hw_unit(bool apply_quirk)
* of 2. Datasheet, September 2014, Reference Number: 330784-001 "
*/
if (apply_quirk)
rapl_hw_unit[RAPL_IDX_RAM_NRG_STAT] = 16;
rapl_hw_unit[PERF_RAPL_RAM] = 16;
/*
* Calculate the timer rate:
@ -674,6 +634,15 @@ static void cleanup_rapl_pmus(void)
kfree(rapl_pmus);
}
const struct attribute_group *rapl_attr_update[] = {
&rapl_events_cores_group,
&rapl_events_pkg_group,
&rapl_events_ram_group,
&rapl_events_gpu_group,
&rapl_events_gpu_group,
NULL,
};
static int __init init_rapl_pmus(void)
{
int maxdie = topology_max_packages() * topology_max_die_per_package();
@ -686,6 +655,7 @@ static int __init init_rapl_pmus(void)
rapl_pmus->maxdie = maxdie;
rapl_pmus->pmu.attr_groups = rapl_attr_groups;
rapl_pmus->pmu.attr_update = rapl_attr_update;
rapl_pmus->pmu.task_ctx_nr = perf_invalid_context;
rapl_pmus->pmu.event_init = rapl_pmu_event_init;
rapl_pmus->pmu.add = rapl_pmu_event_add;
@ -701,105 +671,96 @@ static int __init init_rapl_pmus(void)
#define X86_RAPL_MODEL_MATCH(model, init) \
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
struct intel_rapl_init_fun {
bool apply_quirk;
int cntr_mask;
struct attribute **attrs;
static struct rapl_model model_snb = {
.events = BIT(PERF_RAPL_PP0) |
BIT(PERF_RAPL_PKG) |
BIT(PERF_RAPL_PP1),
.apply_quirk = false,
};
static const struct intel_rapl_init_fun snb_rapl_init __initconst = {
.apply_quirk = false,
.cntr_mask = RAPL_IDX_CLN,
.attrs = rapl_events_cln_attr,
static struct rapl_model model_snbep = {
.events = BIT(PERF_RAPL_PP0) |
BIT(PERF_RAPL_PKG) |
BIT(PERF_RAPL_RAM),
.apply_quirk = false,
};
static const struct intel_rapl_init_fun hsx_rapl_init __initconst = {
.apply_quirk = true,
.cntr_mask = RAPL_IDX_SRV,
.attrs = rapl_events_srv_attr,
static struct rapl_model model_hsw = {
.events = BIT(PERF_RAPL_PP0) |
BIT(PERF_RAPL_PKG) |
BIT(PERF_RAPL_RAM) |
BIT(PERF_RAPL_PP1),
.apply_quirk = false,
};
static const struct intel_rapl_init_fun hsw_rapl_init __initconst = {
.apply_quirk = false,
.cntr_mask = RAPL_IDX_HSW,
.attrs = rapl_events_hsw_attr,
static struct rapl_model model_hsx = {
.events = BIT(PERF_RAPL_PP0) |
BIT(PERF_RAPL_PKG) |
BIT(PERF_RAPL_RAM),
.apply_quirk = true,
};
static const struct intel_rapl_init_fun snbep_rapl_init __initconst = {
.apply_quirk = false,
.cntr_mask = RAPL_IDX_SRV,
.attrs = rapl_events_srv_attr,
static struct rapl_model model_knl = {
.events = BIT(PERF_RAPL_PKG) |
BIT(PERF_RAPL_RAM),
.apply_quirk = true,
};
static const struct intel_rapl_init_fun knl_rapl_init __initconst = {
.apply_quirk = true,
.cntr_mask = RAPL_IDX_KNL,
.attrs = rapl_events_knl_attr,
static struct rapl_model model_skl = {
.events = BIT(PERF_RAPL_PP0) |
BIT(PERF_RAPL_PKG) |
BIT(PERF_RAPL_RAM) |
BIT(PERF_RAPL_PP1) |
BIT(PERF_RAPL_PSYS),
.apply_quirk = false,
};
static const struct intel_rapl_init_fun skl_rapl_init __initconst = {
.apply_quirk = false,
.cntr_mask = RAPL_IDX_SKL_CLN,
.attrs = rapl_events_skl_attr,
};
static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE, snb_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, snbep_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, snb_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, snbep_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hsx_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, hsx_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsx_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, hsx_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_MOBILE, skl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, skl_rapl_init),
static const struct x86_cpu_id rapl_model_match[] __initconst = {
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE, model_snb),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, model_snbep),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, model_snb),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, model_snbep),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, model_hsw),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, model_hsx),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, model_hsw),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, model_hsw),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, model_hsw),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, model_hsw),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, model_hsx),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, model_hsx),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, model_knl),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, model_knl),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, model_skl),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, model_skl),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, model_hsx),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, model_skl),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, model_skl),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_MOBILE, model_skl),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, model_hsw),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, model_hsw),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, model_hsw),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, model_skl),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_DESKTOP, model_skl),
{},
};
MODULE_DEVICE_TABLE(x86cpu, rapl_cpu_match);
MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
static int __init rapl_pmu_init(void)
{
const struct x86_cpu_id *id;
struct intel_rapl_init_fun *rapl_init;
bool apply_quirk;
struct rapl_model *rm;
int ret;
id = x86_match_cpu(rapl_cpu_match);
id = x86_match_cpu(rapl_model_match);
if (!id)
return -ENODEV;
rapl_init = (struct intel_rapl_init_fun *)id->driver_data;
apply_quirk = rapl_init->apply_quirk;
rapl_cntr_mask = rapl_init->cntr_mask;
rapl_pmu_events_group.attrs = rapl_init->attrs;
rm = (struct rapl_model *) id->driver_data;
rapl_cntr_mask = perf_msr_probe(rapl_msrs, PERF_RAPL_MAX,
false, (void *) &rm->events);
ret = rapl_check_hw_unit(apply_quirk);
ret = rapl_check_hw_unit(rm->apply_quirk);
if (ret)
return ret;

122
arch/x86/events/intel/uncore.c
View File

@ -8,6 +8,7 @@
static struct intel_uncore_type *empty_uncore[] = { NULL, };
struct intel_uncore_type **uncore_msr_uncores = empty_uncore;
struct intel_uncore_type **uncore_pci_uncores = empty_uncore;
struct intel_uncore_type **uncore_mmio_uncores = empty_uncore;
static bool pcidrv_registered;
struct pci_driver *uncore_pci_driver;
@ -28,7 +29,7 @@ struct event_constraint uncore_constraint_empty =
MODULE_LICENSE("GPL");
static int uncore_pcibus_to_physid(struct pci_bus *bus)
int uncore_pcibus_to_physid(struct pci_bus *bus)
{
struct pci2phy_map *map;
int phys_id = -1;
@ -119,6 +120,21 @@ u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *eve
return count;
}
void uncore_mmio_exit_box(struct intel_uncore_box *box)
{
if (box->io_addr)
iounmap(box->io_addr);
}
u64 uncore_mmio_read_counter(struct intel_uncore_box *box,
struct perf_event *event)
{
if (!box->io_addr)
return 0;
return readq(box->io_addr + event->hw.event_base);
}
/*
* generic get constraint function for shared match/mask registers.
*/
@ -1143,12 +1159,27 @@ static void uncore_change_context(struct intel_uncore_type **uncores,
uncore_change_type_ctx(*uncores, old_cpu, new_cpu);
}
static int uncore_event_cpu_offline(unsigned int cpu)
static void uncore_box_unref(struct intel_uncore_type **types, int id)
{
struct intel_uncore_type *type, **types = uncore_msr_uncores;
struct intel_uncore_type *type;
struct intel_uncore_pmu *pmu;
struct intel_uncore_box *box;
int i, die, target;
int i;
for (; *types; types++) {
type = *types;
pmu = type->pmus;
for (i = 0; i < type->num_boxes; i++, pmu++) {
box = pmu->boxes[id];
if (box && atomic_dec_return(&box->refcnt) == 0)
uncore_box_exit(box);
}
}
}
static int uncore_event_cpu_offline(unsigned int cpu)
{
int die, target;
/* Check if exiting cpu is used for collecting uncore events */
if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
@ -1163,20 +1194,14 @@ static int uncore_event_cpu_offline(unsigned int cpu)
target = -1;
uncore_change_context(uncore_msr_uncores, cpu, target);
uncore_change_context(uncore_mmio_uncores, cpu, target);
uncore_change_context(uncore_pci_uncores, cpu, target);
unref:
/* Clear the references */
die = topology_logical_die_id(cpu);
for (; *types; types++) {
type = *types;
pmu = type->pmus;
for (i = 0; i < type->num_boxes; i++, pmu++) {
box = pmu->boxes[die];
if (box && atomic_dec_return(&box->refcnt) == 0)
uncore_box_exit(box);
}
}
uncore_box_unref(uncore_msr_uncores, die);
uncore_box_unref(uncore_mmio_uncores, die);
return 0;
}
@ -1219,15 +1244,15 @@ cleanup:
return -ENOMEM;
}
static int uncore_event_cpu_online(unsigned int cpu)
static int uncore_box_ref(struct intel_uncore_type **types,
int id, unsigned int cpu)
{
struct intel_uncore_type *type, **types = uncore_msr_uncores;
struct intel_uncore_type *type;
struct intel_uncore_pmu *pmu;
struct intel_uncore_box *box;
int i, ret, die, target;
int i, ret;
die = topology_logical_die_id(cpu);
ret = allocate_boxes(types, die, cpu);
ret = allocate_boxes(types, id, cpu);
if (ret)
return ret;
@ -1235,11 +1260,23 @@ static int uncore_event_cpu_online(unsigned int cpu)
type = *types;
pmu = type->pmus;
for (i = 0; i < type->num_boxes; i++, pmu++) {
box = pmu->boxes[die];
box = pmu->boxes[id];
if (box && atomic_inc_return(&box->refcnt) == 1)
uncore_box_init(box);
}
}
return 0;
}
static int uncore_event_cpu_online(unsigned int cpu)
{
int die, target, msr_ret, mmio_ret;
die = topology_logical_die_id(cpu);
msr_ret = uncore_box_ref(uncore_msr_uncores, die, cpu);
mmio_ret = uncore_box_ref(uncore_mmio_uncores, die, cpu);
if (msr_ret && mmio_ret)
return -ENOMEM;
/*
* Check if there is an online cpu in the package
@ -1251,7 +1288,10 @@ static int uncore_event_cpu_online(unsigned int cpu)
cpumask_set_cpu(cpu, &uncore_cpu_mask);
uncore_change_context(uncore_msr_uncores, -1, cpu);
if (!msr_ret)
uncore_change_context(uncore_msr_uncores, -1, cpu);
if (!mmio_ret)
uncore_change_context(uncore_mmio_uncores, -1, cpu);
uncore_change_context(uncore_pci_uncores, -1, cpu);
return 0;
}
@ -1299,12 +1339,35 @@ err:
return ret;
}
static int __init uncore_mmio_init(void)
{
struct intel_uncore_type **types = uncore_mmio_uncores;
int ret;
ret = uncore_types_init(types, true);
if (ret)
goto err;
for (; *types; types++) {
ret = type_pmu_register(*types);
if (ret)
goto err;
}
return 0;
err:
uncore_types_exit(uncore_mmio_uncores);
uncore_mmio_uncores = empty_uncore;
return ret;
}
#define X86_UNCORE_MODEL_MATCH(model, init) \
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
struct intel_uncore_init_fun {
void (*cpu_init)(void);
int (*pci_init)(void);
void (*mmio_init)(void);
};
static const struct intel_uncore_init_fun nhm_uncore_init __initconst = {
@ -1375,6 +1438,12 @@ static const struct intel_uncore_init_fun icl_uncore_init __initconst = {
.pci_init = skl_uncore_pci_init,
};
static const struct intel_uncore_init_fun snr_uncore_init __initconst = {
.cpu_init = snr_uncore_cpu_init,
.pci_init = snr_uncore_pci_init,
.mmio_init = snr_uncore_mmio_init,
};
static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP, nhm_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM, nhm_uncore_init),
@ -1403,6 +1472,8 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, icl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_NNPI, icl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_DESKTOP, icl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ATOM_TREMONT_X, snr_uncore_init),
{},
};
@ -1412,7 +1483,7 @@ static int __init intel_uncore_init(void)
{
const struct x86_cpu_id *id;
struct intel_uncore_init_fun *uncore_init;
int pret = 0, cret = 0, ret;
int pret = 0, cret = 0, mret = 0, ret;
id = x86_match_cpu(intel_uncore_match);
if (!id)
@ -1435,7 +1506,12 @@ static int __init intel_uncore_init(void)
cret = uncore_cpu_init();
}
if (cret && pret)
if (uncore_init->mmio_init) {
uncore_init->mmio_init();
mret = uncore_mmio_init();
}
if (cret && pret && mret)
return -ENODEV;
/* Install hotplug callbacks to setup the targets for each package */
@ -1449,6 +1525,7 @@ static int __init intel_uncore_init(void)
err:
uncore_types_exit(uncore_msr_uncores);
uncore_types_exit(uncore_mmio_uncores);
uncore_pci_exit();
return ret;
}
@ -1458,6 +1535,7 @@ static void __exit intel_uncore_exit(void)
{
cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
uncore_types_exit(uncore_msr_uncores);
uncore_types_exit(uncore_mmio_uncores);
uncore_pci_exit();
}
module_exit(intel_uncore_exit);

41
arch/x86/events/intel/uncore.h
View File

@ -2,6 +2,7 @@
#include <linux/slab.h>
#include <linux/pci.h>
#include <asm/apicdef.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/perf_event.h>
#include "../perf_event.h"
@ -56,7 +57,10 @@ struct intel_uncore_type {
unsigned fixed_ctr;
unsigned fixed_ctl;
unsigned box_ctl;
unsigned msr_offset;
union {
unsigned msr_offset;
unsigned mmio_offset;
};
unsigned num_shared_regs:8;
unsigned single_fixed:1;
unsigned pair_ctr_ctl:1;
@ -125,7 +129,7 @@ struct intel_uncore_box {
struct hrtimer hrtimer;
struct list_head list;
struct list_head active_list;
void *io_addr;
void __iomem *io_addr;
struct intel_uncore_extra_reg shared_regs[0];
};
@ -159,6 +163,7 @@ struct pci2phy_map {
};
struct pci2phy_map *__find_pci2phy_map(int segment);
int uncore_pcibus_to_physid(struct pci_bus *bus);
ssize_t uncore_event_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf);
@ -190,6 +195,13 @@ static inline bool uncore_pmc_freerunning(int idx)
return idx == UNCORE_PMC_IDX_FREERUNNING;
}
static inline
unsigned int uncore_mmio_box_ctl(struct intel_uncore_box *box)
{
return box->pmu->type->box_ctl +
box->pmu->type->mmio_offset * box->pmu->pmu_idx;
}
static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box)
{
return box->pmu->type->box_ctl;
@ -330,7 +342,7 @@ unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx)
static inline
unsigned uncore_fixed_ctl(struct intel_uncore_box *box)
{
if (box->pci_dev)
if (box->pci_dev || box->io_addr)
return uncore_pci_fixed_ctl(box);
else
return uncore_msr_fixed_ctl(box);
@ -339,7 +351,7 @@ unsigned uncore_fixed_ctl(struct intel_uncore_box *box)
static inline
unsigned uncore_fixed_ctr(struct intel_uncore_box *box)
{
if (box->pci_dev)
if (box->pci_dev || box->io_addr)
return uncore_pci_fixed_ctr(box);
else
return uncore_msr_fixed_ctr(box);
@ -348,7 +360,7 @@ unsigned uncore_fixed_ctr(struct intel_uncore_box *box)
static inline
unsigned uncore_event_ctl(struct intel_uncore_box *box, int idx)
{
if (box->pci_dev)
if (box->pci_dev || box->io_addr)
return uncore_pci_event_ctl(box, idx);
else
return uncore_msr_event_ctl(box, idx);
@ -357,7 +369,7 @@ unsigned uncore_event_ctl(struct intel_uncore_box *box, int idx)
static inline
unsigned uncore_perf_ctr(struct intel_uncore_box *box, int idx)
{
if (box->pci_dev)
if (box->pci_dev || box->io_addr)
return uncore_pci_perf_ctr(box, idx);
else
return uncore_msr_perf_ctr(box, idx);
@ -419,6 +431,16 @@ static inline bool is_freerunning_event(struct perf_event *event)
(((cfg >> 8) & 0xff) >= UNCORE_FREERUNNING_UMASK_START);
}
/* Check and reject invalid config */
static inline int uncore_freerunning_hw_config(struct intel_uncore_box *box,
struct perf_event *event)
{
if (is_freerunning_event(event))
return 0;
return -EINVAL;
}
static inline void uncore_disable_box(struct intel_uncore_box *box)
{
if (box->pmu->type->ops->disable_box)
@ -482,6 +504,9 @@ static inline struct intel_uncore_box *uncore_event_to_box(struct perf_event *ev
struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu);
u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event);
void uncore_mmio_exit_box(struct intel_uncore_box *box);
u64 uncore_mmio_read_counter(struct intel_uncore_box *box,
struct perf_event *event);
void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
void uncore_pmu_event_start(struct perf_event *event, int flags);
@ -497,6 +522,7 @@ u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx);
extern struct intel_uncore_type **uncore_msr_uncores;
extern struct intel_uncore_type **uncore_pci_uncores;
extern struct intel_uncore_type **uncore_mmio_uncores;
extern struct pci_driver *uncore_pci_driver;
extern raw_spinlock_t pci2phy_map_lock;
extern struct list_head pci2phy_map_head;
@ -528,6 +554,9 @@ int knl_uncore_pci_init(void);
void knl_uncore_cpu_init(void);
int skx_uncore_pci_init(void);
void skx_uncore_cpu_init(void);
int snr_uncore_pci_init(void);
void snr_uncore_cpu_init(void);
void snr_uncore_mmio_init(void);
/* uncore_nhmex.c */
void nhmex_uncore_cpu_init(void);

101
arch/x86/events/intel/uncore_snb.c
View File

@ -3,27 +3,29 @@
#include "uncore.h"
/* Uncore IMC PCI IDs */
#define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100
#define PCI_DEVICE_ID_INTEL_IVB_IMC 0x0154
#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150
#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00
#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04
#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604
#define PCI_DEVICE_ID_INTEL_SKL_U_IMC 0x1904
#define PCI_DEVICE_ID_INTEL_SKL_Y_IMC 0x190c
#define PCI_DEVICE_ID_INTEL_SKL_HD_IMC 0x1900
#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910
#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f
#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f
#define PCI_DEVICE_ID_INTEL_KBL_Y_IMC 0x590c
#define PCI_DEVICE_ID_INTEL_KBL_U_IMC 0x5904
#define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC 0x5914
#define PCI_DEVICE_ID_INTEL_KBL_SD_IMC 0x590f
#define PCI_DEVICE_ID_INTEL_KBL_SQ_IMC 0x591f
#define PCI_DEVICE_ID_INTEL_CFL_2U_IMC 0x3ecc
#define PCI_DEVICE_ID_INTEL_CFL_4U_IMC 0x3ed0
#define PCI_DEVICE_ID_INTEL_CFL_4H_IMC 0x3e10
#define PCI_DEVICE_ID_INTEL_CFL_6H_IMC 0x3ec4
#define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100
#define PCI_DEVICE_ID_INTEL_IVB_IMC 0x0154
#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150
#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00
#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04
#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604
#define PCI_DEVICE_ID_INTEL_SKL_U_IMC 0x1904
#define PCI_DEVICE_ID_INTEL_SKL_Y_IMC 0x190c
#define PCI_DEVICE_ID_INTEL_SKL_HD_IMC 0x1900
#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910
#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f
#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f
#define PCI_DEVICE_ID_INTEL_KBL_Y_IMC 0x590c
#define PCI_DEVICE_ID_INTEL_KBL_U_IMC 0x5904
#define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC 0x5914
#define PCI_DEVICE_ID_INTEL_KBL_SD_IMC 0x590f
#define PCI_DEVICE_ID_INTEL_KBL_SQ_IMC 0x591f
#define PCI_DEVICE_ID_INTEL_KBL_HQ_IMC 0x5910
#define PCI_DEVICE_ID_INTEL_KBL_WQ_IMC 0x5918
#define PCI_DEVICE_ID_INTEL_CFL_2U_IMC 0x3ecc
#define PCI_DEVICE_ID_INTEL_CFL_4U_IMC 0x3ed0
#define PCI_DEVICE_ID_INTEL_CFL_4H_IMC 0x3e10
#define PCI_DEVICE_ID_INTEL_CFL_6H_IMC 0x3ec4
#define PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC 0x3e0f
#define PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC 0x3e1f
#define PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC 0x3ec2
@ -34,9 +36,15 @@
#define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC 0x3e33
#define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC 0x3eca
#define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC 0x3e32
#define PCI_DEVICE_ID_INTEL_AML_YD_IMC 0x590c
#define PCI_DEVICE_ID_INTEL_AML_YQ_IMC 0x590d
#define PCI_DEVICE_ID_INTEL_WHL_UQ_IMC 0x3ed0
#define PCI_DEVICE_ID_INTEL_WHL_4_UQ_IMC 0x3e34
#define PCI_DEVICE_ID_INTEL_WHL_UD_IMC 0x3e35
#define PCI_DEVICE_ID_INTEL_ICL_U_IMC 0x8a02
#define PCI_DEVICE_ID_INTEL_ICL_U2_IMC 0x8a12
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
#define SNB_UNC_CTL_UMASK_MASK 0x0000ff00
@ -420,11 +428,6 @@ static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
}
static void snb_uncore_imc_exit_box(struct intel_uncore_box *box)
{
iounmap(box->io_addr);
}
static void snb_uncore_imc_enable_box(struct intel_uncore_box *box)
{}
@ -437,13 +440,6 @@ static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct per
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);
}
/*
* Keep the custom event_init() function compatible with old event
* encoding for free running counters.
@ -570,13 +566,13 @@ static struct pmu snb_uncore_imc_pmu = {
static struct intel_uncore_ops snb_uncore_imc_ops = {
.init_box = snb_uncore_imc_init_box,
.exit_box = snb_uncore_imc_exit_box,
.exit_box = uncore_mmio_exit_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,
.read_counter = uncore_mmio_read_counter,
};
static struct intel_uncore_type snb_uncore_imc = {
@ -681,6 +677,14 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SQ_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
{ /* IMC */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_HQ_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
{ /* IMC */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_WQ_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
{ /* IMC */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2U_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
@ -737,6 +741,26 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
{ /* IMC */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_AML_YD_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
{ /* IMC */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_AML_YQ_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
{ /* IMC */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_UQ_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
{ /* IMC */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_4_UQ_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
{ /* IMC */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_UD_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
{ /* end: all zeroes */ },
};
@ -807,6 +831,8 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U Quad Core */
IMC_DEV(KBL_SD_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S Dual Core */
IMC_DEV(KBL_SQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S Quad Core */
IMC_DEV(KBL_HQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core H Quad Core */
IMC_DEV(KBL_WQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S 4 cores Work Station */
IMC_DEV(CFL_2U_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U 2 Cores */
IMC_DEV(CFL_4U_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U 4 Cores */
IMC_DEV(CFL_4H_IMC, &skl_uncore_pci_driver), /* 8th Gen Core H 4 Cores */
@ -821,6 +847,11 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Server */
IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Server */
IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Server */
IMC_DEV(AML_YD_IMC, &skl_uncore_pci_driver), /* 8th Gen Core Y Mobile Dual Core */
IMC_DEV(AML_YQ_IMC, &skl_uncore_pci_driver), /* 8th Gen Core Y Mobile Quad Core */
IMC_DEV(WHL_UQ_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U Mobile Quad Core */
IMC_DEV(WHL_4_UQ_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U Mobile Quad Core */
IMC_DEV(WHL_UD_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U Mobile Dual Core */
IMC_DEV(ICL_U_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
IMC_DEV(ICL_U2_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
{ /* end marker */ }

601
arch/x86/events/intel/uncore_snbep.c
View File

@ -324,12 +324,77 @@
#define SKX_M2M_PCI_PMON_CTR0 0x200
#define SKX_M2M_PCI_PMON_BOX_CTL 0x258
/* SNR Ubox */
#define SNR_U_MSR_PMON_CTR0 0x1f98
#define SNR_U_MSR_PMON_CTL0 0x1f91
#define SNR_U_MSR_PMON_UCLK_FIXED_CTL 0x1f93
#define SNR_U_MSR_PMON_UCLK_FIXED_CTR 0x1f94
/* SNR CHA */
#define SNR_CHA_RAW_EVENT_MASK_EXT 0x3ffffff
#define SNR_CHA_MSR_PMON_CTL0 0x1c01
#define SNR_CHA_MSR_PMON_CTR0 0x1c08
#define SNR_CHA_MSR_PMON_BOX_CTL 0x1c00
#define SNR_C0_MSR_PMON_BOX_FILTER0 0x1c05
/* SNR IIO */
#define SNR_IIO_MSR_PMON_CTL0 0x1e08
#define SNR_IIO_MSR_PMON_CTR0 0x1e01
#define SNR_IIO_MSR_PMON_BOX_CTL 0x1e00
#define SNR_IIO_MSR_OFFSET 0x10
#define SNR_IIO_PMON_RAW_EVENT_MASK_EXT 0x7ffff
/* SNR IRP */
#define SNR_IRP0_MSR_PMON_CTL0 0x1ea8
#define SNR_IRP0_MSR_PMON_CTR0 0x1ea1
#define SNR_IRP0_MSR_PMON_BOX_CTL 0x1ea0
#define SNR_IRP_MSR_OFFSET 0x10
/* SNR M2PCIE */
#define SNR_M2PCIE_MSR_PMON_CTL0 0x1e58
#define SNR_M2PCIE_MSR_PMON_CTR0 0x1e51
#define SNR_M2PCIE_MSR_PMON_BOX_CTL 0x1e50
#define SNR_M2PCIE_MSR_OFFSET 0x10
/* SNR PCU */
#define SNR_PCU_MSR_PMON_CTL0 0x1ef1
#define SNR_PCU_MSR_PMON_CTR0 0x1ef8
#define SNR_PCU_MSR_PMON_BOX_CTL 0x1ef0
#define SNR_PCU_MSR_PMON_BOX_FILTER 0x1efc
/* SNR M2M */
#define SNR_M2M_PCI_PMON_CTL0 0x468
#define SNR_M2M_PCI_PMON_CTR0 0x440
#define SNR_M2M_PCI_PMON_BOX_CTL 0x438
#define SNR_M2M_PCI_PMON_UMASK_EXT 0xff
/* SNR PCIE3 */
#define SNR_PCIE3_PCI_PMON_CTL0 0x508
#define SNR_PCIE3_PCI_PMON_CTR0 0x4e8
#define SNR_PCIE3_PCI_PMON_BOX_CTL 0x4e4
/* SNR IMC */
#define SNR_IMC_MMIO_PMON_FIXED_CTL 0x54
#define SNR_IMC_MMIO_PMON_FIXED_CTR 0x38
#define SNR_IMC_MMIO_PMON_CTL0 0x40
#define SNR_IMC_MMIO_PMON_CTR0 0x8
#define SNR_IMC_MMIO_PMON_BOX_CTL 0x22800
#define SNR_IMC_MMIO_OFFSET 0x4000
#define SNR_IMC_MMIO_SIZE 0x4000
#define SNR_IMC_MMIO_BASE_OFFSET 0xd0
#define SNR_IMC_MMIO_BASE_MASK 0x1FFFFFFF
#define SNR_IMC_MMIO_MEM0_OFFSET 0xd8
#define SNR_IMC_MMIO_MEM0_MASK 0x7FF
DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6");
DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7");
DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55");
DEFINE_UNCORE_FORMAT_ATTR(umask_ext2, umask, "config:8-15,32-57");
DEFINE_UNCORE_FORMAT_ATTR(umask_ext3, umask, "config:8-15,32-39");
DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16");
DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
@ -343,11 +408,14 @@ DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30");
DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
DEFINE_UNCORE_FORMAT_ATTR(occ_edge_det, occ_edge_det, "config:31");
DEFINE_UNCORE_FORMAT_ATTR(ch_mask, ch_mask, "config:36-43");
DEFINE_UNCORE_FORMAT_ATTR(ch_mask2, ch_mask, "config:36-47");
DEFINE_UNCORE_FORMAT_ATTR(fc_mask, fc_mask, "config:44-46");
DEFINE_UNCORE_FORMAT_ATTR(fc_mask2, fc_mask, "config:48-50");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid4, filter_tid, "config1:0-8");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid5, filter_tid, "config1:0-9");
DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5");
DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8");
@ -3585,6 +3653,7 @@ static struct uncore_event_desc skx_uncore_iio_freerunning_events[] = {
static struct intel_uncore_ops skx_uncore_iio_freerunning_ops = {
.read_counter = uncore_msr_read_counter,
.hw_config = uncore_freerunning_hw_config,
};
static struct attribute *skx_uncore_iio_freerunning_formats_attr[] = {
@ -3967,3 +4036,535 @@ int skx_uncore_pci_init(void)
}
/* end of SKX uncore support */
/* SNR uncore support */
static struct intel_uncore_type snr_uncore_ubox = {
.name = "ubox",
.num_counters = 2,
.num_boxes = 1,
.perf_ctr_bits = 48,
.fixed_ctr_bits = 48,
.perf_ctr = SNR_U_MSR_PMON_CTR0,
.event_ctl = SNR_U_MSR_PMON_CTL0,
.event_mask = SNBEP_PMON_RAW_EVENT_MASK,
.fixed_ctr = SNR_U_MSR_PMON_UCLK_FIXED_CTR,
.fixed_ctl = SNR_U_MSR_PMON_UCLK_FIXED_CTL,
.ops = &ivbep_uncore_msr_ops,
.format_group = &ivbep_uncore_format_group,
};
static struct attribute *snr_uncore_cha_formats_attr[] = {
&format_attr_event.attr,
&format_attr_umask_ext2.attr,
&format_attr_edge.attr,
&format_attr_tid_en.attr,
&format_attr_inv.attr,
&format_attr_thresh8.attr,
&format_attr_filter_tid5.attr,
NULL,
};
static const struct attribute_group snr_uncore_chabox_format_group = {
.name = "format",
.attrs = snr_uncore_cha_formats_attr,
};
static int snr_cha_hw_config(struct intel_uncore_box *box, struct perf_event *event)
{
struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
reg1->reg = SNR_C0_MSR_PMON_BOX_FILTER0 +
box->pmu->type->msr_offset * box->pmu->pmu_idx;
reg1->config = event->attr.config1 & SKX_CHA_MSR_PMON_BOX_FILTER_TID;
reg1->idx = 0;
return 0;
}
static void snr_cha_enable_event(struct intel_uncore_box *box,
struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
if (reg1->idx != EXTRA_REG_NONE)
wrmsrl(reg1->reg, reg1->config);
wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
}
static struct intel_uncore_ops snr_uncore_chabox_ops = {
.init_box = ivbep_uncore_msr_init_box,
.disable_box = snbep_uncore_msr_disable_box,
.enable_box = snbep_uncore_msr_enable_box,
.disable_event = snbep_uncore_msr_disable_event,
.enable_event = snr_cha_enable_event,
.read_counter = uncore_msr_read_counter,
.hw_config = snr_cha_hw_config,
};
static struct intel_uncore_type snr_uncore_chabox = {
.name = "cha",
.num_counters = 4,
.num_boxes = 6,
.perf_ctr_bits = 48,
.event_ctl = SNR_CHA_MSR_PMON_CTL0,
.perf_ctr = SNR_CHA_MSR_PMON_CTR0,
.box_ctl = SNR_CHA_MSR_PMON_BOX_CTL,
.msr_offset = HSWEP_CBO_MSR_OFFSET,
.event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
.event_mask_ext = SNR_CHA_RAW_EVENT_MASK_EXT,
.ops = &snr_uncore_chabox_ops,
.format_group = &snr_uncore_chabox_format_group,
};
static struct attribute *snr_uncore_iio_formats_attr[] = {
&format_attr_event.attr,
&format_attr_umask.attr,
&format_attr_edge.attr,
&format_attr_inv.attr,
&format_attr_thresh9.attr,
&format_attr_ch_mask2.attr,
&format_attr_fc_mask2.attr,
NULL,
};
static const struct attribute_group snr_uncore_iio_format_group = {
.name = "format",
.attrs = snr_uncore_iio_formats_attr,
};
static struct intel_uncore_type snr_uncore_iio = {
.name = "iio",
.num_counters = 4,
.num_boxes = 5,
.perf_ctr_bits = 48,
.event_ctl = SNR_IIO_MSR_PMON_CTL0,
.perf_ctr = SNR_IIO_MSR_PMON_CTR0,
.event_mask = SNBEP_PMON_RAW_EVENT_MASK,
.event_mask_ext = SNR_IIO_PMON_RAW_EVENT_MASK_EXT,
.box_ctl = SNR_IIO_MSR_PMON_BOX_CTL,
.msr_offset = SNR_IIO_MSR_OFFSET,
.ops = &ivbep_uncore_msr_ops,
.format_group = &snr_uncore_iio_format_group,
};
static struct intel_uncore_type snr_uncore_irp = {
.name = "irp",
.num_counters = 2,
.num_boxes = 5,
.perf_ctr_bits = 48,
.event_ctl = SNR_IRP0_MSR_PMON_CTL0,
.perf_ctr = SNR_IRP0_MSR_PMON_CTR0,
.event_mask = SNBEP_PMON_RAW_EVENT_MASK,
.box_ctl = SNR_IRP0_MSR_PMON_BOX_CTL,
.msr_offset = SNR_IRP_MSR_OFFSET,
.ops = &ivbep_uncore_msr_ops,
.format_group = &ivbep_uncore_format_group,
};
static struct intel_uncore_type snr_uncore_m2pcie = {
.name = "m2pcie",
.num_counters = 4,
.num_boxes = 5,
.perf_ctr_bits = 48,
.event_ctl = SNR_M2PCIE_MSR_PMON_CTL0,
.perf_ctr = SNR_M2PCIE_MSR_PMON_CTR0,
.box_ctl = SNR_M2PCIE_MSR_PMON_BOX_CTL,
.msr_offset = SNR_M2PCIE_MSR_OFFSET,
.event_mask = SNBEP_PMON_RAW_EVENT_MASK,
.ops = &ivbep_uncore_msr_ops,
.format_group = &ivbep_uncore_format_group,
};
static int snr_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK;
if (ev_sel >= 0xb && ev_sel <= 0xe) {
reg1->reg = SNR_PCU_MSR_PMON_BOX_FILTER;
reg1->idx = ev_sel - 0xb;
reg1->config = event->attr.config1 & (0xff << reg1->idx);
}
return 0;
}
static struct intel_uncore_ops snr_uncore_pcu_ops = {
IVBEP_UNCORE_MSR_OPS_COMMON_INIT(),
.hw_config = snr_pcu_hw_config,
.get_constraint = snbep_pcu_get_constraint,
.put_constraint = snbep_pcu_put_constraint,
};
static struct intel_uncore_type snr_uncore_pcu = {
.name = "pcu",
.num_counters = 4,
.num_boxes = 1,
.perf_ctr_bits = 48,
.perf_ctr = SNR_PCU_MSR_PMON_CTR0,
.event_ctl = SNR_PCU_MSR_PMON_CTL0,
.event_mask = SNBEP_PMON_RAW_EVENT_MASK,
.box_ctl = SNR_PCU_MSR_PMON_BOX_CTL,
.num_shared_regs = 1,
.ops = &snr_uncore_pcu_ops,
.format_group = &skx_uncore_pcu_format_group,
};
enum perf_uncore_snr_iio_freerunning_type_id {
SNR_IIO_MSR_IOCLK,
SNR_IIO_MSR_BW_IN,
SNR_IIO_FREERUNNING_TYPE_MAX,
};
static struct freerunning_counters snr_iio_freerunning[] = {
[SNR_IIO_MSR_IOCLK] = { 0x1eac, 0x1, 0x10, 1, 48 },
[SNR_IIO_MSR_BW_IN] = { 0x1f00, 0x1, 0x10, 8, 48 },
};
static struct uncore_event_desc snr_uncore_iio_freerunning_events[] = {
/* Free-Running IIO CLOCKS Counter */
INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"),
/* Free-Running IIO BANDWIDTH IN Counters */
INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"),
INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"),
INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"),
INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"),
INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"),
INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"),
INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"),
INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"),
INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"),
INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"),
INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"),
INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"),
INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"),
INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"),
INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"),
INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"),
INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"),
{ /* end: all zeroes */ },
};
static struct intel_uncore_type snr_uncore_iio_free_running = {
.name = "iio_free_running",
.num_counters = 9,
.num_boxes = 5,
.num_freerunning_types = SNR_IIO_FREERUNNING_TYPE_MAX,
.freerunning = snr_iio_freerunning,
.ops = &skx_uncore_iio_freerunning_ops,
.event_descs = snr_uncore_iio_freerunning_events,
.format_group = &skx_uncore_iio_freerunning_format_group,
};
static struct intel_uncore_type *snr_msr_uncores[] = {
&snr_uncore_ubox,
&snr_uncore_chabox,
&snr_uncore_iio,
&snr_uncore_irp,
&snr_uncore_m2pcie,
&snr_uncore_pcu,
&snr_uncore_iio_free_running,
NULL,
};
void snr_uncore_cpu_init(void)
{
uncore_msr_uncores = snr_msr_uncores;
}
static void snr_m2m_uncore_pci_init_box(struct intel_uncore_box *box)
{
struct pci_dev *pdev = box->pci_dev;
int box_ctl = uncore_pci_box_ctl(box);
__set_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags);
pci_write_config_dword(pdev, box_ctl, IVBEP_PMON_BOX_CTL_INT);
}
static struct intel_uncore_ops snr_m2m_uncore_pci_ops = {
.init_box = snr_m2m_uncore_pci_init_box,
.disable_box = snbep_uncore_pci_disable_box,
.enable_box = snbep_uncore_pci_enable_box,
.disable_event = snbep_uncore_pci_disable_event,
.enable_event = snbep_uncore_pci_enable_event,
.read_counter = snbep_uncore_pci_read_counter,
};
static struct attribute *snr_m2m_uncore_formats_attr[] = {
&format_attr_event.attr,
&format_attr_umask_ext3.attr,
&format_attr_edge.attr,
&format_attr_inv.attr,
&format_attr_thresh8.attr,
NULL,
};
static const struct attribute_group snr_m2m_uncore_format_group = {
.name = "format",
.attrs = snr_m2m_uncore_formats_attr,
};
static struct intel_uncore_type snr_uncore_m2m = {
.name = "m2m",
.num_counters = 4,
.num_boxes = 1,
.perf_ctr_bits = 48,
.perf_ctr = SNR_M2M_PCI_PMON_CTR0,
.event_ctl = SNR_M2M_PCI_PMON_CTL0,
.event_mask = SNBEP_PMON_RAW_EVENT_MASK,
.event_mask_ext = SNR_M2M_PCI_PMON_UMASK_EXT,
.box_ctl = SNR_M2M_PCI_PMON_BOX_CTL,
.ops = &snr_m2m_uncore_pci_ops,
.format_group = &snr_m2m_uncore_format_group,
};
static struct intel_uncore_type snr_uncore_pcie3 = {
.name = "pcie3",
.num_counters = 4,
.num_boxes = 1,
.perf_ctr_bits = 48,
.perf_ctr = SNR_PCIE3_PCI_PMON_CTR0,
.event_ctl = SNR_PCIE3_PCI_PMON_CTL0,
.event_mask = SNBEP_PMON_RAW_EVENT_MASK,
.box_ctl = SNR_PCIE3_PCI_PMON_BOX_CTL,
.ops = &ivbep_uncore_pci_ops,
.format_group = &ivbep_uncore_format_group,
};
enum {
SNR_PCI_UNCORE_M2M,
SNR_PCI_UNCORE_PCIE3,
};
static struct intel_uncore_type *snr_pci_uncores[] = {
[SNR_PCI_UNCORE_M2M] = &snr_uncore_m2m,
[SNR_PCI_UNCORE_PCIE3] = &snr_uncore_pcie3,
NULL,
};
static const struct pci_device_id snr_uncore_pci_ids[] = {
{ /* M2M */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a),
.driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 0, SNR_PCI_UNCORE_M2M, 0),
},
{ /* PCIe3 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x334a),
.driver_data = UNCORE_PCI_DEV_FULL_DATA(4, 0, SNR_PCI_UNCORE_PCIE3, 0),
},
{ /* end: all zeroes */ }
};
static struct pci_driver snr_uncore_pci_driver = {
.name = "snr_uncore",
.id_table = snr_uncore_pci_ids,
};
int snr_uncore_pci_init(void)
{
/* SNR UBOX DID */
int ret = snbep_pci2phy_map_init(0x3460, SKX_CPUNODEID,
SKX_GIDNIDMAP, true);
if (ret)
return ret;
uncore_pci_uncores = snr_pci_uncores;
uncore_pci_driver = &snr_uncore_pci_driver;
return 0;
}
static struct pci_dev *snr_uncore_get_mc_dev(int id)
{
struct pci_dev *mc_dev = NULL;
int phys_id, pkg;
while (1) {
mc_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x3451, mc_dev);
if (!mc_dev)
break;
phys_id = uncore_pcibus_to_physid(mc_dev->bus);
if (phys_id < 0)
continue;
pkg = topology_phys_to_logical_pkg(phys_id);
if (pkg < 0)
continue;
else if (pkg == id)
break;
}
return mc_dev;
}
static void snr_uncore_mmio_init_box(struct intel_uncore_box *box)
{
struct pci_dev *pdev = snr_uncore_get_mc_dev(box->dieid);
unsigned int box_ctl = uncore_mmio_box_ctl(box);
resource_size_t addr;
u32 pci_dword;
if (!pdev)
return;
pci_read_config_dword(pdev, SNR_IMC_MMIO_BASE_OFFSET, &pci_dword);
addr = (pci_dword & SNR_IMC_MMIO_BASE_MASK) << 23;
pci_read_config_dword(pdev, SNR_IMC_MMIO_MEM0_OFFSET, &pci_dword);
addr |= (pci_dword & SNR_IMC_MMIO_MEM0_MASK) << 12;
addr += box_ctl;
box->io_addr = ioremap(addr, SNR_IMC_MMIO_SIZE);
if (!box->io_addr)
return;
writel(IVBEP_PMON_BOX_CTL_INT, box->io_addr);
}
static void snr_uncore_mmio_disable_box(struct intel_uncore_box *box)
{
u32 config;
if (!box->io_addr)
return;
config = readl(box->io_addr);
config |= SNBEP_PMON_BOX_CTL_FRZ;
writel(config, box->io_addr);
}
static void snr_uncore_mmio_enable_box(struct intel_uncore_box *box)
{
u32 config;
if (!box->io_addr)
return;
config = readl(box->io_addr);
config &= ~SNBEP_PMON_BOX_CTL_FRZ;
writel(config, box->io_addr);
}
static void snr_uncore_mmio_enable_event(struct intel_uncore_box *box,
struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
if (!box->io_addr)
return;
writel(hwc->config | SNBEP_PMON_CTL_EN,
box->io_addr + hwc->config_base);
}
static void snr_uncore_mmio_disable_event(struct intel_uncore_box *box,
struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
if (!box->io_addr)
return;
writel(hwc->config, box->io_addr + hwc->config_base);
}
static struct intel_uncore_ops snr_uncore_mmio_ops = {
.init_box = snr_uncore_mmio_init_box,
.exit_box = uncore_mmio_exit_box,
.disable_box = snr_uncore_mmio_disable_box,
.enable_box = snr_uncore_mmio_enable_box,
.disable_event = snr_uncore_mmio_disable_event,
.enable_event = snr_uncore_mmio_enable_event,
.read_counter = uncore_mmio_read_counter,
};
static struct uncore_event_desc snr_uncore_imc_events[] = {
INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x00,umask=0x00"),
INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x0f"),
INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"),
INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x30"),
INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"),
INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"),
{ /* end: all zeroes */ },
};
static struct intel_uncore_type snr_uncore_imc = {
.name = "imc",
.num_counters = 4,
.num_boxes = 2,
.perf_ctr_bits = 48,
.fixed_ctr_bits = 48,
.fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR,
.fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL,
.event_descs = snr_uncore_imc_events,
.perf_ctr = SNR_IMC_MMIO_PMON_CTR0,
.event_ctl = SNR_IMC_MMIO_PMON_CTL0,
.event_mask = SNBEP_PMON_RAW_EVENT_MASK,
.box_ctl = SNR_IMC_MMIO_PMON_BOX_CTL,
.mmio_offset = SNR_IMC_MMIO_OFFSET,
.ops = &snr_uncore_mmio_ops,
.format_group = &skx_uncore_format_group,
};
enum perf_uncore_snr_imc_freerunning_type_id {
SNR_IMC_DCLK,
SNR_IMC_DDR,
SNR_IMC_FREERUNNING_TYPE_MAX,
};
static struct freerunning_counters snr_imc_freerunning[] = {
[SNR_IMC_DCLK] = { 0x22b0, 0x0, 0, 1, 48 },
[SNR_IMC_DDR] = { 0x2290, 0x8, 0, 2, 48 },
};
static struct uncore_event_desc snr_uncore_imc_freerunning_events[] = {
INTEL_UNCORE_EVENT_DESC(dclk, "event=0xff,umask=0x10"),
INTEL_UNCORE_EVENT_DESC(read, "event=0xff,umask=0x20"),
INTEL_UNCORE_EVENT_DESC(read.scale, "3.814697266e-6"),
INTEL_UNCORE_EVENT_DESC(read.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(write, "event=0xff,umask=0x21"),
INTEL_UNCORE_EVENT_DESC(write.scale, "3.814697266e-6"),
INTEL_UNCORE_EVENT_DESC(write.unit, "MiB"),
};
static struct intel_uncore_ops snr_uncore_imc_freerunning_ops = {
.init_box = snr_uncore_mmio_init_box,
.exit_box = uncore_mmio_exit_box,
.read_counter = uncore_mmio_read_counter,
.hw_config = uncore_freerunning_hw_config,
};
static struct intel_uncore_type snr_uncore_imc_free_running = {
.name = "imc_free_running",
.num_counters = 3,
.num_boxes = 1,
.num_freerunning_types = SNR_IMC_FREERUNNING_TYPE_MAX,
.freerunning = snr_imc_freerunning,
.ops = &snr_uncore_imc_freerunning_ops,
.event_descs = snr_uncore_imc_freerunning_events,
.format_group = &skx_uncore_iio_freerunning_format_group,
};
static struct intel_uncore_type *snr_mmio_uncores[] = {
&snr_uncore_imc,
&snr_uncore_imc_free_running,
NULL,
};
void snr_uncore_mmio_init(void)
{
uncore_mmio_uncores = snr_mmio_uncores;
}
/* end of SNR uncore support */

110
arch/x86/events/msr.c
View File

@ -1,7 +1,9 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/perf_event.h>
#include <linux/sysfs.h>
#include <linux/nospec.h>
#include <asm/intel-family.h>
#include "probe.h"
enum perf_msr_id {
PERF_MSR_TSC = 0,
@ -12,32 +14,30 @@ enum perf_msr_id {
PERF_MSR_PTSC = 5,
PERF_MSR_IRPERF = 6,
PERF_MSR_THERM = 7,
PERF_MSR_THERM_SNAP = 8,
PERF_MSR_THERM_UNIT = 9,
PERF_MSR_EVENT_MAX,
};
static bool test_aperfmperf(int idx)
static bool test_aperfmperf(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_APERFMPERF);
}
static bool test_ptsc(int idx)
static bool test_ptsc(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_PTSC);
}
static bool test_irperf(int idx)
static bool test_irperf(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_IRPERF);
}
static bool test_therm_status(int idx)
static bool test_therm_status(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_DTHERM);
}
static bool test_intel(int idx)
static bool test_intel(int idx, void *data)
{
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
boot_cpu_data.x86 != 6)
@ -98,37 +98,51 @@ static bool test_intel(int idx)
return false;
}
struct perf_msr {
u64 msr;
struct perf_pmu_events_attr *attr;
bool (*test)(int idx);
PMU_EVENT_ATTR_STRING(tsc, attr_tsc, "event=0x00" );
PMU_EVENT_ATTR_STRING(aperf, attr_aperf, "event=0x01" );
PMU_EVENT_ATTR_STRING(mperf, attr_mperf, "event=0x02" );
PMU_EVENT_ATTR_STRING(pperf, attr_pperf, "event=0x03" );
PMU_EVENT_ATTR_STRING(smi, attr_smi, "event=0x04" );
PMU_EVENT_ATTR_STRING(ptsc, attr_ptsc, "event=0x05" );
PMU_EVENT_ATTR_STRING(irperf, attr_irperf, "event=0x06" );
PMU_EVENT_ATTR_STRING(cpu_thermal_margin, attr_therm, "event=0x07" );
PMU_EVENT_ATTR_STRING(cpu_thermal_margin.snapshot, attr_therm_snap, "1" );
PMU_EVENT_ATTR_STRING(cpu_thermal_margin.unit, attr_therm_unit, "C" );
static unsigned long msr_mask;
PMU_EVENT_GROUP(events, aperf);
PMU_EVENT_GROUP(events, mperf);
PMU_EVENT_GROUP(events, pperf);
PMU_EVENT_GROUP(events, smi);
PMU_EVENT_GROUP(events, ptsc);
PMU_EVENT_GROUP(events, irperf);
static struct attribute *attrs_therm[] = {
&attr_therm.attr.attr,
&attr_therm_snap.attr.attr,
&attr_therm_unit.attr.attr,
NULL,
};
PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00" );
PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01" );
PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02" );
PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03" );
PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04" );
PMU_EVENT_ATTR_STRING(ptsc, evattr_ptsc, "event=0x05" );
PMU_EVENT_ATTR_STRING(irperf, evattr_irperf, "event=0x06" );
PMU_EVENT_ATTR_STRING(cpu_thermal_margin, evattr_therm, "event=0x07" );
PMU_EVENT_ATTR_STRING(cpu_thermal_margin.snapshot, evattr_therm_snap, "1" );
PMU_EVENT_ATTR_STRING(cpu_thermal_margin.unit, evattr_therm_unit, "C" );
static struct attribute_group group_therm = {
.name = "events",
.attrs = attrs_therm,
};
static struct perf_msr msr[] = {
[PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, },
[PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, },
[PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, },
[PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, },
[PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, },
[PERF_MSR_PTSC] = { MSR_F15H_PTSC, &evattr_ptsc, test_ptsc, },
[PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &evattr_irperf, test_irperf, },
[PERF_MSR_THERM] = { MSR_IA32_THERM_STATUS, &evattr_therm, test_therm_status, },
[PERF_MSR_THERM_SNAP] = { MSR_IA32_THERM_STATUS, &evattr_therm_snap, test_therm_status, },
[PERF_MSR_THERM_UNIT] = { MSR_IA32_THERM_STATUS, &evattr_therm_unit, test_therm_status, },
[PERF_MSR_TSC] = { .no_check = true, },
[PERF_MSR_APERF] = { MSR_IA32_APERF, &group_aperf, test_aperfmperf, },
[PERF_MSR_MPERF] = { MSR_IA32_MPERF, &group_mperf, test_aperfmperf, },
[PERF_MSR_PPERF] = { MSR_PPERF, &group_pperf, test_intel, },
[PERF_MSR_SMI] = { MSR_SMI_COUNT, &group_smi, test_intel, },
[PERF_MSR_PTSC] = { MSR_F15H_PTSC, &group_ptsc, test_ptsc, },
[PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &group_irperf, test_irperf, },
[PERF_MSR_THERM] = { MSR_IA32_THERM_STATUS, &group_therm, test_therm_status, },
};
static struct attribute *events_attrs[PERF_MSR_EVENT_MAX + 1] = {
static struct attribute *events_attrs[] = {
&attr_tsc.attr.attr,
NULL,
};
@ -153,6 +167,17 @@ static const struct attribute_group *attr_groups[] = {
NULL,
};
const struct attribute_group *attr_update[] = {
&group_aperf,
&group_mperf,
&group_pperf,
&group_smi,
&group_ptsc,
&group_irperf,
&group_therm,
NULL,
};
static int msr_event_init(struct perf_event *event)
{
u64 cfg = event->attr.config;
@ -169,7 +194,7 @@ static int msr_event_init(struct perf_event *event)
cfg = array_index_nospec((unsigned long)cfg, PERF_MSR_EVENT_MAX);
if (!msr[cfg].attr)
if (!(msr_mask & (1 << cfg)))
return -EINVAL;
event->hw.idx = -1;
@ -252,32 +277,17 @@ static struct pmu pmu_msr = {
.stop = msr_event_stop,
.read = msr_event_update,
.capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE,
.attr_update = attr_update,
};
static int __init msr_init(void)
{
int i, j = 0;
if (!boot_cpu_has(X86_FEATURE_TSC)) {
pr_cont("no MSR PMU driver.\n");
return 0;
}
/* Probe the MSRs. */
for (i = PERF_MSR_TSC + 1; i < PERF_MSR_EVENT_MAX; i++) {
u64 val;
/* Virt sucks; you cannot tell if a R/O MSR is present :/ */
if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val))
msr[i].attr = NULL;
}
/* List remaining MSRs in the sysfs attrs. */
for (i = 0; i < PERF_MSR_EVENT_MAX; i++) {
if (msr[i].attr)
events_attrs[j++] = &msr[i].attr->attr.attr;
}
events_attrs[j] = NULL;
msr_mask = perf_msr_probe(msr, PERF_MSR_EVENT_MAX, true, NULL);
perf_pmu_register(&pmu_msr, "msr", -1);

7
arch/x86/events/perf_event.h
View File

@ -613,14 +613,11 @@ struct x86_pmu {
int attr_rdpmc_broken;
int attr_rdpmc;
struct attribute **format_attrs;
struct attribute **event_attrs;
struct attribute **caps_attrs;
ssize_t (*events_sysfs_show)(char *page, u64 config);
struct attribute **cpu_events;
const struct attribute_group **attr_update;
unsigned long attr_freeze_on_smi;
struct attribute **attrs;
/*
* CPU Hotplug hooks
@ -886,8 +883,6 @@ static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip)
ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event);
ssize_t intel_event_sysfs_show(char *page, u64 config);
struct attribute **merge_attr(struct attribute **a, struct attribute **b);
ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
char *page);
ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,

45
arch/x86/events/probe.c Normal file
View File

@ -0,0 +1,45 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/export.h>
#include <linux/types.h>
#include <linux/bits.h>
#include "probe.h"
static umode_t
not_visible(struct kobject *kobj, struct attribute *attr, int i)
{
return 0;
}
unsigned long
perf_msr_probe(struct perf_msr *msr, int cnt, bool zero, void *data)
{
unsigned long avail = 0;
unsigned int bit;
u64 val;
if (cnt >= BITS_PER_LONG)
return 0;
for (bit = 0; bit < cnt; bit++) {
if (!msr[bit].no_check) {
struct attribute_group *grp = msr[bit].grp;
grp->is_visible = not_visible;
if (msr[bit].test && !msr[bit].test(bit, data))
continue;
/* Virt sucks; you cannot tell if a R/O MSR is present :/ */
if (rdmsrl_safe(msr[bit].msr, &val))
continue;
/* Disable zero counters if requested. */
if (!zero && !val)
continue;
grp->is_visible = NULL;
}
avail |= BIT(bit);
}
return avail;
}
EXPORT_SYMBOL_GPL(perf_msr_probe);

29
arch/x86/events/probe.h Normal file
View File

@ -0,0 +1,29 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __ARCH_X86_EVENTS_PROBE_H__
#define __ARCH_X86_EVENTS_PROBE_H__
#include <linux/sysfs.h>
struct perf_msr {
u64 msr;
struct attribute_group *grp;
bool (*test)(int idx, void *data);
bool no_check;
};
unsigned long
perf_msr_probe(struct perf_msr *msr, int cnt, bool no_zero, void *data);
#define __PMU_EVENT_GROUP(_name) \
static struct attribute *attrs_##_name[] = { \
&attr_##_name.attr.attr, \
NULL, \
}
#define PMU_EVENT_GROUP(_grp, _name) \
__PMU_EVENT_GROUP(_name); \
static struct attribute_group group_##_name = { \
.name = #_grp, \
.attrs = attrs_##_name, \
}
#endif /* __ARCH_X86_EVENTS_PROBE_H__ */

54
fs/sysfs/group.c
View File

@ -175,6 +175,26 @@ int sysfs_create_group(struct kobject *kobj,
}
EXPORT_SYMBOL_GPL(sysfs_create_group);
static int internal_create_groups(struct kobject *kobj, int update,
const struct attribute_group **groups)
{
int error = 0;
int i;
if (!groups)
return 0;
for (i = 0; groups[i]; i++) {
error = internal_create_group(kobj, update, groups[i]);
if (error) {
while (--i >= 0)
sysfs_remove_group(kobj, groups[i]);
break;
}
}
return error;
}
/**
* sysfs_create_groups - given a directory kobject, create a bunch of attribute groups
* @kobj: The kobject to create the group on
@ -191,24 +211,28 @@ EXPORT_SYMBOL_GPL(sysfs_create_group);
int sysfs_create_groups(struct kobject *kobj,
const struct attribute_group **groups)
{
int error = 0;
int i;
if (!groups)
return 0;
for (i = 0; groups[i]; i++) {
error = sysfs_create_group(kobj, groups[i]);
if (error) {
while (--i >= 0)
sysfs_remove_group(kobj, groups[i]);
break;
}
}
return error;
return internal_create_groups(kobj, 0, groups);
}
EXPORT_SYMBOL_GPL(sysfs_create_groups);
/**
* sysfs_update_groups - given a directory kobject, create a bunch of attribute groups
* @kobj: The kobject to update the group on
* @groups: The attribute groups to update, NULL terminated
*
* This function update a bunch of attribute groups. If an error occurs when
* updating a group, all previously updated groups will be removed together
* with already existing (not updated) attributes.
*
* Returns 0 on success or error code from sysfs_update_group on failure.
*/
int sysfs_update_groups(struct kobject *kobj,
const struct attribute_group **groups)
{
return internal_create_groups(kobj, 1, groups);
}
EXPORT_SYMBOL_GPL(sysfs_update_groups);
/**
* sysfs_update_group - given a directory kobject, update an attribute group
* @kobj: The kobject to update the group on

6
include/linux/perf_event.h
View File

@ -256,6 +256,7 @@ struct pmu {
struct module *module;
struct device *dev;
const struct attribute_group **attr_groups;
const struct attribute_group **attr_update;
const char *name;
int type;
@ -749,6 +750,11 @@ struct perf_event_context {
int nr_stat;
int nr_freq;
int rotate_disable;
/*
* Set when nr_events != nr_active, except tolerant to events not
* necessary to be active due to scheduling constraints, such as cgroups.
*/
int rotate_necessary;
refcount_t refcount;
struct task_struct *task;

8
include/linux/sysfs.h
View File

@ -268,6 +268,8 @@ int __must_check sysfs_create_group(struct kobject *kobj,
const struct attribute_group *grp);
int __must_check sysfs_create_groups(struct kobject *kobj,
const struct attribute_group **groups);
int __must_check sysfs_update_groups(struct kobject *kobj,
const struct attribute_group **groups);
int sysfs_update_group(struct kobject *kobj,
const struct attribute_group *grp);
void sysfs_remove_group(struct kobject *kobj,
@ -433,6 +435,12 @@ static inline int sysfs_create_groups(struct kobject *kobj,
return 0;
}
static inline int sysfs_update_groups(struct kobject *kobj,
const struct attribute_group **groups)
{
return 0;
}
static inline int sysfs_update_group(struct kobject *kobj,
const struct attribute_group *grp)
{

52
kernel/events/core.c
View File

@ -2952,6 +2952,12 @@ static void ctx_sched_out(struct perf_event_context *ctx,
if (!ctx->nr_active || !(is_active & EVENT_ALL))
return;
/*
* If we had been multiplexing, no rotations are necessary, now no events
* are active.
*/
ctx->rotate_necessary = 0;
perf_pmu_disable(ctx->pmu);
if (is_active & EVENT_PINNED) {
list_for_each_entry_safe(event, tmp, &ctx->pinned_active, active_list)
@ -3319,10 +3325,13 @@ static int flexible_sched_in(struct perf_event *event, void *data)
return 0;
if (group_can_go_on(event, sid->cpuctx, sid->can_add_hw)) {
if (!group_sched_in(event, sid->cpuctx, sid->ctx))
list_add_tail(&event->active_list, &sid->ctx->flexible_active);
else
int ret = group_sched_in(event, sid->cpuctx, sid->ctx);
if (ret) {
sid->can_add_hw = 0;
sid->ctx->rotate_necessary = 1;
return 0;
}
list_add_tail(&event->active_list, &sid->ctx->flexible_active);
}
return 0;
@ -3690,24 +3699,17 @@ ctx_first_active(struct perf_event_context *ctx)
static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
{
struct perf_event *cpu_event = NULL, *task_event = NULL;
bool cpu_rotate = false, task_rotate = false;
struct perf_event_context *ctx = NULL;
struct perf_event_context *task_ctx = NULL;
int cpu_rotate, task_rotate;
/*
* Since we run this from IRQ context, nobody can install new
* events, thus the event count values are stable.
*/
if (cpuctx->ctx.nr_events) {
if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
cpu_rotate = true;
}
ctx = cpuctx->task_ctx;
if (ctx && ctx->nr_events) {
if (ctx->nr_events != ctx->nr_active)
task_rotate = true;
}
cpu_rotate = cpuctx->ctx.rotate_necessary;
task_ctx = cpuctx->task_ctx;
task_rotate = task_ctx ? task_ctx->rotate_necessary : 0;
if (!(cpu_rotate || task_rotate))
return false;
@ -3716,7 +3718,7 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
perf_pmu_disable(cpuctx->ctx.pmu);
if (task_rotate)
task_event = ctx_first_active(ctx);
task_event = ctx_first_active(task_ctx);
if (cpu_rotate)
cpu_event = ctx_first_active(&cpuctx->ctx);
@ -3724,17 +3726,17 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
* As per the order given at ctx_resched() first 'pop' task flexible
* and then, if needed CPU flexible.
*/
if (task_event || (ctx && cpu_event))
ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
if (task_event || (task_ctx && cpu_event))
ctx_sched_out(task_ctx, cpuctx, EVENT_FLEXIBLE);
if (cpu_event)
cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
if (task_event)
rotate_ctx(ctx, task_event);
rotate_ctx(task_ctx, task_event);
if (cpu_event)
rotate_ctx(&cpuctx->ctx, cpu_event);
perf_event_sched_in(cpuctx, ctx, current);
perf_event_sched_in(cpuctx, task_ctx, current);
perf_pmu_enable(cpuctx->ctx.pmu);
perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
@ -8535,9 +8537,9 @@ static int perf_tp_event_match(struct perf_event *event,
if (event->hw.state & PERF_HES_STOPPED)
return 0;
/*
* All tracepoints are from kernel-space.
* If exclude_kernel, only trace user-space tracepoints (uprobes)
*/
if (event->attr.exclude_kernel)
if (event->attr.exclude_kernel && !user_mode(regs))
return 0;
if (!perf_tp_filter_match(event, data))
@ -9877,6 +9879,12 @@ static int pmu_dev_alloc(struct pmu *pmu)
if (ret)
goto del_dev;
if (pmu->attr_update)
ret = sysfs_update_groups(&pmu->dev->kobj, pmu->attr_update);
if (ret)
goto del_dev;
out:
return ret;

2
kernel/trace/trace_uprobe.c
View File

@ -1336,7 +1336,7 @@ static inline void init_trace_event_call(struct trace_uprobe *tu,
call->event.funcs = &uprobe_funcs;
call->class->define_fields = uprobe_event_define_fields;
call->flags = TRACE_EVENT_FL_UPROBE;
call->flags = TRACE_EVENT_FL_UPROBE | TRACE_EVENT_FL_CAP_ANY;
call->class->reg = trace_uprobe_register;
call->data = tu;
}

7
tools/arch/arm64/include/uapi/asm/kvm.h
View File

@ -260,6 +260,13 @@ struct kvm_vcpu_events {
KVM_REG_SIZE_U256 | \
((i) & (KVM_ARM64_SVE_MAX_SLICES - 1)))
/*
* Register values for KVM_REG_ARM64_SVE_ZREG(), KVM_REG_ARM64_SVE_PREG() and
* KVM_REG_ARM64_SVE_FFR() are represented in memory in an endianness-
* invariant layout which differs from the layout used for the FPSIMD
* V-registers on big-endian systems: see sigcontext.h for more explanation.
*/
#define KVM_ARM64_SVE_VQ_MIN __SVE_VQ_MIN
#define KVM_ARM64_SVE_VQ_MAX __SVE_VQ_MAX

21
tools/arch/x86/include/asm/cpufeatures.h
View File

@ -239,12 +239,14 @@
#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */
#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */
#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */
#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* "" FPU data pointer updated only on x87 exceptions */
#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */
#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */
#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */
#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */
#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */
#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */
#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* "" Zero out FPU CS and FPU DS */
#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */
#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */
#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */
@ -269,13 +271,19 @@
#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */
#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */
/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */
#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */
/*
* Extended auxiliary flags: Linux defined - for features scattered in various
* CPUID levels like 0xf, etc.
*
* Reuse free bits when adding new feature flags!
*/
#define X86_FEATURE_CQM_LLC (11*32+ 0) /* LLC QoS if 1 */
#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring */
#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring */
#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */
/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */
#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring */
#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */
#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
@ -322,6 +330,7 @@
#define X86_FEATURE_UMIP (16*32+ 2) /* User Mode Instruction Protection */
#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */
#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */
#define X86_FEATURE_WAITPKG (16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */
#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
#define X86_FEATURE_GFNI (16*32+ 8) /* Galois Field New Instructions */
#define X86_FEATURE_VAES (16*32+ 9) /* Vector AES */

31
tools/arch/x86/include/uapi/asm/kvm.h
View File

@ -383,6 +383,9 @@ struct kvm_sync_regs {
#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2)
#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3)
#define KVM_STATE_NESTED_FORMAT_VMX 0
#define KVM_STATE_NESTED_FORMAT_SVM 1 /* unused */
#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
#define KVM_STATE_NESTED_EVMCS 0x00000004
@ -390,7 +393,14 @@ struct kvm_sync_regs {
#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_SMM_VMXON 0x00000002
struct kvm_vmx_nested_state {
#define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000
struct kvm_vmx_nested_state_data {
__u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
__u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
};
struct kvm_vmx_nested_state_hdr {
__u64 vmxon_pa;
__u64 vmcs12_pa;
@ -401,24 +411,25 @@ struct kvm_vmx_nested_state {
/* for KVM_CAP_NESTED_STATE */
struct kvm_nested_state {
/* KVM_STATE_* flags */
__u16 flags;
/* 0 for VMX, 1 for SVM. */
__u16 format;
/* 128 for SVM, 128 + VMCS size for VMX. */
__u32 size;
union {
/* VMXON, VMCS */
struct kvm_vmx_nested_state vmx;
struct kvm_vmx_nested_state_hdr vmx;
/* Pad the header to 128 bytes. */
__u8 pad[120];
};
} hdr;
__u8 data[0];
/*
* Define data region as 0 bytes to preserve backwards-compatability
* to old definition of kvm_nested_state in order to avoid changing
* KVM_{GET,PUT}_NESTED_STATE ioctl values.
*/
union {
struct kvm_vmx_nested_state_data vmx[0];
} data;
};
#endif /* _ASM_X86_KVM_H */

3
tools/build/Makefile.feature
View File

@ -36,6 +36,7 @@ FEATURE_TESTS_BASIC := \
fortify-source \
sync-compare-and-swap \
get_current_dir_name \
gettid \
glibc \
gtk2 \
gtk2-infobar \
@ -52,6 +53,7 @@ FEATURE_TESTS_BASIC := \
libpython \
libpython-version \
libslang \
libslang-include-subdir \
libcrypto \
libunwind \
pthread-attr-setaffinity-np \
@ -113,7 +115,6 @@ FEATURE_DISPLAY ?= \
numa_num_possible_cpus \
libperl \
libpython \
libslang \
libcrypto \
libunwind \
libdw-dwarf-unwind \

10
tools/build/feature/Makefile
View File

@ -31,6 +31,7 @@ FILES= \
test-libpython.bin \
test-libpython-version.bin \
test-libslang.bin \
test-libslang-include-subdir.bin \
test-libcrypto.bin \
test-libunwind.bin \
test-libunwind-debug-frame.bin \
@ -54,6 +55,7 @@ FILES= \
test-get_cpuid.bin \
test-sdt.bin \
test-cxx.bin \
test-gettid.bin \
test-jvmti.bin \
test-jvmti-cmlr.bin \
test-sched_getcpu.bin \
@ -181,7 +183,10 @@ $(OUTPUT)test-libaudit.bin:
$(BUILD) -laudit
$(OUTPUT)test-libslang.bin:
$(BUILD) -I/usr/include/slang -lslang
$(BUILD) -lslang
$(OUTPUT)test-libslang-include-subdir.bin:
$(BUILD) -lslang
$(OUTPUT)test-libcrypto.bin:
$(BUILD) -lcrypto
@ -267,6 +272,9 @@ $(OUTPUT)test-sdt.bin:
$(OUTPUT)test-cxx.bin:
$(BUILDXX) -std=gnu++11
$(OUTPUT)test-gettid.bin:
$(BUILD)
$(OUTPUT)test-jvmti.bin:
$(BUILD)

7
tools/build/feature/test-all.c
View File

@ -38,6 +38,10 @@
# include "test-get_current_dir_name.c"
#undef main
#define main main_test_gettid
# include "test-gettid.c"
#undef main
#define main main_test_glibc
# include "test-glibc.c"
#undef main
@ -182,7 +186,7 @@
# include "test-disassembler-four-args.c"
#undef main
#define main main_test_zstd
#define main main_test_libzstd
# include "test-libzstd.c"
#undef main
@ -195,6 +199,7 @@ int main(int argc, char *argv[])
main_test_libelf();
main_test_libelf_mmap();
main_test_get_current_dir_name();
main_test_gettid();
main_test_glibc();
main_test_dwarf();
main_test_dwarf_getlocations();

1
tools/build/feature/test-fortify-source.c
View File

@ -1,3 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
#include <stdio.h>
int main(void)

11
tools/build/feature/test-gettid.c Normal file
View File

@ -0,0 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
#define _GNU_SOURCE
#include <unistd.h>
int main(void)
{
return gettid();
}
#undef _GNU_SOURCE

1
tools/build/feature/test-hello.c
View File

@ -1,3 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
#include <stdio.h>
int main(void)

7
tools/build/feature/test-libslang-include-subdir.c Normal file
View File

@ -0,0 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <slang/slang.h>
int main(void)
{
return SLsmg_init_smg();
}

1
tools/build/feature/test-setns.c
View File

@ -1,3 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
#define _GNU_SOURCE
#include <sched.h>

75
tools/include/linux/ctype.h Normal file
View File

@ -0,0 +1,75 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_CTYPE_H
#define _LINUX_CTYPE_H
/*
* NOTE! This ctype does not handle EOF like the standard C
* library is required to.
*/
#define _U 0x01 /* upper */
#define _L 0x02 /* lower */
#define _D 0x04 /* digit */
#define _C 0x08 /* cntrl */
#define _P 0x10 /* punct */
#define _S 0x20 /* white space (space/lf/tab) */
#define _X 0x40 /* hex digit */
#define _SP 0x80 /* hard space (0x20) */
extern const unsigned char _ctype[];
#define __ismask(x) (_ctype[(int)(unsigned char)(x)])
#define isalnum(c) ((__ismask(c)&(_U|_L|_D)) != 0)
#define isalpha(c) ((__ismask(c)&(_U|_L)) != 0)
#define iscntrl(c) ((__ismask(c)&(_C)) != 0)
static inline int __isdigit(int c)
{
return '0' <= c && c <= '9';
}
#define isdigit(c) __isdigit(c)
#define isgraph(c) ((__ismask(c)&(_P|_U|_L|_D)) != 0)
#define islower(c) ((__ismask(c)&(_L)) != 0)
#define isprint(c) ((__ismask(c)&(_P|_U|_L|_D|_SP)) != 0)
#define ispunct(c) ((__ismask(c)&(_P)) != 0)
/* Note: isspace() must return false for %NUL-terminator */
#define isspace(c) ((__ismask(c)&(_S)) != 0)
#define isupper(c) ((__ismask(c)&(_U)) != 0)
#define isxdigit(c) ((__ismask(c)&(_D|_X)) != 0)
#define isascii(c) (((unsigned char)(c))<=0x7f)
#define toascii(c) (((unsigned char)(c))&0x7f)
static inline unsigned char __tolower(unsigned char c)
{
if (isupper(c))
c -= 'A'-'a';
return c;
}
static inline unsigned char __toupper(unsigned char c)
{
if (islower(c))
c -= 'a'-'A';
return c;
}
#define tolower(c) __tolower(c)
#define toupper(c) __toupper(c)
/*
* Fast implementation of tolower() for internal usage. Do not use in your
* code.
*/
static inline char _tolower(const char c)
{
return c | 0x20;
}
/* Fast check for octal digit */
static inline int isodigit(const char c)
{
return c >= '0' && c <= '7';
}
#endif

1
tools/include/linux/kernel.h
View File

@ -102,6 +102,7 @@
int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
int scnprintf(char * buf, size_t size, const char * fmt, ...);
int scnprintf_pad(char * buf, size_t size, const char * fmt, ...);
#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))

11
tools/include/linux/string.h
View File

@ -7,6 +7,9 @@
void *memdup(const void *src, size_t len);
char **argv_split(const char *str, int *argcp);
void argv_free(char **argv);
int strtobool(const char *s, bool *res);
/*
@ -19,6 +22,8 @@ extern size_t strlcpy(char *dest, const char *src, size_t size);
char *str_error_r(int errnum, char *buf, size_t buflen);
char *strreplace(char *s, char old, char new);
/**
* strstarts - does @str start with @prefix?
* @str: string to examine
@ -29,4 +34,8 @@ static inline bool strstarts(const char *str, const char *prefix)
return strncmp(str, prefix, strlen(prefix)) == 0;
}
#endif /* _LINUX_STRING_H_ */
extern char * __must_check skip_spaces(const char *);
extern char *strim(char *);
#endif /* _TOOLS_LINUX_STRING_H_ */

100
tools/lib/argv_split.c Normal file
View File

@ -0,0 +1,100 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Helper function for splitting a string into an argv-like array.
*/
#include <stdlib.h>
#include <linux/kernel.h>
#include <linux/ctype.h>
#include <linux/string.h>
static const char *skip_arg(const char *cp)
{
while (*cp && !isspace(*cp))
cp++;
return cp;
}
static int count_argc(const char *str)
{
int count = 0;
while (*str) {
str = skip_spaces(str);
if (*str) {
count++;
str = skip_arg(str);
}
}
return count;
}
/**
* argv_free - free an argv
* @argv - the argument vector to be freed
*
* Frees an argv and the strings it points to.
*/
void argv_free(char **argv)
{
char **p;
for (p = argv; *p; p++) {
free(*p);
*p = NULL;
}
free(argv);
}
/**
* argv_split - split a string at whitespace, returning an argv
* @str: the string to be split
* @argcp: returned argument count
*
* Returns an array of pointers to strings which are split out from
* @str. This is performed by strictly splitting on white-space; no
* quote processing is performed. Multiple whitespace characters are
* considered to be a single argument separator. The returned array
* is always NULL-terminated. Returns NULL on memory allocation
* failure.
*/
char **argv_split(const char *str, int *argcp)
{
int argc = count_argc(str);
char **argv = calloc(argc + 1, sizeof(*argv));
char **argvp;
if (argv == NULL)
goto out;
if (argcp)
*argcp = argc;
argvp = argv;
while (*str) {
str = skip_spaces(str);
if (*str) {
const char *p = str;
char *t;
str = skip_arg(str);
t = strndup(p, str-p);
if (t == NULL)
goto fail;
*argvp++ = t;
}
}
*argvp = NULL;
out:
return argv;
fail:
argv_free(argv);
return NULL;
}

35
tools/lib/ctype.c Normal file
View File

@ -0,0 +1,35 @@
// SPDX-License-Identifier: GPL-2.0
/*
* linux/lib/ctype.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/ctype.h>
#include <linux/compiler.h>
const unsigned char _ctype[] = {
_C,_C,_C,_C,_C,_C,_C,_C, /* 0-7 */
_C,_C|_S,_C|_S,_C|_S,_C|_S,_C|_S,_C,_C, /* 8-15 */
_C,_C,_C,_C,_C,_C,_C,_C, /* 16-23 */
_C,_C,_C,_C,_C,_C,_C,_C, /* 24-31 */
_S|_SP,_P,_P,_P,_P,_P,_P,_P, /* 32-39 */
_P,_P,_P,_P,_P,_P,_P,_P, /* 40-47 */
_D,_D,_D,_D,_D,_D,_D,_D, /* 48-55 */
_D,_D,_P,_P,_P,_P,_P,_P, /* 56-63 */
_P,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U, /* 64-71 */
_U,_U,_U,_U,_U,_U,_U,_U, /* 72-79 */
_U,_U,_U,_U,_U,_U,_U,_U, /* 80-87 */
_U,_U,_U,_P,_P,_P,_P,_P, /* 88-95 */
_P,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L, /* 96-103 */
_L,_L,_L,_L,_L,_L,_L,_L, /* 104-111 */
_L,_L,_L,_L,_L,_L,_L,_L, /* 112-119 */
_L,_L,_L,_P,_P,_P,_P,_C, /* 120-127 */
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 128-143 */
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 144-159 */
_S|_SP,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P, /* 160-175 */
_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P, /* 176-191 */
_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U, /* 192-207 */
_U,_U,_U,_U,_U,_U,_U,_P,_U,_U,_U,_U,_U,_U,_U,_L, /* 208-223 */
_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L, /* 224-239 */
_L,_L,_L,_L,_L,_L,_L,_P,_L,_L,_L,_L,_L,_L,_L,_L}; /* 240-255 */

55
tools/lib/string.c
View File

@ -17,6 +17,7 @@
#include <string.h>
#include <errno.h>
#include <linux/string.h>
#include <linux/ctype.h>
#include <linux/compiler.h>
/**
@ -106,3 +107,57 @@ size_t __weak strlcpy(char *dest, const char *src, size_t size)
}
return ret;
}
/**
* skip_spaces - Removes leading whitespace from @str.
* @str: The string to be stripped.
*
* Returns a pointer to the first non-whitespace character in @str.
*/
char *skip_spaces(const char *str)
{
while (isspace(*str))
++str;
return (char *)str;
}
/**
* strim - Removes leading and trailing whitespace from @s.
* @s: The string to be stripped.
*
* Note that the first trailing whitespace is replaced with a %NUL-terminator
* in the given string @s. Returns a pointer to the first non-whitespace
* character in @s.
*/
char *strim(char *s)
{
size_t size;
char *end;
size = strlen(s);
if (!size)
return s;
end = s + size - 1;
while (end >= s && isspace(*end))
end--;
*(end + 1) = '\0';
return skip_spaces(s);
}
/**
* strreplace - Replace all occurrences of character in string.
* @s: The string to operate on.
* @old: The character being replaced.
* @new: The character @old is replaced with.
*
* Returns pointer to the nul byte at the end of @s.
*/
char *strreplace(char *s, char old, char new)
{
for (; *s; ++s)
if (*s == old)
*s = new;
return s;
}

14
tools/lib/symbol/kallsyms.c
View File

@ -1,5 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
#include <ctype.h>
#include "symbol/kallsyms.h"
#include <stdio.h>
#include <stdlib.h>
@ -16,6 +15,19 @@ bool kallsyms__is_function(char symbol_type)
return symbol_type == 'T' || symbol_type == 'W';
}
/*
* While we find nice hex chars, build a long_val.
* Return number of chars processed.
*/
int hex2u64(const char *ptr, u64 *long_val)
{
char *p;
*long_val = strtoull(ptr, &p, 16);
return p - ptr;
}
int kallsyms__parse(const char *filename, void *arg,
int (*process_symbol)(void *arg, const char *name,
char type, u64 start))

2
tools/lib/symbol/kallsyms.h
View File

@ -18,6 +18,8 @@ static inline u8 kallsyms2elf_binding(char type)
return isupper(type) ? STB_GLOBAL : STB_LOCAL;
}
int hex2u64(const char *ptr, u64 *long_val);
u8 kallsyms2elf_type(char type);
bool kallsyms__is_function(char symbol_type);

19
tools/lib/vsprintf.c
View File

@ -23,3 +23,22 @@ int scnprintf(char * buf, size_t size, const char * fmt, ...)
return (i >= ssize) ? (ssize - 1) : i;
}
int scnprintf_pad(char * buf, size_t size, const char * fmt, ...)
{
ssize_t ssize = size;
va_list args;
int i;
va_start(args, fmt);
i = vscnprintf(buf, size, fmt, args);
va_end(args);
if (i < (int) size) {
for (; i < (int) size; i++)
buf[i] = ' ';
buf[i] = 0x0;
}
return (i >= ssize) ? (ssize - 1) : i;
}

5
tools/objtool/Build
View File

@ -9,6 +9,7 @@ objtool-y += special.o
objtool-y += objtool.o
objtool-y += libstring.o
objtool-y += libctype.o
objtool-y += str_error_r.o
CFLAGS += -I$(srctree)/tools/lib
@ -17,6 +18,10 @@ $(OUTPUT)libstring.o: ../lib/string.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)libctype.o: ../lib/ctype.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)str_error_r.o: ../lib/str_error_r.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)

41
tools/perf/Documentation/db-export.txt Normal file
View File

@ -0,0 +1,41 @@
Database Export
===============
perf tool's python scripting engine:
tools/perf/util/scripting-engines/trace-event-python.c
supports scripts:
tools/perf/scripts/python/export-to-sqlite.py
tools/perf/scripts/python/export-to-postgresql.py
which export data to a SQLite3 or PostgreSQL database.
The export process provides records with unique sequential ids which allows the
data to be imported directly to a database and provides the relationships
between tables.
Over time it is possible to continue to expand the export while maintaining
backward and forward compatibility, by following some simple rules:
1. Because of the nature of SQL, existing tables and columns can continue to be
used so long as the names and meanings (and to some extent data types) remain
the same.
2. New tables and columns can be added, without affecting existing SQL queries,
so long as the new names are unique.
3. Scripts that use a database (e.g. exported-sql-viewer.py) can maintain
backward compatibility by testing for the presence of new tables and columns
before using them. e.g. function IsSelectable() in exported-sql-viewer.py
4. The export scripts themselves maintain forward compatibility (i.e. an existing
script will continue to work with new versions of perf) by accepting a variable
number of arguments (e.g. def call_return_table(*x)) i.e. perf can pass more
arguments which old scripts will ignore.
5. The scripting engine tests for the existence of script handler functions
before calling them. The scripting engine can also test for the support of new
or optional features by checking for the existence and value of script global
variables.

40
tools/perf/Documentation/intel-pt.txt
View File

@ -88,21 +88,51 @@ smaller.
To represent software control flow, "branches" samples are produced. By default
a branch sample is synthesized for every single branch. To get an idea what
data is available you can use the 'perf script' tool with no parameters, which
will list all the samples.
data is available you can use the 'perf script' tool with all itrace sampling
options, which will list all the samples.
perf record -e intel_pt//u ls
perf script
perf script --itrace=ibxwpe
An interesting field that is not printed by default is 'flags' which can be
displayed as follows:
perf script -Fcomm,tid,pid,time,cpu,event,trace,ip,sym,dso,addr,symoff,flags
perf script --itrace=ibxwpe -F+flags
The flags are "bcrosyiABEx" which stand for branch, call, return, conditional,
system, asynchronous, interrupt, transaction abort, trace begin, trace end, and
in transaction, respectively.
Another interesting field that is not printed by default is 'ipc' which can be
displayed as follows:
perf script --itrace=be -F+ipc
There are two ways that instructions-per-cycle (IPC) can be calculated depending
on the recording.
If the 'cyc' config term (see config terms section below) was used, then IPC is
calculated using the cycle count from CYC packets, otherwise MTC packets are
used - refer to the 'mtc' config term. When MTC is used, however, the values
are less accurate because the timing is less accurate.
Because Intel PT does not update the cycle count on every branch or instruction,
the values will often be zero. When there are values, they will be the number
of instructions and number of cycles since the last update, and thus represent
the average IPC since the last IPC for that event type. Note IPC for "branches"
events is calculated separately from IPC for "instructions" events.
Also note that the IPC instruction count may or may not include the current
instruction. If the cycle count is associated with an asynchronous branch
(e.g. page fault or interrupt), then the instruction count does not include the
current instruction, otherwise it does. That is consistent with whether or not
that instruction has retired when the cycle count is updated.
Another note, in the case of "branches" events, non-taken branches are not
presently sampled, so IPC values for them do not appear e.g. a CYC packet with a
TNT packet that starts with a non-taken branch. To see every possible IPC
value, "instructions" events can be used e.g. --itrace=i0ns
While it is possible to create scripts to analyze the data, an alternative
approach is available to export the data to a sqlite or postgresql database.
Refer to script export-to-sqlite.py or export-to-postgresql.py for more details,
@ -713,7 +743,7 @@ Having no option is the same as
which, in turn, is the same as
--itrace=ibxwpe
--itrace=cepwx
The letters are:

9
tools/perf/Documentation/perf-config.txt
View File

@ -564,9 +564,12 @@ llvm.*::
llvm.clang-bpf-cmd-template::
Cmdline template. Below lines show its default value. Environment
variable is used to pass options.
"$CLANG_EXEC -D__KERNEL__ $CLANG_OPTIONS $KERNEL_INC_OPTIONS \
-Wno-unused-value -Wno-pointer-sign -working-directory \
$WORKING_DIR -c $CLANG_SOURCE -target bpf -O2 -o -"
"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE " \
"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
"-Wno-unused-value -Wno-pointer-sign " \
"-working-directory $WORKING_DIR " \
"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
llvm.clang-opt::
Options passed to clang.

31
tools/perf/Documentation/perf-diff.txt
View File

@ -90,9 +90,10 @@ OPTIONS
-c::
--compute::
Differential computation selection - delta, ratio, wdiff, delta-abs
(default is delta-abs). Default can be changed using diff.compute
config option. See COMPARISON METHODS section for more info.
Differential computation selection - delta, ratio, wdiff, cycles,
delta-abs (default is delta-abs). Default can be changed using
diff.compute config option. See COMPARISON METHODS section for
more info.
-p::
--period::
@ -142,12 +143,14 @@ OPTIONS
perf diff --time 0%-10%,30%-40%
It also supports analyzing samples within a given time window
<start>,<stop>. Times have the format seconds.microseconds. If 'start'
is not given (i.e., time string is ',x.y') then analysis starts at
the beginning of the file. If stop time is not given (i.e, time
string is 'x.y,') then analysis goes to the end of the file. Time string is
'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different
perf.data files.
<start>,<stop>. Times have the format seconds.nanoseconds. If 'start'
is not given (i.e. time string is ',x.y') then analysis starts at
the beginning of the file. If stop time is not given (i.e. time
string is 'x.y,') then analysis goes to the end of the file.
Multiple ranges can be separated by spaces, which requires the argument
to be quoted e.g. --time "1234.567,1234.789 1235,"
Time string is'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps
for different perf.data files.
For example, we get the timestamp information from 'perf script'.
@ -278,6 +281,16 @@ If specified the 'Weighted diff' column is displayed with value 'd' computed as:
- WEIGHT-A being the weight of the data file
- WEIGHT-B being the weight of the baseline data file
cycles
~~~~~~
If specified the '[Program Block Range] Cycles Diff' column is displayed.
It displays the cycles difference of same program basic block amongst
two perf.data. The program basic block is the code between two branches.
'[Program Block Range]' indicates the range of a program basic block.
Source line is reported if it can be found otherwise uses symbol+offset
instead.
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-report[1]

11
tools/perf/Documentation/perf-record.txt
View File

@ -490,6 +490,17 @@ Configure all used events to run in kernel space.
--all-user::
Configure all used events to run in user space.
--kernel-callchains::
Collect callchains only from kernel space. I.e. this option sets
perf_event_attr.exclude_callchain_user to 1.
--user-callchains::
Collect callchains only from user space. I.e. this option sets
perf_event_attr.exclude_callchain_kernel to 1.
Don't use both --kernel-callchains and --user-callchains at the same time or no
callchains will be collected.
--timestamp-filename
Append timestamp to output file name.

11
tools/perf/Documentation/perf-report.txt
View File

@ -89,7 +89,7 @@ OPTIONS
- socket: processor socket number the task ran at the time of sample
- srcline: filename and line number executed at the time of sample. The
DWARF debugging info must be provided.
- srcfile: file name of the source file of the same. Requires dwarf
- srcfile: file name of the source file of the samples. Requires dwarf
information.
- weight: Event specific weight, e.g. memory latency or transaction
abort cost. This is the global weight.
@ -412,12 +412,13 @@ OPTIONS
--time::
Only analyze samples within given time window: <start>,<stop>. Times
have the format seconds.microseconds. If start is not given (i.e., time
have the format seconds.nanoseconds. If start is not given (i.e. time
string is ',x.y') then analysis starts at the beginning of the file. If
stop time is not given (i.e, time string is 'x.y,') then analysis goes
to end of file.
stop time is not given (i.e. time string is 'x.y,') then analysis goes
to end of file. Multiple ranges can be separated by spaces, which
requires the argument to be quoted e.g. --time "1234.567,1234.789 1235,"
Also support time percent with multiple time range. Time string is
Also support time percent with multiple time ranges. Time string is
'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'.
For example:

17
tools/perf/Documentation/perf-script.txt
View File

@ -117,7 +117,7 @@ OPTIONS
Comma separated list of fields to print. Options are:
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc, srccode.
brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc, srccode, ipc.
Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace
@ -203,6 +203,9 @@ OPTIONS
The synth field is used by synthesized events which may be created when
Instruction Trace decoding.
The ipc (instructions per cycle) field is synthesized and may have a value when
Instruction Trace decoding.
Finally, a user may not set fields to none for all event types.
i.e., -F "" is not allowed.
@ -313,6 +316,9 @@ OPTIONS
--show-round-events
Display finished round events i.e. events of type PERF_RECORD_FINISHED_ROUND.
--show-bpf-events
Display bpf events i.e. events of type PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT.
--demangle::
Demangle symbol names to human readable form. It's enabled by default,
disable with --no-demangle.
@ -355,12 +361,13 @@ include::itrace.txt[]
--time::
Only analyze samples within given time window: <start>,<stop>. Times
have the format seconds.microseconds. If start is not given (i.e., time
have the format seconds.nanoseconds. If start is not given (i.e. time
string is ',x.y') then analysis starts at the beginning of the file. If
stop time is not given (i.e, time string is 'x.y,') then analysis goes
to end of file.
stop time is not given (i.e. time string is 'x.y,') then analysis goes
to end of file. Multiple ranges can be separated by spaces, which
requires the argument to be quoted e.g. --time "1234.567,1234.789 1235,"
Also support time percent with multipe time range. Time string is
Also support time percent with multiple time ranges. Time string is
'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'.
For example:

10
tools/perf/Documentation/perf-stat.txt
View File

@ -200,6 +200,13 @@ use --per-socket in addition to -a. (system-wide). The output includes the
socket number and the number of online processors on that socket. This is
useful to gauge the amount of aggregation.
--per-die::
Aggregate counts per processor die for system-wide mode measurements. This
is a useful mode to detect imbalance between dies. To enable this mode,
use --per-die in addition to -a. (system-wide). The output includes the
die number and the number of online processors on that die. This is
useful to gauge the amount of aggregation.
--per-core::
Aggregate counts per physical processor for system-wide mode measurements. This
is a useful mode to detect imbalance between physical cores. To enable this mode,
@ -239,6 +246,9 @@ Input file name.
--per-socket::
Aggregate counts per processor socket for system-wide mode measurements.
--per-die::
Aggregate counts per processor die for system-wide mode measurements.
--per-core::
Aggregate counts per physical processor for system-wide mode measurements.

5
tools/perf/Documentation/perf-top.txt
View File

@ -262,6 +262,11 @@ Default is to monitor all CPUS.
The number of threads to run when synthesizing events for existing processes.
By default, the number of threads equals to the number of online CPUs.
--namespaces::
Record events of type PERF_RECORD_NAMESPACES and display it with the
'cgroup_id' sort key.
INTERACTIVE PROMPTING KEYS
--------------------------

97
tools/perf/Documentation/perf.data-file-format.txt
View File

@ -151,25 +151,45 @@ struct {
HEADER_CPU_TOPOLOGY = 13,
String lists defining the core and CPU threads topology.
The string lists are followed by a variable length array
which contains core_id and socket_id of each cpu.
The number of entries can be determined by the size of the
section minus the sizes of both string lists.
struct {
/*
* First revision of HEADER_CPU_TOPOLOGY
*
* See 'struct perf_header_string_list' definition earlier
* in this file.
*/
struct perf_header_string_list cores; /* Variable length */
struct perf_header_string_list threads; /* Variable length */
/*
* Second revision of HEADER_CPU_TOPOLOGY, older tools
* will not consider what comes next
*/
struct {
uint32_t core_id;
uint32_t socket_id;
} cpus[nr]; /* Variable length records */
/* 'nr' comes from previously processed HEADER_NRCPUS's nr_cpu_avail */
/*
* Third revision of HEADER_CPU_TOPOLOGY, older tools
* will not consider what comes next
*/
struct perf_header_string_list dies; /* Variable length */
uint32_t die_id[nr_cpus_avail]; /* from previously processed HEADER_NR_CPUS, VLA */
};
Example:
sibling cores : 0-3
sibling sockets : 0-8
sibling dies : 0-3
sibling dies : 4-7
sibling threads : 0-1
sibling threads : 2-3
sibling threads : 4-5
sibling threads : 6-7
HEADER_NUMA_TOPOLOGY = 14,
@ -272,6 +292,69 @@ struct {
Two uint64_t for the time of first sample and the time of last sample.
HEADER_SAMPLE_TOPOLOGY = 22,
Physical memory map and its node assignments.
The format of data in MEM_TOPOLOGY is as follows:
0 - version | for future changes
8 - block_size_bytes | /sys/devices/system/memory/block_size_bytes
16 - count | number of nodes
For each node we store map of physical indexes:
32 - node id | node index
40 - size | size of bitmap
48 - bitmap | bitmap of memory indexes that belongs to node
| /sys/devices/system/node/node<NODE>/memory<INDEX>
The MEM_TOPOLOGY can be displayed with following command:
$ perf report --header-only -I
...
# memory nodes (nr 1, block size 0x8000000):
# 0 [7G]: 0-23,32-69
HEADER_CLOCKID = 23,
One uint64_t for the clockid frequency, specified, for instance, via 'perf
record -k' (see clock_gettime()), to enable timestamps derived metrics
conversion into wall clock time on the reporting stage.
HEADER_DIR_FORMAT = 24,
The data files layout is described by HEADER_DIR_FORMAT feature. Currently it
holds only version number (1):
uint64_t version;
The current version holds only version value (1) means that data files:
- Follow the 'data.*' name format.
- Contain raw events data in standard perf format as read from kernel (and need
to be sorted)
Future versions are expected to describe different data files layout according
to special needs.
HEADER_BPF_PROG_INFO = 25,
struct bpf_prog_info_linear, which contains detailed information about
a BPF program, including type, id, tag, jited/xlated instructions, etc.
HEADER_BPF_BTF = 26,
Contains BPF Type Format (BTF). For more information about BTF, please
refer to Documentation/bpf/btf.rst.
struct {
u32 id;
u32 data_size;
char data[];
};
HEADER_COMPRESSED = 27,
struct {

2
tools/perf/Documentation/tips.txt
View File

@ -38,6 +38,6 @@ To report cacheline events from previous recording: perf c2c report
To browse sample contexts use perf report --sample 10 and select in context menu
To separate samples by time use perf report --sort time,overhead,sym
To set sample time separation other than 100ms with --sort time use --time-quantum
Add -I to perf report to sample register values visible in perf report context.
Add -I to perf record to sample register values, which will be visible in perf report sample context.
To show IPC for sampling periods use perf record -e '{cycles,instructions}:S' and then browse context
To show context switches in perf report sample context add --switch-events to perf record.

2
tools/perf/MANIFEST
View File

@ -7,6 +7,8 @@ tools/lib/traceevent
tools/lib/api
tools/lib/bpf
tools/lib/subcmd
tools/lib/argv_split.c
tools/lib/ctype.c
tools/lib/hweight.c
tools/lib/rbtree.c
tools/lib/string.c

19
tools/perf/Makefile.config
View File

@ -332,6 +332,10 @@ ifeq ($(feature-get_current_dir_name), 1)
CFLAGS += -DHAVE_GET_CURRENT_DIR_NAME
endif
ifeq ($(feature-gettid), 1)
CFLAGS += -DHAVE_GETTID
endif
ifdef NO_LIBELF
NO_DWARF := 1
NO_DEMANGLE := 1
@ -413,6 +417,9 @@ ifdef CORESIGHT
$(call feature_check,libopencsd)
ifeq ($(feature-libopencsd), 1)
CFLAGS += -DHAVE_CSTRACE_SUPPORT $(LIBOPENCSD_CFLAGS)
ifeq ($(feature-reallocarray), 0)
CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
endif
LDFLAGS += $(LIBOPENCSD_LDFLAGS)
EXTLIBS += $(OPENCSDLIBS)
$(call detected,CONFIG_LIBOPENCSD)
@ -637,11 +644,15 @@ endif
ifndef NO_SLANG
ifneq ($(feature-libslang), 1)
msg := $(warning slang not found, disables TUI support. Please install slang-devel, libslang-dev or libslang2-dev);
NO_SLANG := 1
else
ifneq ($(feature-libslang-include-subdir), 1)
msg := $(warning slang not found, disables TUI support. Please install slang-devel, libslang-dev or libslang2-dev);
NO_SLANG := 1
else
CFLAGS += -DHAVE_SLANG_INCLUDE_SUBDIR
endif
endif
ifndef NO_SLANG
# Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
CFLAGS += -I/usr/include/slang
CFLAGS += -DHAVE_SLANG_SUPPORT
EXTLIBS += -lslang
$(call detected,CONFIG_SLANG)

44
tools/perf/Makefile.perf
View File

@ -420,6 +420,24 @@ fadvise_advice_tbl := $(srctree)/tools/perf/trace/beauty/fadvise.sh
$(fadvise_advice_array): $(linux_uapi_dir)/in.h $(fadvise_advice_tbl)
$(Q)$(SHELL) '$(fadvise_advice_tbl)' $(linux_uapi_dir) > $@
fsmount_arrays := $(beauty_outdir)/fsmount_arrays.c
fsmount_tbls := $(srctree)/tools/perf/trace/beauty/fsmount.sh
$(fsmount_arrays): $(linux_uapi_dir)/fs.h $(fsmount_tbls)
$(Q)$(SHELL) '$(fsmount_tbls)' $(linux_uapi_dir) > $@
fspick_arrays := $(beauty_outdir)/fspick_arrays.c
fspick_tbls := $(srctree)/tools/perf/trace/beauty/fspick.sh
$(fspick_arrays): $(linux_uapi_dir)/fs.h $(fspick_tbls)
$(Q)$(SHELL) '$(fspick_tbls)' $(linux_uapi_dir) > $@
fsconfig_arrays := $(beauty_outdir)/fsconfig_arrays.c
fsconfig_tbls := $(srctree)/tools/perf/trace/beauty/fsconfig.sh
$(fsconfig_arrays): $(linux_uapi_dir)/fs.h $(fsconfig_tbls)
$(Q)$(SHELL) '$(fsconfig_tbls)' $(linux_uapi_dir) > $@
pkey_alloc_access_rights_array := $(beauty_outdir)/pkey_alloc_access_rights_array.c
asm_generic_hdr_dir := $(srctree)/tools/include/uapi/asm-generic/
pkey_alloc_access_rights_tbl := $(srctree)/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
@ -494,6 +512,12 @@ mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
$(mount_flags_array): $(linux_uapi_dir)/fs.h $(mount_flags_tbl)
$(Q)$(SHELL) '$(mount_flags_tbl)' $(linux_uapi_dir) > $@
move_mount_flags_array := $(beauty_outdir)/move_mount_flags_array.c
move_mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/move_mount_flags.sh
$(move_mount_flags_array): $(linux_uapi_dir)/fs.h $(move_mount_flags_tbl)
$(Q)$(SHELL) '$(move_mount_flags_tbl)' $(linux_uapi_dir) > $@
prctl_option_array := $(beauty_outdir)/prctl_option_array.c
prctl_hdr_dir := $(srctree)/tools/include/uapi/linux/
prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh
@ -526,6 +550,12 @@ arch_errno_tbl := $(srctree)/tools/perf/trace/beauty/arch_errno_names.sh
$(arch_errno_name_array): $(arch_errno_tbl)
$(Q)$(SHELL) '$(arch_errno_tbl)' $(CC) $(arch_errno_hdr_dir) > $@
sync_file_range_arrays := $(beauty_outdir)/sync_file_range_arrays.c
sync_file_range_tbls := $(srctree)/tools/perf/trace/beauty/sync_file_range.sh
$(sync_file_range_arrays): $(linux_uapi_dir)/fs.h $(sync_file_range_tbls)
$(Q)$(SHELL) '$(sync_file_range_tbls)' $(linux_uapi_dir) > $@
all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
# Create python binding output directory if not already present
@ -629,6 +659,9 @@ build-dir = $(if $(__build-dir),$(__build-dir),.)
prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioctl_array) \
$(fadvise_advice_array) \
$(fsconfig_arrays) \
$(fsmount_arrays) \
$(fspick_arrays) \
$(pkey_alloc_access_rights_array) \
$(sndrv_pcm_ioctl_array) \
$(sndrv_ctl_ioctl_array) \
@ -639,12 +672,14 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
$(madvise_behavior_array) \
$(mmap_flags_array) \
$(mount_flags_array) \
$(move_mount_flags_array) \
$(perf_ioctl_array) \
$(prctl_option_array) \
$(usbdevfs_ioctl_array) \
$(x86_arch_prctl_code_array) \
$(rename_flags_array) \
$(arch_errno_name_array)
$(arch_errno_name_array) \
$(sync_file_range_arrays)
$(OUTPUT)%.o: %.c prepare FORCE
$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
@ -923,9 +958,13 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
$(OUTPUT)pmu-events/pmu-events.c \
$(OUTPUT)$(fadvise_advice_array) \
$(OUTPUT)$(fsconfig_arrays) \
$(OUTPUT)$(fsmount_arrays) \
$(OUTPUT)$(fspick_arrays) \
$(OUTPUT)$(madvise_behavior_array) \
$(OUTPUT)$(mmap_flags_array) \
$(OUTPUT)$(mount_flags_array) \
$(OUTPUT)$(move_mount_flags_array) \
$(OUTPUT)$(drm_ioctl_array) \
$(OUTPUT)$(pkey_alloc_access_rights_array) \
$(OUTPUT)$(sndrv_ctl_ioctl_array) \
@ -939,7 +978,8 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
$(OUTPUT)$(usbdevfs_ioctl_array) \
$(OUTPUT)$(x86_arch_prctl_code_array) \
$(OUTPUT)$(rename_flags_array) \
$(OUTPUT)$(arch_errno_name_array)
$(OUTPUT)$(arch_errno_name_array) \
$(OUTPUT)$(sync_file_range_arrays)
$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
#

310
tools/perf/arch/arm/util/cs-etm.c
View File

@ -22,6 +22,7 @@
#include "../../util/pmu.h"
#include "../../util/thread_map.h"
#include "../../util/cs-etm.h"
#include "../../util/util.h"
#include <errno.h>
#include <stdlib.h>
@ -31,12 +32,158 @@ struct cs_etm_recording {
struct auxtrace_record itr;
struct perf_pmu *cs_etm_pmu;
struct perf_evlist *evlist;
int wrapped_cnt;
bool *wrapped;
bool snapshot_mode;
size_t snapshot_size;
};
static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = {
[CS_ETM_ETMCCER] = "mgmt/etmccer",
[CS_ETM_ETMIDR] = "mgmt/etmidr",
};
static const char *metadata_etmv4_ro[CS_ETMV4_PRIV_MAX] = {
[CS_ETMV4_TRCIDR0] = "trcidr/trcidr0",
[CS_ETMV4_TRCIDR1] = "trcidr/trcidr1",
[CS_ETMV4_TRCIDR2] = "trcidr/trcidr2",
[CS_ETMV4_TRCIDR8] = "trcidr/trcidr8",
[CS_ETMV4_TRCAUTHSTATUS] = "mgmt/trcauthstatus",
};
static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu);
static int cs_etm_set_context_id(struct auxtrace_record *itr,
struct perf_evsel *evsel, int cpu)
{
struct cs_etm_recording *ptr;
struct perf_pmu *cs_etm_pmu;
char path[PATH_MAX];
int err = -EINVAL;
u32 val;
ptr = container_of(itr, struct cs_etm_recording, itr);
cs_etm_pmu = ptr->cs_etm_pmu;
if (!cs_etm_is_etmv4(itr, cpu))
goto out;
/* Get a handle on TRCIRD2 */
snprintf(path, PATH_MAX, "cpu%d/%s",
cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR2]);
err = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val);
/* There was a problem reading the file, bailing out */
if (err != 1) {
pr_err("%s: can't read file %s\n",
CORESIGHT_ETM_PMU_NAME, path);
goto out;
}
/*
* TRCIDR2.CIDSIZE, bit [9-5], indicates whether contextID tracing
* is supported:
* 0b00000 Context ID tracing is not supported.
* 0b00100 Maximum of 32-bit Context ID size.
* All other values are reserved.
*/
val = BMVAL(val, 5, 9);
if (!val || val != 0x4) {
err = -EINVAL;
goto out;
}
/* All good, let the kernel know */
evsel->attr.config |= (1 << ETM_OPT_CTXTID);
err = 0;
out:
return err;
}
static int cs_etm_set_timestamp(struct auxtrace_record *itr,
struct perf_evsel *evsel, int cpu)
{
struct cs_etm_recording *ptr;
struct perf_pmu *cs_etm_pmu;
char path[PATH_MAX];
int err = -EINVAL;
u32 val;
ptr = container_of(itr, struct cs_etm_recording, itr);
cs_etm_pmu = ptr->cs_etm_pmu;
if (!cs_etm_is_etmv4(itr, cpu))
goto out;
/* Get a handle on TRCIRD0 */
snprintf(path, PATH_MAX, "cpu%d/%s",
cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR0]);
err = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val);
/* There was a problem reading the file, bailing out */
if (err != 1) {
pr_err("%s: can't read file %s\n",
CORESIGHT_ETM_PMU_NAME, path);
goto out;
}
/*
* TRCIDR0.TSSIZE, bit [28-24], indicates whether global timestamping
* is supported:
* 0b00000 Global timestamping is not implemented
* 0b00110 Implementation supports a maximum timestamp of 48bits.
* 0b01000 Implementation supports a maximum timestamp of 64bits.
*/
val &= GENMASK(28, 24);
if (!val) {
err = -EINVAL;
goto out;
}
/* All good, let the kernel know */
evsel->attr.config |= (1 << ETM_OPT_TS);
err = 0;
out:
return err;
}
static int cs_etm_set_option(struct auxtrace_record *itr,
struct perf_evsel *evsel, u32 option)
{
int i, err = -EINVAL;
struct cpu_map *event_cpus = evsel->evlist->cpus;
struct cpu_map *online_cpus = cpu_map__new(NULL);
/* Set option of each CPU we have */
for (i = 0; i < cpu__max_cpu(); i++) {
if (!cpu_map__has(event_cpus, i) ||
!cpu_map__has(online_cpus, i))
continue;
if (option & ETM_OPT_CTXTID) {
err = cs_etm_set_context_id(itr, evsel, i);
if (err)
goto out;
}
if (option & ETM_OPT_TS) {
err = cs_etm_set_timestamp(itr, evsel, i);
if (err)
goto out;
}
if (option & ~(ETM_OPT_CTXTID | ETM_OPT_TS))
/* Nothing else is currently supported */
goto out;
}
err = 0;
out:
cpu_map__put(online_cpus);
return err;
}
static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr,
struct record_opts *opts,
const char *str)
@ -105,12 +252,16 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
container_of(itr, struct cs_etm_recording, itr);
struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
struct perf_evsel *evsel, *cs_etm_evsel = NULL;
const struct cpu_map *cpus = evlist->cpus;
struct cpu_map *cpus = evlist->cpus;
bool privileged = (geteuid() == 0 || perf_event_paranoid() < 0);
int err = 0;
ptr->evlist = evlist;
ptr->snapshot_mode = opts->auxtrace_snapshot_mode;
if (perf_can_record_switch_events())
opts->record_switch_events = true;
evlist__for_each_entry(evlist, evsel) {
if (evsel->attr.type == cs_etm_pmu->type) {
if (cs_etm_evsel) {
@ -241,19 +392,25 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
/*
* In the case of per-cpu mmaps, we need the CPU on the
* AUX event.
* AUX event. We also need the contextID in order to be notified
* when a context switch happened.
*/
if (!cpu_map__empty(cpus))
if (!cpu_map__empty(cpus)) {
perf_evsel__set_sample_bit(cs_etm_evsel, CPU);
err = cs_etm_set_option(itr, cs_etm_evsel,
ETM_OPT_CTXTID | ETM_OPT_TS);
if (err)
goto out;
}
/* Add dummy event to keep tracking */
if (opts->full_auxtrace) {
struct perf_evsel *tracking_evsel;
int err;
err = parse_events(evlist, "dummy:u", NULL);
if (err)
return err;
goto out;
tracking_evsel = perf_evlist__last(evlist);
perf_evlist__set_tracking_event(evlist, tracking_evsel);
@ -266,7 +423,8 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
perf_evsel__set_sample_bit(tracking_evsel, TIME);
}
return 0;
out:
return err;
}
static u64 cs_etm_get_config(struct auxtrace_record *itr)
@ -314,6 +472,8 @@ static u64 cs_etmv4_get_config(struct auxtrace_record *itr)
config_opts = cs_etm_get_config(itr);
if (config_opts & BIT(ETM_OPT_CYCACC))
config |= BIT(ETM4_CFG_BIT_CYCACC);
if (config_opts & BIT(ETM_OPT_CTXTID))
config |= BIT(ETM4_CFG_BIT_CTXTID);
if (config_opts & BIT(ETM_OPT_TS))
config |= BIT(ETM4_CFG_BIT_TS);
if (config_opts & BIT(ETM_OPT_RETSTK))
@ -363,19 +523,6 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
(etmv3 * CS_ETMV3_PRIV_SIZE));
}
static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = {
[CS_ETM_ETMCCER] = "mgmt/etmccer",
[CS_ETM_ETMIDR] = "mgmt/etmidr",
};
static const char *metadata_etmv4_ro[CS_ETMV4_PRIV_MAX] = {
[CS_ETMV4_TRCIDR0] = "trcidr/trcidr0",
[CS_ETMV4_TRCIDR1] = "trcidr/trcidr1",
[CS_ETMV4_TRCIDR2] = "trcidr/trcidr2",
[CS_ETMV4_TRCIDR8] = "trcidr/trcidr8",
[CS_ETMV4_TRCAUTHSTATUS] = "mgmt/trcauthstatus",
};
static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu)
{
bool ret = false;
@ -536,16 +683,131 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
return 0;
}
static int cs_etm_find_snapshot(struct auxtrace_record *itr __maybe_unused,
static int cs_etm_alloc_wrapped_array(struct cs_etm_recording *ptr, int idx)
{
bool *wrapped;
int cnt = ptr->wrapped_cnt;
/* Make @ptr->wrapped as big as @idx */
while (cnt <= idx)
cnt++;
/*
* Free'ed in cs_etm_recording_free(). Using realloc() to avoid
* cross compilation problems where the host's system supports
* reallocarray() but not the target.
*/
wrapped = realloc(ptr->wrapped, cnt * sizeof(bool));
if (!wrapped)
return -ENOMEM;
wrapped[cnt - 1] = false;
ptr->wrapped_cnt = cnt;
ptr->wrapped = wrapped;
return 0;
}
static bool cs_etm_buffer_has_wrapped(unsigned char *buffer,
size_t buffer_size, u64 head)
{
u64 i, watermark;
u64 *buf = (u64 *)buffer;
size_t buf_size = buffer_size;
/*
* We want to look the very last 512 byte (chosen arbitrarily) in
* the ring buffer.
*/
watermark = buf_size - 512;
/*
* @head is continuously increasing - if its value is equal or greater
* than the size of the ring buffer, it has wrapped around.
*/
if (head >= buffer_size)
return true;
/*
* The value of @head is somewhere within the size of the ring buffer.
* This can be that there hasn't been enough data to fill the ring
* buffer yet or the trace time was so long that @head has numerically
* wrapped around. To find we need to check if we have data at the very
* end of the ring buffer. We can reliably do this because mmap'ed
* pages are zeroed out and there is a fresh mapping with every new
* session.
*/
/* @head is less than 512 byte from the end of the ring buffer */
if (head > watermark)
watermark = head;
/*
* Speed things up by using 64 bit transactions (see "u64 *buf" above)
*/
watermark >>= 3;
buf_size >>= 3;
/*
* If we find trace data at the end of the ring buffer, @head has
* been there and has numerically wrapped around at least once.
*/
for (i = watermark; i < buf_size; i++)
if (buf[i])
return true;
return false;
}
static int cs_etm_find_snapshot(struct auxtrace_record *itr,
int idx, struct auxtrace_mmap *mm,
unsigned char *data __maybe_unused,
unsigned char *data,
u64 *head, u64 *old)
{
int err;
bool wrapped;
struct cs_etm_recording *ptr =
container_of(itr, struct cs_etm_recording, itr);
/*
* Allocate memory to keep track of wrapping if this is the first
* time we deal with this *mm.
*/
if (idx >= ptr->wrapped_cnt) {
err = cs_etm_alloc_wrapped_array(ptr, idx);
if (err)
return err;
}
/*
* Check to see if *head has wrapped around. If it hasn't only the
* amount of data between *head and *old is snapshot'ed to avoid
* bloating the perf.data file with zeros. But as soon as *head has
* wrapped around the entire size of the AUX ring buffer it taken.
*/
wrapped = ptr->wrapped[idx];
if (!wrapped && cs_etm_buffer_has_wrapped(data, mm->len, *head)) {
wrapped = true;
ptr->wrapped[idx] = true;
}
pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n",
__func__, idx, (size_t)*old, (size_t)*head, mm->len);
*old = *head;
*head += mm->len;
/* No wrap has occurred, we can just use *head and *old. */
if (!wrapped)
return 0;
/*
* *head has wrapped around - adjust *head and *old to pickup the
* entire content of the AUX buffer.
*/
if (*head >= mm->len) {
*old = *head - mm->len;
} else {
*head += mm->len;
*old = *head - mm->len;
}
return 0;
}
@ -586,6 +848,8 @@ static void cs_etm_recording_free(struct auxtrace_record *itr)
{
struct cs_etm_recording *ptr =
container_of(itr, struct cs_etm_recording, itr);
zfree(&ptr->wrapped);
free(ptr);
}

2
tools/perf/arch/arm64/Build
View File

@ -1,2 +1,2 @@
perf-y += util/
perf-$(CONFIG_DWARF_UNWIND) += tests/
perf-y += tests/

2
tools/perf/arch/arm64/tests/Build
View File

@ -1,4 +1,4 @@
perf-y += regs_load.o
perf-y += dwarf-unwind.o
perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
perf-y += arch-tests.o

48
tools/perf/arch/csky/annotate/instructions.c Normal file
View File

@ -0,0 +1,48 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd.
#include <linux/compiler.h>
static struct ins_ops *csky__associate_ins_ops(struct arch *arch,
const char *name)
{
struct ins_ops *ops = NULL;
/* catch all kind of jumps */
if (!strcmp(name, "bt") ||
!strcmp(name, "bf") ||
!strcmp(name, "bez") ||
!strcmp(name, "bnez") ||
!strcmp(name, "bnezad") ||
!strcmp(name, "bhsz") ||
!strcmp(name, "bhz") ||
!strcmp(name, "blsz") ||
!strcmp(name, "blz") ||
!strcmp(name, "br") ||
!strcmp(name, "jmpi") ||
!strcmp(name, "jmp"))
ops = &jump_ops;
/* catch function call */
if (!strcmp(name, "bsr") ||
!strcmp(name, "jsri") ||
!strcmp(name, "jsr"))
ops = &call_ops;
/* catch function return */
if (!strcmp(name, "rts"))
ops = &ret_ops;
if (ops)
arch__associate_ins_ops(arch, name, ops);
return ops;
}
static int csky__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
{
arch->initialized = true;
arch->objdump.comment_char = '/';
arch->associate_instruction_ops = csky__associate_ins_ops;
return 0;
}

2
tools/perf/arch/s390/util/header.c
View File

@ -11,7 +11,7 @@
#include <unistd.h>
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include <linux/ctype.h>
#include "../../util/header.h"
#include "../../util/util.h"

1
tools/perf/arch/x86/include/arch-tests.h
View File

@ -9,6 +9,7 @@ struct test;
int test__rdpmc(struct test *test __maybe_unused, int subtest);
int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest);
int test__insn_x86(struct test *test __maybe_unused, int subtest);
int test__intel_pt_pkt_decoder(struct test *test, int subtest);
int test__bp_modify(struct test *test, int subtest);
#ifdef HAVE_DWARF_UNWIND_SUPPORT

2
tools/perf/arch/x86/tests/Build
View File

@ -4,5 +4,5 @@ perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
perf-y += arch-tests.o
perf-y += rdpmc.o
perf-y += perf-time-to-tsc.o
perf-$(CONFIG_AUXTRACE) += insn-x86.o
perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-pkt-decoder-test.o
perf-$(CONFIG_X86_64) += bp-modify.o

4
tools/perf/arch/x86/tests/arch-tests.c
View File

@ -23,6 +23,10 @@ struct test arch_tests[] = {
.desc = "x86 instruction decoder - new instructions",
.func = test__insn_x86,
},
{
.desc = "Intel PT packet decoder",
.func = test__intel_pt_pkt_decoder,
},
#endif
#if defined(__x86_64__)
{

1
tools/perf/arch/x86/tests/intel-cqm.c
View File

@ -6,6 +6,7 @@
#include "evlist.h"
#include "evsel.h"
#include "arch-tests.h"
#include "util.h"
#include <signal.h>
#include <sys/mman.h>

304
tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c Normal file
View File

@ -0,0 +1,304 @@
// SPDX-License-Identifier: GPL-2.0
#include <string.h>
#include "intel-pt-decoder/intel-pt-pkt-decoder.h"
#include "debug.h"
#include "tests/tests.h"
#include "arch-tests.h"
/**
* struct test_data - Test data.
* @len: number of bytes to decode
* @bytes: bytes to decode
* @ctx: packet context to decode
* @packet: expected packet
* @new_ctx: expected new packet context
* @ctx_unchanged: the packet context must not change
*/
struct test_data {
int len;
u8 bytes[INTEL_PT_PKT_MAX_SZ];
enum intel_pt_pkt_ctx ctx;
struct intel_pt_pkt packet;
enum intel_pt_pkt_ctx new_ctx;
int ctx_unchanged;
} data[] = {
/* Padding Packet */
{1, {0}, 0, {INTEL_PT_PAD, 0, 0}, 0, 1 },
/* Short Taken/Not Taken Packet */
{1, {4}, 0, {INTEL_PT_TNT, 1, 0}, 0, 0 },
{1, {6}, 0, {INTEL_PT_TNT, 1, 0x20ULL << 58}, 0, 0 },
{1, {0x80}, 0, {INTEL_PT_TNT, 6, 0}, 0, 0 },
{1, {0xfe}, 0, {INTEL_PT_TNT, 6, 0x3fULL << 58}, 0, 0 },
/* Long Taken/Not Taken Packet */
{8, {0x02, 0xa3, 2}, 0, {INTEL_PT_TNT, 1, 0xa302ULL << 47}, 0, 0 },
{8, {0x02, 0xa3, 3}, 0, {INTEL_PT_TNT, 1, 0x1a302ULL << 47}, 0, 0 },
{8, {0x02, 0xa3, 0, 0, 0, 0, 0, 0x80}, 0, {INTEL_PT_TNT, 47, 0xa302ULL << 1}, 0, 0 },
{8, {0x02, 0xa3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff}, 0, {INTEL_PT_TNT, 47, 0xffffffffffffa302ULL << 1}, 0, 0 },
/* Target IP Packet */
{1, {0x0d}, 0, {INTEL_PT_TIP, 0, 0}, 0, 0 },
{3, {0x2d, 1, 2}, 0, {INTEL_PT_TIP, 1, 0x201}, 0, 0 },
{5, {0x4d, 1, 2, 3, 4}, 0, {INTEL_PT_TIP, 2, 0x4030201}, 0, 0 },
{7, {0x6d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP, 3, 0x60504030201}, 0, 0 },
{7, {0x8d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP, 4, 0x60504030201}, 0, 0 },
{9, {0xcd, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_TIP, 6, 0x807060504030201}, 0, 0 },
/* Packet Generation Enable */
{1, {0x11}, 0, {INTEL_PT_TIP_PGE, 0, 0}, 0, 0 },
{3, {0x31, 1, 2}, 0, {INTEL_PT_TIP_PGE, 1, 0x201}, 0, 0 },
{5, {0x51, 1, 2, 3, 4}, 0, {INTEL_PT_TIP_PGE, 2, 0x4030201}, 0, 0 },
{7, {0x71, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGE, 3, 0x60504030201}, 0, 0 },
{7, {0x91, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGE, 4, 0x60504030201}, 0, 0 },
{9, {0xd1, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_TIP_PGE, 6, 0x807060504030201}, 0, 0 },
/* Packet Generation Disable */
{1, {0x01}, 0, {INTEL_PT_TIP_PGD, 0, 0}, 0, 0 },
{3, {0x21, 1, 2}, 0, {INTEL_PT_TIP_PGD, 1, 0x201}, 0, 0 },
{5, {0x41, 1, 2, 3, 4}, 0, {INTEL_PT_TIP_PGD, 2, 0x4030201}, 0, 0 },
{7, {0x61, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGD, 3, 0x60504030201}, 0, 0 },
{7, {0x81, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGD, 4, 0x60504030201}, 0, 0 },
{9, {0xc1, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_TIP_PGD, 6, 0x807060504030201}, 0, 0 },
/* Flow Update Packet */
{1, {0x1d}, 0, {INTEL_PT_FUP, 0, 0}, 0, 0 },
{3, {0x3d, 1, 2}, 0, {INTEL_PT_FUP, 1, 0x201}, 0, 0 },
{5, {0x5d, 1, 2, 3, 4}, 0, {INTEL_PT_FUP, 2, 0x4030201}, 0, 0 },
{7, {0x7d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_FUP, 3, 0x60504030201}, 0, 0 },
{7, {0x9d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_FUP, 4, 0x60504030201}, 0, 0 },
{9, {0xdd, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_FUP, 6, 0x807060504030201}, 0, 0 },
/* Paging Information Packet */
{8, {0x02, 0x43, 2, 4, 6, 8, 10, 12}, 0, {INTEL_PT_PIP, 0, 0x60504030201}, 0, 0 },
{8, {0x02, 0x43, 3, 4, 6, 8, 10, 12}, 0, {INTEL_PT_PIP, 0, 0x60504030201 | (1ULL << 63)}, 0, 0 },
/* Mode Exec Packet */
{2, {0x99, 0x00}, 0, {INTEL_PT_MODE_EXEC, 0, 16}, 0, 0 },
{2, {0x99, 0x01}, 0, {INTEL_PT_MODE_EXEC, 0, 64}, 0, 0 },
{2, {0x99, 0x02}, 0, {INTEL_PT_MODE_EXEC, 0, 32}, 0, 0 },
/* Mode TSX Packet */
{2, {0x99, 0x20}, 0, {INTEL_PT_MODE_TSX, 0, 0}, 0, 0 },
{2, {0x99, 0x21}, 0, {INTEL_PT_MODE_TSX, 0, 1}, 0, 0 },
{2, {0x99, 0x22}, 0, {INTEL_PT_MODE_TSX, 0, 2}, 0, 0 },
/* Trace Stop Packet */
{2, {0x02, 0x83}, 0, {INTEL_PT_TRACESTOP, 0, 0}, 0, 0 },
/* Core:Bus Ratio Packet */
{4, {0x02, 0x03, 0x12, 0}, 0, {INTEL_PT_CBR, 0, 0x12}, 0, 1 },
/* Timestamp Counter Packet */
{8, {0x19, 1, 2, 3, 4, 5, 6, 7}, 0, {INTEL_PT_TSC, 0, 0x7060504030201}, 0, 1 },
/* Mini Time Counter Packet */
{2, {0x59, 0x12}, 0, {INTEL_PT_MTC, 0, 0x12}, 0, 1 },
/* TSC / MTC Alignment Packet */
{7, {0x02, 0x73}, 0, {INTEL_PT_TMA, 0, 0}, 0, 1 },
{7, {0x02, 0x73, 1, 2}, 0, {INTEL_PT_TMA, 0, 0x201}, 0, 1 },
{7, {0x02, 0x73, 0, 0, 0, 0xff, 1}, 0, {INTEL_PT_TMA, 0x1ff, 0}, 0, 1 },
{7, {0x02, 0x73, 0x80, 0xc0, 0, 0xff, 1}, 0, {INTEL_PT_TMA, 0x1ff, 0xc080}, 0, 1 },
/* Cycle Count Packet */
{1, {0x03}, 0, {INTEL_PT_CYC, 0, 0}, 0, 1 },
{1, {0x0b}, 0, {INTEL_PT_CYC, 0, 1}, 0, 1 },
{1, {0xfb}, 0, {INTEL_PT_CYC, 0, 0x1f}, 0, 1 },
{2, {0x07, 2}, 0, {INTEL_PT_CYC, 0, 0x20}, 0, 1 },
{2, {0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0xfff}, 0, 1 },
{3, {0x07, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x1000}, 0, 1 },
{3, {0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x7ffff}, 0, 1 },
{4, {0x07, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x80000}, 0, 1 },
{4, {0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x3ffffff}, 0, 1 },
{5, {0x07, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x4000000}, 0, 1 },
{5, {0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x1ffffffff}, 0, 1 },
{6, {0x07, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x200000000}, 0, 1 },
{6, {0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0xffffffffff}, 0, 1 },
{7, {0x07, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x10000000000}, 0, 1 },
{7, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x7fffffffffff}, 0, 1 },
{8, {0x07, 1, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x800000000000}, 0, 1 },
{8, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x3fffffffffffff}, 0, 1 },
{9, {0x07, 1, 1, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x40000000000000}, 0, 1 },
{9, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x1fffffffffffffff}, 0, 1 },
{10, {0x07, 1, 1, 1, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x2000000000000000}, 0, 1 },
{10, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xe}, 0, {INTEL_PT_CYC, 0, 0xffffffffffffffff}, 0, 1 },
/* Virtual-Machine Control Structure Packet */
{7, {0x02, 0xc8, 1, 2, 3, 4, 5}, 0, {INTEL_PT_VMCS, 5, 0x504030201}, 0, 0 },
/* Overflow Packet */
{2, {0x02, 0xf3}, 0, {INTEL_PT_OVF, 0, 0}, 0, 0 },
{2, {0x02, 0xf3}, INTEL_PT_BLK_4_CTX, {INTEL_PT_OVF, 0, 0}, 0, 0 },
{2, {0x02, 0xf3}, INTEL_PT_BLK_8_CTX, {INTEL_PT_OVF, 0, 0}, 0, 0 },
/* Packet Stream Boundary*/
{16, {0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82}, 0, {INTEL_PT_PSB, 0, 0}, 0, 0 },
{16, {0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82}, INTEL_PT_BLK_4_CTX, {INTEL_PT_PSB, 0, 0}, 0, 0 },
{16, {0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82}, INTEL_PT_BLK_8_CTX, {INTEL_PT_PSB, 0, 0}, 0, 0 },
/* PSB End Packet */
{2, {0x02, 0x23}, 0, {INTEL_PT_PSBEND, 0, 0}, 0, 0 },
/* Maintenance Packet */
{11, {0x02, 0xc3, 0x88, 1, 2, 3, 4, 5, 6, 7}, 0, {INTEL_PT_MNT, 0, 0x7060504030201}, 0, 1 },
/* Write Data to PT Packet */
{6, {0x02, 0x12, 1, 2, 3, 4}, 0, {INTEL_PT_PTWRITE, 0, 0x4030201}, 0, 0 },
{10, {0x02, 0x32, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_PTWRITE, 1, 0x807060504030201}, 0, 0 },
{6, {0x02, 0x92, 1, 2, 3, 4}, 0, {INTEL_PT_PTWRITE_IP, 0, 0x4030201}, 0, 0 },
{10, {0x02, 0xb2, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_PTWRITE_IP, 1, 0x807060504030201}, 0, 0 },
/* Execution Stop Packet */
{2, {0x02, 0x62}, 0, {INTEL_PT_EXSTOP, 0, 0}, 0, 1 },
{2, {0x02, 0xe2}, 0, {INTEL_PT_EXSTOP_IP, 0, 0}, 0, 1 },
/* Monitor Wait Packet */
{10, {0x02, 0xc2}, 0, {INTEL_PT_MWAIT, 0, 0}, 0, 0 },
{10, {0x02, 0xc2, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_MWAIT, 0, 0x807060504030201}, 0, 0 },
{10, {0x02, 0xc2, 0xff, 2, 3, 4, 7, 6, 7, 8}, 0, {INTEL_PT_MWAIT, 0, 0x8070607040302ff}, 0, 0 },
/* Power Entry Packet */
{4, {0x02, 0x22}, 0, {INTEL_PT_PWRE, 0, 0}, 0, 1 },
{4, {0x02, 0x22, 1, 2}, 0, {INTEL_PT_PWRE, 0, 0x0201}, 0, 1 },
{4, {0x02, 0x22, 0x80, 0x34}, 0, {INTEL_PT_PWRE, 0, 0x3480}, 0, 1 },
{4, {0x02, 0x22, 0x00, 0x56}, 0, {INTEL_PT_PWRE, 0, 0x5600}, 0, 1 },
/* Power Exit Packet */
{7, {0x02, 0xa2}, 0, {INTEL_PT_PWRX, 0, 0}, 0, 1 },
{7, {0x02, 0xa2, 1, 2, 3, 4, 5}, 0, {INTEL_PT_PWRX, 0, 0x504030201}, 0, 1 },
{7, {0x02, 0xa2, 0xff, 0xff, 0xff, 0xff, 0xff}, 0, {INTEL_PT_PWRX, 0, 0xffffffffff}, 0, 1 },
/* Block Begin Packet */
{3, {0x02, 0x63, 0x00}, 0, {INTEL_PT_BBP, 0, 0}, INTEL_PT_BLK_8_CTX, 0 },
{3, {0x02, 0x63, 0x80}, 0, {INTEL_PT_BBP, 1, 0}, INTEL_PT_BLK_4_CTX, 0 },
{3, {0x02, 0x63, 0x1f}, 0, {INTEL_PT_BBP, 0, 0x1f}, INTEL_PT_BLK_8_CTX, 0 },
{3, {0x02, 0x63, 0x9f}, 0, {INTEL_PT_BBP, 1, 0x1f}, INTEL_PT_BLK_4_CTX, 0 },
/* 4-byte Block Item Packet */
{5, {0x04}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0, 0}, INTEL_PT_BLK_4_CTX, 0 },
{5, {0xfc}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0x1f, 0}, INTEL_PT_BLK_4_CTX, 0 },
{5, {0x04, 1, 2, 3, 4}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0, 0x04030201}, INTEL_PT_BLK_4_CTX, 0 },
{5, {0xfc, 1, 2, 3, 4}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0x1f, 0x04030201}, INTEL_PT_BLK_4_CTX, 0 },
/* 8-byte Block Item Packet */
{9, {0x04}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0, 0}, INTEL_PT_BLK_8_CTX, 0 },
{9, {0xfc}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0x1f, 0}, INTEL_PT_BLK_8_CTX, 0 },
{9, {0x04, 1, 2, 3, 4, 5, 6, 7, 8}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0, 0x0807060504030201}, INTEL_PT_BLK_8_CTX, 0 },
{9, {0xfc, 1, 2, 3, 4, 5, 6, 7, 8}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0x1f, 0x0807060504030201}, INTEL_PT_BLK_8_CTX, 0 },
/* Block End Packet */
{2, {0x02, 0x33}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BEP, 0, 0}, 0, 0 },
{2, {0x02, 0xb3}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BEP_IP, 0, 0}, 0, 0 },
{2, {0x02, 0x33}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BEP, 0, 0}, 0, 0 },
{2, {0x02, 0xb3}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BEP_IP, 0, 0}, 0, 0 },
/* Terminator */
{0, {0}, 0, {0, 0, 0}, 0, 0 },
};
static int dump_packet(struct intel_pt_pkt *packet, u8 *bytes, int len)
{
char desc[INTEL_PT_PKT_DESC_MAX];
int ret, i;
for (i = 0; i < len; i++)
pr_debug(" %02x", bytes[i]);
for (; i < INTEL_PT_PKT_MAX_SZ; i++)
pr_debug(" ");
pr_debug(" ");
ret = intel_pt_pkt_desc(packet, desc, INTEL_PT_PKT_DESC_MAX);
if (ret < 0) {
pr_debug("intel_pt_pkt_desc failed!\n");
return TEST_FAIL;
}
pr_debug("%s\n", desc);
return TEST_OK;
}
static void decoding_failed(struct test_data *d)
{
pr_debug("Decoding failed!\n");
pr_debug("Decoding: ");
dump_packet(&d->packet, d->bytes, d->len);
}
static int fail(struct test_data *d, struct intel_pt_pkt *packet, int len,
enum intel_pt_pkt_ctx new_ctx)
{
decoding_failed(d);
if (len != d->len)
pr_debug("Expected length: %d Decoded length %d\n",
d->len, len);
if (packet->type != d->packet.type)
pr_debug("Expected type: %d Decoded type %d\n",
d->packet.type, packet->type);
if (packet->count != d->packet.count)
pr_debug("Expected count: %d Decoded count %d\n",
d->packet.count, packet->count);
if (packet->payload != d->packet.payload)
pr_debug("Expected payload: 0x%llx Decoded payload 0x%llx\n",
(unsigned long long)d->packet.payload,
(unsigned long long)packet->payload);
if (new_ctx != d->new_ctx)
pr_debug("Expected packet context: %d Decoded packet context %d\n",
d->new_ctx, new_ctx);
return TEST_FAIL;
}
static int test_ctx_unchanged(struct test_data *d, struct intel_pt_pkt *packet,
enum intel_pt_pkt_ctx ctx)
{
enum intel_pt_pkt_ctx old_ctx = ctx;
intel_pt_upd_pkt_ctx(packet, &ctx);
if (ctx != old_ctx) {
decoding_failed(d);
pr_debug("Packet context changed!\n");
return TEST_FAIL;
}
return TEST_OK;
}
static int test_one(struct test_data *d)
{
struct intel_pt_pkt packet;
enum intel_pt_pkt_ctx ctx = d->ctx;
int ret;
memset(&packet, 0xff, sizeof(packet));
/* Decode a packet */
ret = intel_pt_get_packet(d->bytes, d->len, &packet, &ctx);
if (ret < 0 || ret > INTEL_PT_PKT_MAX_SZ) {
decoding_failed(d);
pr_debug("intel_pt_get_packet returned %d\n", ret);
return TEST_FAIL;
}
/* Some packets must always leave the packet context unchanged */
if (d->ctx_unchanged) {
int err;
err = test_ctx_unchanged(d, &packet, INTEL_PT_NO_CTX);
if (err)
return err;
err = test_ctx_unchanged(d, &packet, INTEL_PT_BLK_4_CTX);
if (err)
return err;
err = test_ctx_unchanged(d, &packet, INTEL_PT_BLK_8_CTX);
if (err)
return err;
}
/* Compare to the expected values */
if (ret != d->len || packet.type != d->packet.type ||
packet.count != d->packet.count ||
packet.payload != d->packet.payload || ctx != d->new_ctx)
return fail(d, &packet, ret, ctx);
pr_debug("Decoded ok:");
ret = dump_packet(&d->packet, d->bytes, d->len);
return ret;
}
/*
* This test feeds byte sequences to the Intel PT packet decoder and checks the
* results. Changes to the packet context are also checked.
*/
int test__intel_pt_pkt_decoder(struct test *test __maybe_unused, int subtest __maybe_unused)
{
struct test_data *d = data;
int ret;
for (d = data; d->len; d++) {
ret = test_one(d);
if (ret)
return ret;
}
return TEST_OK;
}

1
tools/perf/arch/x86/util/intel-pt.c
View File

@ -25,6 +25,7 @@
#include "../../util/auxtrace.h"
#include "../../util/tsc.h"
#include "../../util/intel-pt.h"
#include "../../util/util.h"
#define KiB(x) ((x) * 1024)
#define MiB(x) ((x) * 1024 * 1024)

3
tools/perf/arch/x86/util/machine.c
View File

@ -3,10 +3,11 @@
#include <linux/string.h>
#include <stdlib.h>
#include "../../util/util.h"
#include "../../util/machine.h"
#include "../../util/map.h"
#include "../../util/symbol.h"
#include "../../util/sane_ctype.h"
#include <linux/ctype.h>
#include <symbol/kallsyms.h>

382
tools/perf/builtin-diff.c
View File

@ -20,6 +20,8 @@
#include "util/data.h"
#include "util/config.h"
#include "util/time-utils.h"
#include "util/annotate.h"
#include "util/map.h"
#include <errno.h>
#include <inttypes.h>
@ -32,6 +34,7 @@ struct perf_diff {
struct perf_time_interval *ptime_range;
int range_size;
int range_num;
bool has_br_stack;
};
/* Diff command specific HPP columns. */
@ -44,6 +47,7 @@ enum {
PERF_HPP_DIFF__WEIGHTED_DIFF,
PERF_HPP_DIFF__FORMULA,
PERF_HPP_DIFF__DELTA_ABS,
PERF_HPP_DIFF__CYCLES,
PERF_HPP_DIFF__MAX_INDEX
};
@ -86,11 +90,14 @@ static s64 compute_wdiff_w2;
static const char *cpu_list;
static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
static struct addr_location dummy_al;
enum {
COMPUTE_DELTA,
COMPUTE_RATIO,
COMPUTE_WEIGHTED_DIFF,
COMPUTE_DELTA_ABS,
COMPUTE_CYCLES,
COMPUTE_MAX,
};
@ -99,6 +106,7 @@ const char *compute_names[COMPUTE_MAX] = {
[COMPUTE_DELTA_ABS] = "delta-abs",
[COMPUTE_RATIO] = "ratio",
[COMPUTE_WEIGHTED_DIFF] = "wdiff",
[COMPUTE_CYCLES] = "cycles",
};
static int compute = COMPUTE_DELTA_ABS;
@ -108,6 +116,7 @@ static int compute_2_hpp[COMPUTE_MAX] = {
[COMPUTE_DELTA_ABS] = PERF_HPP_DIFF__DELTA_ABS,
[COMPUTE_RATIO] = PERF_HPP_DIFF__RATIO,
[COMPUTE_WEIGHTED_DIFF] = PERF_HPP_DIFF__WEIGHTED_DIFF,
[COMPUTE_CYCLES] = PERF_HPP_DIFF__CYCLES,
};
#define MAX_COL_WIDTH 70
@ -146,6 +155,10 @@ static struct header_column {
[PERF_HPP_DIFF__FORMULA] = {
.name = "Formula",
.width = MAX_COL_WIDTH,
},
[PERF_HPP_DIFF__CYCLES] = {
.name = "[Program Block Range] Cycles Diff",
.width = 70,
}
};
@ -335,6 +348,31 @@ static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair,
return -1;
}
static void *block_hist_zalloc(size_t size)
{
struct block_hist *bh;
bh = zalloc(size + sizeof(*bh));
if (!bh)
return NULL;
return &bh->he;
}
static void block_hist_free(void *he)
{
struct block_hist *bh;
bh = container_of(he, struct block_hist, he);
hists__delete_entries(&bh->block_hists);
free(bh);
}
struct hist_entry_ops block_hist_ops = {
.new = block_hist_zalloc,
.free = block_hist_free,
};
static int diff__process_sample_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
@ -362,9 +400,22 @@ static int diff__process_sample_event(struct perf_tool *tool,
goto out_put;
}
if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample, true)) {
pr_warning("problem incrementing symbol period, skipping event\n");
goto out_put;
if (compute != COMPUTE_CYCLES) {
if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample,
true)) {
pr_warning("problem incrementing symbol period, "
"skipping event\n");
goto out_put;
}
} else {
if (!hists__add_entry_ops(hists, &block_hist_ops, &al, NULL,
NULL, NULL, sample, true)) {
pr_warning("problem incrementing symbol period, "
"skipping event\n");
goto out_put;
}
hist__account_cycles(sample->branch_stack, &al, sample, false);
}
/*
@ -474,6 +525,203 @@ static void hists__baseline_only(struct hists *hists)
}
}
static int64_t block_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left, struct hist_entry *right)
{
struct block_info *bi_l = left->block_info;
struct block_info *bi_r = right->block_info;
int cmp;
if (!bi_l->sym || !bi_r->sym) {
if (!bi_l->sym && !bi_r->sym)
return 0;
else if (!bi_l->sym)
return -1;
else
return 1;
}
if (bi_l->sym == bi_r->sym) {
if (bi_l->start == bi_r->start) {
if (bi_l->end == bi_r->end)
return 0;
else
return (int64_t)(bi_r->end - bi_l->end);
} else
return (int64_t)(bi_r->start - bi_l->start);
} else {
cmp = strcmp(bi_l->sym->name, bi_r->sym->name);
return cmp;
}
if (bi_l->sym->start != bi_r->sym->start)
return (int64_t)(bi_r->sym->start - bi_l->sym->start);
return (int64_t)(bi_r->sym->end - bi_l->sym->end);
}
static int64_t block_cycles_diff_cmp(struct hist_entry *left,
struct hist_entry *right)
{
bool pairs_left = hist_entry__has_pairs(left);
bool pairs_right = hist_entry__has_pairs(right);
s64 l, r;
if (!pairs_left && !pairs_right)
return 0;
l = labs(left->diff.cycles);
r = labs(right->diff.cycles);
return r - l;
}
static int64_t block_sort(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left, struct hist_entry *right)
{
return block_cycles_diff_cmp(right, left);
}
static void init_block_hist(struct block_hist *bh)
{
__hists__init(&bh->block_hists, &bh->block_list);
perf_hpp_list__init(&bh->block_list);
INIT_LIST_HEAD(&bh->block_fmt.list);
INIT_LIST_HEAD(&bh->block_fmt.sort_list);
bh->block_fmt.cmp = block_cmp;
bh->block_fmt.sort = block_sort;
perf_hpp_list__register_sort_field(&bh->block_list,
&bh->block_fmt);
bh->valid = true;
}
static void init_block_info(struct block_info *bi, struct symbol *sym,
struct cyc_hist *ch, int offset)
{
bi->sym = sym;
bi->start = ch->start;
bi->end = offset;
bi->cycles = ch->cycles;
bi->cycles_aggr = ch->cycles_aggr;
bi->num = ch->num;
bi->num_aggr = ch->num_aggr;
}
static int process_block_per_sym(struct hist_entry *he)
{
struct annotation *notes;
struct cyc_hist *ch;
struct block_hist *bh;
if (!he->ms.map || !he->ms.sym)
return 0;
notes = symbol__annotation(he->ms.sym);
if (!notes || !notes->src || !notes->src->cycles_hist)
return 0;
bh = container_of(he, struct block_hist, he);
init_block_hist(bh);
ch = notes->src->cycles_hist;
for (unsigned int i = 0; i < symbol__size(he->ms.sym); i++) {
if (ch[i].num_aggr) {
struct block_info *bi;
struct hist_entry *he_block;
bi = block_info__new();
if (!bi)
return -1;
init_block_info(bi, he->ms.sym, &ch[i], i);
he_block = hists__add_entry_block(&bh->block_hists,
&dummy_al, bi);
if (!he_block) {
block_info__put(bi);
return -1;
}
}
}
return 0;
}
static int block_pair_cmp(struct hist_entry *a, struct hist_entry *b)
{
struct block_info *bi_a = a->block_info;
struct block_info *bi_b = b->block_info;
int cmp;
if (!bi_a->sym || !bi_b->sym)
return -1;
cmp = strcmp(bi_a->sym->name, bi_b->sym->name);
if ((!cmp) && (bi_a->start == bi_b->start) && (bi_a->end == bi_b->end))
return 0;
return -1;
}
static struct hist_entry *get_block_pair(struct hist_entry *he,
struct hists *hists_pair)
{
struct rb_root_cached *root = hists_pair->entries_in;
struct rb_node *next = rb_first_cached(root);
int cmp;
while (next != NULL) {
struct hist_entry *he_pair = rb_entry(next, struct hist_entry,
rb_node_in);
next = rb_next(&he_pair->rb_node_in);
cmp = block_pair_cmp(he_pair, he);
if (!cmp)
return he_pair;
}
return NULL;
}
static void compute_cycles_diff(struct hist_entry *he,
struct hist_entry *pair)
{
pair->diff.computed = true;
if (pair->block_info->num && he->block_info->num) {
pair->diff.cycles =
pair->block_info->cycles_aggr / pair->block_info->num_aggr -
he->block_info->cycles_aggr / he->block_info->num_aggr;
}
}
static void block_hists_match(struct hists *hists_base,
struct hists *hists_pair)
{
struct rb_root_cached *root = hists_base->entries_in;
struct rb_node *next = rb_first_cached(root);
while (next != NULL) {
struct hist_entry *he = rb_entry(next, struct hist_entry,
rb_node_in);
struct hist_entry *pair = get_block_pair(he, hists_pair);
next = rb_next(&he->rb_node_in);
if (pair) {
hist_entry__add_pair(pair, he);
compute_cycles_diff(he, pair);
}
}
}
static int filter_cb(struct hist_entry *he, void *arg __maybe_unused)
{
/* Skip the calculation of column length in output_resort */
he->filtered = true;
return 0;
}
static void hists__precompute(struct hists *hists)
{
struct rb_root_cached *root;
@ -486,6 +734,7 @@ static void hists__precompute(struct hists *hists)
next = rb_first_cached(root);
while (next != NULL) {
struct block_hist *bh, *pair_bh;
struct hist_entry *he, *pair;
struct data__file *d;
int i;
@ -493,6 +742,9 @@ static void hists__precompute(struct hists *hists)
he = rb_entry(next, struct hist_entry, rb_node_in);
next = rb_next(&he->rb_node_in);
if (compute == COMPUTE_CYCLES)
process_block_per_sym(he);
data__for_each_file_new(i, d) {
pair = get_pair_data(he, d);
if (!pair)
@ -509,6 +761,19 @@ static void hists__precompute(struct hists *hists)
case COMPUTE_WEIGHTED_DIFF:
compute_wdiff(he, pair);
break;
case COMPUTE_CYCLES:
process_block_per_sym(pair);
bh = container_of(he, struct block_hist, he);
pair_bh = container_of(pair, struct block_hist,
he);
if (bh->valid && pair_bh->valid) {
block_hists_match(&bh->block_hists,
&pair_bh->block_hists);
hists__output_resort_cb(&pair_bh->block_hists,
NULL, filter_cb);
}
break;
default:
BUG_ON(1);
}
@ -720,6 +985,9 @@ static void hists__process(struct hists *hists)
hists__precompute(hists);
hists__output_resort(hists, NULL);
if (compute == COMPUTE_CYCLES)
symbol_conf.report_block = true;
hists__fprintf(hists, !quiet, 0, 0, 0, stdout,
!symbol_conf.use_callchain);
}
@ -873,6 +1141,31 @@ static int parse_time_str(struct data__file *d, char *abstime_ostr,
return ret;
}
static int check_file_brstack(void)
{
struct data__file *d;
bool has_br_stack;
int i;
data__for_each_file(i, d) {
d->session = perf_session__new(&d->data, false, &pdiff.tool);
if (!d->session) {
pr_err("Failed to open %s\n", d->data.path);
return -1;
}
has_br_stack = perf_header__has_feat(&d->session->header,
HEADER_BRANCH_STACK);
perf_session__delete(d->session);
if (!has_br_stack)
return 0;
}
/* Set only all files having branch stacks */
pdiff.has_br_stack = true;
return 0;
}
static int __cmd_diff(void)
{
struct data__file *d;
@ -950,7 +1243,7 @@ static const struct option options[] = {
OPT_BOOLEAN('b', "baseline-only", &show_baseline_only,
"Show only items with match in baseline"),
OPT_CALLBACK('c', "compute", &compute,
"delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs)",
"delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs),cycles",
"Entries differential computation selection",
setup_compute),
OPT_BOOLEAN('p', "period", &show_period,
@ -1028,6 +1321,49 @@ static int hpp__entry_baseline(struct hist_entry *he, char *buf, size_t size)
return ret;
}
static int cycles_printf(struct hist_entry *he, struct hist_entry *pair,
struct perf_hpp *hpp, int width)
{
struct block_hist *bh = container_of(he, struct block_hist, he);
struct block_hist *bh_pair = container_of(pair, struct block_hist, he);
struct hist_entry *block_he;
struct block_info *bi;
char buf[128];
char *start_line, *end_line;
block_he = hists__get_entry(&bh_pair->block_hists, bh->block_idx);
if (!block_he) {
hpp->skip = true;
return 0;
}
/*
* Avoid printing the warning "addr2line_init failed for ..."
*/
symbol_conf.disable_add2line_warn = true;
bi = block_he->block_info;
start_line = map__srcline(he->ms.map, bi->sym->start + bi->start,
he->ms.sym);
end_line = map__srcline(he->ms.map, bi->sym->start + bi->end,
he->ms.sym);
if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) {
scnprintf(buf, sizeof(buf), "[%s -> %s] %4ld",
start_line, end_line, block_he->diff.cycles);
} else {
scnprintf(buf, sizeof(buf), "[%7lx -> %7lx] %4ld",
bi->start, bi->end, block_he->diff.cycles);
}
free_srcline(start_line);
free_srcline(end_line);
return scnprintf(hpp->buf, hpp->size, "%*s", width, buf);
}
static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
struct perf_hpp *hpp, struct hist_entry *he,
int comparison_method)
@ -1039,8 +1375,17 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
s64 wdiff;
char pfmt[20] = " ";
if (!pair)
if (!pair) {
if (comparison_method == COMPUTE_CYCLES) {
struct block_hist *bh;
bh = container_of(he, struct block_hist, he);
if (bh->block_idx)
hpp->skip = true;
}
goto no_print;
}
switch (comparison_method) {
case COMPUTE_DELTA:
@ -1075,6 +1420,8 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
return color_snprintf(hpp->buf, hpp->size,
get_percent_color(wdiff),
pfmt, wdiff);
case COMPUTE_CYCLES:
return cycles_printf(he, pair, hpp, dfmt->header_width);
default:
BUG_ON(1);
}
@ -1104,6 +1451,12 @@ static int hpp__color_wdiff(struct perf_hpp_fmt *fmt,
return __hpp__color_compare(fmt, hpp, he, COMPUTE_WEIGHTED_DIFF);
}
static int hpp__color_cycles(struct perf_hpp_fmt *fmt,
struct perf_hpp *hpp, struct hist_entry *he)
{
return __hpp__color_compare(fmt, hpp, he, COMPUTE_CYCLES);
}
static void
hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
{
@ -1305,6 +1658,10 @@ static void data__hpp_register(struct data__file *d, int idx)
fmt->color = hpp__color_delta;
fmt->sort = hist_entry__cmp_delta_abs;
break;
case PERF_HPP_DIFF__CYCLES:
fmt->color = hpp__color_cycles;
fmt->sort = hist_entry__cmp_nop;
break;
default:
fmt->sort = hist_entry__cmp_nop;
break;
@ -1385,6 +1742,13 @@ static int ui_init(void)
case COMPUTE_DELTA_ABS:
fmt->sort = hist_entry__cmp_delta_abs_idx;
break;
case COMPUTE_CYCLES:
/*
* Should set since 'fmt->sort' is called without
* checking valid during sorting
*/
fmt->sort = hist_entry__cmp_nop;
break;
default:
BUG_ON(1);
}
@ -1481,12 +1845,20 @@ int cmd_diff(int argc, const char **argv)
if (quiet)
perf_quiet_option();
symbol__annotation_init();
if (symbol__init(NULL) < 0)
return -1;
if (data_init(argc, argv) < 0)
return -1;
if (check_file_brstack() < 0)
return -1;
if (compute == COMPUTE_CYCLES && !pdiff.has_br_stack)
return -1;
if (ui_init() < 0)
return -1;

3
tools/perf/builtin-kmem.c
View File

@ -21,6 +21,7 @@
#include "util/cpumap.h"
#include "util/debug.h"
#include "util/string2.h"
#include <linux/kernel.h>
#include <linux/rbtree.h>
@ -30,7 +31,7 @@
#include <locale.h>
#include <regex.h>
#include "sane_ctype.h"
#include <linux/ctype.h>
static int kmem_slab;
static int kmem_page;

4
tools/perf/builtin-record.c
View File

@ -2191,6 +2191,10 @@ static struct option __record_options[] = {
OPT_BOOLEAN_FLAG(0, "all-user", &record.opts.all_user,
"Configure all used events to run in user space.",
PARSE_OPT_EXCLUSIVE),
OPT_BOOLEAN(0, "kernel-callchains", &record.opts.kernel_callchains,
"collect kernel callchains"),
OPT_BOOLEAN(0, "user-callchains", &record.opts.user_callchains,
"collect user callchains"),
OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path",
"clang binary to use for compiling BPF scriptlets"),
OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options",

13
tools/perf/builtin-report.c
View File

@ -47,7 +47,7 @@
#include <errno.h>
#include <inttypes.h>
#include <regex.h>
#include "sane_ctype.h"
#include <linux/ctype.h>
#include <signal.h>
#include <linux/bitmap.h>
#include <linux/stringify.h>
@ -941,8 +941,7 @@ parse_time_quantum(const struct option *opt, const char *arg,
pr_err("time quantum cannot be 0");
return -1;
}
while (isspace(*end))
end++;
end = skip_spaces(end);
if (*end == 0)
return 0;
if (!strcmp(end, "s")) {
@ -1428,6 +1427,10 @@ repeat:
&report.range_num);
if (ret < 0)
goto error;
itrace_synth_opts__set_time_range(&itrace_synth_opts,
report.ptime_range,
report.range_num);
}
if (session->tevent.pevent &&
@ -1449,8 +1452,10 @@ repeat:
ret = 0;
error:
if (report.ptime_range)
if (report.ptime_range) {
itrace_synth_opts__clear_time_range(&itrace_synth_opts);
zfree(&report.ptime_range);
}
zstd_fini(&(session->zstd_data));
perf_session__delete(session);
return ret;

3
tools/perf/builtin-sched.c
View File

@ -15,6 +15,7 @@
#include "util/thread_map.h"
#include "util/color.h"
#include "util/stat.h"
#include "util/string2.h"
#include "util/callchain.h"
#include "util/time-utils.h"
@ -36,7 +37,7 @@
#include <api/fs/fs.h>
#include <linux/time64.h>
#include "sane_ctype.h"
#include <linux/ctype.h>
#define PR_SET_NAME 15 /* Set process name */
#define MAX_CPUS 4096

107
tools/perf/builtin-script.c
View File

@ -49,7 +49,7 @@
#include <unistd.h>
#include <subcmd/pager.h>
#include "sane_ctype.h"
#include <linux/ctype.h>
static char const *script_name;
static char const *generate_script_lang;
@ -102,6 +102,7 @@ enum perf_output_field {
PERF_OUTPUT_METRIC = 1U << 28,
PERF_OUTPUT_MISC = 1U << 29,
PERF_OUTPUT_SRCCODE = 1U << 30,
PERF_OUTPUT_IPC = 1U << 31,
};
struct output_option {
@ -139,6 +140,7 @@ struct output_option {
{.str = "metric", .field = PERF_OUTPUT_METRIC},
{.str = "misc", .field = PERF_OUTPUT_MISC},
{.str = "srccode", .field = PERF_OUTPUT_SRCCODE},
{.str = "ipc", .field = PERF_OUTPUT_IPC},
};
enum {
@ -1268,6 +1270,20 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample,
return printed;
}
static int perf_sample__fprintf_ipc(struct perf_sample *sample,
struct perf_event_attr *attr, FILE *fp)
{
unsigned int ipc;
if (!PRINT_FIELD(IPC) || !sample->cyc_cnt || !sample->insn_cnt)
return 0;
ipc = (sample->insn_cnt * 100) / sample->cyc_cnt;
return fprintf(fp, " \t IPC: %u.%02u (%" PRIu64 "/%" PRIu64 ") ",
ipc / 100, ipc % 100, sample->insn_cnt, sample->cyc_cnt);
}
static int perf_sample__fprintf_bts(struct perf_sample *sample,
struct perf_evsel *evsel,
struct thread *thread,
@ -1312,6 +1328,8 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample,
printed += perf_sample__fprintf_addr(sample, thread, attr, fp);
}
printed += perf_sample__fprintf_ipc(sample, attr, fp);
if (print_srcline_last)
printed += map__fprintf_srcline(al->map, al->addr, "\n ", fp);
@ -1606,6 +1624,7 @@ struct perf_script {
bool show_namespace_events;
bool show_lost_events;
bool show_round_events;
bool show_bpf_events;
bool allocated;
bool per_event_dump;
struct cpu_map *cpus;
@ -1858,6 +1877,9 @@ static void process_event(struct perf_script *script,
if (PRINT_FIELD(PHYS_ADDR))
fprintf(fp, "%16" PRIx64, sample->phys_addr);
perf_sample__fprintf_ipc(sample, attr, fp);
fprintf(fp, "\n");
if (PRINT_FIELD(SRCCODE)) {
@ -2318,6 +2340,41 @@ process_finished_round_event(struct perf_tool *tool __maybe_unused,
return 0;
}
static int
process_bpf_events(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine)
{
struct thread *thread;
struct perf_script *script = container_of(tool, struct perf_script, tool);
struct perf_session *session = script->session;
struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
if (machine__process_ksymbol(machine, event, sample) < 0)
return -1;
if (!evsel->attr.sample_id_all) {
perf_event__fprintf(event, stdout);
return 0;
}
thread = machine__findnew_thread(machine, sample->pid, sample->tid);
if (thread == NULL) {
pr_debug("problem processing MMAP event, skipping it.\n");
return -1;
}
if (!filter_cpu(sample)) {
perf_sample__fprintf_start(sample, thread, evsel,
event->header.type, stdout);
perf_event__fprintf(event, stdout);
}
thread__put(thread);
return 0;
}
static void sig_handler(int sig __maybe_unused)
{
session_done = 1;
@ -2420,6 +2477,10 @@ static int __cmd_script(struct perf_script *script)
script->tool.ordered_events = false;
script->tool.finished_round = process_finished_round_event;
}
if (script->show_bpf_events) {
script->tool.ksymbol = process_bpf_events;
script->tool.bpf_event = process_bpf_events;
}
if (perf_script__setup_per_event_dump(script)) {
pr_err("Couldn't create the per event dump files\n");
@ -2819,7 +2880,7 @@ static int read_script_info(struct script_desc *desc, const char *filename)
return -1;
while (fgets(line, sizeof(line), fp)) {
p = ltrim(line);
p = skip_spaces(line);
if (strlen(p) == 0)
continue;
if (*p != '#')
@ -2828,19 +2889,19 @@ static int read_script_info(struct script_desc *desc, const char *filename)
if (strlen(p) && *p == '!')
continue;
p = ltrim(p);
p = skip_spaces(p);
if (strlen(p) && p[strlen(p) - 1] == '\n')
p[strlen(p) - 1] = '\0';
if (!strncmp(p, "description:", strlen("description:"))) {
p += strlen("description:");
desc->half_liner = strdup(ltrim(p));
desc->half_liner = strdup(skip_spaces(p));
continue;
}
if (!strncmp(p, "args:", strlen("args:"))) {
p += strlen("args:");
desc->args = strdup(ltrim(p));
desc->args = strdup(skip_spaces(p));
continue;
}
}
@ -2947,7 +3008,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
return -1;
while (fgets(line, sizeof(line), fp)) {
p = ltrim(line);
p = skip_spaces(line);
if (*p == '#')
continue;
@ -2957,7 +3018,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
break;
p += 2;
p = ltrim(p);
p = skip_spaces(p);
len = strcspn(p, " \t");
if (!len)
break;
@ -3297,6 +3358,7 @@ static int parse_call_trace(const struct option *opt __maybe_unused,
parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0);
itrace_parse_synth_opts(opt, "cewp", 0);
symbol_conf.nanosecs = true;
symbol_conf.pad_output_len_dso = 50;
return 0;
}
@ -3392,7 +3454,7 @@ int cmd_script(int argc, const char **argv)
"Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
"addr,symoff,srcline,period,iregs,uregs,brstack,"
"brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
"callindent,insn,insnlen,synth,phys_addr,metric,misc",
"callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc",
parse_output_fields),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
@ -3438,6 +3500,8 @@ int cmd_script(int argc, const char **argv)
"Show lost events (if recorded)"),
OPT_BOOLEAN('\0', "show-round-events", &script.show_round_events,
"Show round events (if recorded)"),
OPT_BOOLEAN('\0', "show-bpf-events", &script.show_bpf_events,
"Show bpf related events (if recorded)"),
OPT_BOOLEAN('\0', "per-event-dump", &script.per_event_dump,
"Dump trace output to files named by the monitored events"),
OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
@ -3458,6 +3522,15 @@ int cmd_script(int argc, const char **argv)
"Time span of interest (start,stop)"),
OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name,
"Show inline function"),
OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory",
"guest mount directory under which every guest os"
" instance has a subdir"),
OPT_STRING(0, "guestvmlinux", &symbol_conf.default_guest_vmlinux_name,
"file", "file saving guest os vmlinux"),
OPT_STRING(0, "guestkallsyms", &symbol_conf.default_guest_kallsyms,
"file", "file saving guest os /proc/kallsyms"),
OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules,
"file", "file saving guest os /proc/modules"),
OPT_END()
};
const char * const script_subcommands[] = { "record", "report", NULL };
@ -3477,6 +3550,16 @@ int cmd_script(int argc, const char **argv)
argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (symbol_conf.guestmount ||
symbol_conf.default_guest_vmlinux_name ||
symbol_conf.default_guest_kallsyms ||
symbol_conf.default_guest_modules) {
/*
* Enable guest sample processing.
*/
perf_guest = true;
}
data.path = input_name;
data.force = symbol_conf.force;
@ -3765,6 +3848,10 @@ int cmd_script(int argc, const char **argv)
&script.range_num);
if (err < 0)
goto out_delete;
itrace_synth_opts__set_time_range(&itrace_synth_opts,
script.ptime_range,
script.range_num);
}
err = __cmd_script(&script);
@ -3772,8 +3859,10 @@ int cmd_script(int argc, const char **argv)
flush_scripting();
out_delete:
if (script.ptime_range)
if (script.ptime_range) {
itrace_synth_opts__clear_time_range(&itrace_synth_opts);
zfree(&script.ptime_range);
}
perf_evlist__free_stats(session->evlist);
perf_session__delete(session);

89
tools/perf/builtin-stat.c
View File

@ -82,7 +82,7 @@
#include <sys/time.h>
#include <sys/resource.h>
#include "sane_ctype.h"
#include <linux/ctype.h>
#define DEFAULT_SEPARATOR " "
#define FREEZE_ON_SMI_PATH "devices/cpu/freeze_on_smi"
@ -776,6 +776,8 @@ static struct option stat_options[] = {
"stop workload and print counts after a timeout period in ms (>= 10ms)"),
OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
"aggregate counts per processor socket", AGGR_SOCKET),
OPT_SET_UINT(0, "per-die", &stat_config.aggr_mode,
"aggregate counts per processor die", AGGR_DIE),
OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode,
"aggregate counts per physical processor core", AGGR_CORE),
OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode,
@ -800,6 +802,12 @@ static int perf_stat__get_socket(struct perf_stat_config *config __maybe_unused,
return cpu_map__get_socket(map, cpu, NULL);
}
static int perf_stat__get_die(struct perf_stat_config *config __maybe_unused,
struct cpu_map *map, int cpu)
{
return cpu_map__get_die(map, cpu, NULL);
}
static int perf_stat__get_core(struct perf_stat_config *config __maybe_unused,
struct cpu_map *map, int cpu)
{
@ -840,6 +848,12 @@ static int perf_stat__get_socket_cached(struct perf_stat_config *config,
return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx);
}
static int perf_stat__get_die_cached(struct perf_stat_config *config,
struct cpu_map *map, int idx)
{
return perf_stat__get_aggr(config, perf_stat__get_die, map, idx);
}
static int perf_stat__get_core_cached(struct perf_stat_config *config,
struct cpu_map *map, int idx)
{
@ -870,6 +884,13 @@ static int perf_stat_init_aggr_mode(void)
}
stat_config.aggr_get_id = perf_stat__get_socket_cached;
break;
case AGGR_DIE:
if (cpu_map__build_die_map(evsel_list->cpus, &stat_config.aggr_map)) {
perror("cannot build die map");
return -1;
}
stat_config.aggr_get_id = perf_stat__get_die_cached;
break;
case AGGR_CORE:
if (cpu_map__build_core_map(evsel_list->cpus, &stat_config.aggr_map)) {
perror("cannot build core map");
@ -935,21 +956,55 @@ static int perf_env__get_socket(struct cpu_map *map, int idx, void *data)
return cpu == -1 ? -1 : env->cpu[cpu].socket_id;
}
static int perf_env__get_die(struct cpu_map *map, int idx, void *data)
{
struct perf_env *env = data;
int die_id = -1, cpu = perf_env__get_cpu(env, map, idx);
if (cpu != -1) {
/*
* Encode socket in bit range 15:8
* die_id is relative to socket,
* we need a global id. So we combine
* socket + die id
*/
if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.\n"))
return -1;
if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n"))
return -1;
die_id = (env->cpu[cpu].socket_id << 8) | (env->cpu[cpu].die_id & 0xff);
}
return die_id;
}
static int perf_env__get_core(struct cpu_map *map, int idx, void *data)
{
struct perf_env *env = data;
int core = -1, cpu = perf_env__get_cpu(env, map, idx);
if (cpu != -1) {
int socket_id = env->cpu[cpu].socket_id;
/*
* Encode socket in upper 16 bits
* core_id is relative to socket, and
* Encode socket in bit range 31:24
* encode die id in bit range 23:16
* core_id is relative to socket and die,
* we need a global id. So we combine
* socket + core id.
* socket + die id + core id
*/
core = (socket_id << 16) | (env->cpu[cpu].core_id & 0xffff);
if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.\n"))
return -1;
if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n"))
return -1;
if (WARN_ONCE(env->cpu[cpu].core_id >> 16, "The core id number is too big.\n"))
return -1;
core = (env->cpu[cpu].socket_id << 24) |
(env->cpu[cpu].die_id << 16) |
(env->cpu[cpu].core_id & 0xffff);
}
return core;
@ -961,6 +1016,12 @@ static int perf_env__build_socket_map(struct perf_env *env, struct cpu_map *cpus
return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env);
}
static int perf_env__build_die_map(struct perf_env *env, struct cpu_map *cpus,
struct cpu_map **diep)
{
return cpu_map__build_map(cpus, diep, perf_env__get_die, env);
}
static int perf_env__build_core_map(struct perf_env *env, struct cpu_map *cpus,
struct cpu_map **corep)
{
@ -972,6 +1033,11 @@ static int perf_stat__get_socket_file(struct perf_stat_config *config __maybe_un
{
return perf_env__get_socket(map, idx, &perf_stat.session->header.env);
}
static int perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused,
struct cpu_map *map, int idx)
{
return perf_env__get_die(map, idx, &perf_stat.session->header.env);
}
static int perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused,
struct cpu_map *map, int idx)
@ -991,6 +1057,13 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
}
stat_config.aggr_get_id = perf_stat__get_socket_file;
break;
case AGGR_DIE:
if (perf_env__build_die_map(env, evsel_list->cpus, &stat_config.aggr_map)) {
perror("cannot build die map");
return -1;
}
stat_config.aggr_get_id = perf_stat__get_die_file;
break;
case AGGR_CORE:
if (perf_env__build_core_map(env, evsel_list->cpus, &stat_config.aggr_map)) {
perror("cannot build core map");
@ -1541,6 +1614,8 @@ static int __cmd_report(int argc, const char **argv)
OPT_STRING('i', "input", &input_name, "file", "input file name"),
OPT_SET_UINT(0, "per-socket", &perf_stat.aggr_mode,
"aggregate counts per processor socket", AGGR_SOCKET),
OPT_SET_UINT(0, "per-die", &perf_stat.aggr_mode,
"aggregate counts per processor die", AGGR_DIE),
OPT_SET_UINT(0, "per-core", &perf_stat.aggr_mode,
"aggregate counts per physical processor core", AGGR_CORE),
OPT_SET_UINT('A', "no-aggr", &perf_stat.aggr_mode,

10
tools/perf/builtin-top.c
View File

@ -40,6 +40,7 @@
#include "util/cpumap.h"
#include "util/xyarray.h"
#include "util/sort.h"
#include "util/string2.h"
#include "util/term.h"
#include "util/intlist.h"
#include "util/parse-branch-options.h"
@ -75,7 +76,7 @@
#include <linux/time64.h>
#include <linux/types.h>
#include "sane_ctype.h"
#include <linux/ctype.h>
static volatile int done;
static volatile int resize;
@ -1207,11 +1208,14 @@ static int __cmd_top(struct perf_top *top)
init_process_thread(top);
if (opts->record_namespaces)
top->tool.namespace_events = true;
ret = perf_event__synthesize_bpf_events(top->session, perf_event__process,
&top->session->machines.host,
&top->record_opts);
if (ret < 0)
pr_warning("Couldn't synthesize bpf events.\n");
pr_debug("Couldn't synthesize BPF events: Pre-existing BPF programs won't have symbols resolved.\n");
machine__synthesize_threads(&top->session->machines.host, &opts->target,
top->evlist->threads, false,
@ -1499,6 +1503,8 @@ int cmd_top(int argc, const char **argv)
OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"),
OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize,
"number of thread to run event synthesize"),
OPT_BOOLEAN(0, "namespaces", &opts->record_namespaces,
"Record namespaces events"),
OPT_END()
};
struct perf_evlist *sb_evlist = NULL;

139
tools/perf/builtin-trace.c
View File

@ -64,7 +64,7 @@
#include <fcntl.h>
#include <sys/sysmacros.h>
#include "sane_ctype.h"
#include <linux/ctype.h>
#ifndef O_CLOEXEC
# define O_CLOEXEC 02000000
@ -402,6 +402,11 @@ static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size,
#define SCA_STRARRAY syscall_arg__scnprintf_strarray
size_t syscall_arg__scnprintf_strarray_flags(char *bf, size_t size, struct syscall_arg *arg)
{
return strarray__scnprintf_flags(arg->parm, bf, size, arg->show_string_prefix, arg->val);
}
size_t strarrays__scnprintf(struct strarrays *sas, char *bf, size_t size, const char *intfmt, bool show_prefix, int val)
{
size_t printed;
@ -481,6 +486,15 @@ static const char *bpf_cmd[] = {
};
static DEFINE_STRARRAY(bpf_cmd, "BPF_");
static const char *fsmount_flags[] = {
[1] = "CLOEXEC",
};
static DEFINE_STRARRAY(fsmount_flags, "FSMOUNT_");
#include "trace/beauty/generated/fsconfig_arrays.c"
static DEFINE_STRARRAY(fsconfig_cmds, "FSCONFIG_");
static const char *epoll_ctl_ops[] = { "ADD", "DEL", "MOD", };
static DEFINE_STRARRAY_OFFSET(epoll_ctl_ops, "EPOLL_CTL_", 1);
@ -641,6 +655,10 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
{ .scnprintf = SCA_STRARRAY, \
.parm = &strarray__##array, }
#define STRARRAY_FLAGS(name, array) \
{ .scnprintf = SCA_STRARRAY_FLAGS, \
.parm = &strarray__##array, }
#include "trace/beauty/arch_errno_names.c"
#include "trace/beauty/eventfd.c"
#include "trace/beauty/futex_op.c"
@ -712,6 +730,15 @@ static struct syscall_fmt {
[2] = { .scnprintf = SCA_FCNTL_ARG, /* arg */ }, }, },
{ .name = "flock",
.arg = { [1] = { .scnprintf = SCA_FLOCK, /* cmd */ }, }, },
{ .name = "fsconfig",
.arg = { [1] = STRARRAY(cmd, fsconfig_cmds), }, },
{ .name = "fsmount",
.arg = { [1] = STRARRAY_FLAGS(flags, fsmount_flags),
[2] = { .scnprintf = SCA_FSMOUNT_ATTR_FLAGS, /* attr_flags */ }, }, },
{ .name = "fspick",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ },
[1] = { .scnprintf = SCA_FILENAME, /* path */ },
[2] = { .scnprintf = SCA_FSPICK_FLAGS, /* flags */ }, }, },
{ .name = "fstat", .alias = "newfstat", },
{ .name = "fstatat", .alias = "newfstatat", },
{ .name = "futex",
@ -774,6 +801,12 @@ static struct syscall_fmt {
.arg = { [0] = { .scnprintf = SCA_FILENAME, /* dev_name */ },
[3] = { .scnprintf = SCA_MOUNT_FLAGS, /* flags */
.mask_val = SCAMV_MOUNT_FLAGS, /* flags */ }, }, },
{ .name = "move_mount",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* from_dfd */ },
[1] = { .scnprintf = SCA_FILENAME, /* from_pathname */ },
[2] = { .scnprintf = SCA_FDAT, /* to_dfd */ },
[3] = { .scnprintf = SCA_FILENAME, /* to_pathname */ },
[4] = { .scnprintf = SCA_MOVE_MOUNT_FLAGS, /* flags */ }, }, },
{ .name = "mprotect",
.arg = { [0] = { .scnprintf = SCA_HEX, /* start */ },
[2] = { .scnprintf = SCA_MMAP_PROT, /* prot */ }, }, },
@ -878,6 +911,8 @@ static struct syscall_fmt {
.arg = { [0] = { .scnprintf = SCA_FILENAME, /* specialfile */ }, }, },
{ .name = "symlinkat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
{ .name = "sync_file_range",
.arg = { [3] = { .scnprintf = SCA_SYNC_FILE_RANGE_FLAGS, /* flags */ }, }, },
{ .name = "tgkill",
.arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
{ .name = "tkill",
@ -936,8 +971,14 @@ struct syscall {
struct syscall_arg_fmt *arg_fmt;
};
/*
* Must match what is in the BPF program:
*
* tools/perf/examples/bpf/augmented_raw_syscalls.c
*/
struct bpf_map_syscall_entry {
bool enabled;
u16 string_args_len[6];
};
/*
@ -1191,8 +1232,17 @@ static void thread__set_filename_pos(struct thread *thread, const char *bf,
static size_t syscall_arg__scnprintf_augmented_string(struct syscall_arg *arg, char *bf, size_t size)
{
struct augmented_arg *augmented_arg = arg->augmented.args;
size_t printed = scnprintf(bf, size, "\"%.*s\"", augmented_arg->size, augmented_arg->value);
/*
* So that the next arg with a payload can consume its augmented arg, i.e. for rename* syscalls
* we would have two strings, each prefixed by its size.
*/
int consumed = sizeof(*augmented_arg) + augmented_arg->size;
return scnprintf(bf, size, "\"%.*s\"", augmented_arg->size, augmented_arg->value);
arg->augmented.args = ((void *)arg->augmented.args) + consumed;
arg->augmented.size -= consumed;
return printed;
}
static size_t syscall_arg__scnprintf_filename(char *bf, size_t size,
@ -1380,10 +1430,11 @@ static int syscall__set_arg_fmts(struct syscall *sc)
if (sc->fmt && sc->fmt->arg[idx].scnprintf)
continue;
len = strlen(field->name);
if (strcmp(field->type, "const char *") == 0 &&
(strcmp(field->name, "filename") == 0 ||
strcmp(field->name, "path") == 0 ||
strcmp(field->name, "pathname") == 0))
((len >= 4 && strcmp(field->name + len - 4, "name") == 0) ||
strstr(field->name, "path") != NULL))
sc->arg_fmt[idx].scnprintf = SCA_FILENAME;
else if ((field->flags & TEP_FIELD_IS_POINTER) || strstr(field->name, "addr"))
sc->arg_fmt[idx].scnprintf = SCA_PTR;
@ -1394,8 +1445,7 @@ static int syscall__set_arg_fmts(struct syscall *sc)
else if ((strcmp(field->type, "int") == 0 ||
strcmp(field->type, "unsigned int") == 0 ||
strcmp(field->type, "long") == 0) &&
(len = strlen(field->name)) >= 2 &&
strcmp(field->name + len - 2, "fd") == 0) {
len >= 2 && strcmp(field->name + len - 2, "fd") == 0) {
/*
* /sys/kernel/tracing/events/syscalls/sys_enter*
* egrep 'field:.*fd;' .../format|sed -r 's/.*field:([a-z ]+) [a-z_]*fd.+/\1/g'|sort|uniq -c
@ -1477,12 +1527,12 @@ static int trace__read_syscall_info(struct trace *trace, int id)
static int trace__validate_ev_qualifier(struct trace *trace)
{
int err = 0, i;
size_t nr_allocated;
int err = 0;
bool printed_invalid_prefix = false;
struct str_node *pos;
size_t nr_used = 0, nr_allocated = strlist__nr_entries(trace->ev_qualifier);
trace->ev_qualifier_ids.nr = strlist__nr_entries(trace->ev_qualifier);
trace->ev_qualifier_ids.entries = malloc(trace->ev_qualifier_ids.nr *
trace->ev_qualifier_ids.entries = malloc(nr_allocated *
sizeof(trace->ev_qualifier_ids.entries[0]));
if (trace->ev_qualifier_ids.entries == NULL) {
@ -1492,9 +1542,6 @@ static int trace__validate_ev_qualifier(struct trace *trace)
goto out;
}
nr_allocated = trace->ev_qualifier_ids.nr;
i = 0;
strlist__for_each_entry(pos, trace->ev_qualifier) {
const char *sc = pos->s;
int id = syscalltbl__id(trace->sctbl, sc), match_next = -1;
@ -1504,17 +1551,18 @@ static int trace__validate_ev_qualifier(struct trace *trace)
if (id >= 0)
goto matches;
if (err == 0) {
fputs("Error:\tInvalid syscall ", trace->output);
err = -EINVAL;
if (!printed_invalid_prefix) {
pr_debug("Skipping unknown syscalls: ");
printed_invalid_prefix = true;
} else {
fputs(", ", trace->output);
pr_debug(", ");
}
fputs(sc, trace->output);
pr_debug("%s", sc);
continue;
}
matches:
trace->ev_qualifier_ids.entries[i++] = id;
trace->ev_qualifier_ids.entries[nr_used++] = id;
if (match_next == -1)
continue;
@ -1522,7 +1570,7 @@ matches:
id = syscalltbl__strglobmatch_next(trace->sctbl, sc, &match_next);
if (id < 0)
break;
if (nr_allocated == trace->ev_qualifier_ids.nr) {
if (nr_allocated == nr_used) {
void *entries;
nr_allocated += 8;
@ -1535,20 +1583,19 @@ matches:
}
trace->ev_qualifier_ids.entries = entries;
}
trace->ev_qualifier_ids.nr++;
trace->ev_qualifier_ids.entries[i++] = id;
trace->ev_qualifier_ids.entries[nr_used++] = id;
}
}
if (err < 0) {
fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'"
"\nHint:\tand: 'man syscalls'\n", trace->output);
out_free:
zfree(&trace->ev_qualifier_ids.entries);
trace->ev_qualifier_ids.nr = 0;
}
trace->ev_qualifier_ids.nr = nr_used;
out:
if (printed_invalid_prefix)
pr_debug("\n");
return err;
out_free:
zfree(&trace->ev_qualifier_ids.entries);
trace->ev_qualifier_ids.nr = 0;
goto out;
}
/*
@ -2675,6 +2722,25 @@ out_enomem:
}
#ifdef HAVE_LIBBPF_SUPPORT
static void trace__init_bpf_map_syscall_args(struct trace *trace, int id, struct bpf_map_syscall_entry *entry)
{
struct syscall *sc = trace__syscall_info(trace, NULL, id);
int arg = 0;
if (sc == NULL)
goto out;
for (; arg < sc->nr_args; ++arg) {
entry->string_args_len[arg] = 0;
if (sc->arg_fmt[arg].scnprintf == SCA_FILENAME) {
/* Should be set like strace -s strsize */
entry->string_args_len[arg] = PATH_MAX;
}
}
out:
for (; arg < 6; ++arg)
entry->string_args_len[arg] = 0;
}
static int trace__set_ev_qualifier_bpf_filter(struct trace *trace)
{
int fd = bpf_map__fd(trace->syscalls.map);
@ -2687,6 +2753,9 @@ static int trace__set_ev_qualifier_bpf_filter(struct trace *trace)
for (i = 0; i < trace->ev_qualifier_ids.nr; ++i) {
int key = trace->ev_qualifier_ids.entries[i];
if (value.enabled)
trace__init_bpf_map_syscall_args(trace, key, &value);
err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST);
if (err)
break;
@ -2704,6 +2773,9 @@ static int __trace__init_syscalls_bpf_map(struct trace *trace, bool enabled)
int err = 0, key;
for (key = 0; key < trace->sctbl->syscalls.nr_entries; ++key) {
if (enabled)
trace__init_bpf_map_syscall_args(trace, key, &value);
err = bpf_map_update_elem(fd, &key, &value, BPF_ANY);
if (err)
break;
@ -3627,7 +3699,12 @@ static int trace__config(const char *var, const char *value, void *arg)
struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
"event selector. use 'perf list' to list available events",
parse_events_option);
err = parse_events_option(&o, value, 0);
/*
* We can't propagate parse_event_option() return, as it is 1
* for failure while perf_config() expects -1.
*/
if (parse_events_option(&o, value, 0))
err = -1;
} else if (!strcmp(var, "trace.show_timestamp")) {
trace->show_tstamp = perf_config_bool(var, value);
} else if (!strcmp(var, "trace.show_duration")) {

2
tools/perf/check-headers.sh
View File

@ -105,6 +105,8 @@ check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/ex
check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"'
check include/linux/ctype.h '-I "isdigit("'
check lib/ctype.c '-I "^EXPORT_SYMBOL" -I "^#include <linux/export.h>" -B'
# diff non-symmetric files
check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl

268
tools/perf/examples/bpf/augmented_raw_syscalls.c
View File

@ -21,8 +21,14 @@
/* bpf-output associated map */
bpf_map(__augmented_syscalls__, PERF_EVENT_ARRAY, int, u32, __NR_CPUS__);
/*
* string_args_len: one per syscall arg, 0 means not a string or don't copy it,
* PATH_MAX for copying everything, any other value to limit
* it a la 'strace -s strsize'.
*/
struct syscall {
bool enabled;
u16 string_args_len[6];
};
bpf_map(syscalls, ARRAY, int, struct syscall, 512);
@ -41,83 +47,10 @@ struct syscall_exit_args {
struct augmented_filename {
unsigned int size;
int reserved;
int err;
char value[PATH_MAX];
};
/* syscalls where the first arg is a string */
#define SYS_OPEN 2
#define SYS_STAT 4
#define SYS_LSTAT 6
#define SYS_ACCESS 21
#define SYS_EXECVE 59
#define SYS_TRUNCATE 76
#define SYS_CHDIR 80
#define SYS_RENAME 82
#define SYS_MKDIR 83
#define SYS_RMDIR 84
#define SYS_CREAT 85
#define SYS_LINK 86
#define SYS_UNLINK 87
#define SYS_SYMLINK 88
#define SYS_READLINK 89
#define SYS_CHMOD 90
#define SYS_CHOWN 92
#define SYS_LCHOWN 94
#define SYS_MKNOD 133
#define SYS_STATFS 137
#define SYS_PIVOT_ROOT 155
#define SYS_CHROOT 161
#define SYS_ACCT 163
#define SYS_SWAPON 167
#define SYS_SWAPOFF 168
#define SYS_DELETE_MODULE 176
#define SYS_SETXATTR 188
#define SYS_LSETXATTR 189
#define SYS_GETXATTR 191
#define SYS_LGETXATTR 192
#define SYS_LISTXATTR 194
#define SYS_LLISTXATTR 195
#define SYS_REMOVEXATTR 197
#define SYS_LREMOVEXATTR 198
#define SYS_MQ_OPEN 240
#define SYS_MQ_UNLINK 241
#define SYS_ADD_KEY 248
#define SYS_REQUEST_KEY 249
#define SYS_SYMLINKAT 266
#define SYS_MEMFD_CREATE 319
/* syscalls where the first arg is a string */
#define SYS_PWRITE64 18
#define SYS_EXECVE 59
#define SYS_RENAME 82
#define SYS_QUOTACTL 179
#define SYS_FSETXATTR 190
#define SYS_FGETXATTR 193
#define SYS_FREMOVEXATTR 199
#define SYS_MQ_TIMEDSEND 242
#define SYS_REQUEST_KEY 249
#define SYS_INOTIFY_ADD_WATCH 254
#define SYS_OPENAT 257
#define SYS_MKDIRAT 258
#define SYS_MKNODAT 259
#define SYS_FCHOWNAT 260
#define SYS_FUTIMESAT 261
#define SYS_NEWFSTATAT 262
#define SYS_UNLINKAT 263
#define SYS_RENAMEAT 264
#define SYS_LINKAT 265
#define SYS_READLINKAT 267
#define SYS_FCHMODAT 268
#define SYS_FACCESSAT 269
#define SYS_UTIMENSAT 280
#define SYS_NAME_TO_HANDLE_AT 303
#define SYS_FINIT_MODULE 313
#define SYS_RENAMEAT2 316
#define SYS_EXECVEAT 322
#define SYS_STATX 332
pid_filter(pids_filtered);
struct augmented_args_filename {
@ -127,12 +60,48 @@ struct augmented_args_filename {
bpf_map(augmented_filename_map, PERCPU_ARRAY, int, struct augmented_args_filename, 1);
static inline
unsigned int augmented_filename__read(struct augmented_filename *augmented_filename,
const void *filename_arg, unsigned int filename_len)
{
unsigned int len = sizeof(*augmented_filename);
int size = probe_read_str(&augmented_filename->value, filename_len, filename_arg);
augmented_filename->size = augmented_filename->err = 0;
/*
* probe_read_str may return < 0, e.g. -EFAULT
* So we leave that in the augmented_filename->size that userspace will
*/
if (size > 0) {
len -= sizeof(augmented_filename->value) - size;
len &= sizeof(augmented_filename->value) - 1;
augmented_filename->size = size;
} else {
/*
* So that username notice the error while still being able
* to skip this augmented arg record
*/
augmented_filename->err = size;
len = offsetof(struct augmented_filename, value);
}
return len;
}
SEC("raw_syscalls:sys_enter")
int sys_enter(struct syscall_enter_args *args)
{
struct augmented_args_filename *augmented_args;
unsigned int len = sizeof(*augmented_args);
const void *filename_arg = NULL;
/*
* We start len, the amount of data that will be in the perf ring
* buffer, if this is not filtered out by one of pid_filter__has(),
* syscall->enabled, etc, with the non-augmented raw syscall payload,
* i.e. sizeof(augmented_args->args).
*
* We'll add to this as we add augmented syscalls right after that
* initial, non-augmented raw_syscalls:sys_enter payload.
*/
unsigned int len = sizeof(augmented_args->args);
struct syscall *syscall;
int key = 0;
@ -189,101 +158,66 @@ int sys_enter(struct syscall_enter_args *args)
* after the ctx memory access to prevent their down stream merging.
*/
/*
* This table of what args are strings will be provided by userspace,
* in the syscalls map, i.e. we will already have to do the lookup to
* see if this specific syscall is filtered, so we can as well get more
* info about what syscall args are strings or pointers, and how many
* bytes to copy, per arg, etc.
* For now copy just the first string arg, we need to improve the protocol
* and have more than one.
*
* For now hard code it, till we have all the basic mechanisms in place
* to automate everything and make the kernel part be completely driven
* by information obtained in userspace for each kernel version and
* processor architecture, making the kernel part the same no matter what
* kernel version or processor architecture it runs on.
*/
switch (augmented_args->args.syscall_nr) {
case SYS_ACCT:
case SYS_ADD_KEY:
case SYS_CHDIR:
case SYS_CHMOD:
case SYS_CHOWN:
case SYS_CHROOT:
case SYS_CREAT:
case SYS_DELETE_MODULE:
case SYS_EXECVE:
case SYS_GETXATTR:
case SYS_LCHOWN:
case SYS_LGETXATTR:
case SYS_LINK:
case SYS_LISTXATTR:
case SYS_LLISTXATTR:
case SYS_LREMOVEXATTR:
case SYS_LSETXATTR:
case SYS_LSTAT:
case SYS_MEMFD_CREATE:
case SYS_MKDIR:
case SYS_MKNOD:
case SYS_MQ_OPEN:
case SYS_MQ_UNLINK:
case SYS_PIVOT_ROOT:
case SYS_READLINK:
case SYS_REMOVEXATTR:
case SYS_RENAME:
case SYS_REQUEST_KEY:
case SYS_RMDIR:
case SYS_SETXATTR:
case SYS_STAT:
case SYS_STATFS:
case SYS_SWAPOFF:
case SYS_SWAPON:
case SYS_SYMLINK:
case SYS_SYMLINKAT:
case SYS_TRUNCATE:
case SYS_UNLINK:
case SYS_ACCESS:
case SYS_OPEN: filename_arg = (const void *)args->args[0];
* Using the unrolled loop is not working, only when we do it manually,
* check this out later...
u8 arg;
#pragma clang loop unroll(full)
for (arg = 0; arg < 6; ++arg) {
if (syscall->string_args_len[arg] != 0) {
filename_len = syscall->string_args_len[arg];
filename_arg = (const void *)args->args[arg];
__asm__ __volatile__("": : :"memory");
break;
case SYS_EXECVEAT:
case SYS_FACCESSAT:
case SYS_FCHMODAT:
case SYS_FCHOWNAT:
case SYS_FGETXATTR:
case SYS_FINIT_MODULE:
case SYS_FREMOVEXATTR:
case SYS_FSETXATTR:
case SYS_FUTIMESAT:
case SYS_INOTIFY_ADD_WATCH:
case SYS_LINKAT:
case SYS_MKDIRAT:
case SYS_MKNODAT:
case SYS_MQ_TIMEDSEND:
case SYS_NAME_TO_HANDLE_AT:
case SYS_NEWFSTATAT:
case SYS_PWRITE64:
case SYS_QUOTACTL:
case SYS_READLINKAT:
case SYS_RENAMEAT:
case SYS_RENAMEAT2:
case SYS_STATX:
case SYS_UNLINKAT:
case SYS_UTIMENSAT:
case SYS_OPENAT: filename_arg = (const void *)args->args[1];
break;
break;
}
}
if (filename_arg != NULL) {
augmented_args->filename.reserved = 0;
augmented_args->filename.size = probe_read_str(&augmented_args->filename.value,
sizeof(augmented_args->filename.value),
filename_arg);
if (augmented_args->filename.size < sizeof(augmented_args->filename.value)) {
len -= sizeof(augmented_args->filename.value) - augmented_args->filename.size;
len &= sizeof(augmented_args->filename.value) - 1;
}
} else {
len = sizeof(augmented_args->args);
}
verifier log:
; if (syscall->string_args_len[arg] != 0) {
37: (69) r3 = *(u16 *)(r0 +2)
R0=map_value(id=0,off=0,ks=4,vs=14,imm=0) R1_w=inv0 R2_w=map_value(id=0,off=2,ks=4,vs=14,imm=0) R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=4168,imm=0) R10=fp0,call_-1 fp-8=mmmmmmmm
; if (syscall->string_args_len[arg] != 0) {
38: (55) if r3 != 0x0 goto pc+5
R0=map_value(id=0,off=0,ks=4,vs=14,imm=0) R1=inv0 R2=map_value(id=0,off=2,ks=4,vs=14,imm=0) R3=inv0 R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=4168,imm=0) R10=fp0,call_-1 fp-8=mmmmmmmm
39: (b7) r1 = 1
; if (syscall->string_args_len[arg] != 0) {
40: (bf) r2 = r0
41: (07) r2 += 4
42: (69) r3 = *(u16 *)(r0 +4)
R0=map_value(id=0,off=0,ks=4,vs=14,imm=0) R1_w=inv1 R2_w=map_value(id=0,off=4,ks=4,vs=14,imm=0) R3_w=inv0 R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=4168,imm=0) R10=fp0,call_-1 fp-8=mmmmmmmm
; if (syscall->string_args_len[arg] != 0) {
43: (15) if r3 == 0x0 goto pc+32
R0=map_value(id=0,off=0,ks=4,vs=14,imm=0) R1=inv1 R2=map_value(id=0,off=4,ks=4,vs=14,imm=0) R3=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff)) R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=4168,imm=0) R10=fp0,call_-1 fp-8=mmmmmmmm
; filename_arg = (const void *)args->args[arg];
44: (67) r1 <<= 3
45: (bf) r3 = r6
46: (0f) r3 += r1
47: (b7) r5 = 64
48: (79) r3 = *(u64 *)(r3 +16)
dereference of modified ctx ptr R3 off=8 disallowed
processed 46 insns (limit 1000000) max_states_per_insn 0 total_states 12 peak_states 12 mark_read 7
*/
#define __loop_iter(arg) \
if (syscall->string_args_len[arg] != 0) { \
unsigned int filename_len = syscall->string_args_len[arg]; \
const void *filename_arg = (const void *)args->args[arg]; \
if (filename_len <= sizeof(augmented_args->filename.value)) \
len += augmented_filename__read(&augmented_args->filename, filename_arg, filename_len);
#define loop_iter_first() __loop_iter(0); }
#define loop_iter(arg) else __loop_iter(arg); }
#define loop_iter_last(arg) else __loop_iter(arg); __asm__ __volatile__("": : :"memory"); }
loop_iter_first()
loop_iter(1)
loop_iter(2)
loop_iter(3)
loop_iter(4)
loop_iter_last(5)
/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len);

2
tools/perf/jvmti/jvmti_agent.c
View File

@ -45,10 +45,12 @@
static char jit_path[PATH_MAX];
static void *marker_addr;
#ifndef HAVE_GETTID
static inline pid_t gettid(void)
{
return (pid_t)syscall(__NR_gettid);
}
#endif
static int get_e_machine(struct jitheader *hdr)
{

4
tools/perf/jvmti/libjvmti.c
View File

@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/compiler.h>
#include <linux/string.h>
#include <sys/types.h>
#include <stdio.h>
#include <string.h>
@ -162,8 +163,7 @@ copy_class_filename(const char * class_sign, const char * file_name, char * resu
result[i] = '\0';
} else {
/* fallback case */
size_t file_name_len = strlen(file_name);
strncpy(result, file_name, file_name_len < max_length ? file_name_len : max_length);
strlcpy(result, file_name, max_length);
}
}

5
tools/perf/perf-with-kcore.sh
View File

@ -104,11 +104,6 @@ fix_buildid_cache_permissions()
USER_HOME=$(bash <<< "echo ~$SUDO_USER")
if [ "$HOME" != "$USER_HOME" ] ; then
echo "Fix unnecessary because root has a home: $HOME" >&2
exit 1
fi
echo "Fixing buildid cache permissions"
find "$USER_HOME/.debug" -xdev -type d ! -user "$SUDO_USER" -ls -exec chown "$SUDO_USER" \{\} \;

1
tools/perf/perf.c
View File

@ -18,6 +18,7 @@
#include "util/bpf-loader.h"
#include "util/debug.h"
#include "util/event.h"
#include "util/util.h"
#include <api/fs/fs.h>
#include <api/fs/tracing_path.h>
#include <errno.h>

4
tools/perf/perf.h
View File

@ -26,7 +26,7 @@ static inline unsigned long long rdclock(void)
}
#ifndef MAX_NR_CPUS
#define MAX_NR_CPUS 1024
#define MAX_NR_CPUS 2048
#endif
extern const char *input_name;
@ -61,6 +61,8 @@ struct record_opts {
bool record_switch_events;
bool all_kernel;
bool all_user;
bool kernel_callchains;
bool user_callchains;
bool tail_synthesize;
bool overwrite;
bool ignore_missing_thread;

44
tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json Normal file
View File

@ -0,0 +1,44 @@
[
{
"EventCode": "0x02",
"EventName": "uncore_hisi_ddrc.flux_wcmd",
"BriefDescription": "DDRC write commands",
"PublicDescription": "DDRC write commands",
"Unit": "hisi_sccl,ddrc",
},
{
"EventCode": "0x03",
"EventName": "uncore_hisi_ddrc.flux_rcmd",
"BriefDescription": "DDRC read commands",
"PublicDescription": "DDRC read commands",
"Unit": "hisi_sccl,ddrc",
},
{
"EventCode": "0x04",
"EventName": "uncore_hisi_ddrc.flux_wr",
"BriefDescription": "DDRC precharge commands",
"PublicDescription": "DDRC precharge commands",
"Unit": "hisi_sccl,ddrc",
},
{
"EventCode": "0x05",
"EventName": "uncore_hisi_ddrc.act_cmd",
"BriefDescription": "DDRC active commands",
"PublicDescription": "DDRC active commands",
"Unit": "hisi_sccl,ddrc",
},
{
"EventCode": "0x06",
"EventName": "uncore_hisi_ddrc.rnk_chg",
"BriefDescription": "DDRC rank commands",
"PublicDescription": "DDRC rank commands",
"Unit": "hisi_sccl,ddrc",
},
{
"EventCode": "0x07",
"EventName": "uncore_hisi_ddrc.rw_chg",
"BriefDescription": "DDRC read and write changes",
"PublicDescription": "DDRC read and write changes",
"Unit": "hisi_sccl,ddrc",
},
]

51
tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json Normal file
View File

@ -0,0 +1,51 @@
[
{
"EventCode": "0x00",
"EventName": "uncore_hisi_hha.rx_ops_num",
"BriefDescription": "The number of all operations received by the HHA",
"PublicDescription": "The number of all operations received by the HHA",
"Unit": "hisi_sccl,hha",
},
{
"EventCode": "0x01",
"EventName": "uncore_hisi_hha.rx_outer",
"BriefDescription": "The number of all operations received by the HHA from another socket",
"PublicDescription": "The number of all operations received by the HHA from another socket",
"Unit": "hisi_sccl,hha",
},
{
"EventCode": "0x02",
"EventName": "uncore_hisi_hha.rx_sccl",
"BriefDescription": "The number of all operations received by the HHA from another SCCL in this socket",
"PublicDescription": "The number of all operations received by the HHA from another SCCL in this socket",
"Unit": "hisi_sccl,hha",
},
{
"EventCode": "0x1c",
"EventName": "uncore_hisi_hha.rd_ddr_64b",
"BriefDescription": "The number of read operations sent by HHA to DDRC which size is 64 bytes",
"PublicDescription": "The number of read operations sent by HHA to DDRC which size is 64bytes",
"Unit": "hisi_sccl,hha",
},
{
"EventCode": "0x1d",
"EventName": "uncore_hisi_hha.wr_dr_64b",
"BriefDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes",
"PublicDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes",
"Unit": "hisi_sccl,hha",
},
{
"EventCode": "0x1e",
"EventName": "uncore_hisi_hha.rd_ddr_128b",
"BriefDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes",
"PublicDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes",
"Unit": "hisi_sccl,hha",
},
{
"EventCode": "0x1f",
"EventName": "uncore_hisi_hha.wr_ddr_128b",
"BriefDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes",
"PublicDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes",
"Unit": "hisi_sccl,hha",
},
]

37
tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json Normal file
View File

@ -0,0 +1,37 @@
[
{
"EventCode": "0x00",
"EventName": "uncore_hisi_l3c.rd_cpipe",
"BriefDescription": "Total read accesses",
"PublicDescription": "Total read accesses",
"Unit": "hisi_sccl,l3c",
},
{
"EventCode": "0x01",
"EventName": "uncore_hisi_l3c.wr_cpipe",
"BriefDescription": "Total write accesses",
"PublicDescription": "Total write accesses",
"Unit": "hisi_sccl,l3c",
},
{
"EventCode": "0x02",
"EventName": "uncore_hisi_l3c.rd_hit_cpipe",
"BriefDescription": "Total read hits",
"PublicDescription": "Total read hits",
"Unit": "hisi_sccl,l3c",
},
{
"EventCode": "0x03",
"EventName": "uncore_hisi_l3c.wr_hit_cpipe",
"BriefDescription": "Total write hits",
"PublicDescription": "Total write hits",
"Unit": "hisi_sccl,l3c",
},
{
"EventCode": "0x04",
"EventName": "uncore_hisi_l3c.victim_num",
"BriefDescription": "l3c precharge commands",
"PublicDescription": "l3c precharge commands",
"Unit": "hisi_sccl,l3c",
},
]

4
tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
View File

@ -314,13 +314,13 @@
"MetricName": "DRAM_BW_Use"
},
{
"MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x35\\\\\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )",
"MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,config\\=0x40433@ / cha@event\\=0x35\\\\\\,umask\\=0x21\\\\\\,config\\=0x40433@ ) / ( cha_0@event\\=0x0@ / duration_time )",
"BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
"MetricGroup": "Memory_Lat",
"MetricName": "DRAM_Read_Latency"
},
{
"MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1@",
"MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,config\\=0x40433@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1\\\\\\,config\\=0x40433@",
"BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
"MetricGroup": "Memory_BW",
"MetricName": "DRAM_Parallel_Reads"

22
tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
View File

@ -314,35 +314,17 @@
"MetricName": "DRAM_BW_Use"
},
{
"MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x35\\\\\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )",
"MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,config\\=0x40433@ / cha@event\\=0x35\\\\\\,umask\\=0x21\\\\\\,config\\=0x40433@ ) / ( cha_0@event\\=0x0@ / duration_time )",
"BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
"MetricGroup": "Memory_Lat",
"MetricName": "DRAM_Read_Latency"
},
{
"MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1@",
"MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,config\\=0x40433@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1\\\\\\,config\\=0x40433@",
"BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
"MetricGroup": "Memory_BW",
"MetricName": "DRAM_Parallel_Reads"
},
{
"MetricExpr": "( 1000000000 * ( imc@event\\=0xe0\\\\\\,umask\\=0x1@ / imc@event\\=0xe3@ ) / imc_0@event\\=0x0@ ) if 1 if 0 == 1 else 0 else 0",
"BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches",
"MetricGroup": "Memory_Lat",
"MetricName": "MEM_PMM_Read_Latency"
},
{
"MetricExpr": "( ( 64 * imc@event\\=0xe3@ / 1000000000 ) / duration_time ) if 1 if 0 == 1 else 0 else 0",
"BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]",
"MetricGroup": "Memory_BW",
"MetricName": "PMM_Read_BW"
},
{
"MetricExpr": "( ( 64 * imc@event\\=0xe7@ / 1000000000 ) / duration_time ) if 1 if 0 == 1 else 0 else 0",
"BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]",
"MetricGroup": "Memory_BW",
"MetricName": "PMM_Write_BW"
},
{
"MetricExpr": "cha_0@event\\=0x0@",
"BriefDescription": "Socket actual clocks when any core is active on that socket",

7
tools/perf/pmu-events/jevents.c
View File

@ -236,6 +236,9 @@ static struct map {
{ "CPU-M-CF", "cpum_cf" },
{ "CPU-M-SF", "cpum_sf" },
{ "UPI LL", "uncore_upi" },
{ "hisi_sccl,ddrc", "hisi_sccl,ddrc" },
{ "hisi_sccl,hha", "hisi_sccl,hha" },
{ "hisi_sccl,l3c", "hisi_sccl,l3c" },
{}
};
@ -841,7 +844,7 @@ static void create_empty_mapping(const char *output_file)
_Exit(1);
}
fprintf(outfp, "#include \"../../pmu-events/pmu-events.h\"\n");
fprintf(outfp, "#include \"pmu-events/pmu-events.h\"\n");
print_mapping_table_prefix(outfp);
print_mapping_table_suffix(outfp);
fclose(outfp);
@ -1096,7 +1099,7 @@ int main(int argc, char *argv[])
}
/* Include pmu-events.h first */
fprintf(eventsfp, "#include \"../../pmu-events/pmu-events.h\"\n");
fprintf(eventsfp, "#include \"pmu-events/pmu-events.h\"\n");
/*
* The mapfile allows multiple CPUids to point to the same JSON file,

330
tools/perf/scripts/python/export-to-postgresql.py
View File

@ -27,18 +27,31 @@ import datetime
#
# fedora:
#
# $ sudo yum install postgresql postgresql-server python-pyside qt-postgresql
# $ sudo yum install postgresql postgresql-server qt-postgresql
# $ sudo su - postgres -c initdb
# $ sudo service postgresql start
# $ sudo su - postgres
# $ createuser <your user id here>
# $ createuser -s <your user id here> # Older versions may not support -s, in which case answer the prompt below:
# Shall the new role be a superuser? (y/n) y
# $ sudo yum install python-pyside
#
# Alternately, to use Python3 and/or pyside 2, one of the following:
# $ sudo yum install python3-pyside
# $ pip install --user PySide2
# $ pip3 install --user PySide2
#
# ubuntu:
#
# $ sudo apt-get install postgresql python-pyside.qtsql libqt4-sql-psql
# $ sudo apt-get install postgresql
# $ sudo su - postgres
# $ createuser -s <your user id here>
# $ sudo apt-get install python-pyside.qtsql libqt4-sql-psql
#
# Alternately, to use Python3 and/or pyside 2, one of the following:
#
# $ sudo apt-get install python3-pyside.qtsql libqt4-sql-psql
# $ sudo apt-get install python-pyside2.qtsql libqt5sql5-psql
# $ sudo apt-get install python3-pyside2.qtsql libqt5sql5-psql
#
# An example of using this script with Intel PT:
#
@ -199,7 +212,16 @@ import datetime
# print "{0:>6} {1:>10} {2:>9} {3:<30} {4:>6} {5:<30}".format(query.value(0), query.value(1), query.value(2), query.value(3), query.value(4), query.value(5))
# call_path_id = query.value(6)
from PySide.QtSql import *
pyside_version_1 = True
if not "pyside-version-1" in sys.argv:
try:
from PySide2.QtSql import *
pyside_version_1 = False
except:
pass
if pyside_version_1:
from PySide.QtSql import *
if sys.version_info < (3, 0):
def toserverstr(str):
@ -255,11 +277,12 @@ def printdate(*args, **kw_args):
print(datetime.datetime.today(), *args, sep=' ', **kw_args)
def usage():
printerr("Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>]")
printerr("where: columns 'all' or 'branches'")
printerr(" calls 'calls' => create calls and call_paths table")
printerr(" callchains 'callchains' => create call_paths table")
raise Exception("Too few arguments")
printerr("Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>] [<pyside-version-1>]");
printerr("where: columns 'all' or 'branches'");
printerr(" calls 'calls' => create calls and call_paths table");
printerr(" callchains 'callchains' => create call_paths table");
printerr(" pyside-version-1 'pyside-version-1' => use pyside version 1");
raise Exception("Too few or bad arguments")
if (len(sys.argv) < 2):
usage()
@ -281,6 +304,8 @@ for i in range(3,len(sys.argv)):
perf_db_export_calls = True
elif (sys.argv[i] == "callchains"):
perf_db_export_callchains = True
elif (sys.argv[i] == "pyside-version-1"):
pass
else:
usage()
@ -369,7 +394,9 @@ if branches:
'to_ip bigint,'
'branch_type integer,'
'in_tx boolean,'
'call_path_id bigint)')
'call_path_id bigint,'
'insn_count bigint,'
'cyc_count bigint)')
else:
do_query(query, 'CREATE TABLE samples ('
'id bigint NOT NULL,'
@ -393,7 +420,9 @@ else:
'data_src bigint,'
'branch_type integer,'
'in_tx boolean,'
'call_path_id bigint)')
'call_path_id bigint,'
'insn_count bigint,'
'cyc_count bigint)')
if perf_db_export_calls or perf_db_export_callchains:
do_query(query, 'CREATE TABLE call_paths ('
@ -414,7 +443,41 @@ if perf_db_export_calls:
'return_id bigint,'
'parent_call_path_id bigint,'
'flags integer,'
'parent_id bigint)')
'parent_id bigint,'
'insn_count bigint,'
'cyc_count bigint)')
do_query(query, 'CREATE TABLE ptwrite ('
'id bigint NOT NULL,'
'payload bigint,'
'exact_ip boolean)')
do_query(query, 'CREATE TABLE cbr ('
'id bigint NOT NULL,'
'cbr integer,'
'mhz integer,'
'percent integer)')
do_query(query, 'CREATE TABLE mwait ('
'id bigint NOT NULL,'
'hints integer,'
'extensions integer)')
do_query(query, 'CREATE TABLE pwre ('
'id bigint NOT NULL,'
'cstate integer,'
'subcstate integer,'
'hw boolean)')
do_query(query, 'CREATE TABLE exstop ('
'id bigint NOT NULL,'
'exact_ip boolean)')
do_query(query, 'CREATE TABLE pwrx ('
'id bigint NOT NULL,'
'deepest_cstate integer,'
'last_cstate integer,'
'wake_reason integer)')
do_query(query, 'CREATE VIEW machines_view AS '
'SELECT '
@ -496,6 +559,9 @@ if perf_db_export_calls:
'return_time,'
'return_time - call_time AS elapsed_time,'
'branch_count,'
'insn_count,'
'cyc_count,'
'CASE WHEN cyc_count=0 THEN CAST(0 AS NUMERIC(20, 2)) ELSE CAST((CAST(insn_count AS FLOAT) / cyc_count) AS NUMERIC(20, 2)) END AS IPC,'
'call_id,'
'return_id,'
'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE CAST ( flags AS VARCHAR(6) ) END AS flags,'
@ -521,9 +587,110 @@ do_query(query, 'CREATE VIEW samples_view AS '
'to_sym_offset,'
'(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,'
'(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,'
'in_tx'
'in_tx,'
'insn_count,'
'cyc_count,'
'CASE WHEN cyc_count=0 THEN CAST(0 AS NUMERIC(20, 2)) ELSE CAST((CAST(insn_count AS FLOAT) / cyc_count) AS NUMERIC(20, 2)) END AS IPC'
' FROM samples')
do_query(query, 'CREATE VIEW ptwrite_view AS '
'SELECT '
'ptwrite.id,'
'time,'
'cpu,'
'to_hex(payload) AS payload_hex,'
'CASE WHEN exact_ip=FALSE THEN \'False\' ELSE \'True\' END AS exact_ip'
' FROM ptwrite'
' INNER JOIN samples ON samples.id = ptwrite.id')
do_query(query, 'CREATE VIEW cbr_view AS '
'SELECT '
'cbr.id,'
'time,'
'cpu,'
'cbr,'
'mhz,'
'percent'
' FROM cbr'
' INNER JOIN samples ON samples.id = cbr.id')
do_query(query, 'CREATE VIEW mwait_view AS '
'SELECT '
'mwait.id,'
'time,'
'cpu,'
'to_hex(hints) AS hints_hex,'
'to_hex(extensions) AS extensions_hex'
' FROM mwait'
' INNER JOIN samples ON samples.id = mwait.id')
do_query(query, 'CREATE VIEW pwre_view AS '
'SELECT '
'pwre.id,'
'time,'
'cpu,'
'cstate,'
'subcstate,'
'CASE WHEN hw=FALSE THEN \'False\' ELSE \'True\' END AS hw'
' FROM pwre'
' INNER JOIN samples ON samples.id = pwre.id')
do_query(query, 'CREATE VIEW exstop_view AS '
'SELECT '
'exstop.id,'
'time,'
'cpu,'
'CASE WHEN exact_ip=FALSE THEN \'False\' ELSE \'True\' END AS exact_ip'
' FROM exstop'
' INNER JOIN samples ON samples.id = exstop.id')
do_query(query, 'CREATE VIEW pwrx_view AS '
'SELECT '
'pwrx.id,'
'time,'
'cpu,'
'deepest_cstate,'
'last_cstate,'
'CASE WHEN wake_reason=1 THEN \'Interrupt\''
' WHEN wake_reason=2 THEN \'Timer Deadline\''
' WHEN wake_reason=4 THEN \'Monitored Address\''
' WHEN wake_reason=8 THEN \'HW\''
' ELSE CAST ( wake_reason AS VARCHAR(2) )'
'END AS wake_reason'
' FROM pwrx'
' INNER JOIN samples ON samples.id = pwrx.id')
do_query(query, 'CREATE VIEW power_events_view AS '
'SELECT '
'samples.id,'
'samples.time,'
'samples.cpu,'
'selected_events.name AS event,'
'FORMAT(\'%6s\', cbr.cbr) AS cbr,'
'FORMAT(\'%6s\', cbr.mhz) AS MHz,'
'FORMAT(\'%5s\', cbr.percent) AS percent,'
'to_hex(mwait.hints) AS hints_hex,'
'to_hex(mwait.extensions) AS extensions_hex,'
'FORMAT(\'%3s\', pwre.cstate) AS cstate,'
'FORMAT(\'%3s\', pwre.subcstate) AS subcstate,'
'CASE WHEN pwre.hw=FALSE THEN \'False\' WHEN pwre.hw=TRUE THEN \'True\' ELSE NULL END AS hw,'
'CASE WHEN exstop.exact_ip=FALSE THEN \'False\' WHEN exstop.exact_ip=TRUE THEN \'True\' ELSE NULL END AS exact_ip,'
'FORMAT(\'%3s\', pwrx.deepest_cstate) AS deepest_cstate,'
'FORMAT(\'%3s\', pwrx.last_cstate) AS last_cstate,'
'CASE WHEN pwrx.wake_reason=1 THEN \'Interrupt\''
' WHEN pwrx.wake_reason=2 THEN \'Timer Deadline\''
' WHEN pwrx.wake_reason=4 THEN \'Monitored Address\''
' WHEN pwrx.wake_reason=8 THEN \'HW\''
' ELSE FORMAT(\'%2s\', pwrx.wake_reason)'
'END AS wake_reason'
' FROM cbr'
' FULL JOIN mwait ON mwait.id = cbr.id'
' FULL JOIN pwre ON pwre.id = cbr.id'
' FULL JOIN exstop ON exstop.id = cbr.id'
' FULL JOIN pwrx ON pwrx.id = cbr.id'
' INNER JOIN samples ON samples.id = coalesce(cbr.id, mwait.id, pwre.id, exstop.id, pwrx.id)'
' INNER JOIN selected_events ON selected_events.id = samples.evsel_id'
' ORDER BY samples.id')
file_header = struct.pack("!11sii", b"PGCOPY\n\377\r\n\0", 0, 0)
file_trailer = b"\377\377"
@ -583,6 +750,12 @@ if perf_db_export_calls or perf_db_export_callchains:
call_path_file = open_output_file("call_path_table.bin")
if perf_db_export_calls:
call_file = open_output_file("call_table.bin")
ptwrite_file = open_output_file("ptwrite_table.bin")
cbr_file = open_output_file("cbr_table.bin")
mwait_file = open_output_file("mwait_table.bin")
pwre_file = open_output_file("pwre_table.bin")
exstop_file = open_output_file("exstop_table.bin")
pwrx_file = open_output_file("pwrx_table.bin")
def trace_begin():
printdate("Writing to intermediate files...")
@ -593,13 +766,23 @@ def trace_begin():
comm_table(0, "unknown")
dso_table(0, 0, "unknown", "unknown", "")
symbol_table(0, 0, 0, 0, 0, "unknown")
sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
if perf_db_export_calls or perf_db_export_callchains:
call_path_table(0, 0, 0, 0)
call_return_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
call_return_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
unhandled_count = 0
def is_table_empty(table_name):
do_query(query, 'SELECT * FROM ' + table_name + ' LIMIT 1');
if query.next():
return False
return True
def drop(table_name):
do_query(query, 'DROP VIEW ' + table_name + '_view');
do_query(query, 'DROP TABLE ' + table_name);
def trace_end():
printdate("Copying to database...")
copy_output_file(evsel_file, "selected_events")
@ -615,6 +798,12 @@ def trace_end():
copy_output_file(call_path_file, "call_paths")
if perf_db_export_calls:
copy_output_file(call_file, "calls")
copy_output_file(ptwrite_file, "ptwrite")
copy_output_file(cbr_file, "cbr")
copy_output_file(mwait_file, "mwait")
copy_output_file(pwre_file, "pwre")
copy_output_file(exstop_file, "exstop")
copy_output_file(pwrx_file, "pwrx")
printdate("Removing intermediate files...")
remove_output_file(evsel_file)
@ -630,6 +819,12 @@ def trace_end():
remove_output_file(call_path_file)
if perf_db_export_calls:
remove_output_file(call_file)
remove_output_file(ptwrite_file)
remove_output_file(cbr_file)
remove_output_file(mwait_file)
remove_output_file(pwre_file)
remove_output_file(exstop_file)
remove_output_file(pwrx_file)
os.rmdir(output_dir_name)
printdate("Adding primary keys")
do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)')
@ -645,6 +840,12 @@ def trace_end():
do_query(query, 'ALTER TABLE call_paths ADD PRIMARY KEY (id)')
if perf_db_export_calls:
do_query(query, 'ALTER TABLE calls ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE ptwrite ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE cbr ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE mwait ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE pwre ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE exstop ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE pwrx ADD PRIMARY KEY (id)')
printdate("Adding foreign keys")
do_query(query, 'ALTER TABLE threads '
@ -680,6 +881,30 @@ def trace_end():
'ADD CONSTRAINT parent_call_pathfk FOREIGN KEY (parent_call_path_id) REFERENCES call_paths (id)')
do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)')
do_query(query, 'ALTER TABLE ptwrite '
'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)')
do_query(query, 'ALTER TABLE cbr '
'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)')
do_query(query, 'ALTER TABLE mwait '
'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)')
do_query(query, 'ALTER TABLE pwre '
'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)')
do_query(query, 'ALTER TABLE exstop '
'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)')
do_query(query, 'ALTER TABLE pwrx '
'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)')
printdate("Dropping unused tables")
if is_table_empty("ptwrite"):
drop("ptwrite")
if is_table_empty("mwait") and is_table_empty("pwre") and is_table_empty("exstop") and is_table_empty("pwrx"):
drop("mwait")
drop("pwre")
drop("exstop")
drop("pwrx")
do_query(query, 'DROP VIEW power_events_view');
if is_table_empty("cbr"):
drop("cbr")
if (unhandled_count):
printdate("Warning: ", unhandled_count, " unhandled events")
@ -747,11 +972,11 @@ def branch_type_table(branch_type, name, *x):
value = struct.pack(fmt, 2, 4, branch_type, n, name)
branch_type_file.write(value)
def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, call_path_id, *x):
def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, call_path_id, insn_cnt, cyc_cnt, *x):
if branches:
value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiBiq", 18, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx, 8, call_path_id)
value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiBiqiqiq", 20, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx, 8, call_path_id, 8, insn_cnt, 8, cyc_cnt)
else:
value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiBiq", 22, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx, 8, call_path_id)
value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiBiqiqiq", 24, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx, 8, call_path_id, 8, insn_cnt, 8, cyc_cnt)
sample_file.write(value)
def call_path_table(cp_id, parent_id, symbol_id, ip, *x):
@ -759,7 +984,70 @@ def call_path_table(cp_id, parent_id, symbol_id, ip, *x):
value = struct.pack(fmt, 4, 8, cp_id, 8, parent_id, 8, symbol_id, 8, ip)
call_path_file.write(value)
def call_return_table(cr_id, thread_id, comm_id, call_path_id, call_time, return_time, branch_count, call_id, return_id, parent_call_path_id, flags, parent_id, *x):
fmt = "!hiqiqiqiqiqiqiqiqiqiqiiiq"
value = struct.pack(fmt, 12, 8, cr_id, 8, thread_id, 8, comm_id, 8, call_path_id, 8, call_time, 8, return_time, 8, branch_count, 8, call_id, 8, return_id, 8, parent_call_path_id, 4, flags, 8, parent_id)
def call_return_table(cr_id, thread_id, comm_id, call_path_id, call_time, return_time, branch_count, call_id, return_id, parent_call_path_id, flags, parent_id, insn_cnt, cyc_cnt, *x):
fmt = "!hiqiqiqiqiqiqiqiqiqiqiiiqiqiq"
value = struct.pack(fmt, 14, 8, cr_id, 8, thread_id, 8, comm_id, 8, call_path_id, 8, call_time, 8, return_time, 8, branch_count, 8, call_id, 8, return_id, 8, parent_call_path_id, 4, flags, 8, parent_id, 8, insn_cnt, 8, cyc_cnt)
call_file.write(value)
def ptwrite(id, raw_buf):
data = struct.unpack_from("<IQ", raw_buf)
flags = data[0]
payload = data[1]
exact_ip = flags & 1
value = struct.pack("!hiqiqiB", 3, 8, id, 8, payload, 1, exact_ip)
ptwrite_file.write(value)
def cbr(id, raw_buf):
data = struct.unpack_from("<BBBBII", raw_buf)
cbr = data[0]
MHz = (data[4] + 500) / 1000
percent = ((cbr * 1000 / data[2]) + 5) / 10
value = struct.pack("!hiqiiiiii", 4, 8, id, 4, cbr, 4, MHz, 4, percent)
cbr_file.write(value)
def mwait(id, raw_buf):
data = struct.unpack_from("<IQ", raw_buf)
payload = data[1]
hints = payload & 0xff
extensions = (payload >> 32) & 0x3
value = struct.pack("!hiqiiii", 3, 8, id, 4, hints, 4, extensions)
mwait_file.write(value)
def pwre(id, raw_buf):
data = struct.unpack_from("<IQ", raw_buf)
payload = data[1]
hw = (payload >> 7) & 1
cstate = (payload >> 12) & 0xf
subcstate = (payload >> 8) & 0xf
value = struct.pack("!hiqiiiiiB", 4, 8, id, 4, cstate, 4, subcstate, 1, hw)
pwre_file.write(value)
def exstop(id, raw_buf):
data = struct.unpack_from("<I", raw_buf)
flags = data[0]
exact_ip = flags & 1
value = struct.pack("!hiqiB", 2, 8, id, 1, exact_ip)
exstop_file.write(value)
def pwrx(id, raw_buf):
data = struct.unpack_from("<IQ", raw_buf)
payload = data[1]
deepest_cstate = payload & 0xf
last_cstate = (payload >> 4) & 0xf
wake_reason = (payload >> 8) & 0xf
value = struct.pack("!hiqiiiiii", 4, 8, id, 4, deepest_cstate, 4, last_cstate, 4, wake_reason)
pwrx_file.write(value)
def synth_data(id, config, raw_buf, *x):
if config == 0:
ptwrite(id, raw_buf)
elif config == 1:
mwait(id, raw_buf)
elif config == 2:
pwre(id, raw_buf)
elif config == 3:
exstop(id, raw_buf)
elif config == 4:
pwrx(id, raw_buf)
elif config == 5:
cbr(id, raw_buf)

319
tools/perf/scripts/python/export-to-sqlite.py
View File

@ -21,6 +21,26 @@ import datetime
# provides LGPL-licensed Python bindings for Qt. You will also need the package
# libqt4-sql-sqlite for Qt sqlite3 support.
#
# Examples of installing pyside:
#
# ubuntu:
#
# $ sudo apt-get install python-pyside.qtsql libqt4-sql-psql
#
# Alternately, to use Python3 and/or pyside 2, one of the following:
#
# $ sudo apt-get install python3-pyside.qtsql libqt4-sql-psql
# $ sudo apt-get install python-pyside2.qtsql libqt5sql5-psql
# $ sudo apt-get install python3-pyside2.qtsql libqt5sql5-psql
# fedora:
#
# $ sudo yum install python-pyside
#
# Alternately, to use Python3 and/or pyside 2, one of the following:
# $ sudo yum install python3-pyside
# $ pip install --user PySide2
# $ pip3 install --user PySide2
#
# An example of using this script with Intel PT:
#
# $ perf record -e intel_pt//u ls
@ -49,7 +69,16 @@ import datetime
# difference is the 'transaction' column of the 'samples' table which is
# renamed 'transaction_' in sqlite because 'transaction' is a reserved word.
from PySide.QtSql import *
pyside_version_1 = True
if not "pyside-version-1" in sys.argv:
try:
from PySide2.QtSql import *
pyside_version_1 = False
except:
pass
if pyside_version_1:
from PySide.QtSql import *
sys.path.append(os.environ['PERF_EXEC_PATH'] + \
'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
@ -69,11 +98,12 @@ def printdate(*args, **kw_args):
print(datetime.datetime.today(), *args, sep=' ', **kw_args)
def usage():
printerr("Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>]");
printerr("where: columns 'all' or 'branches'");
printerr(" calls 'calls' => create calls and call_paths table");
printerr(" callchains 'callchains' => create call_paths table");
raise Exception("Too few arguments")
printerr("Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>] [<pyside-version-1>]");
printerr("where: columns 'all' or 'branches'");
printerr(" calls 'calls' => create calls and call_paths table");
printerr(" callchains 'callchains' => create call_paths table");
printerr(" pyside-version-1 'pyside-version-1' => use pyside version 1");
raise Exception("Too few or bad arguments")
if (len(sys.argv) < 2):
usage()
@ -95,6 +125,8 @@ for i in range(3,len(sys.argv)):
perf_db_export_calls = True
elif (sys.argv[i] == "callchains"):
perf_db_export_callchains = True
elif (sys.argv[i] == "pyside-version-1"):
pass
else:
usage()
@ -186,7 +218,9 @@ if branches:
'to_ip bigint,'
'branch_type integer,'
'in_tx boolean,'
'call_path_id bigint)')
'call_path_id bigint,'
'insn_count bigint,'
'cyc_count bigint)')
else:
do_query(query, 'CREATE TABLE samples ('
'id integer NOT NULL PRIMARY KEY,'
@ -210,7 +244,9 @@ else:
'data_src bigint,'
'branch_type integer,'
'in_tx boolean,'
'call_path_id bigint)')
'call_path_id bigint,'
'insn_count bigint,'
'cyc_count bigint)')
if perf_db_export_calls or perf_db_export_callchains:
do_query(query, 'CREATE TABLE call_paths ('
@ -231,7 +267,41 @@ if perf_db_export_calls:
'return_id bigint,'
'parent_call_path_id bigint,'
'flags integer,'
'parent_id bigint)')
'parent_id bigint,'
'insn_count bigint,'
'cyc_count bigint)')
do_query(query, 'CREATE TABLE ptwrite ('
'id integer NOT NULL PRIMARY KEY,'
'payload bigint,'
'exact_ip integer)')
do_query(query, 'CREATE TABLE cbr ('
'id integer NOT NULL PRIMARY KEY,'
'cbr integer,'
'mhz integer,'
'percent integer)')
do_query(query, 'CREATE TABLE mwait ('
'id integer NOT NULL PRIMARY KEY,'
'hints integer,'
'extensions integer)')
do_query(query, 'CREATE TABLE pwre ('
'id integer NOT NULL PRIMARY KEY,'
'cstate integer,'
'subcstate integer,'
'hw integer)')
do_query(query, 'CREATE TABLE exstop ('
'id integer NOT NULL PRIMARY KEY,'
'exact_ip integer)')
do_query(query, 'CREATE TABLE pwrx ('
'id integer NOT NULL PRIMARY KEY,'
'deepest_cstate integer,'
'last_cstate integer,'
'wake_reason integer)')
# printf was added to sqlite in version 3.8.3
sqlite_has_printf = False
@ -327,6 +397,9 @@ if perf_db_export_calls:
'return_time,'
'return_time - call_time AS elapsed_time,'
'branch_count,'
'insn_count,'
'cyc_count,'
'CASE WHEN cyc_count=0 THEN CAST(0 AS FLOAT) ELSE ROUND(CAST(insn_count AS FLOAT) / cyc_count, 2) END AS IPC,'
'call_id,'
'return_id,'
'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,'
@ -352,9 +425,108 @@ do_query(query, 'CREATE VIEW samples_view AS '
'to_sym_offset,'
'(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,'
'(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,'
'in_tx'
'in_tx,'
'insn_count,'
'cyc_count,'
'CASE WHEN cyc_count=0 THEN CAST(0 AS FLOAT) ELSE ROUND(CAST(insn_count AS FLOAT) / cyc_count, 2) END AS IPC'
' FROM samples')
do_query(query, 'CREATE VIEW ptwrite_view AS '
'SELECT '
'ptwrite.id,'
'time,'
'cpu,'
+ emit_to_hex('payload') + ' AS payload_hex,'
'CASE WHEN exact_ip=0 THEN \'False\' ELSE \'True\' END AS exact_ip'
' FROM ptwrite'
' INNER JOIN samples ON samples.id = ptwrite.id')
do_query(query, 'CREATE VIEW cbr_view AS '
'SELECT '
'cbr.id,'
'time,'
'cpu,'
'cbr,'
'mhz,'
'percent'
' FROM cbr'
' INNER JOIN samples ON samples.id = cbr.id')
do_query(query, 'CREATE VIEW mwait_view AS '
'SELECT '
'mwait.id,'
'time,'
'cpu,'
+ emit_to_hex('hints') + ' AS hints_hex,'
+ emit_to_hex('extensions') + ' AS extensions_hex'
' FROM mwait'
' INNER JOIN samples ON samples.id = mwait.id')
do_query(query, 'CREATE VIEW pwre_view AS '
'SELECT '
'pwre.id,'
'time,'
'cpu,'
'cstate,'
'subcstate,'
'CASE WHEN hw=0 THEN \'False\' ELSE \'True\' END AS hw'
' FROM pwre'
' INNER JOIN samples ON samples.id = pwre.id')
do_query(query, 'CREATE VIEW exstop_view AS '
'SELECT '
'exstop.id,'
'time,'
'cpu,'
'CASE WHEN exact_ip=0 THEN \'False\' ELSE \'True\' END AS exact_ip'
' FROM exstop'
' INNER JOIN samples ON samples.id = exstop.id')
do_query(query, 'CREATE VIEW pwrx_view AS '
'SELECT '
'pwrx.id,'
'time,'
'cpu,'
'deepest_cstate,'
'last_cstate,'
'CASE WHEN wake_reason=1 THEN \'Interrupt\''
' WHEN wake_reason=2 THEN \'Timer Deadline\''
' WHEN wake_reason=4 THEN \'Monitored Address\''
' WHEN wake_reason=8 THEN \'HW\''
' ELSE wake_reason '
'END AS wake_reason'
' FROM pwrx'
' INNER JOIN samples ON samples.id = pwrx.id')
do_query(query, 'CREATE VIEW power_events_view AS '
'SELECT '
'samples.id,'
'time,'
'cpu,'
'selected_events.name AS event,'
'CASE WHEN selected_events.name=\'cbr\' THEN (SELECT cbr FROM cbr WHERE cbr.id = samples.id) ELSE "" END AS cbr,'
'CASE WHEN selected_events.name=\'cbr\' THEN (SELECT mhz FROM cbr WHERE cbr.id = samples.id) ELSE "" END AS mhz,'
'CASE WHEN selected_events.name=\'cbr\' THEN (SELECT percent FROM cbr WHERE cbr.id = samples.id) ELSE "" END AS percent,'
'CASE WHEN selected_events.name=\'mwait\' THEN (SELECT ' + emit_to_hex('hints') + ' FROM mwait WHERE mwait.id = samples.id) ELSE "" END AS hints_hex,'
'CASE WHEN selected_events.name=\'mwait\' THEN (SELECT ' + emit_to_hex('extensions') + ' FROM mwait WHERE mwait.id = samples.id) ELSE "" END AS extensions_hex,'
'CASE WHEN selected_events.name=\'pwre\' THEN (SELECT cstate FROM pwre WHERE pwre.id = samples.id) ELSE "" END AS cstate,'
'CASE WHEN selected_events.name=\'pwre\' THEN (SELECT subcstate FROM pwre WHERE pwre.id = samples.id) ELSE "" END AS subcstate,'
'CASE WHEN selected_events.name=\'pwre\' THEN (SELECT hw FROM pwre WHERE pwre.id = samples.id) ELSE "" END AS hw,'
'CASE WHEN selected_events.name=\'exstop\' THEN (SELECT exact_ip FROM exstop WHERE exstop.id = samples.id) ELSE "" END AS exact_ip,'
'CASE WHEN selected_events.name=\'pwrx\' THEN (SELECT deepest_cstate FROM pwrx WHERE pwrx.id = samples.id) ELSE "" END AS deepest_cstate,'
'CASE WHEN selected_events.name=\'pwrx\' THEN (SELECT last_cstate FROM pwrx WHERE pwrx.id = samples.id) ELSE "" END AS last_cstate,'
'CASE WHEN selected_events.name=\'pwrx\' THEN (SELECT '
'CASE WHEN wake_reason=1 THEN \'Interrupt\''
' WHEN wake_reason=2 THEN \'Timer Deadline\''
' WHEN wake_reason=4 THEN \'Monitored Address\''
' WHEN wake_reason=8 THEN \'HW\''
' ELSE wake_reason '
'END'
' FROM pwrx WHERE pwrx.id = samples.id) ELSE "" END AS wake_reason'
' FROM samples'
' INNER JOIN selected_events ON selected_events.id = evsel_id'
' WHERE selected_events.name IN (\'cbr\',\'mwait\',\'exstop\',\'pwre\',\'pwrx\')')
do_query(query, 'END TRANSACTION')
evsel_query = QSqlQuery(db)
@ -375,15 +547,27 @@ branch_type_query = QSqlQuery(db)
branch_type_query.prepare("INSERT INTO branch_types VALUES (?, ?)")
sample_query = QSqlQuery(db)
if branches:
sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
else:
sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
if perf_db_export_calls or perf_db_export_callchains:
call_path_query = QSqlQuery(db)
call_path_query.prepare("INSERT INTO call_paths VALUES (?, ?, ?, ?)")
if perf_db_export_calls:
call_query = QSqlQuery(db)
call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
ptwrite_query = QSqlQuery(db)
ptwrite_query.prepare("INSERT INTO ptwrite VALUES (?, ?, ?)")
cbr_query = QSqlQuery(db)
cbr_query.prepare("INSERT INTO cbr VALUES (?, ?, ?, ?)")
mwait_query = QSqlQuery(db)
mwait_query.prepare("INSERT INTO mwait VALUES (?, ?, ?)")
pwre_query = QSqlQuery(db)
pwre_query.prepare("INSERT INTO pwre VALUES (?, ?, ?, ?)")
exstop_query = QSqlQuery(db)
exstop_query.prepare("INSERT INTO exstop VALUES (?, ?)")
pwrx_query = QSqlQuery(db)
pwrx_query.prepare("INSERT INTO pwrx VALUES (?, ?, ?, ?)")
def trace_begin():
printdate("Writing records...")
@ -395,13 +579,23 @@ def trace_begin():
comm_table(0, "unknown")
dso_table(0, 0, "unknown", "unknown", "")
symbol_table(0, 0, 0, 0, 0, "unknown")
sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
if perf_db_export_calls or perf_db_export_callchains:
call_path_table(0, 0, 0, 0)
call_return_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
call_return_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
unhandled_count = 0
def is_table_empty(table_name):
do_query(query, 'SELECT * FROM ' + table_name + ' LIMIT 1');
if query.next():
return False
return True
def drop(table_name):
do_query(query, 'DROP VIEW ' + table_name + '_view');
do_query(query, 'DROP TABLE ' + table_name);
def trace_end():
do_query(query, 'END TRANSACTION')
@ -410,6 +604,18 @@ def trace_end():
do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)')
printdate("Dropping unused tables")
if is_table_empty("ptwrite"):
drop("ptwrite")
if is_table_empty("mwait") and is_table_empty("pwre") and is_table_empty("exstop") and is_table_empty("pwrx"):
drop("mwait")
drop("pwre")
drop("exstop")
drop("pwrx")
do_query(query, 'DROP VIEW power_events_view');
if is_table_empty("cbr"):
drop("cbr")
if (unhandled_count):
printdate("Warning: ", unhandled_count, " unhandled events")
printdate("Done")
@ -454,14 +660,91 @@ def sample_table(*x):
if branches:
for xx in x[0:15]:
sample_query.addBindValue(str(xx))
for xx in x[19:22]:
for xx in x[19:24]:
sample_query.addBindValue(str(xx))
do_query_(sample_query)
else:
bind_exec(sample_query, 22, x)
bind_exec(sample_query, 24, x)
def call_path_table(*x):
bind_exec(call_path_query, 4, x)
def call_return_table(*x):
bind_exec(call_query, 12, x)
bind_exec(call_query, 14, x)
def ptwrite(id, raw_buf):
data = struct.unpack_from("<IQ", raw_buf)
flags = data[0]
payload = data[1]
exact_ip = flags & 1
ptwrite_query.addBindValue(str(id))
ptwrite_query.addBindValue(str(payload))
ptwrite_query.addBindValue(str(exact_ip))
do_query_(ptwrite_query)
def cbr(id, raw_buf):
data = struct.unpack_from("<BBBBII", raw_buf)
cbr = data[0]
MHz = (data[4] + 500) / 1000
percent = ((cbr * 1000 / data[2]) + 5) / 10
cbr_query.addBindValue(str(id))
cbr_query.addBindValue(str(cbr))
cbr_query.addBindValue(str(MHz))
cbr_query.addBindValue(str(percent))
do_query_(cbr_query)
def mwait(id, raw_buf):
data = struct.unpack_from("<IQ", raw_buf)
payload = data[1]
hints = payload & 0xff
extensions = (payload >> 32) & 0x3
mwait_query.addBindValue(str(id))
mwait_query.addBindValue(str(hints))
mwait_query.addBindValue(str(extensions))
do_query_(mwait_query)
def pwre(id, raw_buf):
data = struct.unpack_from("<IQ", raw_buf)
payload = data[1]
hw = (payload >> 7) & 1
cstate = (payload >> 12) & 0xf
subcstate = (payload >> 8) & 0xf
pwre_query.addBindValue(str(id))
pwre_query.addBindValue(str(cstate))
pwre_query.addBindValue(str(subcstate))
pwre_query.addBindValue(str(hw))
do_query_(pwre_query)
def exstop(id, raw_buf):
data = struct.unpack_from("<I", raw_buf)
flags = data[0]
exact_ip = flags & 1
exstop_query.addBindValue(str(id))
exstop_query.addBindValue(str(exact_ip))
do_query_(exstop_query)
def pwrx(id, raw_buf):
data = struct.unpack_from("<IQ", raw_buf)
payload = data[1]
deepest_cstate = payload & 0xf
last_cstate = (payload >> 4) & 0xf
wake_reason = (payload >> 8) & 0xf
pwrx_query.addBindValue(str(id))
pwrx_query.addBindValue(str(deepest_cstate))
pwrx_query.addBindValue(str(last_cstate))
pwrx_query.addBindValue(str(wake_reason))
do_query_(pwrx_query)
def synth_data(id, config, raw_buf, *x):
if config == 0:
ptwrite(id, raw_buf)
elif config == 1:
mwait(id, raw_buf)
elif config == 2:
pwre(id, raw_buf)
elif config == 3:
exstop(id, raw_buf)
elif config == 4:
pwrx(id, raw_buf)
elif config == 5:
cbr(id, raw_buf)

343
tools/perf/scripts/python/exported-sql-viewer.py
View File

@ -1,4 +1,4 @@
#!/usr/bin/env python2
#!/usr/bin/env python
# SPDX-License-Identifier: GPL-2.0
# exported-sql-viewer.py: view data from sql database
# Copyright (c) 2014-2018, Intel Corporation.
@ -91,6 +91,7 @@
from __future__ import print_function
import sys
import argparse
import weakref
import threading
import string
@ -104,10 +105,23 @@ except ImportError:
glb_nsz = 16
import re
import os
from PySide.QtCore import *
from PySide.QtGui import *
from PySide.QtSql import *
pyside_version_1 = True
if not "--pyside-version-1" in sys.argv:
try:
from PySide2.QtCore import *
from PySide2.QtGui import *
from PySide2.QtSql import *
from PySide2.QtWidgets import *
pyside_version_1 = False
except:
pass
if pyside_version_1:
from PySide.QtCore import *
from PySide.QtGui import *
from PySide.QtSql import *
from decimal import *
from ctypes import *
from multiprocessing import Process, Array, Value, Event
@ -186,9 +200,10 @@ class Thread(QThread):
class TreeModel(QAbstractItemModel):
def __init__(self, glb, parent=None):
def __init__(self, glb, params, parent=None):
super(TreeModel, self).__init__(parent)
self.glb = glb
self.params = params
self.root = self.GetRoot()
self.last_row_read = 0
@ -385,6 +400,7 @@ class FindBar():
def Activate(self):
self.bar.show()
self.textbox.lineEdit().selectAll()
self.textbox.setFocus()
def Deactivate(self):
@ -449,8 +465,9 @@ class FindBar():
class CallGraphLevelItemBase(object):
def __init__(self, glb, row, parent_item):
def __init__(self, glb, params, row, parent_item):
self.glb = glb
self.params = params
self.row = row
self.parent_item = parent_item
self.query_done = False;
@ -489,18 +506,24 @@ class CallGraphLevelItemBase(object):
class CallGraphLevelTwoPlusItemBase(CallGraphLevelItemBase):
def __init__(self, glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item):
super(CallGraphLevelTwoPlusItemBase, self).__init__(glb, row, parent_item)
def __init__(self, glb, params, row, comm_id, thread_id, call_path_id, time, insn_cnt, cyc_cnt, branch_count, parent_item):
super(CallGraphLevelTwoPlusItemBase, self).__init__(glb, params, row, parent_item)
self.comm_id = comm_id
self.thread_id = thread_id
self.call_path_id = call_path_id
self.insn_cnt = insn_cnt
self.cyc_cnt = cyc_cnt
self.branch_count = branch_count
self.time = time
def Select(self):
self.query_done = True;
query = QSqlQuery(self.glb.db)
QueryExec(query, "SELECT call_path_id, name, short_name, COUNT(calls.id), SUM(return_time - call_time), SUM(branch_count)"
if self.params.have_ipc:
ipc_str = ", SUM(insn_count), SUM(cyc_count)"
else:
ipc_str = ""
QueryExec(query, "SELECT call_path_id, name, short_name, COUNT(calls.id), SUM(return_time - call_time)" + ipc_str + ", SUM(branch_count)"
" FROM calls"
" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
@ -511,7 +534,15 @@ class CallGraphLevelTwoPlusItemBase(CallGraphLevelItemBase):
" GROUP BY call_path_id, name, short_name"
" ORDER BY call_path_id")
while query.next():
child_item = CallGraphLevelThreeItem(self.glb, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), int(query.value(5)), self)
if self.params.have_ipc:
insn_cnt = int(query.value(5))
cyc_cnt = int(query.value(6))
branch_count = int(query.value(7))
else:
insn_cnt = 0
cyc_cnt = 0
branch_count = int(query.value(5))
child_item = CallGraphLevelThreeItem(self.glb, self.params, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), insn_cnt, cyc_cnt, branch_count, self)
self.child_items.append(child_item)
self.child_count += 1
@ -519,37 +550,57 @@ class CallGraphLevelTwoPlusItemBase(CallGraphLevelItemBase):
class CallGraphLevelThreeItem(CallGraphLevelTwoPlusItemBase):
def __init__(self, glb, row, comm_id, thread_id, call_path_id, name, dso, count, time, branch_count, parent_item):
super(CallGraphLevelThreeItem, self).__init__(glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item)
def __init__(self, glb, params, row, comm_id, thread_id, call_path_id, name, dso, count, time, insn_cnt, cyc_cnt, branch_count, parent_item):
super(CallGraphLevelThreeItem, self).__init__(glb, params, row, comm_id, thread_id, call_path_id, time, insn_cnt, cyc_cnt, branch_count, parent_item)
dso = dsoname(dso)
self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
if self.params.have_ipc:
insn_pcnt = PercentToOneDP(insn_cnt, parent_item.insn_cnt)
cyc_pcnt = PercentToOneDP(cyc_cnt, parent_item.cyc_cnt)
br_pcnt = PercentToOneDP(branch_count, parent_item.branch_count)
ipc = CalcIPC(cyc_cnt, insn_cnt)
self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(insn_cnt), insn_pcnt, str(cyc_cnt), cyc_pcnt, ipc, str(branch_count), br_pcnt ]
else:
self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
self.dbid = call_path_id
# Context-sensitive call graph data model level two item
class CallGraphLevelTwoItem(CallGraphLevelTwoPlusItemBase):
def __init__(self, glb, row, comm_id, thread_id, pid, tid, parent_item):
super(CallGraphLevelTwoItem, self).__init__(glb, row, comm_id, thread_id, 1, 0, 0, parent_item)
self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
def __init__(self, glb, params, row, comm_id, thread_id, pid, tid, parent_item):
super(CallGraphLevelTwoItem, self).__init__(glb, params, row, comm_id, thread_id, 1, 0, 0, 0, 0, parent_item)
if self.params.have_ipc:
self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", "", "", "", "", "", ""]
else:
self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
self.dbid = thread_id
def Select(self):
super(CallGraphLevelTwoItem, self).Select()
for child_item in self.child_items:
self.time += child_item.time
self.insn_cnt += child_item.insn_cnt
self.cyc_cnt += child_item.cyc_cnt
self.branch_count += child_item.branch_count
for child_item in self.child_items:
child_item.data[4] = PercentToOneDP(child_item.time, self.time)
child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
if self.params.have_ipc:
child_item.data[6] = PercentToOneDP(child_item.insn_cnt, self.insn_cnt)
child_item.data[8] = PercentToOneDP(child_item.cyc_cnt, self.cyc_cnt)
child_item.data[11] = PercentToOneDP(child_item.branch_count, self.branch_count)
else:
child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
# Context-sensitive call graph data model level one item
class CallGraphLevelOneItem(CallGraphLevelItemBase):
def __init__(self, glb, row, comm_id, comm, parent_item):
super(CallGraphLevelOneItem, self).__init__(glb, row, parent_item)
self.data = [comm, "", "", "", "", "", ""]
def __init__(self, glb, params, row, comm_id, comm, parent_item):
super(CallGraphLevelOneItem, self).__init__(glb, params, row, parent_item)
if self.params.have_ipc:
self.data = [comm, "", "", "", "", "", "", "", "", "", "", ""]
else:
self.data = [comm, "", "", "", "", "", ""]
self.dbid = comm_id
def Select(self):
@ -560,7 +611,7 @@ class CallGraphLevelOneItem(CallGraphLevelItemBase):
" INNER JOIN threads ON thread_id = threads.id"
" WHERE comm_id = " + str(self.dbid))
while query.next():
child_item = CallGraphLevelTwoItem(self.glb, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
child_item = CallGraphLevelTwoItem(self.glb, self.params, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
self.child_items.append(child_item)
self.child_count += 1
@ -568,8 +619,8 @@ class CallGraphLevelOneItem(CallGraphLevelItemBase):
class CallGraphRootItem(CallGraphLevelItemBase):
def __init__(self, glb):
super(CallGraphRootItem, self).__init__(glb, 0, None)
def __init__(self, glb, params):
super(CallGraphRootItem, self).__init__(glb, params, 0, None)
self.dbid = 0
self.query_done = True;
query = QSqlQuery(glb.db)
@ -577,16 +628,23 @@ class CallGraphRootItem(CallGraphLevelItemBase):
while query.next():
if not query.value(0):
continue
child_item = CallGraphLevelOneItem(glb, self.child_count, query.value(0), query.value(1), self)
child_item = CallGraphLevelOneItem(glb, params, self.child_count, query.value(0), query.value(1), self)
self.child_items.append(child_item)
self.child_count += 1
# Call graph model parameters
class CallGraphModelParams():
def __init__(self, glb, parent=None):
self.have_ipc = IsSelectable(glb.db, "calls", columns = "insn_count, cyc_count")
# Context-sensitive call graph data model base
class CallGraphModelBase(TreeModel):
def __init__(self, glb, parent=None):
super(CallGraphModelBase, self).__init__(glb, parent)
super(CallGraphModelBase, self).__init__(glb, CallGraphModelParams(glb), parent)
def FindSelect(self, value, pattern, query):
if pattern:
@ -668,17 +726,26 @@ class CallGraphModel(CallGraphModelBase):
super(CallGraphModel, self).__init__(glb, parent)
def GetRoot(self):
return CallGraphRootItem(self.glb)
return CallGraphRootItem(self.glb, self.params)
def columnCount(self, parent=None):
return 7
if self.params.have_ipc:
return 12
else:
return 7
def columnHeader(self, column):
headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
if self.params.have_ipc:
headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Insn Cnt", "Insn Cnt (%)", "Cyc Cnt", "Cyc Cnt (%)", "IPC", "Branch Count ", "Branch Count (%) "]
else:
headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
return headers[column]
def columnAlignment(self, column):
alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
if self.params.have_ipc:
alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
else:
alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
return alignment[column]
def DoFindSelect(self, query, match):
@ -715,11 +782,13 @@ class CallGraphModel(CallGraphModelBase):
class CallTreeLevelTwoPlusItemBase(CallGraphLevelItemBase):
def __init__(self, glb, row, comm_id, thread_id, calls_id, time, branch_count, parent_item):
super(CallTreeLevelTwoPlusItemBase, self).__init__(glb, row, parent_item)
def __init__(self, glb, params, row, comm_id, thread_id, calls_id, time, insn_cnt, cyc_cnt, branch_count, parent_item):
super(CallTreeLevelTwoPlusItemBase, self).__init__(glb, params, row, parent_item)
self.comm_id = comm_id
self.thread_id = thread_id
self.calls_id = calls_id
self.insn_cnt = insn_cnt
self.cyc_cnt = cyc_cnt
self.branch_count = branch_count
self.time = time
@ -729,8 +798,12 @@ class CallTreeLevelTwoPlusItemBase(CallGraphLevelItemBase):
comm_thread = " AND comm_id = " + str(self.comm_id) + " AND thread_id = " + str(self.thread_id)
else:
comm_thread = ""
if self.params.have_ipc:
ipc_str = ", insn_count, cyc_count"
else:
ipc_str = ""
query = QSqlQuery(self.glb.db)
QueryExec(query, "SELECT calls.id, name, short_name, call_time, return_time - call_time, branch_count"
QueryExec(query, "SELECT calls.id, name, short_name, call_time, return_time - call_time" + ipc_str + ", branch_count"
" FROM calls"
" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
@ -738,7 +811,15 @@ class CallTreeLevelTwoPlusItemBase(CallGraphLevelItemBase):
" WHERE calls.parent_id = " + str(self.calls_id) + comm_thread +
" ORDER BY call_time, calls.id")
while query.next():
child_item = CallTreeLevelThreeItem(self.glb, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), int(query.value(5)), self)
if self.params.have_ipc:
insn_cnt = int(query.value(5))
cyc_cnt = int(query.value(6))
branch_count = int(query.value(7))
else:
insn_cnt = 0
cyc_cnt = 0
branch_count = int(query.value(5))
child_item = CallTreeLevelThreeItem(self.glb, self.params, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), insn_cnt, cyc_cnt, branch_count, self)
self.child_items.append(child_item)
self.child_count += 1
@ -746,37 +827,57 @@ class CallTreeLevelTwoPlusItemBase(CallGraphLevelItemBase):
class CallTreeLevelThreeItem(CallTreeLevelTwoPlusItemBase):
def __init__(self, glb, row, comm_id, thread_id, calls_id, name, dso, count, time, branch_count, parent_item):
super(CallTreeLevelThreeItem, self).__init__(glb, row, comm_id, thread_id, calls_id, time, branch_count, parent_item)
def __init__(self, glb, params, row, comm_id, thread_id, calls_id, name, dso, count, time, insn_cnt, cyc_cnt, branch_count, parent_item):
super(CallTreeLevelThreeItem, self).__init__(glb, params, row, comm_id, thread_id, calls_id, time, insn_cnt, cyc_cnt, branch_count, parent_item)
dso = dsoname(dso)
self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
if self.params.have_ipc:
insn_pcnt = PercentToOneDP(insn_cnt, parent_item.insn_cnt)
cyc_pcnt = PercentToOneDP(cyc_cnt, parent_item.cyc_cnt)
br_pcnt = PercentToOneDP(branch_count, parent_item.branch_count)
ipc = CalcIPC(cyc_cnt, insn_cnt)
self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(insn_cnt), insn_pcnt, str(cyc_cnt), cyc_pcnt, ipc, str(branch_count), br_pcnt ]
else:
self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
self.dbid = calls_id
# Call tree data model level two item
class CallTreeLevelTwoItem(CallTreeLevelTwoPlusItemBase):
def __init__(self, glb, row, comm_id, thread_id, pid, tid, parent_item):
super(CallTreeLevelTwoItem, self).__init__(glb, row, comm_id, thread_id, 0, 0, 0, parent_item)
self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
def __init__(self, glb, params, row, comm_id, thread_id, pid, tid, parent_item):
super(CallTreeLevelTwoItem, self).__init__(glb, params, row, comm_id, thread_id, 0, 0, 0, 0, 0, parent_item)
if self.params.have_ipc:
self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", "", "", "", "", "", ""]
else:
self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
self.dbid = thread_id
def Select(self):
super(CallTreeLevelTwoItem, self).Select()
for child_item in self.child_items:
self.time += child_item.time
self.insn_cnt += child_item.insn_cnt
self.cyc_cnt += child_item.cyc_cnt
self.branch_count += child_item.branch_count
for child_item in self.child_items:
child_item.data[4] = PercentToOneDP(child_item.time, self.time)
child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
if self.params.have_ipc:
child_item.data[6] = PercentToOneDP(child_item.insn_cnt, self.insn_cnt)
child_item.data[8] = PercentToOneDP(child_item.cyc_cnt, self.cyc_cnt)
child_item.data[11] = PercentToOneDP(child_item.branch_count, self.branch_count)
else:
child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
# Call tree data model level one item
class CallTreeLevelOneItem(CallGraphLevelItemBase):
def __init__(self, glb, row, comm_id, comm, parent_item):
super(CallTreeLevelOneItem, self).__init__(glb, row, parent_item)
self.data = [comm, "", "", "", "", "", ""]
def __init__(self, glb, params, row, comm_id, comm, parent_item):
super(CallTreeLevelOneItem, self).__init__(glb, params, row, parent_item)
if self.params.have_ipc:
self.data = [comm, "", "", "", "", "", "", "", "", "", "", ""]
else:
self.data = [comm, "", "", "", "", "", ""]
self.dbid = comm_id
def Select(self):
@ -787,7 +888,7 @@ class CallTreeLevelOneItem(CallGraphLevelItemBase):
" INNER JOIN threads ON thread_id = threads.id"
" WHERE comm_id = " + str(self.dbid))
while query.next():
child_item = CallTreeLevelTwoItem(self.glb, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
child_item = CallTreeLevelTwoItem(self.glb, self.params, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
self.child_items.append(child_item)
self.child_count += 1
@ -795,8 +896,8 @@ class CallTreeLevelOneItem(CallGraphLevelItemBase):
class CallTreeRootItem(CallGraphLevelItemBase):
def __init__(self, glb):
super(CallTreeRootItem, self).__init__(glb, 0, None)
def __init__(self, glb, params):
super(CallTreeRootItem, self).__init__(glb, params, 0, None)
self.dbid = 0
self.query_done = True;
query = QSqlQuery(glb.db)
@ -804,7 +905,7 @@ class CallTreeRootItem(CallGraphLevelItemBase):
while query.next():
if not query.value(0):
continue
child_item = CallTreeLevelOneItem(glb, self.child_count, query.value(0), query.value(1), self)
child_item = CallTreeLevelOneItem(glb, params, self.child_count, query.value(0), query.value(1), self)
self.child_items.append(child_item)
self.child_count += 1
@ -816,17 +917,26 @@ class CallTreeModel(CallGraphModelBase):
super(CallTreeModel, self).__init__(glb, parent)
def GetRoot(self):
return CallTreeRootItem(self.glb)
return CallTreeRootItem(self.glb, self.params)
def columnCount(self, parent=None):
return 7
if self.params.have_ipc:
return 12
else:
return 7
def columnHeader(self, column):
headers = ["Call Path", "Object", "Call Time", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
if self.params.have_ipc:
headers = ["Call Path", "Object", "Call Time", "Time (ns) ", "Time (%) ", "Insn Cnt", "Insn Cnt (%)", "Cyc Cnt", "Cyc Cnt (%)", "IPC", "Branch Count ", "Branch Count (%) "]
else:
headers = ["Call Path", "Object", "Call Time", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
return headers[column]
def columnAlignment(self, column):
alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
if self.params.have_ipc:
alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
else:
alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
return alignment[column]
def DoFindSelect(self, query, match):
@ -1355,11 +1465,11 @@ class FetchMoreRecordsBar():
class BranchLevelTwoItem():
def __init__(self, row, text, parent_item):
def __init__(self, row, col, text, parent_item):
self.row = row
self.parent_item = parent_item
self.data = [""] * 8
self.data[7] = text
self.data = [""] * (col + 1)
self.data[col] = text
self.level = 2
def getParentItem(self):
@ -1391,6 +1501,7 @@ class BranchLevelOneItem():
self.dbid = data[0]
self.level = 1
self.query_done = False
self.br_col = len(self.data) - 1
def getChildItem(self, row):
return self.child_items[row]
@ -1471,7 +1582,7 @@ class BranchLevelOneItem():
while k < 15:
byte_str += " "
k += 1
self.child_items.append(BranchLevelTwoItem(0, byte_str + " " + text, self))
self.child_items.append(BranchLevelTwoItem(0, self.br_col, byte_str + " " + text, self))
self.child_count += 1
else:
return
@ -1522,16 +1633,37 @@ class BranchRootItem():
def getData(self, column):
return ""
# Calculate instructions per cycle
def CalcIPC(cyc_cnt, insn_cnt):
if cyc_cnt and insn_cnt:
ipc = Decimal(float(insn_cnt) / cyc_cnt)
ipc = str(ipc.quantize(Decimal(".01"), rounding=ROUND_HALF_UP))
else:
ipc = "0"
return ipc
# Branch data preparation
def BranchDataPrepBr(query, data):
data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) +
" (" + dsoname(query.value(11)) + ")" + " -> " +
tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) +
" (" + dsoname(query.value(15)) + ")")
def BranchDataPrepIPC(query, data):
insn_cnt = query.value(16)
cyc_cnt = query.value(17)
ipc = CalcIPC(cyc_cnt, insn_cnt)
data.append(insn_cnt)
data.append(cyc_cnt)
data.append(ipc)
def BranchDataPrep(query):
data = []
for i in xrange(0, 8):
data.append(query.value(i))
data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) +
" (" + dsoname(query.value(11)) + ")" + " -> " +
tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) +
" (" + dsoname(query.value(15)) + ")")
BranchDataPrepBr(query, data)
return data
def BranchDataPrepWA(query):
@ -1541,10 +1673,26 @@ def BranchDataPrepWA(query):
data.append("{:>19}".format(query.value(1)))
for i in xrange(2, 8):
data.append(query.value(i))
data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) +
" (" + dsoname(query.value(11)) + ")" + " -> " +
tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) +
" (" + dsoname(query.value(15)) + ")")
BranchDataPrepBr(query, data)
return data
def BranchDataWithIPCPrep(query):
data = []
for i in xrange(0, 8):
data.append(query.value(i))
BranchDataPrepIPC(query, data)
BranchDataPrepBr(query, data)
return data
def BranchDataWithIPCPrepWA(query):
data = []
data.append(query.value(0))
# Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
data.append("{:>19}".format(query.value(1)))
for i in xrange(2, 8):
data.append(query.value(i))
BranchDataPrepIPC(query, data)
BranchDataPrepBr(query, data)
return data
# Branch data model
@ -1554,14 +1702,24 @@ class BranchModel(TreeModel):
progress = Signal(object)
def __init__(self, glb, event_id, where_clause, parent=None):
super(BranchModel, self).__init__(glb, parent)
super(BranchModel, self).__init__(glb, None, parent)
self.event_id = event_id
self.more = True
self.populated = 0
self.have_ipc = IsSelectable(glb.db, "samples", columns = "insn_count, cyc_count")
if self.have_ipc:
select_ipc = ", insn_count, cyc_count"
prep_fn = BranchDataWithIPCPrep
prep_wa_fn = BranchDataWithIPCPrepWA
else:
select_ipc = ""
prep_fn = BranchDataPrep
prep_wa_fn = BranchDataPrepWA
sql = ("SELECT samples.id, time, cpu, comm, pid, tid, branch_types.name,"
" CASE WHEN in_tx = '0' THEN 'No' ELSE 'Yes' END,"
" ip, symbols.name, sym_offset, dsos.short_name,"
" to_ip, to_symbols.name, to_sym_offset, to_dsos.short_name"
+ select_ipc +
" FROM samples"
" INNER JOIN comms ON comm_id = comms.id"
" INNER JOIN threads ON thread_id = threads.id"
@ -1575,9 +1733,9 @@ class BranchModel(TreeModel):
" ORDER BY samples.id"
" LIMIT " + str(glb_chunk_sz))
if pyside_version_1 and sys.version_info[0] == 3:
prep = BranchDataPrepWA
prep = prep_fn
else:
prep = BranchDataPrep
prep = prep_wa_fn
self.fetcher = SQLFetcher(glb, sql, prep, self.AddSample)
self.fetcher.done.connect(self.Update)
self.fetcher.Fetch(glb_chunk_sz)
@ -1586,13 +1744,23 @@ class BranchModel(TreeModel):
return BranchRootItem()
def columnCount(self, parent=None):
return 8
if self.have_ipc:
return 11
else:
return 8
def columnHeader(self, column):
return ("Time", "CPU", "Command", "PID", "TID", "Branch Type", "In Tx", "Branch")[column]
if self.have_ipc:
return ("Time", "CPU", "Command", "PID", "TID", "Branch Type", "In Tx", "Insn Cnt", "Cyc Cnt", "IPC", "Branch")[column]
else:
return ("Time", "CPU", "Command", "PID", "TID", "Branch Type", "In Tx", "Branch")[column]
def columnFont(self, column):
if column != 7:
if self.have_ipc:
br_col = 10
else:
br_col = 7
if column != br_col:
return None
return QFont("Monospace")
@ -2100,10 +2268,10 @@ def GetEventList(db):
# Is a table selectable
def IsSelectable(db, table, sql = ""):
def IsSelectable(db, table, sql = "", columns = "*"):
query = QSqlQuery(db)
try:
QueryExec(query, "SELECT * FROM " + table + " " + sql + " LIMIT 1")
QueryExec(query, "SELECT " + columns + " FROM " + table + " " + sql + " LIMIT 1")
except:
return False
return True
@ -2754,7 +2922,7 @@ class WindowMenu():
action = self.window_menu.addAction(label)
action.setCheckable(True)
action.setChecked(sub_window == self.mdi_area.activeSubWindow())
action.triggered.connect(lambda x=nr: self.setActiveSubWindow(x))
action.triggered.connect(lambda a=None,x=nr: self.setActiveSubWindow(x))
self.window_menu.addAction(action)
nr += 1
@ -2840,6 +3008,12 @@ cd xed
sudo ./mfile.py --prefix=/usr/local install
sudo ldconfig
</pre>
<h3>Instructions per Cycle (IPC)</h3>
If available, IPC information is displayed in columns 'insn_cnt', 'cyc_cnt' and 'IPC'.
<p><b>Intel PT note:</b> The information applies to the blocks of code ending with, and including, that branch.
Due to the granularity of timing information, the number of cycles for some code blocks will not be known.
In that case, 'insn_cnt', 'cyc_cnt' and 'IPC' are zero, but when 'IPC' is displayed it covers the period
since the previous displayed 'IPC'.
<h3>Find</h3>
Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match.
Refer to Python documentation for the regular expression syntax.
@ -3114,14 +3288,14 @@ class MainWindow(QMainWindow):
event = event.split(":")[0]
if event == "branches":
label = "All branches" if branches_events == 1 else "All branches " + "(id=" + dbid + ")"
reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewBranchView(x), self))
reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda a=None,x=dbid: self.NewBranchView(x), self))
label = "Selected branches" if branches_events == 1 else "Selected branches " + "(id=" + dbid + ")"
reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewSelectedBranchView(x), self))
reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda a=None,x=dbid: self.NewSelectedBranchView(x), self))
def TableMenu(self, tables, menu):
table_menu = menu.addMenu("&Tables")
for table in tables:
table_menu.addAction(CreateAction(table, "Create a new window containing a table view", lambda t=table: self.NewTableView(t), self))
table_menu.addAction(CreateAction(table, "Create a new window containing a table view", lambda a=None,t=table: self.NewTableView(t), self))
def NewCallGraph(self):
CallGraphWindow(self.glb, self)
@ -3361,18 +3535,27 @@ class DBRef():
# Main
def Main():
if (len(sys.argv) < 2):
printerr("Usage is: exported-sql-viewer.py {<database name> | --help-only}");
raise Exception("Too few arguments")
usage_str = "exported-sql-viewer.py [--pyside-version-1] <database name>\n" \
" or: exported-sql-viewer.py --help-only"
ap = argparse.ArgumentParser(usage = usage_str, add_help = False)
ap.add_argument("--pyside-version-1", action='store_true')
ap.add_argument("dbname", nargs="?")
ap.add_argument("--help-only", action='store_true')
args = ap.parse_args()
dbname = sys.argv[1]
if dbname == "--help-only":
if args.help_only:
app = QApplication(sys.argv)
mainwindow = HelpOnlyWindow()
mainwindow.show()
err = app.exec_()
sys.exit(err)
dbname = args.dbname
if dbname is None:
ap.print_usage()
print("Too few arguments")
sys.exit(1)
is_sqlite3 = False
try:
f = open(dbname, "rb")

4
tools/perf/tests/Build
View File

@ -1,3 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
perf-y += builtin-test.o
perf-y += parse-events.o
perf-y += dso-data.o
@ -50,6 +52,8 @@ perf-y += perf-hooks.o
perf-y += clang.o
perf-y += unit_number__scnprintf.o
perf-y += mem2node.o
perf-y += map_groups.o
perf-y += time-utils-test.o
$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
$(call rule_mkdir)

1
tools/perf/tests/bp_account.c
View File

@ -1,3 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select
* 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu.

1
tools/perf/tests/bpf-script-example.c
View File

@ -1,3 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
/*
* bpf-script-example.c
* Test basic LLVM building

1
tools/perf/tests/bpf-script-test-kbuild.c
View File

@ -1,3 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
/*
* bpf-script-test-kbuild.c
* Test include from kernel header

1
tools/perf/tests/bpf-script-test-prologue.c
View File

@ -1,3 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
/*
* bpf-script-test-prologue.c
* Test BPF prologue

1
tools/perf/tests/bpf-script-test-relocation.c
View File

@ -1,3 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
/*
* bpf-script-test-relocation.c
* Test BPF loader checking relocation

1
tools/perf/tests/bpf.c
View File

@ -1,3 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
#include <errno.h>
#include <stdio.h>
#include <sys/epoll.h>

11
tools/perf/tests/builtin-test.c
View File

@ -22,6 +22,7 @@
#include "string2.h"
#include "symbol.h"
#include <linux/kernel.h>
#include <linux/string.h>
#include <subcmd/exec-cmd.h>
static bool dont_fork;
@ -289,6 +290,14 @@ static struct test generic_tests[] = {
.desc = "mem2node",
.func = test__mem2node,
},
{
.desc = "time utils",
.func = test__time_utils,
},
{
.desc = "map_groups__merge_in",
.func = test__map_groups__merge_in,
},
{
.func = NULL,
},
@ -430,7 +439,7 @@ static const char *shell_test__description(char *description, size_t size,
description = fgets(description, size, fp);
fclose(fp);
return description ? trim(description + 1) : NULL;
return description ? strim(description + 1) : NULL;
}
#define for_each_shell_test(dir, base, ent) \

2
tools/perf/tests/code-reading.c
View File

@ -22,7 +22,7 @@
#include "tests.h"
#include "sane_ctype.h"
#include <linux/ctype.h>
#define BUFSZ 1024
#define READLEN 128

121
tools/perf/tests/map_groups.c Normal file
View File

@ -0,0 +1,121 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/compiler.h>
#include <linux/kernel.h>
#include "tests.h"
#include "map.h"
#include "map_groups.h"
#include "dso.h"
#include "debug.h"
struct map_def {
const char *name;
u64 start;
u64 end;
};
static int check_maps(struct map_def *merged, unsigned int size, struct map_groups *mg)
{
struct map *map;
unsigned int i = 0;
map = map_groups__first(mg);
while (map) {
TEST_ASSERT_VAL("wrong map start", map->start == merged[i].start);
TEST_ASSERT_VAL("wrong map end", map->end == merged[i].end);
TEST_ASSERT_VAL("wrong map name", !strcmp(map->dso->name, merged[i].name));
TEST_ASSERT_VAL("wrong map refcnt", refcount_read(&map->refcnt) == 2);
i++;
map = map_groups__next(map);
TEST_ASSERT_VAL("less maps expected", (map && i < size) || (!map && i == size));
}
return TEST_OK;
}
int test__map_groups__merge_in(struct test *t __maybe_unused, int subtest __maybe_unused)
{
struct map_groups mg;
unsigned int i;
struct map_def bpf_progs[] = {
{ "bpf_prog_1", 200, 300 },
{ "bpf_prog_2", 500, 600 },
{ "bpf_prog_3", 800, 900 },
};
struct map_def merged12[] = {
{ "kcore1", 100, 200 },
{ "bpf_prog_1", 200, 300 },
{ "kcore1", 300, 500 },
{ "bpf_prog_2", 500, 600 },
{ "kcore1", 600, 800 },
{ "bpf_prog_3", 800, 900 },
{ "kcore1", 900, 1000 },
};
struct map_def merged3[] = {
{ "kcore1", 100, 200 },
{ "bpf_prog_1", 200, 300 },
{ "kcore1", 300, 500 },
{ "bpf_prog_2", 500, 600 },
{ "kcore1", 600, 800 },
{ "bpf_prog_3", 800, 900 },
{ "kcore1", 900, 1000 },
{ "kcore3", 1000, 1100 },
};
struct map *map_kcore1, *map_kcore2, *map_kcore3;
int ret;
map_groups__init(&mg, NULL);
for (i = 0; i < ARRAY_SIZE(bpf_progs); i++) {
struct map *map;
map = dso__new_map(bpf_progs[i].name);
TEST_ASSERT_VAL("failed to create map", map);
map->start = bpf_progs[i].start;
map->end = bpf_progs[i].end;
map_groups__insert(&mg, map);
map__put(map);
}
map_kcore1 = dso__new_map("kcore1");
TEST_ASSERT_VAL("failed to create map", map_kcore1);
map_kcore2 = dso__new_map("kcore2");
TEST_ASSERT_VAL("failed to create map", map_kcore2);
map_kcore3 = dso__new_map("kcore3");
TEST_ASSERT_VAL("failed to create map", map_kcore3);
/* kcore1 map overlaps over all bpf maps */
map_kcore1->start = 100;
map_kcore1->end = 1000;
/* kcore2 map hides behind bpf_prog_2 */
map_kcore2->start = 550;
map_kcore2->end = 570;
/* kcore3 map hides behind bpf_prog_3, kcore1 and adds new map */
map_kcore3->start = 880;
map_kcore3->end = 1100;
ret = map_groups__merge_in(&mg, map_kcore1);
TEST_ASSERT_VAL("failed to merge map", !ret);
ret = check_maps(merged12, ARRAY_SIZE(merged12), &mg);
TEST_ASSERT_VAL("merge check failed", !ret);
ret = map_groups__merge_in(&mg, map_kcore2);
TEST_ASSERT_VAL("failed to merge map", !ret);
ret = check_maps(merged12, ARRAY_SIZE(merged12), &mg);
TEST_ASSERT_VAL("merge check failed", !ret);
ret = map_groups__merge_in(&mg, map_kcore3);
TEST_ASSERT_VAL("failed to merge map", !ret);
ret = check_maps(merged3, ARRAY_SIZE(merged3), &mg);
TEST_ASSERT_VAL("merge check failed", !ret);
return TEST_OK;
}

Some files were not shown because too many files have changed in this diff Show More