redonkable
/
alistair23-linux
1
0
Fork 0
Code Releases 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:
 "On the kernel side the main changes in this cycle were:

   - Add Intel Kaby Lake CPU support (Srinivas Pandruvada)

   - AMD uncore driver updates for fam17 (Janakarajan Natarajan)

   - Intel/PT updates and core events optimizations and cleanups
     (Alexander Shishkin)

   - cgroups events fixes (David Carrillo-Cisneros)

   - kprobes improvements (Masami Hiramatsu)

   - ... plus misc fixes and updates.

  On the tooling side the main changes were:

   - Support clang build in tools/{perf,lib/{bpf,traceevent,api}} with
     CC=clang, to, for instance, take advantage of better warnings
     (Arnaldo Carvalho de Melo):

   - Introduce the 'delta-abs' 'perf diff' compute method, that orders
     the histogram entries by the absolute value of the percentage delta
     for a function in two perf.data files, i.e. the functions that
     changed the most (increase or decrease in samples) comes first
     (Namhyung Kim)

   - Add support for parsing Intel uncore vendor event files and add
     uncore vendor events for the Intel server processors (Haswell,
     Broadwell, IvyBridge), Xeon Phi (Knights Landing) and Broadwell DE
     (Andi Kleen)

   - Introduce 'perf ftrace' a perf front end to the kernel's ftrace
     function and function_graph tracer, defaulting to the
     "function_graph" tracer, more work will be done in reviving this
     effort, forward porting it from its initial patch submission
     (Namhyung Kim)

   - Add 'e' and 'c' hotkeys to expand/collapse call chains for a single
     hist entry in the 'perf report' and 'perf top' TUI (Jiri Olsa)

   - Account thread wait time (off CPU time) separately: sleep, iowait
     and preempt, based on the prev_state of the last event, show the
     breakdown when using "perf sched timehist --state" (Namhyumg Kim)

   - Add more triggers to switch the output file (perf.data.TIMESTAMP).

     Now, in addition to switching to a different output file when
     receiving a SIGUSR2, one can also specify file size and time based
     triggers:

           perf record -a --switch-output=signal

     is equivalent to what we had before:

           perf record -a --switch-output

     While we can also ask for the file to be "sliced" by size, taking
     into account that that will happen only when we get woken up by the
     kernel, i.e. one has to take into account the --mmap-pages (the
     size of the perf mmap ring buffer):

           perf record -a --switch-output=2G

     will break the perf.data output into multiple files limited to 2GB
     of samples, right when generating the output.

     For time based samples, alert() will be used, so to have 1 minute
     limited perf.data output files:

          perf record -a --switch-output=1m

     (Jiri Olsa)

   - Improve 'perf trace' (Arnaldo Carvalho de Melo)

   - 'perf kallsyms' toy tool to look for extended symbol information on
     the running kernel and demonstrate the machine/thread/symbol APIs
     for use in other tools, such as 'perf probe' (Arnaldo Carvalho de
     Melo)

   - ... plus tons of other changes, see the shortlog and Git log for
     details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (131 commits)
  perf tools: Add missing parse_events_error() prototype
  perf pmu: Fix check for unset alias->unit array
  perf tools: Be consistent on the type of map->symbols[] interator
  perf intel pt decoder: clang has no -Wno-override-init
  perf evsel: Do not put a variable sized type not at the end of a struct
  perf probe: Avoid accessing uninitialized 'map' variable
  perf tools: Do not put a variable sized type not at the end of a struct
  perf record: Do not put a variable sized type not at the end of a struct
  perf tests: Synthesize struct instead of using field after variable sized type
  perf bench numa: Make sure dprintf() is not defined
  Revert "perf bench futex: Sanitize numeric parameters"
  tools lib subcmd: Make it an error to pass a signed value to OPTION_UINTEGER
  tools: Set the maximum optimization level according to the compiler being used
  tools: Suppress request for warning options not existent in clang
  samples/bpf: Reset global variables
  samples/bpf: Ignore already processed ELF sections
  samples/bpf: Add missing header
  perf symbols: dso->name is an array, no need to check it against NULL
  perf tests record: No need to test an array against NULL
  perf symbols: No need to check if sym->name is NULL
  ...
hifive-unleashed-5.1
Linus Torvalds 2017-02-20 12:21:13 -08:00
parent 32e2d7c8af 0c8967c9df
commit 7f4eb0a6d5
154 changed files with 5380 additions and 689 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
Makefile
View File

@ -87,10 +87,12 @@ endif
ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4
ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),)
quiet=silent_
tools_silent=s
endif
else # make-3.8x
ifneq ($(filter s% -s%,$(MAKEFLAGS)),)
quiet=silent_
tools_silent=-s
endif
endif
@ -1607,11 +1609,11 @@ image_name:
# Clear a bunch of variables before executing the submake
tools/: FORCE
$(Q)mkdir -p $(objtree)/tools
$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/
$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/
tools/%: FORCE
$(Q)mkdir -p $(objtree)/tools
$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/ $*
$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/ $*
# Single targets
# ---------------------------------------------------------------------------

2
arch/arm64/Kconfig
View File

@ -96,7 +96,7 @@ config ARM64
select HAVE_RCU_TABLE_FREE
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_KPROBES
select HAVE_KRETPROBES if HAVE_KPROBES
select HAVE_KRETPROBES
select IOMMU_DMA if IOMMU_SUPPORT
select IRQ_DOMAIN
select IRQ_FORCED_THREADING

13
arch/x86/events/Makefile
View File

@ -1,11 +1,4 @@
obj-y += core.o
obj-$(CONFIG_CPU_SUP_AMD) += amd/core.o amd/uncore.o
obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += amd/power.o
obj-$(CONFIG_X86_LOCAL_APIC) += amd/ibs.o msr.o
ifdef CONFIG_AMD_IOMMU
obj-$(CONFIG_CPU_SUP_AMD) += amd/iommu.o
endif
obj-$(CONFIG_CPU_SUP_INTEL) += msr.o
obj-y += core.o
obj-y += amd/
obj-$(CONFIG_X86_LOCAL_APIC) += msr.o
obj-$(CONFIG_CPU_SUP_INTEL) += intel/

7
arch/x86/events/amd/Makefile 100644
View File

@ -0,0 +1,7 @@
obj-$(CONFIG_CPU_SUP_AMD) += core.o uncore.o
obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += power.o
obj-$(CONFIG_X86_LOCAL_APIC) += ibs.o
ifdef CONFIG_AMD_IOMMU
obj-$(CONFIG_CPU_SUP_AMD) += iommu.o
endif

202
arch/x86/events/amd/uncore.c
View File

@ -22,13 +22,17 @@
#define NUM_COUNTERS_NB 4
#define NUM_COUNTERS_L2 4
#define MAX_COUNTERS NUM_COUNTERS_NB
#define NUM_COUNTERS_L3 6
#define MAX_COUNTERS 6
#define RDPMC_BASE_NB 6
#define RDPMC_BASE_L2 10
#define RDPMC_BASE_LLC 10
#define COUNTER_SHIFT 16
static int num_counters_llc;
static int num_counters_nb;
static HLIST_HEAD(uncore_unused_list);
struct amd_uncore {
@ -45,30 +49,30 @@ struct amd_uncore {
};
static struct amd_uncore * __percpu *amd_uncore_nb;
static struct amd_uncore * __percpu *amd_uncore_l2;
static struct amd_uncore * __percpu *amd_uncore_llc;
static struct pmu amd_nb_pmu;
static struct pmu amd_l2_pmu;
static struct pmu amd_llc_pmu;
static cpumask_t amd_nb_active_mask;
static cpumask_t amd_l2_active_mask;
static cpumask_t amd_llc_active_mask;
static bool is_nb_event(struct perf_event *event)
{
return event->pmu->type == amd_nb_pmu.type;
}
static bool is_l2_event(struct perf_event *event)
static bool is_llc_event(struct perf_event *event)
{
return event->pmu->type == amd_l2_pmu.type;
return event->pmu->type == amd_llc_pmu.type;
}
static struct amd_uncore *event_to_amd_uncore(struct perf_event *event)
{
if (is_nb_event(event) && amd_uncore_nb)
return *per_cpu_ptr(amd_uncore_nb, event->cpu);
else if (is_l2_event(event) && amd_uncore_l2)
return *per_cpu_ptr(amd_uncore_l2, event->cpu);
else if (is_llc_event(event) && amd_uncore_llc)
return *per_cpu_ptr(amd_uncore_llc, event->cpu);
return NULL;
}
@ -183,16 +187,16 @@ static int amd_uncore_event_init(struct perf_event *event)
return -ENOENT;
/*
* NB and L2 counters (MSRs) are shared across all cores that share the
* same NB / L2 cache. Interrupts can be directed to a single target
* core, however, event counts generated by processes running on other
* cores cannot be masked out. So we do not support sampling and
* per-thread events.
* NB and Last level cache counters (MSRs) are shared across all cores
* that share the same NB / Last level cache. Interrupts can be directed
* to a single target core, however, event counts generated by processes
* running on other cores cannot be masked out. So we do not support
* sampling and per-thread events.
*/
if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
return -EINVAL;
/* NB and L2 counters do not have usr/os/guest/host bits */
/* NB and Last level cache counters do not have usr/os/guest/host bits */
if (event->attr.exclude_user || event->attr.exclude_kernel ||
event->attr.exclude_host || event->attr.exclude_guest)
return -EINVAL;
@ -226,8 +230,8 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev,
if (pmu->type == amd_nb_pmu.type)
active_mask = &amd_nb_active_mask;
else if (pmu->type == amd_l2_pmu.type)
active_mask = &amd_l2_active_mask;
else if (pmu->type == amd_llc_pmu.type)
active_mask = &amd_llc_active_mask;
else
return 0;
@ -244,30 +248,47 @@ static struct attribute_group amd_uncore_attr_group = {
.attrs = amd_uncore_attrs,
};
PMU_FORMAT_ATTR(event, "config:0-7,32-35");
PMU_FORMAT_ATTR(umask, "config:8-15");
/*
* Similar to PMU_FORMAT_ATTR but allowing for format_attr to be assigned based
* on family
*/
#define AMD_FORMAT_ATTR(_dev, _name, _format) \
static ssize_t \
_dev##_show##_name(struct device *dev, \
struct device_attribute *attr, \
char *page) \
{ \
BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
return sprintf(page, _format "\n"); \
} \
static struct device_attribute format_attr_##_dev##_name = __ATTR_RO(_dev);
static struct attribute *amd_uncore_format_attr[] = {
&format_attr_event.attr,
&format_attr_umask.attr,
NULL,
/* Used for each uncore counter type */
#define AMD_ATTRIBUTE(_name) \
static struct attribute *amd_uncore_format_attr_##_name[] = { \
&format_attr_event_##_name.attr, \
&format_attr_umask.attr, \
NULL, \
}; \
static struct attribute_group amd_uncore_format_group_##_name = { \
.name = "format", \
.attrs = amd_uncore_format_attr_##_name, \
}; \
static const struct attribute_group *amd_uncore_attr_groups_##_name[] = { \
&amd_uncore_attr_group, \
&amd_uncore_format_group_##_name, \
NULL, \
};
static struct attribute_group amd_uncore_format_group = {
.name = "format",
.attrs = amd_uncore_format_attr,
};
static const struct attribute_group *amd_uncore_attr_groups[] = {
&amd_uncore_attr_group,
&amd_uncore_format_group,
NULL,
};
AMD_FORMAT_ATTR(event, , "config:0-7,32-35");
AMD_FORMAT_ATTR(umask, , "config:8-15");
AMD_FORMAT_ATTR(event, _df, "config:0-7,32-35,59-60");
AMD_FORMAT_ATTR(event, _l3, "config:0-7");
AMD_ATTRIBUTE(df);
AMD_ATTRIBUTE(l3);
static struct pmu amd_nb_pmu = {
.task_ctx_nr = perf_invalid_context,
.attr_groups = amd_uncore_attr_groups,
.name = "amd_nb",
.event_init = amd_uncore_event_init,
.add = amd_uncore_add,
.del = amd_uncore_del,
@ -276,10 +297,8 @@ static struct pmu amd_nb_pmu = {
.read = amd_uncore_read,
};
static struct pmu amd_l2_pmu = {
static struct pmu amd_llc_pmu = {
.task_ctx_nr = perf_invalid_context,
.attr_groups = amd_uncore_attr_groups,
.name = "amd_l2",
.event_init = amd_uncore_event_init,
.add = amd_uncore_add,
.del = amd_uncore_del,
@ -296,14 +315,14 @@ static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)
static int amd_uncore_cpu_up_prepare(unsigned int cpu)
{
struct amd_uncore *uncore_nb = NULL, *uncore_l2;
struct amd_uncore *uncore_nb = NULL, *uncore_llc;
if (amd_uncore_nb) {
uncore_nb = amd_uncore_alloc(cpu);
if (!uncore_nb)
goto fail;
uncore_nb->cpu = cpu;
uncore_nb->num_counters = NUM_COUNTERS_NB;
uncore_nb->num_counters = num_counters_nb;
uncore_nb->rdpmc_base = RDPMC_BASE_NB;
uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
uncore_nb->active_mask = &amd_nb_active_mask;
@ -312,18 +331,18 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
}
if (amd_uncore_l2) {
uncore_l2 = amd_uncore_alloc(cpu);
if (!uncore_l2)
if (amd_uncore_llc) {
uncore_llc = amd_uncore_alloc(cpu);
if (!uncore_llc)
goto fail;
uncore_l2->cpu = cpu;
uncore_l2->num_counters = NUM_COUNTERS_L2;
uncore_l2->rdpmc_base = RDPMC_BASE_L2;
uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
uncore_l2->active_mask = &amd_l2_active_mask;
uncore_l2->pmu = &amd_l2_pmu;
uncore_l2->id = -1;
*per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
uncore_llc->cpu = cpu;
uncore_llc->num_counters = num_counters_llc;
uncore_llc->rdpmc_base = RDPMC_BASE_LLC;
uncore_llc->msr_base = MSR_F16H_L2I_PERF_CTL;
uncore_llc->active_mask = &amd_llc_active_mask;
uncore_llc->pmu = &amd_llc_pmu;
uncore_llc->id = -1;
*per_cpu_ptr(amd_uncore_llc, cpu) = uncore_llc;
}
return 0;
@ -376,17 +395,17 @@ static int amd_uncore_cpu_starting(unsigned int cpu)
*per_cpu_ptr(amd_uncore_nb, cpu) = uncore;
}
if (amd_uncore_l2) {
if (amd_uncore_llc) {
unsigned int apicid = cpu_data(cpu).apicid;
unsigned int nshared;
uncore = *per_cpu_ptr(amd_uncore_l2, cpu);
uncore = *per_cpu_ptr(amd_uncore_llc, cpu);
cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx);
nshared = ((eax >> 14) & 0xfff) + 1;
uncore->id = apicid - (apicid % nshared);
uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_l2);
*per_cpu_ptr(amd_uncore_l2, cpu) = uncore;
uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc);
*per_cpu_ptr(amd_uncore_llc, cpu) = uncore;
}
return 0;
@ -419,8 +438,8 @@ static int amd_uncore_cpu_online(unsigned int cpu)
if (amd_uncore_nb)
uncore_online(cpu, amd_uncore_nb);
if (amd_uncore_l2)
uncore_online(cpu, amd_uncore_l2);
if (amd_uncore_llc)
uncore_online(cpu, amd_uncore_llc);
return 0;
}
@ -456,8 +475,8 @@ static int amd_uncore_cpu_down_prepare(unsigned int cpu)
if (amd_uncore_nb)
uncore_down_prepare(cpu, amd_uncore_nb);
if (amd_uncore_l2)
uncore_down_prepare(cpu, amd_uncore_l2);
if (amd_uncore_llc)
uncore_down_prepare(cpu, amd_uncore_llc);
return 0;
}
@ -479,8 +498,8 @@ static int amd_uncore_cpu_dead(unsigned int cpu)
if (amd_uncore_nb)
uncore_dead(cpu, amd_uncore_nb);
if (amd_uncore_l2)
uncore_dead(cpu, amd_uncore_l2);
if (amd_uncore_llc)
uncore_dead(cpu, amd_uncore_llc);
return 0;
}
@ -492,6 +511,47 @@ static int __init amd_uncore_init(void)
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
goto fail_nodev;
switch(boot_cpu_data.x86) {
case 23:
/* Family 17h: */
num_counters_nb = NUM_COUNTERS_NB;
num_counters_llc = NUM_COUNTERS_L3;
/*
* For Family17h, the NorthBridge counters are
* re-purposed as Data Fabric counters. Also, support is
* added for L3 counters. The pmus are exported based on
* family as either L2 or L3 and NB or DF.
*/
amd_nb_pmu.name = "amd_df";
amd_llc_pmu.name = "amd_l3";
format_attr_event_df.show = &event_show_df;
format_attr_event_l3.show = &event_show_l3;
break;
case 22:
/* Family 16h - may change: */
num_counters_nb = NUM_COUNTERS_NB;
num_counters_llc = NUM_COUNTERS_L2;
amd_nb_pmu.name = "amd_nb";
amd_llc_pmu.name = "amd_l2";
format_attr_event_df = format_attr_event;
format_attr_event_l3 = format_attr_event;
break;
default:
/*
* All prior families have the same number of
* NorthBridge and Last Level Cache counters
*/
num_counters_nb = NUM_COUNTERS_NB;
num_counters_llc = NUM_COUNTERS_L2;
amd_nb_pmu.name = "amd_nb";
amd_llc_pmu.name = "amd_l2";
format_attr_event_df = format_attr_event;
format_attr_event_l3 = format_attr_event;
break;
}
amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df;
amd_llc_pmu.attr_groups = amd_uncore_attr_groups_l3;
if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
goto fail_nodev;
@ -510,16 +570,16 @@ static int __init amd_uncore_init(void)
}
if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) {
amd_uncore_l2 = alloc_percpu(struct amd_uncore *);
if (!amd_uncore_l2) {
amd_uncore_llc = alloc_percpu(struct amd_uncore *);
if (!amd_uncore_llc) {
ret = -ENOMEM;
goto fail_l2;
goto fail_llc;
}
ret = perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1);
ret = perf_pmu_register(&amd_llc_pmu, amd_llc_pmu.name, -1);
if (ret)
goto fail_l2;
goto fail_llc;
pr_info("perf: AMD L2I counters detected\n");
pr_info("perf: AMD LLC counters detected\n");
ret = 0;
}
@ -529,7 +589,7 @@ static int __init amd_uncore_init(void)
if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
"perf/x86/amd/uncore:prepare",
amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead))
goto fail_l2;
goto fail_llc;
if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
"perf/x86/amd/uncore:starting",
@ -546,11 +606,11 @@ fail_start:
cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING);
fail_prep:
cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP);
fail_l2:
fail_llc:
if (boot_cpu_has(X86_FEATURE_PERFCTR_NB))
perf_pmu_unregister(&amd_nb_pmu);
if (amd_uncore_l2)
free_percpu(amd_uncore_l2);
if (amd_uncore_llc)
free_percpu(amd_uncore_llc);
fail_nb:
if (amd_uncore_nb)
free_percpu(amd_uncore_nb);

3
arch/x86/events/intel/cstate.c
View File

@ -541,6 +541,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
{ },

6
arch/x86/events/intel/pt.c
View File

@ -99,18 +99,24 @@ static struct attribute_group pt_cap_group = {
};
PMU_FORMAT_ATTR(cyc, "config:1" );
PMU_FORMAT_ATTR(pwr_evt, "config:4" );
PMU_FORMAT_ATTR(fup_on_ptw, "config:5" );
PMU_FORMAT_ATTR(mtc, "config:9" );
PMU_FORMAT_ATTR(tsc, "config:10" );
PMU_FORMAT_ATTR(noretcomp, "config:11" );
PMU_FORMAT_ATTR(ptw, "config:12" );
PMU_FORMAT_ATTR(mtc_period, "config:14-17" );
PMU_FORMAT_ATTR(cyc_thresh, "config:19-22" );
PMU_FORMAT_ATTR(psb_period, "config:24-27" );
static struct attribute *pt_formats_attr[] = {
&format_attr_cyc.attr,
&format_attr_pwr_evt.attr,
&format_attr_fup_on_ptw.attr,
&format_attr_mtc.attr,
&format_attr_tsc.attr,
&format_attr_noretcomp.attr,
&format_attr_ptw.attr,
&format_attr_mtc_period.attr,
&format_attr_cyc_thresh.attr,
&format_attr_psb_period.attr,

3
arch/x86/events/intel/rapl.c
View File

@ -771,6 +771,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
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_ATOM_GOLDMONT, hsw_rapl_init),
{},
};

2
arch/x86/events/intel/uncore.c
View File

@ -1328,6 +1328,8 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
{},
};

2
arch/x86/kernel/kprobes/core.c
View File

@ -745,7 +745,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs)
* will be the real return address, and all the rest will
* point to kretprobe_trampoline.
*/
hlist_for_each_entry_safe(ri, tmp, head, hlist) {
hlist_for_each_entry(ri, head, hlist) {
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;

30
include/linux/kprobes.h
View File

@ -278,9 +278,13 @@ struct kprobe_insn_cache {
int nr_garbage;
};
#ifdef __ARCH_WANT_KPROBES_INSN_SLOT
extern kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c);
extern void __free_insn_slot(struct kprobe_insn_cache *c,
kprobe_opcode_t *slot, int dirty);
/* sleep-less address checking routine */
extern bool __is_insn_slot_addr(struct kprobe_insn_cache *c,
unsigned long addr);
#define DEFINE_INSN_CACHE_OPS(__name) \
extern struct kprobe_insn_cache kprobe_##__name##_slots; \
@ -294,6 +298,18 @@ static inline void free_##__name##_slot(kprobe_opcode_t *slot, int dirty)\
{ \
__free_insn_slot(&kprobe_##__name##_slots, slot, dirty); \
} \
\
static inline bool is_kprobe_##__name##_slot(unsigned long addr) \
{ \
return __is_insn_slot_addr(&kprobe_##__name##_slots, addr); \
}
#else /* __ARCH_WANT_KPROBES_INSN_SLOT */
#define DEFINE_INSN_CACHE_OPS(__name) \
static inline bool is_kprobe_##__name##_slot(unsigned long addr) \
{ \
return 0; \
}
#endif
DEFINE_INSN_CACHE_OPS(insn);
@ -330,7 +346,6 @@ extern int proc_kprobes_optimization_handler(struct ctl_table *table,
int write, void __user *buffer,
size_t *length, loff_t *ppos);
#endif
#endif /* CONFIG_OPTPROBES */
#ifdef CONFIG_KPROBES_ON_FTRACE
extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
@ -481,6 +496,19 @@ static inline int enable_jprobe(struct jprobe *jp)
return enable_kprobe(&jp->kp);
}
#ifndef CONFIG_KPROBES
static inline bool is_kprobe_insn_slot(unsigned long addr)
{
return false;
}
#endif
#ifndef CONFIG_OPTPROBES
static inline bool is_kprobe_optinsn_slot(unsigned long addr)
{
return false;
}
#endif
#ifdef CONFIG_KPROBES
/*
* Blacklist ganerating macro. Specify functions which is not probed

4
include/linux/perf_event.h
View File

@ -482,6 +482,7 @@ struct perf_addr_filter {
* @list: list of filters for this event
* @lock: spinlock that serializes accesses to the @list and event's
* (and its children's) filter generations.
* @nr_file_filters: number of file-based filters
*
* A child event will use parent's @list (and therefore @lock), so they are
* bundled together; see perf_event_addr_filters().
@ -489,6 +490,7 @@ struct perf_addr_filter {
struct perf_addr_filters_head {
struct list_head list;
raw_spinlock_t lock;
unsigned int nr_file_filters;
};
/**
@ -785,9 +787,9 @@ struct perf_cpu_context {
ktime_t hrtimer_interval;
unsigned int hrtimer_active;
struct pmu *unique_pmu;
#ifdef CONFIG_CGROUP_PERF
struct perf_cgroup *cgrp;
struct list_head cgrp_cpuctx_entry;
#endif
struct list_head sched_cb_entry;

268
kernel/events/core.c
View File

@ -355,6 +355,8 @@ enum event_type_t {
EVENT_FLEXIBLE = 0x1,
EVENT_PINNED = 0x2,
EVENT_TIME = 0x4,
/* see ctx_resched() for details */
EVENT_CPU = 0x8,
EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
};
@ -678,6 +680,8 @@ perf_cgroup_set_timestamp(struct task_struct *task,
info->timestamp = ctx->timestamp;
}
static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list);
#define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */
#define PERF_CGROUP_SWIN 0x2 /* cgroup switch in events based on task */
@ -690,61 +694,46 @@ perf_cgroup_set_timestamp(struct task_struct *task,
static void perf_cgroup_switch(struct task_struct *task, int mode)
{
struct perf_cpu_context *cpuctx;
struct pmu *pmu;
struct list_head *list;
unsigned long flags;
/*
* disable interrupts to avoid geting nr_cgroup
* changes via __perf_event_disable(). Also
* avoids preemption.
* Disable interrupts and preemption to avoid this CPU's
* cgrp_cpuctx_entry to change under us.
*/
local_irq_save(flags);
/*
* we reschedule only in the presence of cgroup
* constrained events.
*/
list = this_cpu_ptr(&cgrp_cpuctx_list);
list_for_each_entry(cpuctx, list, cgrp_cpuctx_entry) {
WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
list_for_each_entry_rcu(pmu, &pmus, entry) {
cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
if (cpuctx->unique_pmu != pmu)
continue; /* ensure we process each cpuctx once */
perf_ctx_lock(cpuctx, cpuctx->task_ctx);
perf_pmu_disable(cpuctx->ctx.pmu);
/*
* perf_cgroup_events says at least one
* context on this CPU has cgroup events.
*
* ctx->nr_cgroups reports the number of cgroup
* events for a context.
*/
if (cpuctx->ctx.nr_cgroups > 0) {
perf_ctx_lock(cpuctx, cpuctx->task_ctx);
perf_pmu_disable(cpuctx->ctx.pmu);
if (mode & PERF_CGROUP_SWOUT) {
cpu_ctx_sched_out(cpuctx, EVENT_ALL);
/*
* must not be done before ctxswout due
* to event_filter_match() in event_sched_out()
*/
cpuctx->cgrp = NULL;
}
if (mode & PERF_CGROUP_SWIN) {
WARN_ON_ONCE(cpuctx->cgrp);
/*
* set cgrp before ctxsw in to allow
* event_filter_match() to not have to pass
* task around
* we pass the cpuctx->ctx to perf_cgroup_from_task()
* because cgorup events are only per-cpu
*/
cpuctx->cgrp = perf_cgroup_from_task(task, &cpuctx->ctx);
cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
}
perf_pmu_enable(cpuctx->ctx.pmu);
perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
if (mode & PERF_CGROUP_SWOUT) {
cpu_ctx_sched_out(cpuctx, EVENT_ALL);
/*
* must not be done before ctxswout due
* to event_filter_match() in event_sched_out()
*/
cpuctx->cgrp = NULL;
}
if (mode & PERF_CGROUP_SWIN) {
WARN_ON_ONCE(cpuctx->cgrp);
/*
* set cgrp before ctxsw in to allow
* event_filter_match() to not have to pass
* task around
* we pass the cpuctx->ctx to perf_cgroup_from_task()
* because cgorup events are only per-cpu
*/
cpuctx->cgrp = perf_cgroup_from_task(task,
&cpuctx->ctx);
cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
}
perf_pmu_enable(cpuctx->ctx.pmu);
perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
}
local_irq_restore(flags);
@ -889,6 +878,7 @@ list_update_cgroup_event(struct perf_event *event,
struct perf_event_context *ctx, bool add)
{
struct perf_cpu_context *cpuctx;
struct list_head *cpuctx_entry;
if (!is_cgroup_event(event))
return;
@ -902,15 +892,16 @@ list_update_cgroup_event(struct perf_event *event,
* this will always be called from the right CPU.
*/
cpuctx = __get_cpu_context(ctx);
/*
* cpuctx->cgrp is NULL until a cgroup event is sched in or
* ctx->nr_cgroup == 0 .
*/
if (add && perf_cgroup_from_task(current, ctx) == event->cgrp)
cpuctx->cgrp = event->cgrp;
else if (!add)
cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
/* cpuctx->cgrp is NULL unless a cgroup event is active in this CPU .*/
if (add) {
list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list));
if (perf_cgroup_from_task(current, ctx) == event->cgrp)
cpuctx->cgrp = event->cgrp;
} else {
list_del(cpuctx_entry);
cpuctx->cgrp = NULL;
}
}
#else /* !CONFIG_CGROUP_PERF */
@ -1453,6 +1444,20 @@ static void update_group_times(struct perf_event *leader)
update_event_times(event);
}
static enum event_type_t get_event_type(struct perf_event *event)
{
struct perf_event_context *ctx = event->ctx;
enum event_type_t event_type;
lockdep_assert_held(&ctx->lock);
event_type = event->attr.pinned ? EVENT_PINNED : EVENT_FLEXIBLE;
if (!ctx->task)
event_type |= EVENT_CPU;
return event_type;
}
static struct list_head *
ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
{
@ -2226,7 +2231,8 @@ ctx_sched_in(struct perf_event_context *ctx,
struct task_struct *task);
static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
struct perf_event_context *ctx)
struct perf_event_context *ctx,
enum event_type_t event_type)
{
if (!cpuctx->task_ctx)
return;
@ -2234,7 +2240,7 @@ static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
return;
ctx_sched_out(ctx, cpuctx, EVENT_ALL);
ctx_sched_out(ctx, cpuctx, event_type);
}
static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
@ -2249,13 +2255,51 @@ static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
}
/*
* We want to maintain the following priority of scheduling:
* - CPU pinned (EVENT_CPU | EVENT_PINNED)
* - task pinned (EVENT_PINNED)
* - CPU flexible (EVENT_CPU | EVENT_FLEXIBLE)
* - task flexible (EVENT_FLEXIBLE).
*
* In order to avoid unscheduling and scheduling back in everything every
* time an event is added, only do it for the groups of equal priority and
* below.
*
* This can be called after a batch operation on task events, in which case
* event_type is a bit mask of the types of events involved. For CPU events,
* event_type is only either EVENT_PINNED or EVENT_FLEXIBLE.
*/
static void ctx_resched(struct perf_cpu_context *cpuctx,
struct perf_event_context *task_ctx)
struct perf_event_context *task_ctx,
enum event_type_t event_type)
{
enum event_type_t ctx_event_type = event_type & EVENT_ALL;
bool cpu_event = !!(event_type & EVENT_CPU);
/*
* If pinned groups are involved, flexible groups also need to be
* scheduled out.
*/
if (event_type & EVENT_PINNED)
event_type |= EVENT_FLEXIBLE;
perf_pmu_disable(cpuctx->ctx.pmu);
if (task_ctx)
task_ctx_sched_out(cpuctx, task_ctx);
cpu_ctx_sched_out(cpuctx, EVENT_ALL);
task_ctx_sched_out(cpuctx, task_ctx, event_type);
/*
* Decide which cpu ctx groups to schedule out based on the types
* of events that caused rescheduling:
* - EVENT_CPU: schedule out corresponding groups;
* - EVENT_PINNED task events: schedule out EVENT_FLEXIBLE groups;
* - otherwise, do nothing more.
*/
if (cpu_event)
cpu_ctx_sched_out(cpuctx, ctx_event_type);
else if (ctx_event_type & EVENT_PINNED)
cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
perf_event_sched_in(cpuctx, task_ctx, current);
perf_pmu_enable(cpuctx->ctx.pmu);
}
@ -2302,7 +2346,7 @@ static int __perf_install_in_context(void *info)
if (reprogram) {
ctx_sched_out(ctx, cpuctx, EVENT_TIME);
add_event_to_ctx(event, ctx);
ctx_resched(cpuctx, task_ctx);
ctx_resched(cpuctx, task_ctx, get_event_type(event));
} else {
add_event_to_ctx(event, ctx);
}
@ -2469,7 +2513,7 @@ static void __perf_event_enable(struct perf_event *event,
if (ctx->task)
WARN_ON_ONCE(task_ctx != ctx);
ctx_resched(cpuctx, task_ctx);
ctx_resched(cpuctx, task_ctx, get_event_type(event));
}
/*
@ -2896,7 +2940,7 @@ unlock:
if (do_switch) {
raw_spin_lock(&ctx->lock);
task_ctx_sched_out(cpuctx, ctx);
task_ctx_sched_out(cpuctx, ctx, EVENT_ALL);
raw_spin_unlock(&ctx->lock);
}
}
@ -2943,7 +2987,7 @@ static void perf_pmu_sched_task(struct task_struct *prev,
return;
list_for_each_entry(cpuctx, this_cpu_ptr(&sched_cb_list), sched_cb_entry) {
pmu = cpuctx->unique_pmu; /* software PMUs will not have sched_task */
pmu = cpuctx->ctx.pmu; /* software PMUs will not have sched_task */
if (WARN_ON_ONCE(!pmu->sched_task))
continue;
@ -3133,8 +3177,12 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
* We want to keep the following priority order:
* cpu pinned (that don't need to move), task pinned,
* cpu flexible, task flexible.
*
* However, if task's ctx is not carrying any pinned
* events, no need to flip the cpuctx's events around.
*/
cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
if (!list_empty(&ctx->pinned_groups))
cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
perf_event_sched_in(cpuctx, ctx, task);
perf_pmu_enable(ctx->pmu);
perf_ctx_unlock(cpuctx, ctx);
@ -3449,6 +3497,7 @@ static int event_enable_on_exec(struct perf_event *event,
static void perf_event_enable_on_exec(int ctxn)
{
struct perf_event_context *ctx, *clone_ctx = NULL;
enum event_type_t event_type = 0;
struct perf_cpu_context *cpuctx;
struct perf_event *event;
unsigned long flags;
@ -3462,15 +3511,17 @@ static void perf_event_enable_on_exec(int ctxn)
cpuctx = __get_cpu_context(ctx);
perf_ctx_lock(cpuctx, ctx);
ctx_sched_out(ctx, cpuctx, EVENT_TIME);
list_for_each_entry(event, &ctx->event_list, event_entry)
list_for_each_entry(event, &ctx->event_list, event_entry) {
enabled |= event_enable_on_exec(event, ctx);
event_type |= get_event_type(event);
}
/*
* Unclone and reschedule this context if we enabled any event.
*/
if (enabled) {
clone_ctx = unclone_ctx(ctx);
ctx_resched(cpuctx, ctx);
ctx_resched(cpuctx, ctx, event_type);
}
perf_ctx_unlock(cpuctx, ctx);
@ -8044,6 +8095,9 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
if (task == TASK_TOMBSTONE)
return;
if (!ifh->nr_file_filters)
return;
mm = get_task_mm(event->ctx->task);
if (!mm)
goto restart;
@ -8214,6 +8268,7 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
* attribute.
*/
if (state == IF_STATE_END) {
ret = -EINVAL;
if (kernel && event->attr.exclude_kernel)
goto fail;
@ -8221,6 +8276,18 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
if (!filename)
goto fail;
/*
* For now, we only support file-based filters
* in per-task events; doing so for CPU-wide
* events requires additional context switching
* trickery, since same object code will be
* mapped at different virtual addresses in
* different processes.
*/
ret = -EOPNOTSUPP;
if (!event->ctx->task)
goto fail_free_name;
/* look up the path and grab its inode */
ret = kern_path(filename, LOOKUP_FOLLOW, &path);
if (ret)
@ -8236,6 +8303,8 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
!S_ISREG(filter->inode->i_mode))
/* free_filters_list() will iput() */
goto fail;
event->addr_filters.nr_file_filters++;
}
/* ready to consume more filters */
@ -8275,24 +8344,13 @@ perf_event_set_addr_filter(struct perf_event *event, char *filter_str)
if (WARN_ON_ONCE(event->parent))
return -EINVAL;
/*
* For now, we only support filtering in per-task events; doing so
* for CPU-wide events requires additional context switching trickery,
* since same object code will be mapped at different virtual
* addresses in different processes.
*/
if (!event->ctx->task)
return -EOPNOTSUPP;
ret = perf_event_parse_addr_filter(event, filter_str, &filters);
if (ret)
return ret;
goto fail_clear_files;
ret = event->pmu->addr_filters_validate(&filters);
if (ret) {
free_filters_list(&filters);
return ret;
}
if (ret)
goto fail_free_filters;
/* remove existing filters, if any */
perf_addr_filters_splice(event, &filters);
@ -8300,6 +8358,14 @@ perf_event_set_addr_filter(struct perf_event *event, char *filter_str)
/* install new filters */
perf_event_for_each_child(event, perf_event_addr_filters_apply);
return ret;
fail_free_filters:
free_filters_list(&filters);
fail_clear_files:
event->addr_filters.nr_file_filters = 0;
return ret;
}
@ -8652,37 +8718,10 @@ static struct perf_cpu_context __percpu *find_pmu_context(int ctxn)
return NULL;
}
static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu)
{
int cpu;
for_each_possible_cpu(cpu) {
struct perf_cpu_context *cpuctx;
cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
if (cpuctx->unique_pmu == old_pmu)
cpuctx->unique_pmu = pmu;
}
}
static void free_pmu_context(struct pmu *pmu)
{
struct pmu *i;
mutex_lock(&pmus_lock);
/*
* Like a real lame refcount.
*/
list_for_each_entry(i, &pmus, entry) {
if (i->pmu_cpu_context == pmu->pmu_cpu_context) {
update_pmu_context(i, pmu);
goto out;
}
}
free_percpu(pmu->pmu_cpu_context);
out:
mutex_unlock(&pmus_lock);
}
@ -8886,8 +8925,6 @@ skip_type:
cpuctx->ctx.pmu = pmu;
__perf_mux_hrtimer_init(cpuctx, cpu);
cpuctx->unique_pmu = pmu;
}
got_cpu_context:
@ -9005,6 +9042,14 @@ static struct pmu *perf_init_event(struct perf_event *event)
idx = srcu_read_lock(&pmus_srcu);
/* Try parent's PMU first: */
if (event->parent && event->parent->pmu) {
pmu = event->parent->pmu;
ret = perf_try_init_event(pmu, event);
if (!ret)
goto unlock;
}
rcu_read_lock();
pmu = idr_find(&pmu_idr, event->attr.type);
rcu_read_unlock();
@ -10265,7 +10310,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
* in.
*/
raw_spin_lock_irq(&child_ctx->lock);
task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx);
task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx, EVENT_ALL);
/*
* Now that the context is inactive, destroy the task <-> ctx relation
@ -10714,6 +10759,9 @@ static void __init perf_event_init_all_cpus(void)
INIT_LIST_HEAD(&per_cpu(pmu_sb_events.list, cpu));
raw_spin_lock_init(&per_cpu(pmu_sb_events.lock, cpu));
#ifdef CONFIG_CGROUP_PERF
INIT_LIST_HEAD(&per_cpu(cgrp_cpuctx_list, cpu));
#endif
INIT_LIST_HEAD(&per_cpu(sched_cb_list, cpu));
}
}

9
kernel/extable.c
View File

@ -20,6 +20,7 @@
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/init.h>
#include <linux/kprobes.h>
#include <asm/sections.h>
#include <linux/uaccess.h>
@ -104,6 +105,8 @@ int __kernel_text_address(unsigned long addr)
return 1;
if (is_ftrace_trampoline(addr))
return 1;
if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
return 1;
/*
* There might be init symbols in saved stacktraces.
* Give those symbols a chance to be printed in
@ -123,7 +126,11 @@ int kernel_text_address(unsigned long addr)
return 1;
if (is_module_text_address(addr))
return 1;
return is_ftrace_trampoline(addr);
if (is_ftrace_trampoline(addr))
return 1;
if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
return 1;
return 0;
}
/*

75
kernel/kprobes.c
View File

@ -149,9 +149,11 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
struct kprobe_insn_page *kip;
kprobe_opcode_t *slot = NULL;
/* Since the slot array is not protected by rcu, we need a mutex */
mutex_lock(&c->mutex);
retry:
list_for_each_entry(kip, &c->pages, list) {
rcu_read_lock();
list_for_each_entry_rcu(kip, &c->pages, list) {
if (kip->nused < slots_per_page(c)) {
int i;
for (i = 0; i < slots_per_page(c); i++) {
@ -159,6 +161,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
kip->slot_used[i] = SLOT_USED;
kip->nused++;
slot = kip->insns + (i * c->insn_size);
rcu_read_unlock();
goto out;
}
}
@ -167,6 +170,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
WARN_ON(1);
}
}
rcu_read_unlock();
/* If there are any garbage slots, collect it and try again. */
if (c->nr_garbage && collect_garbage_slots(c) == 0)
@ -193,7 +197,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
kip->nused = 1;
kip->ngarbage = 0;
kip->cache = c;
list_add(&kip->list, &c->pages);
list_add_rcu(&kip->list, &c->pages);
slot = kip->insns;
out:
mutex_unlock(&c->mutex);
@ -213,7 +217,8 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx)
* next time somebody inserts a probe.
*/
if (!list_is_singular(&kip->list)) {
list_del(&kip->list);
list_del_rcu(&kip->list);
synchronize_rcu();
kip->cache->free(kip->insns);
kfree(kip);
}
@ -235,8 +240,7 @@ static int collect_garbage_slots(struct kprobe_insn_cache *c)
continue;
kip->ngarbage = 0; /* we will collect all garbages */
for (i = 0; i < slots_per_page(c); i++) {
if (kip->slot_used[i] == SLOT_DIRTY &&
collect_one_slot(kip, i))
if (kip->slot_used[i] == SLOT_DIRTY && collect_one_slot(kip, i))
break;
}
}
@ -248,29 +252,60 @@ void __free_insn_slot(struct kprobe_insn_cache *c,
kprobe_opcode_t *slot, int dirty)
{
struct kprobe_insn_page *kip;
long idx;
mutex_lock(&c->mutex);
list_for_each_entry(kip, &c->pages, list) {
long idx = ((long)slot - (long)kip->insns) /
(c->insn_size * sizeof(kprobe_opcode_t));
if (idx >= 0 && idx < slots_per_page(c)) {
WARN_ON(kip->slot_used[idx] != SLOT_USED);
if (dirty) {
kip->slot_used[idx] = SLOT_DIRTY;
kip->ngarbage++;
if (++c->nr_garbage > slots_per_page(c))
collect_garbage_slots(c);
} else
collect_one_slot(kip, idx);
rcu_read_lock();
list_for_each_entry_rcu(kip, &c->pages, list) {
idx = ((long)slot - (long)kip->insns) /
(c->insn_size * sizeof(kprobe_opcode_t));
if (idx >= 0 && idx < slots_per_page(c))
goto out;
}
/* Could not find this slot. */
WARN_ON(1);
kip = NULL;
out:
rcu_read_unlock();
/* Mark and sweep: this may sleep */
if (kip) {
/* Check double free */
WARN_ON(kip->slot_used[idx] != SLOT_USED);
if (dirty) {
kip->slot_used[idx] = SLOT_DIRTY;
kip->ngarbage++;
if (++c->nr_garbage > slots_per_page(c))
collect_garbage_slots(c);
} else {
collect_one_slot(kip, idx);
}
}
/* Could not free this slot. */
WARN_ON(1);
out:
mutex_unlock(&c->mutex);
}
/*
* Check given address is on the page of kprobe instruction slots.
* This will be used for checking whether the address on a stack
* is on a text area or not.
*/
bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr)
{
struct kprobe_insn_page *kip;
bool ret = false;
rcu_read_lock();
list_for_each_entry_rcu(kip, &c->pages, list) {
if (addr >= (unsigned long)kip->insns &&
addr < (unsigned long)kip->insns + PAGE_SIZE) {
ret = true;
break;
}
}
rcu_read_unlock();
return ret;
}
#ifdef CONFIG_OPTPROBES
/* For optimized_kprobe buffer */
struct kprobe_insn_cache kprobe_optinsn_slots = {

7
samples/bpf/bpf_load.c
View File

@ -277,6 +277,11 @@ int load_bpf_file(char *path)
Elf_Data *data, *data_prog, *symbols = NULL;
char *shname, *shname_prog;
/* reset global variables */
kern_version = 0;
memset(license, 0, sizeof(license));
memset(processed_sec, 0, sizeof(processed_sec));
if (elf_version(EV_CURRENT) == EV_NONE)
return 1;
@ -328,6 +333,8 @@ int load_bpf_file(char *path)
/* load programs that need map fixup (relocations) */
for (i = 1; i < ehdr.e_shnum; i++) {
if (processed_sec[i])
continue;
if (get_sec(elf, i, &ehdr, &shname, &shdr, &data))
continue;

1
samples/bpf/tracex5_kern.c
View File

@ -8,6 +8,7 @@
#include <linux/version.h>
#include <uapi/linux/bpf.h>
#include <uapi/linux/seccomp.h>
#include <uapi/linux/unistd.h>
#include "bpf_helpers.h"
#define PROG(F) SEC("kprobe/"__stringify(F)) int bpf_func_##F

9
tools/arch/arm/include/uapi/asm/kvm.h
View File

@ -84,6 +84,15 @@ struct kvm_regs {
#define KVM_VGIC_V2_DIST_SIZE 0x1000
#define KVM_VGIC_V2_CPU_SIZE 0x2000
/* Supported VGICv3 address types */
#define KVM_VGIC_V3_ADDR_TYPE_DIST 2
#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3
#define KVM_VGIC_ITS_ADDR_TYPE 4
#define KVM_VGIC_V3_DIST_SIZE SZ_64K
#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K)
#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K)
#define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */
#define KVM_ARM_VCPU_PSCI_0_2 1 /* CPU uses PSCI v0.2 */

5
tools/arch/powerpc/include/uapi/asm/kvm.h
View File

@ -573,6 +573,10 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_SPRG9 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xba)
#define KVM_REG_PPC_DBSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbb)
/* POWER9 registers */
#define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc)
#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
*/
@ -596,6 +600,7 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_TM_VSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67)
#define KVM_REG_PPC_TM_DSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68)
#define KVM_REG_PPC_TM_TAR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69)
#define KVM_REG_PPC_TM_XER (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x6a)
/* PPC64 eXternal Interrupt Controller Specification */
#define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */

11
tools/arch/x86/include/asm/cpufeatures.h
View File

@ -105,6 +105,7 @@
#define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */
#define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */
#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */
/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */
@ -188,10 +189,14 @@
#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */
#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */
#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
@ -220,11 +225,13 @@
#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */
#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */
#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 */
#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
#define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */
#define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */
#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */
#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */
#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */
#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */
@ -278,8 +285,10 @@
#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
#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_RDPID (16*32+ 22) /* RDPID instruction */
/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
@ -310,4 +319,6 @@
#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */
#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */
#endif /* _ASM_X86_CPUFEATURES_H */

5
tools/arch/x86/include/uapi/asm/vmx.h
View File

@ -65,6 +65,8 @@
#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
#define EXIT_REASON_APIC_ACCESS 44
#define EXIT_REASON_EOI_INDUCED 45
#define EXIT_REASON_GDTR_IDTR 46
#define EXIT_REASON_LDTR_TR 47
#define EXIT_REASON_EPT_VIOLATION 48
#define EXIT_REASON_EPT_MISCONFIG 49
#define EXIT_REASON_INVEPT 50
@ -113,6 +115,8 @@
{ EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \
{ EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \
{ EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \
{ EXIT_REASON_GDTR_IDTR, "GDTR_IDTR" }, \
{ EXIT_REASON_LDTR_TR, "LDTR_TR" }, \
{ EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \
{ EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \
{ EXIT_REASON_INVEPT, "INVEPT" }, \
@ -129,6 +133,7 @@
{ EXIT_REASON_XRSTORS, "XRSTORS" }
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
#endif /* _UAPIVMX_H */

10
tools/build/Makefile.build
View File

@ -19,6 +19,16 @@ else
Q=@
endif
ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4
ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),)
quiet=silent_
endif
else # make-3.8x
ifneq ($(filter s% -s%,$(MAKEFLAGS)),)
quiet=silent_
endif
endif
build-dir := $(srctree)/tools/build
# Define $(fixdep) for dep-cmd function

14
tools/include/linux/compiler-gcc.h 100644
View File

@ -0,0 +1,14 @@
#ifndef _TOOLS_LINUX_COMPILER_H_
#error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
#endif
/*
* Common definitions for all gcc versions go here.
*/
#define GCC_VERSION (__GNUC__ * 10000 \
+ __GNUC_MINOR__ * 100 \
+ __GNUC_PATCHLEVEL__)
#if GCC_VERSION >= 70000 && !defined(__CHECKER__)
# define __fallthrough __attribute__ ((fallthrough))
#endif

9
tools/include/linux/compiler.h
View File

@ -1,6 +1,10 @@
#ifndef _TOOLS_LINUX_COMPILER_H_
#define _TOOLS_LINUX_COMPILER_H_
#ifdef __GNUC__
#include <linux/compiler-gcc.h>
#endif
/* Optimization barrier */
/* The "volatile" is due to gcc bugs */
#define barrier() __asm__ __volatile__("": : :"memory")
@ -126,4 +130,9 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
#define WRITE_ONCE(x, val) \
({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
#ifndef __fallthrough
# define __fallthrough
#endif
#endif /* _TOOLS_LINUX_COMPILER_H */

8
tools/lib/api/Makefile
View File

@ -17,7 +17,13 @@ MAKEFLAGS += --no-print-directory
LIBFILE = $(OUTPUT)libapi.a
CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
ifeq ($(CC), clang)
CFLAGS += -O3
else
CFLAGS += -O6
endif
# Treat warnings as errors unless directed not to
ifneq ($(WERROR),0)

16
tools/lib/api/fs/fs.c
View File

@ -38,6 +38,10 @@
#define HUGETLBFS_MAGIC 0x958458f6
#endif
#ifndef BPF_FS_MAGIC
#define BPF_FS_MAGIC 0xcafe4a11
#endif
static const char * const sysfs__fs_known_mountpoints[] = {
"/sys",
0,
@ -75,6 +79,11 @@ static const char * const hugetlbfs__known_mountpoints[] = {
0,
};
static const char * const bpf_fs__known_mountpoints[] = {
"/sys/fs/bpf",
0,
};
struct fs {
const char *name;
const char * const *mounts;
@ -89,6 +98,7 @@ enum {
FS__DEBUGFS = 2,
FS__TRACEFS = 3,
FS__HUGETLBFS = 4,
FS__BPF_FS = 5,
};
#ifndef TRACEFS_MAGIC
@ -121,6 +131,11 @@ static struct fs fs__entries[] = {
.mounts = hugetlbfs__known_mountpoints,
.magic = HUGETLBFS_MAGIC,
},
[FS__BPF_FS] = {
.name = "bpf",
.mounts = bpf_fs__known_mountpoints,
.magic = BPF_FS_MAGIC,
},
};
static bool fs__read_mounts(struct fs *fs)
@ -280,6 +295,7 @@ FS(procfs, FS__PROCFS);
FS(debugfs, FS__DEBUGFS);
FS(tracefs, FS__TRACEFS);
FS(hugetlbfs, FS__HUGETLBFS);
FS(bpf_fs, FS__BPF_FS);
int filename__read_int(const char *filename, int *value)
{

1
tools/lib/api/fs/fs.h
View File

@ -22,6 +22,7 @@ FS(procfs)
FS(debugfs)
FS(tracefs)
FS(hugetlbfs)
FS(bpf_fs)
#undef FS

32
tools/lib/api/fs/tracing_path.c
View File

@ -86,9 +86,13 @@ void put_tracing_file(char *file)
free(file);
}
static int strerror_open(int err, char *buf, size_t size, const char *filename)
int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
const char *sys, const char *name)
{
char sbuf[128];
char filename[PATH_MAX];
snprintf(filename, PATH_MAX, "%s/%s", sys, name ?: "*");
switch (err) {
case ENOENT:
@ -99,10 +103,19 @@ static int strerror_open(int err, char *buf, size_t size, const char *filename)
* - jirka
*/
if (debugfs__configured() || tracefs__configured()) {
snprintf(buf, size,
"Error:\tFile %s/%s not found.\n"
"Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n",
tracing_events_path, filename);
/* sdt markers */
if (!strncmp(filename, "sdt_", 4)) {
snprintf(buf, size,
"Error:\tFile %s/%s not found.\n"
"Hint:\tSDT event cannot be directly recorded on.\n"
"\tPlease first use 'perf probe %s:%s' before recording it.\n",
tracing_events_path, filename, sys, name);
} else {
snprintf(buf, size,
"Error:\tFile %s/%s not found.\n"
"Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n",
tracing_events_path, filename);
}
break;
}
snprintf(buf, size, "%s",
@ -125,12 +138,3 @@ static int strerror_open(int err, char *buf, size_t size, const char *filename)
return 0;
}
int tracing_path__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name)
{
char path[PATH_MAX];
snprintf(path, PATH_MAX, "%s/%s", sys, name ?: "*");
return strerror_open(err, buf, size, path);
}

1
tools/lib/bpf/bpf.h
View File

@ -22,6 +22,7 @@
#define __BPF_BPF_H
#include <linux/bpf.h>
#include <stddef.h>
int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
int max_entries, __u32 map_flags);

262
tools/lib/bpf/libbpf.c
View File

@ -4,6 +4,7 @@
* Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
* Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
* Copyright (C) 2015 Huawei Inc.
* Copyright (C) 2017 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
@ -22,15 +23,21 @@
#include <stdlib.h>
#include <stdio.h>
#include <stdarg.h>
#include <libgen.h>
#include <inttypes.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include <errno.h>
#include <asm/unistd.h>
#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/bpf.h>
#include <linux/list.h>
#include <linux/limits.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/vfs.h>
#include <libelf.h>
#include <gelf.h>
@ -41,6 +48,10 @@
#define EM_BPF 247
#endif
#ifndef BPF_FS_MAGIC
#define BPF_FS_MAGIC 0xcafe4a11
#endif
#define __printf(a, b) __attribute__((format(printf, a, b)))
__printf(1, 2)
@ -779,7 +790,7 @@ static int
bpf_program__collect_reloc(struct bpf_program *prog,
size_t nr_maps, GElf_Shdr *shdr,
Elf_Data *data, Elf_Data *symbols,
int maps_shndx)
int maps_shndx, struct bpf_map *maps)
{
int i, nrels;
@ -829,7 +840,15 @@ bpf_program__collect_reloc(struct bpf_program *prog,
return -LIBBPF_ERRNO__RELOC;
}
map_idx = sym.st_value / sizeof(struct bpf_map_def);
/* TODO: 'maps' is sorted. We can use bsearch to make it faster. */
for (map_idx = 0; map_idx < nr_maps; map_idx++) {
if (maps[map_idx].offset == sym.st_value) {
pr_debug("relocation: find map %zd (%s) for insn %u\n",
map_idx, maps[map_idx].name, insn_idx);
break;
}
}
if (map_idx >= nr_maps) {
pr_warning("bpf relocation: map_idx %d large than %d\n",
(int)map_idx, (int)nr_maps - 1);
@ -953,7 +972,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
err = bpf_program__collect_reloc(prog, nr_maps,
shdr, data,
obj->efile.symbols,
obj->efile.maps_shndx);
obj->efile.maps_shndx,
obj->maps);
if (err)
return err;
}
@ -1227,6 +1247,191 @@ out:
return err;
}
static int check_path(const char *path)
{
struct statfs st_fs;
char *dname, *dir;
int err = 0;
if (path == NULL)
return -EINVAL;
dname = strdup(path);
if (dname == NULL)
return -ENOMEM;
dir = dirname(dname);
if (statfs(dir, &st_fs)) {
pr_warning("failed to statfs %s: %s\n", dir, strerror(errno));
err = -errno;
}
free(dname);
if (!err && st_fs.f_type != BPF_FS_MAGIC) {
pr_warning("specified path %s is not on BPF FS\n", path);
err = -EINVAL;
}
return err;
}
int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
int instance)
{
int err;
err = check_path(path);
if (err)
return err;
if (prog == NULL) {
pr_warning("invalid program pointer\n");
return -EINVAL;
}
if (instance < 0 || instance >= prog->instances.nr) {
pr_warning("invalid prog instance %d of prog %s (max %d)\n",
instance, prog->section_name, prog->instances.nr);
return -EINVAL;
}
if (bpf_obj_pin(prog->instances.fds[instance], path)) {
pr_warning("failed to pin program: %s\n", strerror(errno));
return -errno;
}
pr_debug("pinned program '%s'\n", path);
return 0;
}
static int make_dir(const char *path)
{
int err = 0;
if (mkdir(path, 0700) && errno != EEXIST)
err = -errno;
if (err)
pr_warning("failed to mkdir %s: %s\n", path, strerror(-err));
return err;
}
int bpf_program__pin(struct bpf_program *prog, const char *path)
{
int i, err;
err = check_path(path);
if (err)
return err;
if (prog == NULL) {
pr_warning("invalid program pointer\n");
return -EINVAL;
}
if (prog->instances.nr <= 0) {
pr_warning("no instances of prog %s to pin\n",
prog->section_name);
return -EINVAL;
}
err = make_dir(path);
if (err)
return err;
for (i = 0; i < prog->instances.nr; i++) {
char buf[PATH_MAX];
int len;
len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
if (len < 0)
return -EINVAL;
else if (len >= PATH_MAX)
return -ENAMETOOLONG;
err = bpf_program__pin_instance(prog, buf, i);
if (err)
return err;
}
return 0;
}
int bpf_map__pin(struct bpf_map *map, const char *path)
{
int err;
err = check_path(path);
if (err)
return err;
if (map == NULL) {
pr_warning("invalid map pointer\n");
return -EINVAL;
}
if (bpf_obj_pin(map->fd, path)) {
pr_warning("failed to pin map: %s\n", strerror(errno));
return -errno;
}
pr_debug("pinned map '%s'\n", path);
return 0;
}
int bpf_object__pin(struct bpf_object *obj, const char *path)
{
struct bpf_program *prog;
struct bpf_map *map;
int err;
if (!obj)
return -ENOENT;
if (!obj->loaded) {
pr_warning("object not yet loaded; load it first\n");
return -ENOENT;
}
err = make_dir(path);
if (err)
return err;
bpf_map__for_each(map, obj) {
char buf[PATH_MAX];
int len;
len = snprintf(buf, PATH_MAX, "%s/%s", path,
bpf_map__name(map));
if (len < 0)
return -EINVAL;
else if (len >= PATH_MAX)
return -ENAMETOOLONG;
err = bpf_map__pin(map, buf);
if (err)
return err;
}
bpf_object__for_each_program(prog, obj) {
char buf[PATH_MAX];
int len;
len = snprintf(buf, PATH_MAX, "%s/%s", path,
prog->section_name);
if (len < 0)
return -EINVAL;
else if (len >= PATH_MAX)
return -ENAMETOOLONG;
err = bpf_program__pin(prog, buf);
if (err)
return err;
}
return 0;
}
void bpf_object__close(struct bpf_object *obj)
{
size_t i;
@ -1419,37 +1624,33 @@ static void bpf_program__set_type(struct bpf_program *prog,
prog->type = type;
}
int bpf_program__set_tracepoint(struct bpf_program *prog)
{
if (!prog)
return -EINVAL;
bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT);
return 0;
}
int bpf_program__set_kprobe(struct bpf_program *prog)
{
if (!prog)
return -EINVAL;
bpf_program__set_type(prog, BPF_PROG_TYPE_KPROBE);
return 0;
}
static bool bpf_program__is_type(struct bpf_program *prog,
enum bpf_prog_type type)
{
return prog ? (prog->type == type) : false;
}
bool bpf_program__is_tracepoint(struct bpf_program *prog)
{
return bpf_program__is_type(prog, BPF_PROG_TYPE_TRACEPOINT);
}
#define BPF_PROG_TYPE_FNS(NAME, TYPE) \
int bpf_program__set_##NAME(struct bpf_program *prog) \
{ \
if (!prog) \
return -EINVAL; \
bpf_program__set_type(prog, TYPE); \
return 0; \
} \
\
bool bpf_program__is_##NAME(struct bpf_program *prog) \
{ \
return bpf_program__is_type(prog, TYPE); \
} \
bool bpf_program__is_kprobe(struct bpf_program *prog)
{
return bpf_program__is_type(prog, BPF_PROG_TYPE_KPROBE);
}
BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
int bpf_map__fd(struct bpf_map *map)
{
@ -1537,3 +1738,10 @@ bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset)
}
return ERR_PTR(-ENOENT);
}
long libbpf_get_error(const void *ptr)
{
if (IS_ERR(ptr))
return PTR_ERR(ptr);
return 0;
}

19
tools/lib/bpf/libbpf.h
View File

@ -22,8 +22,8 @@
#define __BPF_LIBBPF_H
#include <stdio.h>
#include <stdint.h>
#include <stdbool.h>
#include <linux/err.h>
#include <sys/types.h> // for size_t
enum libbpf_errno {
@ -65,6 +65,7 @@ struct bpf_object *bpf_object__open(const char *path);
struct bpf_object *bpf_object__open_buffer(void *obj_buf,
size_t obj_buf_sz,
const char *name);
int bpf_object__pin(struct bpf_object *object, const char *path);
void bpf_object__close(struct bpf_object *object);
/* Load/unload object into/from kernel */
@ -106,6 +107,9 @@ void *bpf_program__priv(struct bpf_program *prog);
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
int bpf_program__fd(struct bpf_program *prog);
int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
int instance);
int bpf_program__pin(struct bpf_program *prog, const char *path);
struct bpf_insn;
@ -174,11 +178,21 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n);
/*
* Adjust type of bpf program. Default is kprobe.
*/
int bpf_program__set_socket_filter(struct bpf_program *prog);
int bpf_program__set_tracepoint(struct bpf_program *prog);
int bpf_program__set_kprobe(struct bpf_program *prog);
int bpf_program__set_sched_cls(struct bpf_program *prog);
int bpf_program__set_sched_act(struct bpf_program *prog);
int bpf_program__set_xdp(struct bpf_program *prog);
int bpf_program__set_perf_event(struct bpf_program *prog);
bool bpf_program__is_socket_filter(struct bpf_program *prog);
bool bpf_program__is_tracepoint(struct bpf_program *prog);
bool bpf_program__is_kprobe(struct bpf_program *prog);
bool bpf_program__is_sched_cls(struct bpf_program *prog);
bool bpf_program__is_sched_act(struct bpf_program *prog);
bool bpf_program__is_xdp(struct bpf_program *prog);
bool bpf_program__is_perf_event(struct bpf_program *prog);
/*
* We don't need __attribute__((packed)) now since it is
@ -223,5 +237,8 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
int bpf_map__set_priv(struct bpf_map *map, void *priv,
bpf_map_clear_priv_t clear_priv);
void *bpf_map__priv(struct bpf_map *map);
int bpf_map__pin(struct bpf_map *map, const char *path);
long libbpf_get_error(const void *ptr);
#endif

8
tools/lib/subcmd/Makefile
View File

@ -19,7 +19,13 @@ MAKEFLAGS += --no-print-directory
LIBFILE = $(OUTPUT)libsubcmd.a
CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
ifeq ($(CC), clang)
CFLAGS += -O3
else
CFLAGS += -O6
endif
# Treat warnings as errors unless directed not to
ifneq ($(WERROR),0)

4
tools/lib/subcmd/parse-options.c
View File

@ -270,6 +270,8 @@ static int get_value(struct parse_opt_ctx_t *p,
}
if (get_arg(p, opt, flags, &arg))
return -1;
if (arg[0] == '-')
return opterror(opt, "expects an unsigned numerical value", flags);
*(unsigned int *)opt->value = strtol(arg, (char **)&s, 10);
if (*s)
return opterror(opt, "expects a numerical value", flags);
@ -302,6 +304,8 @@ static int get_value(struct parse_opt_ctx_t *p,
}
if (get_arg(p, opt, flags, &arg))
return -1;
if (arg[0] == '-')
return opterror(opt, "expects an unsigned numerical value", flags);
*(u64 *)opt->value = strtoull(arg, (char **)&s, 10);
if (*s)
return opterror(opt, "expects a numerical value", flags);

19
tools/lib/subcmd/parse-options.h
View File

@ -1,6 +1,7 @@
#ifndef __SUBCMD_PARSE_OPTIONS_H
#define __SUBCMD_PARSE_OPTIONS_H
#include <linux/kernel.h>
#include <stdbool.h>
#include <stdint.h>
@ -132,32 +133,32 @@ struct option {
#define OPT_UINTEGER(s, l, v, h) { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) }
#define OPT_LONG(s, l, v, h) { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
#define OPT_U64(s, l, v, h) { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h) }
#define OPT_STRING_OPTARG(s, l, v, a, h, d) \
{ .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
.value = check_vtype(v, const char **), (a), .help = (h), \
.value = check_vtype(v, const char **), .argh =(a), .help = (h), \
.flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
#define OPT_STRING_OPTARG_SET(s, l, v, os, a, h, d) \
{ .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
.value = check_vtype(v, const char **), (a), .help = (h), \
.value = check_vtype(v, const char **), .argh = (a), .help = (h), \
.flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d), \
.set = check_vtype(os, bool *)}
#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
#define OPT_DATE(s, l, v, h) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
#define OPT_CALLBACK(s, l, v, a, h, f) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f) }
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f) }
#define OPT_CALLBACK_NOOPT(s, l, v, a, h, f) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
#define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
#define OPT_CALLBACK_DEFAULT_NOOPT(s, l, v, a, h, f, d) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\
.value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
.value = (v), .arg = (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
.flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG}
#define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \
.value = (v), (a), .help = (h), .callback = (f), \
.value = (v), .argh = (a), .help = (h), .callback = (f), \
.flags = PARSE_OPT_OPTARG, .data = (d) }
/* parse_options() will filter out the processed options and leave the

14
tools/lib/traceevent/Makefile
View File

@ -257,10 +257,16 @@ define do_install_plugins
endef
define do_generate_dynamic_list_file
(echo '{'; \
$(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u; \
echo '};'; \
) > $2
symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \
xargs echo "U W w" | tr ' ' '\n' | sort -u | xargs echo`;\
if [ "$$symbol_type" = "U W w" ];then \
(echo '{'; \
$(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\
echo '};'; \
) > $2; \
else \
(echo Either missing one of [$1] or bad version of $(NM)) 1>&2;\
fi
endef
install_lib: all_cmd install_plugins

1
tools/lib/traceevent/kbuffer-parse.c
View File

@ -315,6 +315,7 @@ static unsigned int old_update_pointers(struct kbuffer *kbuf)
extend += delta;
delta = extend;
ptr += 4;
length = 0;
break;
case OLD_RINGBUF_TYPE_TIME_STAMP:

2
tools/lib/traceevent/plugin_function.c
View File

@ -130,7 +130,7 @@ static int function_handler(struct trace_seq *s, struct pevent_record *record,
unsigned long long pfunction;
const char *func;
const char *parent;
int index;
int index = 0;
if (pevent_get_field_val(s, event, "ip", record, &function, 1))
return trace_seq_putc(s, '!');

5
tools/perf/Build
View File

@ -3,10 +3,12 @@ perf-y += builtin-annotate.o
perf-y += builtin-config.o
perf-y += builtin-diff.o
perf-y += builtin-evlist.o
perf-y += builtin-ftrace.o
perf-y += builtin-help.o
perf-y += builtin-sched.o
perf-y += builtin-buildid-list.o
perf-y += builtin-buildid-cache.o
perf-y += builtin-kallsyms.o
perf-y += builtin-list.o
perf-y += builtin-record.o
perf-y += builtin-report.o
@ -39,8 +41,7 @@ CFLAGS_builtin-help.o += $(paths)
CFLAGS_builtin-timechart.o += $(paths)
CFLAGS_perf.o += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" \
-DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" \
-DPREFIX="BUILD_STR($(prefix_SQ))" \
-include $(OUTPUT)PERF-VERSION-FILE
-DPREFIX="BUILD_STR($(prefix_SQ))"
CFLAGS_builtin-trace.o += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))"
CFLAGS_builtin-report.o += -DTIPDIR="BUILD_STR($(tipdir_SQ))"
CFLAGS_builtin-report.o += -DDOCDIR="BUILD_STR($(srcdir_SQ)/Documentation)"

2
tools/perf/Documentation/perf-c2c.txt
View File

@ -248,7 +248,7 @@ output fields set for caheline offsets output:
Code address, Code symbol, Shared Object, Source line
dso - coalesced by shared object
By default the coalescing is setup with 'pid,tid,iaddr'.
By default the coalescing is setup with 'pid,iaddr'.
STDIO OUTPUT
------------

12
tools/perf/Documentation/perf-config.txt
View File

@ -498,6 +498,18 @@ record.*::
But if this option is 'no-cache', it will not update the build-id cache.
'skip' skips post-processing and does not update the cache.
diff.*::
diff.order::
This option sets the number of columns to sort the result.
The default is 0, which means sorting by baseline.
Setting it to 1 will sort the result by delta (or other
compute method selected).
diff.compute::
This options sets the method for computing the diff result.
Possible values are 'delta', 'delta-abs', 'ratio' and
'wdiff'. Default is 'delta'.
SEE ALSO
--------
linkperf:perf[1]

15
tools/perf/Documentation/perf-diff.txt
View File

@ -86,8 +86,9 @@ OPTIONS
-c::
--compute::
Differential computation selection - delta,ratio,wdiff (default is delta).
See COMPARISON METHODS section for more info.
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.
-p::
--period::
@ -99,7 +100,11 @@ OPTIONS
-o::
--order::
Specify compute sorting column number.
Specify compute sorting column number. 0 means sorting by baseline
overhead and 1 (default) means sorting by computed value of column 1
(data from the first file other base baseline). Values more than 1
can be used only if enough data files are provided.
The default value can be set using the diff.order config option.
--percentage::
Determine how to display the overhead percentage of filtered entries.
@ -181,6 +186,10 @@ with:
relative to how entries are filtered. Use --percentage=absolute to
prevent such fluctuation.
delta-abs
~~~~~~~~~
Same as 'delta` method, but sort the result with the absolute values.
ratio
~~~~~
If specified the 'Ratio' column is displayed with value 'r' computed as:

36
tools/perf/Documentation/perf-ftrace.txt 100644
View File

@ -0,0 +1,36 @@
perf-ftrace(1)
=============
NAME
----
perf-ftrace - simple wrapper for kernel's ftrace functionality
SYNOPSIS
--------
[verse]
'perf ftrace' <command>
DESCRIPTION
-----------
The 'perf ftrace' command is a simple wrapper of kernel's ftrace
functionality. It only supports single thread tracing currently and
just reads trace_pipe in text and then write it to stdout.
The following options apply to perf ftrace.
OPTIONS
-------
-t::
--tracer=::
Tracer to use: function_graph or function.
-v::
--verbose=::
Verbosity level.
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-trace[1]

24
tools/perf/Documentation/perf-kallsyms.txt 100644
View File

@ -0,0 +1,24 @@
perf-kallsyms(1)
==============
NAME
----
perf-kallsyms - Searches running kernel for symbols
SYNOPSIS
--------
[verse]
'perf kallsyms <options> symbol_name[,symbol_name...]'
DESCRIPTION
-----------
This command searches the running kernel kallsyms file for the given symbol(s)
and prints information about it, including the DSO, the kallsyms begin/end
addresses and the addresses in the ELF kallsyms symbol table (for symbols in
modules).
OPTIONS
-------
-v::
--verbose=::
Increase verbosity level, showing details about symbol table loading, etc.

14
tools/perf/Documentation/perf-record.txt
View File

@ -421,9 +421,19 @@ Configure all used events to run in user space.
--timestamp-filename
Append timestamp to output file name.
--switch-output::
--switch-output[=mode]::
Generate multiple perf.data files, timestamp prefixed, switching to a new one
when receiving a SIGUSR2.
based on 'mode' value:
"signal" - when receiving a SIGUSR2 (default value) or
<size> - when reaching the size threshold, size is expected to
be a number with appended unit character - B/K/M/G
<time> - when reaching the time threshold, size is expected to
be a number with appended unit character - s/m/h/d
Note: the precision of the size threshold hugely depends
on your configuration - the number and size of your ring
buffers (-m). It is generally more precise for higher sizes
(like >5M), for lower values expect different sizes.
A possible use case is to, given an external event, slice the perf.data file
that gets then processed, possibly via a perf script, to decide if that

2
tools/perf/Documentation/perf-sched.txt
View File

@ -143,6 +143,8 @@ OPTIONS for 'perf sched timehist'
stop time is not given (i.e, time string is 'x.y,') then analysis goes
to end of file.
--state::
Show task state when it switched out.
SEE ALSO
--------

4
tools/perf/Documentation/perf-script.txt
View File

@ -36,7 +36,7 @@ There are several variants of perf script:
'perf script report <script> [args]' to run and display the results
of <script>. <script> is the name displayed in the output of 'perf
trace --list' i.e. the actual script name minus any language
script --list' i.e. the actual script name minus any language
extension. The perf.data output from a previous run of 'perf script
record <script>' is used and should be present for this command to
succeed. [args] refers to the (mainly optional) args expected by
@ -76,7 +76,7 @@ OPTIONS
Any command you can specify in a shell.
-D::
--dump-raw-script=::
--dump-raw-trace=::
Display verbose dump of the trace data.
-L::

8
tools/perf/Documentation/perf-trace.txt
View File

@ -35,7 +35,10 @@ OPTIONS
-e::
--expr::
List of syscalls to show, currently only syscall names.
--event::
List of syscalls and other perf events (tracepoints, HW cache events,
etc) to show.
See 'perf list' for a complete list of events.
Prefixing with ! shows all syscalls but the ones specified. You may
need to escape it.
@ -135,9 +138,6 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
--kernel-syscall-graph::
Show the kernel callchains on the syscall exit path.
--event::
Trace other events, see 'perf list' for a complete list.
--max-stack::
Set the stack depth limit when parsing the callchain, anything
beyond the specified depth will be ignored. Note that at this point

1
tools/perf/MANIFEST
View File

@ -61,6 +61,7 @@ tools/include/asm-generic/bitops.h
tools/include/linux/atomic.h
tools/include/linux/bitops.h
tools/include/linux/compiler.h
tools/include/linux/compiler-gcc.h
tools/include/linux/coresight-pmu.h
tools/include/linux/filter.h
tools/include/linux/hash.h

10
tools/perf/Makefile.config
View File

@ -144,8 +144,12 @@ ifndef DEBUG
endif
ifeq ($(DEBUG),0)
ifeq ($(CC), clang)
CFLAGS += -O3
else
CFLAGS += -O6
endif
endif
ifdef PARSER_DEBUG
PARSER_DEBUG_BISON := -t
@ -291,8 +295,10 @@ else
endif
endif
ifneq ($(feature-dwarf), 1)
msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
NO_DWARF := 1
ifndef NO_DWARF
msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
NO_DWARF := 1
endif
else
ifneq ($(feature-dwarf_getlocations), 1)
msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157);

1
tools/perf/Makefile.perf
View File

@ -661,6 +661,7 @@ ifndef NO_PERF_READ_VDSOX32
endif
ifndef NO_JVMTI
$(call QUIET_INSTALL, $(LIBJVMTI)) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \
$(INSTALL) $(OUTPUT)$(LIBJVMTI) '$(DESTDIR_SQ)$(libdir_SQ)';
endif
$(call QUIET_INSTALL, libexec) \

1
tools/perf/arch/arm64/Makefile
View File

@ -2,3 +2,4 @@ ifndef NO_DWARF
PERF_HAVE_DWARF_REGS := 1
endif
PERF_HAVE_JITDUMP := 1
PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1

12
tools/perf/arch/arm64/include/dwarf-regs-table.h
View File

@ -2,12 +2,12 @@
/* This is included in perf/util/dwarf-regs.c */
static const char * const aarch64_regstr_tbl[] = {
"%r0", "%r1", "%r2", "%r3", "%r4",
"%r5", "%r6", "%r7", "%r8", "%r9",
"%r10", "%r11", "%r12", "%r13", "%r14",
"%r15", "%r16", "%r17", "%r18", "%r19",
"%r20", "%r21", "%r22", "%r23", "%r24",
"%r25", "%r26", "%r27", "%r28", "%r29",
"%x0", "%x1", "%x2", "%x3", "%x4",
"%x5", "%x6", "%x7", "%x8", "%x9",
"%x10", "%x11", "%x12", "%x13", "%x14",
"%x15", "%x16", "%x17", "%x18", "%x19",
"%x20", "%x21", "%x22", "%x23", "%x24",
"%x25", "%x26", "%x27", "%x28", "%x29",
"%lr", "%sp",
};
#endif

15
tools/perf/arch/arm64/util/dwarf-regs.c
View File

@ -10,17 +10,20 @@
#include <stddef.h>
#include <dwarf-regs.h>
#include <linux/ptrace.h> /* for struct user_pt_regs */
#include "util.h"
struct pt_regs_dwarfnum {
const char *name;
unsigned int dwarfnum;
};
#define STR(s) #s
#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
#define GPR_DWARFNUM_NAME(num) \
{.name = STR(%x##num), .dwarfnum = num}
#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
#define DWARFNUM2OFFSET(index) \
(index * sizeof((struct user_pt_regs *)0)->regs[0])
/*
* Reference:
@ -78,3 +81,13 @@ const char *get_arch_regstr(unsigned int n)
return roff->name;
return NULL;
}
int regs_query_register_offset(const char *name)
{
const struct pt_regs_dwarfnum *roff;
for (roff = regdwarfnum_table; roff->name != NULL; roff++)
if (!strcmp(roff->name, name))
return DWARFNUM2OFFSET(roff->dwarfnum);
return -EINVAL;
}

4
tools/perf/bench/futex-hash.c
View File

@ -130,8 +130,6 @@ int bench_futex_hash(int argc, const char **argv,
}
ncpus = sysconf(_SC_NPROCESSORS_ONLN);
nsecs = futexbench_sanitize_numeric(nsecs);
nfutexes = futexbench_sanitize_numeric(nfutexes);
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
@ -139,8 +137,6 @@ int bench_futex_hash(int argc, const char **argv,
if (!nthreads) /* default to the number of CPUs */
nthreads = ncpus;
else
nthreads = futexbench_sanitize_numeric(nthreads);
worker = calloc(nthreads, sizeof(*worker));
if (!worker)

3
tools/perf/bench/futex-lock-pi.c
View File

@ -152,7 +152,6 @@ int bench_futex_lock_pi(int argc, const char **argv,
goto err;
ncpus = sysconf(_SC_NPROCESSORS_ONLN);
nsecs = futexbench_sanitize_numeric(nsecs);
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
@ -160,8 +159,6 @@ int bench_futex_lock_pi(int argc, const char **argv,
if (!nthreads)
nthreads = ncpus;
else
nthreads = futexbench_sanitize_numeric(nthreads);
worker = calloc(nthreads, sizeof(*worker));
if (!worker)

2
tools/perf/bench/futex-requeue.c
View File

@ -128,8 +128,6 @@ int bench_futex_requeue(int argc, const char **argv,
if (!nthreads)
nthreads = ncpus;
else
nthreads = futexbench_sanitize_numeric(nthreads);
worker = calloc(nthreads, sizeof(*worker));
if (!worker)

4
tools/perf/bench/futex-wake-parallel.c
View File

@ -217,12 +217,8 @@ int bench_futex_wake_parallel(int argc, const char **argv,
sigaction(SIGINT, &act, NULL);
ncpus = sysconf(_SC_NPROCESSORS_ONLN);
nwaking_threads = futexbench_sanitize_numeric(nwaking_threads);
if (!nblocked_threads)
nblocked_threads = ncpus;
else
nblocked_threads = futexbench_sanitize_numeric(nblocked_threads);
/* some sanity checks */
if (nwaking_threads > nblocked_threads || !nwaking_threads)

3
tools/perf/bench/futex-wake.c
View File

@ -129,7 +129,6 @@ int bench_futex_wake(int argc, const char **argv,
}
ncpus = sysconf(_SC_NPROCESSORS_ONLN);
nwakes = futexbench_sanitize_numeric(nwakes);
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
@ -137,8 +136,6 @@ int bench_futex_wake(int argc, const char **argv,
if (!nthreads)
nthreads = ncpus;
else
nthreads = futexbench_sanitize_numeric(nthreads);
worker = calloc(nthreads, sizeof(*worker));
if (!worker)

4
tools/perf/bench/futex.h
View File

@ -7,7 +7,6 @@
#ifndef _FUTEX_H
#define _FUTEX_H
#include <stdlib.h>
#include <unistd.h>
#include <sys/syscall.h>
#include <sys/types.h>
@ -100,7 +99,4 @@ static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr,
}
#endif
/* User input sanitation */
#define futexbench_sanitize_numeric(__n) abs((__n))
#endif /* _FUTEX_H */

7
tools/perf/bench/numa.c
View File

@ -43,6 +43,7 @@
/*
* Debug printf:
*/
#undef dprintf
#define dprintf(x...) do { if (g && g->p.show_details >= 1) printf(x); } while (0)
struct thread_data {
@ -1573,13 +1574,13 @@ static int __bench_numa(const char *name)
"GB/sec,", "total-speed", "GB/sec total speed");
if (g->p.show_details >= 2) {
char tname[32];
char tname[14 + 2 * 10 + 1];
struct thread_data *td;
for (p = 0; p < g->p.nr_proc; p++) {
for (t = 0; t < g->p.nr_threads; t++) {
memset(tname, 0, 32);
memset(tname, 0, sizeof(tname));
td = g->threads + p*g->p.nr_threads + t;
snprintf(tname, 32, "process%d:thread%d", p, t);
snprintf(tname, sizeof(tname), "process%d:thread%d", p, t);
print_res(tname, td->speed_gbs,
"GB/sec", "thread-speed", "GB/sec/thread speed");
print_res(tname, td->system_time_ns / NSEC_PER_SEC,

3
tools/perf/builtin-c2c.c
View File

@ -58,7 +58,7 @@ struct c2c_hist_entry {
struct hist_entry he;
};
static char const *coalesce_default = "pid,tid,iaddr";
static char const *coalesce_default = "pid,iaddr";
struct perf_c2c {
struct perf_tool tool;
@ -2476,6 +2476,7 @@ static int build_cl_output(char *cl_sort, bool no_source)
"mean_rmt,"
"mean_lcl,"
"mean_load,"
"tot_recs,"
"cpucnt,",
add_sym ? "symbol," : "",
add_dso ? "dso," : "",

78
tools/perf/builtin-diff.c
View File

@ -17,6 +17,7 @@
#include "util/symbol.h"
#include "util/util.h"
#include "util/data.h"
#include "util/config.h"
#include <stdlib.h>
#include <math.h>
@ -30,6 +31,7 @@ enum {
PERF_HPP_DIFF__RATIO,
PERF_HPP_DIFF__WEIGHTED_DIFF,
PERF_HPP_DIFF__FORMULA,
PERF_HPP_DIFF__DELTA_ABS,
PERF_HPP_DIFF__MAX_INDEX
};
@ -64,7 +66,7 @@ static bool force;
static bool show_period;
static bool show_formula;
static bool show_baseline_only;
static unsigned int sort_compute;
static unsigned int sort_compute = 1;
static s64 compute_wdiff_w1;
static s64 compute_wdiff_w2;
@ -73,19 +75,22 @@ enum {
COMPUTE_DELTA,
COMPUTE_RATIO,
COMPUTE_WEIGHTED_DIFF,
COMPUTE_DELTA_ABS,
COMPUTE_MAX,
};
const char *compute_names[COMPUTE_MAX] = {
[COMPUTE_DELTA] = "delta",
[COMPUTE_DELTA_ABS] = "delta-abs",
[COMPUTE_RATIO] = "ratio",
[COMPUTE_WEIGHTED_DIFF] = "wdiff",
};
static int compute;
static int compute = COMPUTE_DELTA_ABS;
static int compute_2_hpp[COMPUTE_MAX] = {
[COMPUTE_DELTA] = PERF_HPP_DIFF__DELTA,
[COMPUTE_DELTA_ABS] = PERF_HPP_DIFF__DELTA_ABS,
[COMPUTE_RATIO] = PERF_HPP_DIFF__RATIO,
[COMPUTE_WEIGHTED_DIFF] = PERF_HPP_DIFF__WEIGHTED_DIFF,
};
@ -111,6 +116,10 @@ static struct header_column {
.name = "Delta",
.width = 7,
},
[PERF_HPP_DIFF__DELTA_ABS] = {
.name = "Delta Abs",
.width = 7,
},
[PERF_HPP_DIFF__RATIO] = {
.name = "Ratio",
.width = 14,
@ -298,6 +307,7 @@ static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair,
{
switch (compute) {
case COMPUTE_DELTA:
case COMPUTE_DELTA_ABS:
return formula_delta(he, pair, buf, size);
case COMPUTE_RATIO:
return formula_ratio(he, pair, buf, size);
@ -461,6 +471,7 @@ static void hists__precompute(struct hists *hists)
switch (compute) {
case COMPUTE_DELTA:
case COMPUTE_DELTA_ABS:
compute_delta(he, pair);
break;
case COMPUTE_RATIO:
@ -498,6 +509,13 @@ __hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
return cmp_doubles(l, r);
}
case COMPUTE_DELTA_ABS:
{
double l = fabs(left->diff.period_ratio_delta);
double r = fabs(right->diff.period_ratio_delta);
return cmp_doubles(l, r);
}
case COMPUTE_RATIO:
{
double l = left->diff.period_ratio;
@ -564,7 +582,7 @@ hist_entry__cmp_compute_idx(struct hist_entry *left, struct hist_entry *right,
if (!p_left || !p_right)
return p_left ? -1 : 1;
if (c != COMPUTE_DELTA) {
if (c != COMPUTE_DELTA && c != COMPUTE_DELTA_ABS) {
/*
* The delta can be computed without the baseline, but
* others are not. Put those entries which have no
@ -606,6 +624,15 @@ hist_entry__cmp_delta(struct perf_hpp_fmt *fmt,
return hist_entry__cmp_compute(right, left, COMPUTE_DELTA, d->idx);
}
static int64_t
hist_entry__cmp_delta_abs(struct perf_hpp_fmt *fmt,
struct hist_entry *left, struct hist_entry *right)
{
struct data__file *d = fmt_to_data_file(fmt);
return hist_entry__cmp_compute(right, left, COMPUTE_DELTA_ABS, d->idx);
}
static int64_t
hist_entry__cmp_ratio(struct perf_hpp_fmt *fmt,
struct hist_entry *left, struct hist_entry *right)
@ -632,6 +659,14 @@ hist_entry__cmp_delta_idx(struct perf_hpp_fmt *fmt __maybe_unused,
sort_compute);
}
static int64_t
hist_entry__cmp_delta_abs_idx(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left, struct hist_entry *right)
{
return hist_entry__cmp_compute_idx(right, left, COMPUTE_DELTA_ABS,
sort_compute);
}
static int64_t
hist_entry__cmp_ratio_idx(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left, struct hist_entry *right)
@ -775,7 +810,7 @@ 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,ratio,wdiff:w1,w2 (default delta)",
"delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs)",
"Entries differential computation selection",
setup_compute),
OPT_BOOLEAN('p', "period", &show_period,
@ -945,6 +980,7 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair,
switch (idx) {
case PERF_HPP_DIFF__DELTA:
case PERF_HPP_DIFF__DELTA_ABS:
if (pair->diff.computed)
diff = pair->diff.period_ratio_delta;
else
@ -1118,6 +1154,10 @@ static void data__hpp_register(struct data__file *d, int idx)
fmt->color = hpp__color_wdiff;
fmt->sort = hist_entry__cmp_wdiff;
break;
case PERF_HPP_DIFF__DELTA_ABS:
fmt->color = hpp__color_delta;
fmt->sort = hist_entry__cmp_delta_abs;
break;
default:
fmt->sort = hist_entry__cmp_nop;
break;
@ -1195,6 +1235,9 @@ static int ui_init(void)
case COMPUTE_WEIGHTED_DIFF:
fmt->sort = hist_entry__cmp_wdiff_idx;
break;
case COMPUTE_DELTA_ABS:
fmt->sort = hist_entry__cmp_delta_abs_idx;
break;
default:
BUG_ON(1);
}
@ -1249,6 +1292,31 @@ static int data_init(int argc, const char **argv)
return 0;
}
static int diff__config(const char *var, const char *value,
void *cb __maybe_unused)
{
if (!strcmp(var, "diff.order")) {
sort_compute = perf_config_int(var, value);
return 0;
}
if (!strcmp(var, "diff.compute")) {
if (!strcmp(value, "delta")) {
compute = COMPUTE_DELTA;
} else if (!strcmp(value, "delta-abs")) {
compute = COMPUTE_DELTA_ABS;
} else if (!strcmp(value, "ratio")) {
compute = COMPUTE_RATIO;
} else if (!strcmp(value, "wdiff")) {
compute = COMPUTE_WEIGHTED_DIFF;
} else {
pr_err("Invalid compute method: %s\n", value);
return -1;
}
}
return 0;
}
int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
{
int ret = hists__init();
@ -1256,6 +1324,8 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
if (ret < 0)
return ret;
perf_config(diff__config, NULL);
argc = parse_options(argc, argv, options, diff_usage, 0);
if (symbol__init(NULL) < 0)

265
tools/perf/builtin-ftrace.c 100644
View File

@ -0,0 +1,265 @@
/*
* builtin-ftrace.c
*
* Copyright (c) 2013 LG Electronics, Namhyung Kim <namhyung@kernel.org>
*
* Released under the GPL v2.
*/
#include "builtin.h"
#include "perf.h"
#include <unistd.h>
#include <signal.h>
#include "debug.h"
#include <subcmd/parse-options.h>
#include "evlist.h"
#include "target.h"
#include "thread_map.h"
#include "util/config.h"
#define DEFAULT_TRACER "function_graph"
struct perf_ftrace {
struct perf_evlist *evlist;
struct target target;
const char *tracer;
};
static bool done;
static void sig_handler(int sig __maybe_unused)
{
done = true;
}
/*
* perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
* we asked by setting its exec_error to the function below,
* ftrace__workload_exec_failed_signal.
*
* XXX We need to handle this more appropriately, emitting an error, etc.
*/
static void ftrace__workload_exec_failed_signal(int signo __maybe_unused,
siginfo_t *info __maybe_unused,
void *ucontext __maybe_unused)
{
/* workload_exec_errno = info->si_value.sival_int; */
done = true;
}
static int write_tracing_file(const char *name, const char *val)
{
char *file;
int fd, ret = -1;
ssize_t size = strlen(val);
file = get_tracing_file(name);
if (!file) {
pr_debug("cannot get tracing file: %s\n", name);
return -1;
}
fd = open(file, O_WRONLY);
if (fd < 0) {
pr_debug("cannot open tracing file: %s\n", name);
goto out;
}
if (write(fd, val, size) == size)
ret = 0;
else
pr_debug("write '%s' to tracing/%s failed\n", val, name);
close(fd);
out:
put_tracing_file(file);
return ret;
}
static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
{
if (write_tracing_file("tracing_on", "0") < 0)
return -1;
if (write_tracing_file("current_tracer", "nop") < 0)
return -1;
if (write_tracing_file("set_ftrace_pid", " ") < 0)
return -1;
return 0;
}
static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
{
char *trace_file;
int trace_fd;
char *trace_pid;
char buf[4096];
struct pollfd pollfd = {
.events = POLLIN,
};
if (geteuid() != 0) {
pr_err("ftrace only works for root!\n");
return -1;
}
if (argc < 1)
return -1;
signal(SIGINT, sig_handler);
signal(SIGUSR1, sig_handler);
signal(SIGCHLD, sig_handler);
reset_tracing_files(ftrace);
/* reset ftrace buffer */
if (write_tracing_file("trace", "0") < 0)
goto out;
if (perf_evlist__prepare_workload(ftrace->evlist, &ftrace->target,
argv, false, ftrace__workload_exec_failed_signal) < 0)
goto out;
if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
goto out;
}
if (asprintf(&trace_pid, "%d", thread_map__pid(ftrace->evlist->threads, 0)) < 0) {
pr_err("failed to allocate pid string\n");
goto out;
}
if (write_tracing_file("set_ftrace_pid", trace_pid) < 0) {
pr_err("failed to set pid: %s\n", trace_pid);
goto out_free_pid;
}
trace_file = get_tracing_file("trace_pipe");
if (!trace_file) {
pr_err("failed to open trace_pipe\n");
goto out_free_pid;
}
trace_fd = open(trace_file, O_RDONLY);
put_tracing_file(trace_file);
if (trace_fd < 0) {
pr_err("failed to open trace_pipe\n");
goto out_free_pid;
}
fcntl(trace_fd, F_SETFL, O_NONBLOCK);
pollfd.fd = trace_fd;
if (write_tracing_file("tracing_on", "1") < 0) {
pr_err("can't enable tracing\n");
goto out_close_fd;
}
perf_evlist__start_workload(ftrace->evlist);
while (!done) {
if (poll(&pollfd, 1, -1) < 0)
break;
if (pollfd.revents & POLLIN) {
int n = read(trace_fd, buf, sizeof(buf));
if (n < 0)
break;
if (fwrite(buf, n, 1, stdout) != 1)
break;
}
}
write_tracing_file("tracing_on", "0");
/* read remaining buffer contents */
while (true) {
int n = read(trace_fd, buf, sizeof(buf));
if (n <= 0)
break;
if (fwrite(buf, n, 1, stdout) != 1)
break;
}
out_close_fd:
close(trace_fd);
out_free_pid:
free(trace_pid);
out:
reset_tracing_files(ftrace);
return done ? 0 : -1;
}
static int perf_ftrace_config(const char *var, const char *value, void *cb)
{
struct perf_ftrace *ftrace = cb;
if (prefixcmp(var, "ftrace."))
return 0;
if (strcmp(var, "ftrace.tracer"))
return -1;
if (!strcmp(value, "function_graph") ||
!strcmp(value, "function")) {
ftrace->tracer = value;
return 0;
}
pr_err("Please select \"function_graph\" (default) or \"function\"\n");
return -1;
}
int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
{
int ret;
struct perf_ftrace ftrace = {
.tracer = DEFAULT_TRACER,
.target = { .uid = UINT_MAX, },
};
const char * const ftrace_usage[] = {
"perf ftrace [<options>] <command>",
"perf ftrace [<options>] -- <command> [<options>]",
NULL
};
const struct option ftrace_options[] = {
OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
"tracer to use: function_graph(default) or function"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose"),
OPT_END()
};
ret = perf_config(perf_ftrace_config, &ftrace);
if (ret < 0)
return -1;
argc = parse_options(argc, argv, ftrace_options, ftrace_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc)
usage_with_options(ftrace_usage, ftrace_options);
ftrace.evlist = perf_evlist__new();
if (ftrace.evlist == NULL)
return -ENOMEM;
ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target);
if (ret < 0)
goto out_delete_evlist;
ret = __cmd_ftrace(&ftrace, argc, argv);
out_delete_evlist:
perf_evlist__delete(ftrace.evlist);
return ret;
}

8
tools/perf/builtin-help.c
View File

@ -434,7 +434,7 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
const char * const builtin_help_subcommands[] = {
"buildid-cache", "buildid-list", "diff", "evlist", "help", "list",
"record", "report", "bench", "stat", "timechart", "top", "annotate",
"script", "sched", "kmem", "lock", "kvm", "test", "inject", "mem", "data",
"script", "sched", "kallsyms", "kmem", "lock", "kvm", "test", "inject", "mem", "data",
#ifdef HAVE_LIBELF_SUPPORT
"probe",
#endif
@ -447,11 +447,13 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
NULL
};
const char *alias;
int rc = 0;
int rc;
load_command_list("perf-", &main_cmds, &other_cmds);
perf_config(perf_help_config, &help_format);
rc = perf_config(perf_help_config, &help_format);
if (rc)
return rc;
argc = parse_options_subcommand(argc, argv, builtin_help_options,
builtin_help_subcommands, builtin_help_usage, 0);

67
tools/perf/builtin-kallsyms.c 100644
View File

@ -0,0 +1,67 @@
/*
* builtin-kallsyms.c
*
* Builtin command: Look for a symbol in the running kernel and its modules
*
* Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
*
* Released under the GPL v2. (and only v2, not any later version)
*/
#include "builtin.h"
#include <linux/compiler.h>
#include <subcmd/parse-options.h>
#include "debug.h"
#include "machine.h"
#include "symbol.h"
static int __cmd_kallsyms(int argc, const char **argv)
{
int i;
struct machine *machine = machine__new_kallsyms();
if (machine == NULL) {
pr_err("Couldn't read /proc/kallsyms\n");
return -1;
}
for (i = 0; i < argc; ++i) {
struct map *map;
struct symbol *symbol = machine__find_kernel_function_by_name(machine, argv[i], &map);
if (symbol == NULL) {
printf("%s: not found\n", argv[i]);
continue;
}
printf("%s: %s %s %#" PRIx64 "-%#" PRIx64 " (%#" PRIx64 "-%#" PRIx64")\n",
symbol->name, map->dso->short_name, map->dso->long_name,
map->unmap_ip(map, symbol->start), map->unmap_ip(map, symbol->end),
symbol->start, symbol->end);
}
machine__delete(machine);
return 0;
}
int cmd_kallsyms(int argc, const char **argv, const char *prefix __maybe_unused)
{
const struct option options[] = {
OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"),
OPT_END()
};
const char * const kallsyms_usage[] = {
"perf kallsyms [<options>] symbol_name",
NULL
};
argc = parse_options(argc, argv, options, kallsyms_usage, 0);
if (argc < 1)
usage_with_options(kallsyms_usage, options);
symbol_conf.sort_by_name = true;
symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
if (symbol__init(NULL) < 0)
return -1;
return __cmd_kallsyms(argc, argv);
}

12
tools/perf/builtin-kmem.c
View File

@ -1065,7 +1065,7 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines)
data = rb_entry(next, struct page_stat, node);
sym = machine__find_kernel_function(machine, data->callsite, &map);
if (sym && sym->name)
if (sym)
caller = sym->name;
else
scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
@ -1107,7 +1107,7 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines
data = rb_entry(next, struct page_stat, node);
sym = machine__find_kernel_function(machine, data->callsite, &map);
if (sym && sym->name)
if (sym)
caller = sym->name;
else
scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
@ -1920,10 +1920,12 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
NULL
};
struct perf_session *session;
int ret = -1;
const char errmsg[] = "No %s allocation events found. Have you run 'perf kmem record --%s'?\n";
int ret = perf_config(kmem_config, NULL);
if (ret)
return ret;
perf_config(kmem_config, NULL);
argc = parse_options_subcommand(argc, argv, kmem_options,
kmem_subcommands, kmem_usage, 0);
@ -1948,6 +1950,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
if (session == NULL)
return -1;
ret = -1;
if (kmem_slab) {
if (!perf_evlist__find_tracepoint_by_name(session->evlist,
"kmem:kmalloc")) {

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

@ -14,6 +14,7 @@
#include "util/parse-events.h"
#include "util/cache.h"
#include "util/pmu.h"
#include "util/debug.h"
#include <subcmd/parse-options.h>
static bool desc_flag = true;
@ -29,6 +30,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
"Print extra event descriptions. --no-desc to not print."),
OPT_BOOLEAN('v', "long-desc", &long_desc_flag,
"Print longer event descriptions."),
OPT_INCR(0, "debug", &verbose,
"Enable debugging output"),
OPT_END()
};
const char * const list_usage[] = {

2
tools/perf/builtin-probe.c
View File

@ -552,6 +552,8 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
"Enable kernel symbol demangling"),
OPT_BOOLEAN(0, "cache", &probe_conf.cache, "Manipulate probe cache"),
OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
"Look for files with symbols relative to this directory"),
OPT_END()
};
int ret;

177
tools/perf/builtin-record.c
View File

@ -46,6 +46,15 @@
#include <asm/bug.h>
#include <linux/time64.h>
struct switch_output {
bool enabled;
bool signal;
unsigned long size;
unsigned long time;
const char *str;
bool set;
};
struct record {
struct perf_tool tool;
struct record_opts opts;
@ -62,10 +71,33 @@ struct record {
bool no_buildid_cache_set;
bool buildid_all;
bool timestamp_filename;
bool switch_output;
struct switch_output switch_output;
unsigned long long samples;
};
static volatile int auxtrace_record__snapshot_started;
static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
static DEFINE_TRIGGER(switch_output_trigger);
static bool switch_output_signal(struct record *rec)
{
return rec->switch_output.signal &&
trigger_is_ready(&switch_output_trigger);
}
static bool switch_output_size(struct record *rec)
{
return rec->switch_output.size &&
trigger_is_ready(&switch_output_trigger) &&
(rec->bytes_written >= rec->switch_output.size);
}
static bool switch_output_time(struct record *rec)
{
return rec->switch_output.time &&
trigger_is_ready(&switch_output_trigger);
}
static int record__write(struct record *rec, void *bf, size_t size)
{
if (perf_data_file__write(rec->session->file, bf, size) < 0) {
@ -74,6 +106,10 @@ static int record__write(struct record *rec, void *bf, size_t size)
}
rec->bytes_written += size;
if (switch_output_size(rec))
trigger_hit(&switch_output_trigger);
return 0;
}
@ -193,10 +229,6 @@ static volatile int done;
static volatile int signr = -1;
static volatile int child_finished;
static volatile int auxtrace_record__snapshot_started;
static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
static DEFINE_TRIGGER(switch_output_trigger);
static void sig_handler(int sig)
{
if (sig == SIGCHLD)
@ -386,7 +418,7 @@ static int record__mmap(struct record *rec)
static int record__open(struct record *rec)
{
char msg[512];
char msg[BUFSIZ];
struct perf_evsel *pos;
struct perf_evlist *evlist = rec->evlist;
struct perf_session *session = rec->session;
@ -623,22 +655,23 @@ record__finish_output(struct record *rec)
static int record__synthesize_workload(struct record *rec, bool tail)
{
struct {
struct thread_map map;
struct thread_map_data map_data;
} thread_map;
int err;
struct thread_map *thread_map;
if (rec->opts.tail_synthesize != tail)
return 0;
thread_map.map.nr = 1;
thread_map.map.map[0].pid = rec->evlist->workload.pid;
thread_map.map.map[0].comm = NULL;
return perf_event__synthesize_thread_map(&rec->tool, &thread_map.map,
thread_map = thread_map__new_by_tid(rec->evlist->workload.pid);
if (thread_map == NULL)
return -1;
err = perf_event__synthesize_thread_map(&rec->tool, thread_map,
process_synthesized_event,
&rec->session->machines.host,
rec->opts.sample_address,
rec->opts.proc_map_timeout);
thread_map__put(thread_map);
return err;
}
static int record__synthesize(struct record *rec, bool tail);
@ -712,6 +745,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
}
static void snapshot_sig_handler(int sig);
static void alarm_sig_handler(int sig);
int __weak
perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused,
@ -842,11 +876,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
signal(SIGTERM, sig_handler);
signal(SIGSEGV, sigsegv_handler);
if (rec->opts.auxtrace_snapshot_mode || rec->switch_output) {
if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {
signal(SIGUSR2, snapshot_sig_handler);
if (rec->opts.auxtrace_snapshot_mode)
trigger_on(&auxtrace_snapshot_trigger);
if (rec->switch_output)
if (rec->switch_output.enabled)
trigger_on(&switch_output_trigger);
} else {
signal(SIGUSR2, SIG_IGN);
@ -1043,6 +1077,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
err = fd;
goto out_child;
}
/* re-arm the alarm */
if (rec->switch_output.time)
alarm(rec->switch_output.time);
}
if (hits == rec->samples) {
@ -1352,6 +1390,78 @@ out_free:
return ret;
}
static void switch_output_size_warn(struct record *rec)
{
u64 wakeup_size = perf_evlist__mmap_size(rec->opts.mmap_pages);
struct switch_output *s = &rec->switch_output;
wakeup_size /= 2;
if (s->size < wakeup_size) {
char buf[100];
unit_number__scnprintf(buf, sizeof(buf), wakeup_size);
pr_warning("WARNING: switch-output data size lower than "
"wakeup kernel buffer size (%s) "
"expect bigger perf.data sizes\n", buf);
}
}
static int switch_output_setup(struct record *rec)
{
struct switch_output *s = &rec->switch_output;
static struct parse_tag tags_size[] = {
{ .tag = 'B', .mult = 1 },
{ .tag = 'K', .mult = 1 << 10 },
{ .tag = 'M', .mult = 1 << 20 },
{ .tag = 'G', .mult = 1 << 30 },
{ .tag = 0 },
};
static struct parse_tag tags_time[] = {
{ .tag = 's', .mult = 1 },
{ .tag = 'm', .mult = 60 },
{ .tag = 'h', .mult = 60*60 },
{ .tag = 'd', .mult = 60*60*24 },
{ .tag = 0 },
};
unsigned long val;
if (!s->set)
return 0;
if (!strcmp(s->str, "signal")) {
s->signal = true;
pr_debug("switch-output with SIGUSR2 signal\n");
goto enabled;
}
val = parse_tag_value(s->str, tags_size);
if (val != (unsigned long) -1) {
s->size = val;
pr_debug("switch-output with %s size threshold\n", s->str);
goto enabled;
}
val = parse_tag_value(s->str, tags_time);
if (val != (unsigned long) -1) {
s->time = val;
pr_debug("switch-output with %s time threshold (%lu seconds)\n",
s->str, s->time);
goto enabled;
}
return -1;
enabled:
rec->timestamp_filename = true;
s->enabled = true;
if (s->size && !rec->opts.no_buffering)
switch_output_size_warn(rec);
return 0;
}
static const char * const __record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
@ -1519,8 +1629,10 @@ static struct option __record_options[] = {
"Record build-id of all DSOs regardless of hits"),
OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename,
"append timestamp to output filename"),
OPT_BOOLEAN(0, "switch-output", &record.switch_output,
"Switch output when receive SIGUSR2"),
OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str,
&record.switch_output.set, "signal,size,time",
"Switch output when receive SIGUSR2 or cross size,time threshold",
"signal"),
OPT_BOOLEAN(0, "dry-run", &dry_run,
"Parse options then exit"),
OPT_END()
@ -1559,7 +1671,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
if (rec->evlist == NULL)
return -ENOMEM;
perf_config(perf_record_config, rec);
err = perf_config(perf_record_config, rec);
if (err)
return err;
argc = parse_options(argc, argv, record_options, record_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
@ -1578,8 +1692,15 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
return -EINVAL;
}
if (rec->switch_output)
rec->timestamp_filename = true;
if (switch_output_setup(rec)) {
parse_options_usage(record_usage, record_options, "switch-output", 0);
return -EINVAL;
}
if (rec->switch_output.time) {
signal(SIGALRM, alarm_sig_handler);
alarm(rec->switch_output.time);
}
if (!rec->itr) {
rec->itr = auxtrace_record__init(rec->evlist, &err);
@ -1629,7 +1750,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
if (rec->no_buildid_cache || rec->no_buildid) {
disable_buildid_cache();
} else if (rec->switch_output) {
} else if (rec->switch_output.enabled) {
/*
* In 'perf record --switch-output', disable buildid
* generation by default to reduce data file switching
@ -1721,6 +1842,8 @@ out:
static void snapshot_sig_handler(int sig __maybe_unused)
{
struct record *rec = &record;
if (trigger_is_ready(&auxtrace_snapshot_trigger)) {
trigger_hit(&auxtrace_snapshot_trigger);
auxtrace_record__snapshot_started = 1;
@ -1728,6 +1851,14 @@ static void snapshot_sig_handler(int sig __maybe_unused)
trigger_error(&auxtrace_snapshot_trigger);
}
if (trigger_is_ready(&switch_output_trigger))
if (switch_output_signal(rec))
trigger_hit(&switch_output_trigger);
}
static void alarm_sig_handler(int sig __maybe_unused)
{
struct record *rec = &record;
if (switch_output_time(rec))
trigger_hit(&switch_output_trigger);
}

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

@ -847,7 +847,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
if (ret < 0)
return ret;
perf_config(report__config, &report);
ret = perf_config(report__config, &report);
if (ret)
return ret;
argc = parse_options(argc, argv, options, report_usage, 0);
if (argc) {

132
tools/perf/builtin-sched.c
View File

@ -77,6 +77,22 @@ struct sched_atom {
#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
/* task state bitmask, copied from include/linux/sched.h */
#define TASK_RUNNING 0
#define TASK_INTERRUPTIBLE 1
#define TASK_UNINTERRUPTIBLE 2
#define __TASK_STOPPED 4
#define __TASK_TRACED 8
/* in tsk->exit_state */
#define EXIT_DEAD 16
#define EXIT_ZOMBIE 32
#define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD)
/* in tsk->state again */
#define TASK_DEAD 64
#define TASK_WAKEKILL 128
#define TASK_WAKING 256
#define TASK_PARKED 512
enum thread_state {
THREAD_SLEEPING = 0,
THREAD_WAIT_CPU,
@ -206,6 +222,7 @@ struct perf_sched {
bool show_cpu_visual;
bool show_wakeups;
bool show_migrations;
bool show_state;
u64 skipped_samples;
const char *time_str;
struct perf_time_interval ptime;
@ -216,13 +233,20 @@ struct perf_sched {
struct thread_runtime {
u64 last_time; /* time of previous sched in/out event */
u64 dt_run; /* run time */
u64 dt_wait; /* time between CPU access (off cpu) */
u64 dt_sleep; /* time between CPU access by sleep (off cpu) */
u64 dt_iowait; /* time between CPU access by iowait (off cpu) */
u64 dt_preempt; /* time between CPU access by preempt (off cpu) */
u64 dt_delay; /* time between wakeup and sched-in */
u64 ready_to_run; /* time of wakeup */
struct stats run_stats;
u64 total_run_time;
u64 total_sleep_time;
u64 total_iowait_time;
u64 total_preempt_time;
u64 total_delay_time;
int last_state;
u64 migrations;
};
@ -1821,6 +1845,9 @@ static void timehist_header(struct perf_sched *sched)
printf(" %-*s %9s %9s %9s", comm_width,
"task name", "wait time", "sch delay", "run time");
if (sched->show_state)
printf(" %s", "state");
printf("\n");
/*
@ -1831,9 +1858,14 @@ static void timehist_header(struct perf_sched *sched)
if (sched->show_cpu_visual)
printf(" %*s ", ncpus, "");
printf(" %-*s %9s %9s %9s\n", comm_width,
printf(" %-*s %9s %9s %9s", comm_width,
"[tid/pid]", "(msec)", "(msec)", "(msec)");
if (sched->show_state)
printf(" %5s", "");
printf("\n");
/*
* separator
*/
@ -1846,18 +1878,34 @@ static void timehist_header(struct perf_sched *sched)
graph_dotted_line, graph_dotted_line, graph_dotted_line,
graph_dotted_line);
if (sched->show_state)
printf(" %.5s", graph_dotted_line);
printf("\n");
}
static char task_state_char(struct thread *thread, int state)
{
static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
unsigned bit = state ? ffs(state) : 0;
/* 'I' for idle */
if (thread->tid == 0)
return 'I';
return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?';
}
static void timehist_print_sample(struct perf_sched *sched,
struct perf_sample *sample,
struct addr_location *al,
struct thread *thread,
u64 t)
u64 t, int state)
{
struct thread_runtime *tr = thread__priv(thread);
u32 max_cpus = sched->max_cpu + 1;
char tstr[64];
u64 wait_time;
timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
printf("%15s [%04d] ", tstr, sample->cpu);
@ -1880,10 +1928,15 @@ static void timehist_print_sample(struct perf_sched *sched,
printf(" %-*s ", comm_width, timehist_get_commstr(thread));
print_sched_time(tr->dt_wait, 6);
wait_time = tr->dt_sleep + tr->dt_iowait + tr->dt_preempt;
print_sched_time(wait_time, 6);
print_sched_time(tr->dt_delay, 6);
print_sched_time(tr->dt_run, 6);
if (sched->show_state)
printf(" %5c ", task_state_char(thread, state));
if (sched->show_wakeups)
printf(" %-*s", comm_width, "");
@ -1930,8 +1983,11 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
u64 t, u64 tprev)
{
r->dt_delay = 0;
r->dt_wait = 0;
r->dt_sleep = 0;
r->dt_iowait = 0;
r->dt_preempt = 0;
r->dt_run = 0;
if (tprev) {
r->dt_run = t - tprev;
if (r->ready_to_run) {
@ -1943,12 +1999,25 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
if (r->last_time > tprev)
pr_debug("time travel: last sched out time for task > previous sched_switch event\n");
else if (r->last_time)
r->dt_wait = tprev - r->last_time;
else if (r->last_time) {
u64 dt_wait = tprev - r->last_time;
if (r->last_state == TASK_RUNNING)
r->dt_preempt = dt_wait;
else if (r->last_state == TASK_UNINTERRUPTIBLE)
r->dt_iowait = dt_wait;
else
r->dt_sleep = dt_wait;
}
}
update_stats(&r->run_stats, r->dt_run);
r->total_run_time += r->dt_run;
r->total_run_time += r->dt_run;
r->total_delay_time += r->dt_delay;
r->total_sleep_time += r->dt_sleep;
r->total_iowait_time += r->dt_iowait;
r->total_preempt_time += r->dt_preempt;
}
static bool is_idle_sample(struct perf_sample *sample,
@ -1998,7 +2067,7 @@ static void save_task_callchain(struct perf_sched *sched,
break;
sym = node->sym;
if (sym && sym->name) {
if (sym) {
if (!strcmp(sym->name, "schedule") ||
!strcmp(sym->name, "__schedule") ||
!strcmp(sym->name, "preempt_schedule"))
@ -2373,6 +2442,8 @@ static int timehist_sched_change_event(struct perf_tool *tool,
struct thread_runtime *tr = NULL;
u64 tprev, t = sample->time;
int rc = 0;
int state = perf_evsel__intval(evsel, sample, "prev_state");
if (machine__resolve(machine, &al, sample) < 0) {
pr_err("problem processing %d event. skipping it\n",
@ -2447,8 +2518,10 @@ static int timehist_sched_change_event(struct perf_tool *tool,
* time. we only care total run time and run stat.
*/
last_tr->dt_run = 0;
last_tr->dt_wait = 0;
last_tr->dt_delay = 0;
last_tr->dt_sleep = 0;
last_tr->dt_iowait = 0;
last_tr->dt_preempt = 0;
if (itr->cursor.nr)
callchain_append(&itr->callchain, &itr->cursor, t - tprev);
@ -2458,7 +2531,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
}
if (!sched->summary_only)
timehist_print_sample(sched, sample, &al, thread, t);
timehist_print_sample(sched, sample, &al, thread, t, state);
out:
if (sched->hist_time.start == 0 && t >= ptime->start)
@ -2470,6 +2543,9 @@ out:
/* time of this sched_switch event becomes last time task seen */
tr->last_time = sample->time;
/* last state is used to determine where to account wait time */
tr->last_state = state;
/* sched out event for task so reset ready to run time */
tr->ready_to_run = 0;
}
@ -2526,7 +2602,26 @@ static void print_thread_runtime(struct thread *t,
printf("\n");
}
static void print_thread_waittime(struct thread *t,
struct thread_runtime *r)
{
printf("%*s %5d %9" PRIu64 " ",
comm_width, timehist_get_commstr(t), t->ppid,
(u64) r->run_stats.n);
print_sched_time(r->total_run_time, 8);
print_sched_time(r->total_sleep_time, 6);
printf(" ");
print_sched_time(r->total_iowait_time, 6);
printf(" ");
print_sched_time(r->total_preempt_time, 6);
printf(" ");
print_sched_time(r->total_delay_time, 6);
printf("\n");
}
struct total_run_stats {
struct perf_sched *sched;
u64 sched_count;
u64 task_count;
u64 total_run_time;
@ -2545,7 +2640,11 @@ static int __show_thread_runtime(struct thread *t, void *priv)
stats->task_count++;
stats->sched_count += r->run_stats.n;
stats->total_run_time += r->total_run_time;
print_thread_runtime(t, r);
if (stats->sched->show_state)
print_thread_waittime(t, r);
else
print_thread_runtime(t, r);
}
return 0;
@ -2633,18 +2732,24 @@ static void timehist_print_summary(struct perf_sched *sched,
u64 hist_time = sched->hist_time.end - sched->hist_time.start;
memset(&totals, 0, sizeof(totals));
totals.sched = sched;
if (sched->idle_hist) {
printf("\nIdle-time summary\n");
printf("%*s parent sched-out ", comm_width, "comm");
printf(" idle-time min-idle avg-idle max-idle stddev migrations\n");
} else if (sched->show_state) {
printf("\nWait-time summary\n");
printf("%*s parent sched-in ", comm_width, "comm");
printf(" run-time sleep iowait preempt delay\n");
} else {
printf("\nRuntime summary\n");
printf("%*s parent sched-in ", comm_width, "comm");
printf(" run-time min-run avg-run max-run stddev migrations\n");
}
printf("%*s (count) ", comm_width, "");
printf(" (msec) (msec) (msec) (msec) %%\n");
printf(" (msec) (msec) (msec) (msec) %s\n",
sched->show_state ? "(msec)" : "%");
printf("%.117s\n", graph_dotted_line);
machine__for_each_thread(m, show_thread_runtime, &totals);
@ -3240,6 +3345,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"),
OPT_STRING(0, "time", &sched.time_str, "str",
"Time span for analysis (start,stop)"),
OPT_BOOLEAN(0, "state", &sched.show_state, "Show task state when sched-out"),
OPT_PARENT(sched_options)
};

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

@ -2180,7 +2180,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
"Show the mmap events"),
OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events,
"Show context switch events (if recorded)"),
OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
OPT_BOOLEAN(0, "ns", &nanosecs,
"Use 9 decimal places when displaying time"),
OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
@ -2212,6 +2212,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
PARSE_OPT_STOP_AT_NON_OPTION);
file.path = input_name;
file.force = symbol_conf.force;
if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);

2
tools/perf/builtin-stat.c
View File

@ -533,7 +533,7 @@ static int store_counter_ids(struct perf_evsel *counter)
static int __run_perf_stat(int argc, const char **argv)
{
int interval = stat_config.interval;
char msg[512];
char msg[BUFSIZ];
unsigned long long t0, t1;
struct perf_evsel *counter;
struct timespec ts;

8
tools/perf/builtin-top.c
View File

@ -643,7 +643,7 @@ repeat:
case -1:
if (errno == EINTR)
continue;
/* Fall trhu */
__fallthrough;
default:
c = getc(stdin);
tcsetattr(0, TCSAFLUSH, &save);
@ -859,7 +859,7 @@ static void perf_top__mmap_read(struct perf_top *top)
static int perf_top__start_counters(struct perf_top *top)
{
char msg[512];
char msg[BUFSIZ];
struct perf_evsel *counter;
struct perf_evlist *evlist = top->evlist;
struct record_opts *opts = &top->record_opts;
@ -1216,7 +1216,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
if (top.evlist == NULL)
return -ENOMEM;
perf_config(perf_top_config, &top);
status = perf_config(perf_top_config, &top);
if (status)
return status;
argc = parse_options(argc, argv, options, top_usage, 0);
if (argc)

120
tools/perf/builtin-trace.c
View File

@ -40,6 +40,7 @@
#include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
#include <stdlib.h>
#include <string.h>
#include <linux/err.h>
#include <linux/filter.h>
#include <linux/audit.h>
@ -2699,6 +2700,91 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler)
evsel->handler = handler;
}
/*
* XXX: Hackish, just splitting the combined -e+--event (syscalls
* (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use
* existing facilities unchanged (trace->ev_qualifier + parse_options()).
*
* It'd be better to introduce a parse_options() variant that would return a
* list with the terms it didn't match to an event...
*/
static int trace__parse_events_option(const struct option *opt, const char *str,
int unset __maybe_unused)
{
struct trace *trace = (struct trace *)opt->value;
const char *s = str;
char *sep = NULL, *lists[2] = { NULL, NULL, };
int len = strlen(str), err = -1, list;
char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
char group_name[PATH_MAX];
if (strace_groups_dir == NULL)
return -1;
if (*s == '!') {
++s;
trace->not_ev_qualifier = true;
}
while (1) {
if ((sep = strchr(s, ',')) != NULL)
*sep = '\0';
list = 0;
if (syscalltbl__id(trace->sctbl, s) >= 0) {
list = 1;
} else {
path__join(group_name, sizeof(group_name), strace_groups_dir, s);
if (access(group_name, R_OK) == 0)
list = 1;
}
if (lists[list]) {
sprintf(lists[list] + strlen(lists[list]), ",%s", s);
} else {
lists[list] = malloc(len);
if (lists[list] == NULL)
goto out;
strcpy(lists[list], s);
}
if (!sep)
break;
*sep = ',';
s = sep + 1;
}
if (lists[1] != NULL) {
struct strlist_config slist_config = {
.dirname = strace_groups_dir,
};
trace->ev_qualifier = strlist__new(lists[1], &slist_config);
if (trace->ev_qualifier == NULL) {
fputs("Not enough memory to parse event qualifier", trace->output);
goto out;
}
if (trace__validate_ev_qualifier(trace))
goto out;
}
err = 0;
if (lists[0]) {
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, lists[0], 0);
}
out:
if (sep)
*sep = ',';
return err;
}
int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
{
const char *trace_usage[] = {
@ -2730,15 +2816,15 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
.max_stack = UINT_MAX,
};
const char *output_name = NULL;
const char *ev_qualifier_str = NULL;
const struct option trace_options[] = {
OPT_CALLBACK(0, "event", &trace.evlist, "event",
"event selector. use 'perf list' to list available events",
parse_events_option),
OPT_CALLBACK('e', "event", &trace, "event",
"event/syscall selector. use 'perf list' to list available events",
trace__parse_events_option),
OPT_BOOLEAN(0, "comm", &trace.show_comm,
"show the thread COMM next to its id"),
OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
OPT_STRING('e', "expr", &ev_qualifier_str, "expr", "list of syscalls to trace"),
OPT_CALLBACK(0, "expr", &trace, "expr", "list of syscalls/events to trace",
trace__parse_events_option),
OPT_STRING('o', "output", &output_name, "file", "output file name"),
OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
@ -2863,7 +2949,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
return -1;
}
if (!trace.trace_syscalls && ev_qualifier_str) {
if (!trace.trace_syscalls && trace.ev_qualifier) {
pr_err("The -e option can't be used with --no-syscalls.\n");
goto out;
}
@ -2878,28 +2964,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
trace.open_id = syscalltbl__id(trace.sctbl, "open");
if (ev_qualifier_str != NULL) {
const char *s = ev_qualifier_str;
struct strlist_config slist_config = {
.dirname = system_path(STRACE_GROUPS_DIR),
};
trace.not_ev_qualifier = *s == '!';
if (trace.not_ev_qualifier)
++s;
trace.ev_qualifier = strlist__new(s, &slist_config);
if (trace.ev_qualifier == NULL) {
fputs("Not enough memory to parse event qualifier",
trace.output);
err = -ENOMEM;
goto out_close;
}
err = trace__validate_ev_qualifier(&trace);
if (err)
goto out_close;
}
err = target__validate(&trace.opts.target);
if (err) {
target__strerror(&trace.opts.target, err, bf, sizeof(bf));

2
tools/perf/builtin.h
View File

@ -23,6 +23,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix);
int cmd_evlist(int argc, const char **argv, const char *prefix);
int cmd_help(int argc, const char **argv, const char *prefix);
int cmd_sched(int argc, const char **argv, const char *prefix);
int cmd_kallsyms(int argc, const char **argv, const char *prefix);
int cmd_list(int argc, const char **argv, const char *prefix);
int cmd_record(int argc, const char **argv, const char *prefix);
int cmd_report(int argc, const char **argv, const char *prefix);
@ -40,6 +41,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix);
int cmd_inject(int argc, const char **argv, const char *prefix);
int cmd_mem(int argc, const char **argv, const char *prefix);
int cmd_data(int argc, const char **argv, const char *prefix);
int cmd_ftrace(int argc, const char **argv, const char *prefix);
int find_scripts(char **scripts_array, char **scripts_path_array);
#endif

2
tools/perf/command-list.txt
View File

@ -11,7 +11,9 @@ perf-data mainporcelain common
perf-diff mainporcelain common
perf-config mainporcelain common
perf-evlist mainporcelain common
perf-ftrace mainporcelain common
perf-inject mainporcelain common
perf-kallsyms mainporcelain common
perf-kmem mainporcelain common
perf-kvm mainporcelain common
perf-list mainporcelain common

20
tools/perf/perf.c
View File

@ -29,7 +29,6 @@ const char perf_usage_string[] =
const char perf_more_info_string[] =
"See 'perf help COMMAND' for more information on a specific command.";
int use_browser = -1;
static int use_pager = -1;
const char *input_name;
@ -47,6 +46,7 @@ static struct cmd_struct commands[] = {
{ "diff", cmd_diff, 0 },
{ "evlist", cmd_evlist, 0 },
{ "help", cmd_help, 0 },
{ "kallsyms", cmd_kallsyms, 0 },
{ "list", cmd_list, 0 },
{ "record", cmd_record, 0 },
{ "report", cmd_report, 0 },
@ -71,6 +71,7 @@ static struct cmd_struct commands[] = {
{ "inject", cmd_inject, 0 },
{ "mem", cmd_mem, 0 },
{ "data", cmd_data, 0 },
{ "ftrace", cmd_ftrace, 0 },
};
struct pager_config {
@ -89,11 +90,12 @@ static int pager_command_config(const char *var, const char *value, void *data)
/* returns 0 for "no pager", 1 for "use pager", and -1 for "not specified" */
int check_pager_config(const char *cmd)
{
int err;
struct pager_config c;
c.cmd = cmd;
c.val = -1;
perf_config(pager_command_config, &c);
return c.val;
err = perf_config(pager_command_config, &c);
return err ?: c.val;
}
static int browser_command_config(const char *var, const char *value, void *data)
@ -112,11 +114,12 @@ static int browser_command_config(const char *var, const char *value, void *data
*/
static int check_browser_config(const char *cmd)
{
int err;
struct pager_config c;
c.cmd = cmd;
c.val = -1;
perf_config(browser_command_config, &c);
return c.val;
err = perf_config(browser_command_config, &c);
return err ?: c.val;
}
static void commit_pager_choice(void)
@ -329,8 +332,6 @@ static int handle_alias(int *argcp, const char ***argv)
return ret;
}
const char perf_version_string[] = PERF_VERSION;
#define RUN_SETUP (1<<0)
#define USE_PAGER (1<<1)
@ -510,6 +511,7 @@ static void cache_line_size(int *cacheline_sizep)
int main(int argc, const char **argv)
{
int err;
const char *cmd;
char sbuf[STRERR_BUFSIZE];
int value;
@ -535,7 +537,9 @@ int main(int argc, const char **argv)
srandom(time(NULL));
perf_config__init();
perf_config(perf_default_config, NULL);
err = perf_config(perf_default_config, NULL);
if (err)
return err;
set_buildid_dir(NULL);
/* get debugfs/tracefs mount point from /proc/mounts */

317
tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json 100644
View File

@ -0,0 +1,317 @@
[
{
"BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
"Counter": "0,1,2,3",
"EventName": "UNC_C_CLOCKTICKS",
"PerPkg": "1",
"Unit": "CBO"
},
{
"BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
"Counter": "0,1,2,3",
"EventCode": "0x34",
"EventName": "UNC_C_LLC_LOOKUP.ANY",
"Filter": "filter_state=0x1",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x11",
"Unit": "CBO"
},
{
"BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
"Counter": "0,1,2,3",
"EventCode": "0x37",
"EventName": "UNC_C_LLC_VICTIMS.M_STATE",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.DATA_READ",
"Filter": "filter_opc=0x182",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.UNCACHEABLE",
"Filter": "filter_opc=0x187",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.MMIO_READ",
"Filter": "filter_opc=0x187,filter_nc=1",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.MMIO_WRITE",
"Filter": "filter_opc=0x18f,filter_nc=1",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
"Filter": "filter_opc=0x190",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
"Filter": "filter_opc=0x191",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
"Filter": "filter_opc=0x192",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.PCIE_READ",
"Filter": "filter_opc=0x19e",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.PCIE_WRITE",
"Filter": "filter_opc=0x1c8",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
"Filter": "filter_opc=0x1c8,filter_tid=0x3e",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
"Filter": "filter_opc=0x180,filter_tid=0x3e",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH",
"Filter": "filter_opc=0x181",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.STREAMING_FULL",
"Filter": "filter_opc=0x18c",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
"Filter": "filter_opc=0x18d",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_READ",
"Filter": "filter_opc=0x19e",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_WRITE",
"Filter": "filter_opc=0x1c8,filter_tid=0x3e",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode",
"EventCode": "0x36",
"EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
"Filter": "filter_opc=0x182",
"PerPkg": "1",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS",
"PerPkg": "1",
"UMask": "0x3",
"Unit": "HA"
},
{
"BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS_LOCAL",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "HA"
},
{
"BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS_REMOTE",
"PerPkg": "1",
"UMask": "0x2",
"Unit": "HA"
},
{
"BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES",
"PerPkg": "1",
"UMask": "0xC",
"Unit": "HA"
},
{
"BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
"PerPkg": "1",
"UMask": "0x4",
"Unit": "HA"
},
{
"BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
"PerPkg": "1",
"UMask": "0x8",
"Unit": "HA"
},
{
"BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
"PerPkg": "1",
"UMask": "0x40",
"Unit": "HA"
},
{
"BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x20",
"Unit": "HA"
},
{
"BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x4",
"Unit": "HA"
},
{
"BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPS",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x2",
"Unit": "HA"
},
{
"BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x8",
"Unit": "HA"
}
]

83
tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json 100644
View File

@ -0,0 +1,83 @@
[
{
"BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_M_CAS_COUNT.RD",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "iMC"
},
{
"BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_M_CAS_COUNT.WR",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0xC",
"Unit": "iMC"
},
{
"BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
"Counter": "0,1,2,3",
"EventName": "UNC_M_CLOCKTICKS",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "UNC_M_POWER_CHANNEL_PPD",
"MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x86",
"EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
"MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
"Counter": "0,1,2,3",
"EventCode": "0x43",
"EventName": "UNC_M_POWER_SELF_REFRESH",
"MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "iMC"
},
{
"BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.RD",
"PerPkg": "1",
"UMask": "0x4",
"Unit": "iMC"
},
{
"BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.WR",
"PerPkg": "1",
"UMask": "0x8",
"Unit": "iMC"
}
]

84
tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json 100644
View File

@ -0,0 +1,84 @@
[
{
"BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
"Counter": "0,1,2,3",
"EventName": "UNC_P_CLOCKTICKS",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
"Filter": "occ_sel=1",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
"Filter": "occ_sel=2",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
"Filter": "occ_sel=3",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xA",
"EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
"MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x6",
"EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x5",
"EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "UNC_P_FREQ_TRANS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
}
]

317
tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json 100644
View File

@ -0,0 +1,317 @@
[
{
"BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
"Counter": "0,1,2,3",
"EventName": "UNC_C_CLOCKTICKS",
"PerPkg": "1",
"Unit": "CBO"
},
{
"BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
"Counter": "0,1,2,3",
"EventCode": "0x34",
"EventName": "UNC_C_LLC_LOOKUP.ANY",
"Filter": "filter_state=0x1",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x11",
"Unit": "CBO"
},
{
"BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
"Counter": "0,1,2,3",
"EventCode": "0x37",
"EventName": "UNC_C_LLC_VICTIMS.M_STATE",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.DATA_READ",
"Filter": "filter_opc=0x182",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.UNCACHEABLE",
"Filter": "filter_opc=0x187",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.MMIO_READ",
"Filter": "filter_opc=0x187,filter_nc=1",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.MMIO_WRITE",
"Filter": "filter_opc=0x18f,filter_nc=1",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
"Filter": "filter_opc=0x190",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
"Filter": "filter_opc=0x191",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
"Filter": "filter_opc=0x192",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.PCIE_READ",
"Filter": "filter_opc=0x19e",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.PCIE_WRITE",
"Filter": "filter_opc=0x1c8",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
"Filter": "filter_opc=0x1c8,filter_tid=0x3e",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
"Filter": "filter_opc=0x180,filter_tid=0x3e",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH",
"Filter": "filter_opc=0x181",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.STREAMING_FULL",
"Filter": "filter_opc=0x18c",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
"Filter": "filter_opc=0x18d",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_READ",
"Filter": "filter_opc=0x19e",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_WRITE",
"Filter": "filter_opc=0x1c8,filter_tid=0x3e",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode",
"EventCode": "0x36",
"EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
"Filter": "filter_opc=0x182",
"PerPkg": "1",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS",
"PerPkg": "1",
"UMask": "0x3",
"Unit": "HA"
},
{
"BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS_LOCAL",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "HA"
},
{
"BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS_REMOTE",
"PerPkg": "1",
"UMask": "0x2",
"Unit": "HA"
},
{
"BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES",
"PerPkg": "1",
"UMask": "0xC",
"Unit": "HA"
},
{
"BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
"PerPkg": "1",
"UMask": "0x4",
"Unit": "HA"
},
{
"BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
"PerPkg": "1",
"UMask": "0x8",
"Unit": "HA"
},
{
"BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
"PerPkg": "1",
"UMask": "0x40",
"Unit": "HA"
},
{
"BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x20",
"Unit": "HA"
},
{
"BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x4",
"Unit": "HA"
},
{
"BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPS",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x2",
"Unit": "HA"
},
{
"BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x8",
"Unit": "HA"
}
]

28
tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json 100644
View File

@ -0,0 +1,28 @@
[
{
"BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks",
"Counter": "0,1,2,3",
"EventCode": "0x14",
"EventName": "UNC_Q_CLOCKTICKS",
"PerPkg": "1",
"Unit": "QPI LL"
},
{
"BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
"Counter": "0,1,2,3",
"EventName": "UNC_Q_TxL_FLITS_G0.DATA",
"PerPkg": "1",
"ScaleUnit": "8Bytes",
"UMask": "0x2",
"Unit": "QPI LL"
},
{
"BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
"Counter": "0,1,2,3",
"EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
"PerPkg": "1",
"ScaleUnit": "8Bytes",
"UMask": "0x4",
"Unit": "QPI LL"
}
]

83
tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json 100644
View File

@ -0,0 +1,83 @@
[
{
"BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_M_CAS_COUNT.RD",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "iMC"
},
{
"BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_M_CAS_COUNT.WR",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0xC",
"Unit": "iMC"
},
{
"BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
"Counter": "0,1,2,3",
"EventName": "UNC_M_CLOCKTICKS",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "UNC_M_POWER_CHANNEL_PPD",
"MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x86",
"EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
"MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
"Counter": "0,1,2,3",
"EventCode": "0x43",
"EventName": "UNC_M_POWER_SELF_REFRESH",
"MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "iMC"
},
{
"BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.RD",
"PerPkg": "1",
"UMask": "0x4",
"Unit": "iMC"
},
{
"BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.WR",
"PerPkg": "1",
"UMask": "0x8",
"Unit": "iMC"
}
]

84
tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json 100644
View File

@ -0,0 +1,84 @@
[
{
"BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
"Counter": "0,1,2,3",
"EventName": "UNC_P_CLOCKTICKS",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
"Filter": "occ_sel=1",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
"Filter": "occ_sel=2",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
"Filter": "occ_sel=3",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xA",
"EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
"MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x6",
"EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x5",
"EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "UNC_P_FREQ_TRANS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
}
]

317
tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json 100644
View File

@ -0,0 +1,317 @@
[
{
"BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
"Counter": "0,1,2,3",
"EventName": "UNC_C_CLOCKTICKS",
"PerPkg": "1",
"Unit": "CBO"
},
{
"BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
"Counter": "0,1,2,3",
"EventCode": "0x34",
"EventName": "UNC_C_LLC_LOOKUP.ANY",
"Filter": "filter_state=0x1",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x11",
"Unit": "CBO"
},
{
"BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
"Counter": "0,1,2,3",
"EventCode": "0x37",
"EventName": "UNC_C_LLC_VICTIMS.M_STATE",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.DATA_READ",
"Filter": "filter_opc=0x182",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.UNCACHEABLE",
"Filter": "filter_opc=0x187",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.MMIO_READ",
"Filter": "filter_opc=0x187,filter_nc=1",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.MMIO_WRITE",
"Filter": "filter_opc=0x18f,filter_nc=1",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
"Filter": "filter_opc=0x190",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
"Filter": "filter_opc=0x191",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
"Filter": "filter_opc=0x192",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.PCIE_READ",
"Filter": "filter_opc=0x19e",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.PCIE_WRITE",
"Filter": "filter_opc=0x1c8",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
"Filter": "filter_opc=0x1c8,filter_tid=0x3e",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
"Filter": "filter_opc=0x180,filter_tid=0x3e",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH",
"Filter": "filter_opc=0x181",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.STREAMING_FULL",
"Filter": "filter_opc=0x18c",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
"Filter": "filter_opc=0x18d",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_READ",
"Filter": "filter_opc=0x19e",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_WRITE",
"Filter": "filter_opc=0x1c8,filter_tid=0x3e",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode",
"EventCode": "0x36",
"EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
"Filter": "filter_opc=0x182",
"PerPkg": "1",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS",
"PerPkg": "1",
"UMask": "0x3",
"Unit": "HA"
},
{
"BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS_LOCAL",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "HA"
},
{
"BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS_REMOTE",
"PerPkg": "1",
"UMask": "0x2",
"Unit": "HA"
},
{
"BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES",
"PerPkg": "1",
"UMask": "0xC",
"Unit": "HA"
},
{
"BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
"PerPkg": "1",
"UMask": "0x4",
"Unit": "HA"
},
{
"BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
"PerPkg": "1",
"UMask": "0x8",
"Unit": "HA"
},
{
"BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
"PerPkg": "1",
"UMask": "0x40",
"Unit": "HA"
},
{
"BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x20",
"Unit": "HA"
},
{
"BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x4",
"Unit": "HA"
},
{
"BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPS",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x2",
"Unit": "HA"
},
{
"BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x8",
"Unit": "HA"
}
]

28
tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json 100644
View File

@ -0,0 +1,28 @@
[
{
"BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks",
"Counter": "0,1,2,3",
"EventCode": "0x14",
"EventName": "UNC_Q_CLOCKTICKS",
"PerPkg": "1",
"Unit": "QPI LL"
},
{
"BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
"Counter": "0,1,2,3",
"EventName": "UNC_Q_TxL_FLITS_G0.DATA",
"PerPkg": "1",
"ScaleUnit": "8Bytes",
"UMask": "0x2",
"Unit": "QPI LL"
},
{
"BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
"Counter": "0,1,2,3",
"EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
"PerPkg": "1",
"ScaleUnit": "8Bytes",
"UMask": "0x4",
"Unit": "QPI LL"
}
]

83
tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json 100644
View File

@ -0,0 +1,83 @@
[
{
"BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_M_CAS_COUNT.RD",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "iMC"
},
{
"BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_M_CAS_COUNT.WR",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0xC",
"Unit": "iMC"
},
{
"BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
"Counter": "0,1,2,3",
"EventName": "UNC_M_CLOCKTICKS",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "UNC_M_POWER_CHANNEL_PPD",
"MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x86",
"EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
"MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
"Counter": "0,1,2,3",
"EventCode": "0x43",
"EventName": "UNC_M_POWER_SELF_REFRESH",
"MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "iMC"
},
{
"BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.RD",
"PerPkg": "1",
"UMask": "0x4",
"Unit": "iMC"
},
{
"BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.WR",
"PerPkg": "1",
"UMask": "0x8",
"Unit": "iMC"
}
]

84
tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json 100644
View File

@ -0,0 +1,84 @@
[
{
"BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
"Counter": "0,1,2,3",
"EventName": "UNC_P_CLOCKTICKS",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
"Filter": "occ_sel=1",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
"Filter": "occ_sel=2",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
"Filter": "occ_sel=3",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xA",
"EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
"MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x6",
"EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x5",
"EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "UNC_P_FREQ_TRANS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
}
]

322
tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json 100644
View File

@ -0,0 +1,322 @@
[
{
"BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
"Counter": "0,1,2,3",
"EventName": "UNC_C_CLOCKTICKS",
"PerPkg": "1",
"Unit": "CBO"
},
{
"BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_C_LLC_LOOKUP.ANY",
"Filter": "filter_state=0x1",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x11",
"Unit": "CBO"
},
{
"BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
"Counter": "0,1",
"EventCode": "0x37",
"EventName": "UNC_C_LLC_VICTIMS.M_STATE",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_MISSES.DATA_READ",
"Filter": "filter_opc=0x182",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_MISSES.UNCACHEABLE",
"Filter": "filter_opc=0x187",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode.rfo_prefetch",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
"Filter": "filter_opc=0x190",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode.code",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
"Filter": "filter_opc=0x191",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode.data_read",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
"Filter": "filter_opc=0x192",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_MISSES.PCIE_WRITE",
"Filter": "filter_opc=0x19c",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode.pcie_read",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_MISSES.PCIE_READ",
"Filter": "filter_opc=0x19e",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_MISSES.ITOM_WRITE",
"Filter": "filter_opc=0x1c8",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses for PCIe non-snoop reads. Derived from unc_c_tor_inserts.miss_opcode.pcie_read",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_MISSES.PCIE_NON_SNOOP_READ",
"Filter": "filter_opc=0x1e4",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses for PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.miss_opcode.pcie_write",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
"Filter": "filter_opc=0x1e6",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.STREAMING_FULL",
"Filter": "filter_opc=0x18c",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
"Filter": "filter_opc=0x18d",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ",
"Filter": "filter_opc=0x195",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_WRITE",
"Filter": "filter_opc=0x19c",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_READ",
"Filter": "filter_opc=0x19e",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.ITOM_WRITE",
"Filter": "filter_opc=0x1c8",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_NS_READ",
"Filter": "filter_opc=0x1e4",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
"Filter": "filter_opc=0x1e5",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_NS_WRITE",
"Filter": "filter_opc=0x1e6",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "Occupancy for all LLC misses that are addressed to local memory. Derived from unc_c_tor_occupancy.miss_local",
"EventCode": "0x36",
"EventName": "UNC_C_TOR_OCCUPANCY.MISS_LOCAL",
"PerPkg": "1",
"UMask": "0x2A",
"Unit": "CBO"
},
{
"BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read",
"EventCode": "0x36",
"EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
"Filter": "filter_opc=0x182",
"PerPkg": "1",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "Occupancy for all LLC misses that are addressed to remote memory. Derived from unc_c_tor_occupancy.miss_remote",
"EventCode": "0x36",
"EventName": "UNC_C_TOR_OCCUPANCY.MISS_REMOTE",
"PerPkg": "1",
"UMask": "0x8A",
"Unit": "CBO"
},
{
"BriefDescription": "Read requests to home agent. Derived from unc_h_requests.reads",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS",
"PerPkg": "1",
"UMask": "0x3",
"Unit": "HA"
},
{
"BriefDescription": "Write requests to home agent. Derived from unc_h_requests.writes",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES",
"PerPkg": "1",
"UMask": "0xC",
"Unit": "HA"
},
{
"BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x20",
"Unit": "HA"
},
{
"BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x4",
"Unit": "HA"
},
{
"BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPS",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x2",
"Unit": "HA"
},
{
"BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x8",
"Unit": "HA"
}
]

46
tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json 100644
View File

@ -0,0 +1,46 @@
[
{
"BriefDescription": "QPI clock ticks. Use to get percentages for QPI cycles events. Derived from unc_q_clockticks",
"Counter": "0,1,2,3",
"EventCode": "0x14",
"EventName": "UNC_Q_CLOCKTICKS",
"PerPkg": "1",
"Unit": "QPI LL"
},
{
"BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x10",
"EventName": "UNC_Q_RxL0P_POWER_CYCLES",
"MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "QPI LL"
},
{
"BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xd",
"EventName": "UNC_Q_TxL0P_POWER_CYCLES",
"MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "QPI LL"
},
{
"BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
"Counter": "0,1,2,3",
"EventName": "UNC_Q_TxL_FLITS_G0.DATA",
"PerPkg": "1",
"ScaleUnit": "8Bytes",
"UMask": "0x2",
"Unit": "QPI LL"
},
{
"BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
"Counter": "0,1,2,3",
"EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
"PerPkg": "1",
"ScaleUnit": "8Bytes",
"UMask": "0x4",
"Unit": "QPI LL"
}
]

75
tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json 100644
View File

@ -0,0 +1,75 @@
[
{
"BriefDescription": "Memory page activates for reads and writes. Derived from unc_m_act_count.rd",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_M_ACT_COUNT.RD",
"PerPkg": "1",
"UMask": "0x1",
"Umask": "0x3",
"Unit": "iMC"
},
{
"BriefDescription": "Read requests to memory controller. Derived from unc_m_cas_count.rd",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_M_CAS_COUNT.RD",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "iMC"
},
{
"BriefDescription": "Write requests to memory controller. Derived from unc_m_cas_count.wr",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_M_CAS_COUNT.WR",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0xC",
"Unit": "iMC"
},
{
"BriefDescription": "Memory controller clock ticks. Use to generate percentages for memory controller CYCLES events. Derived from unc_m_clockticks",
"Counter": "0,1,2,3",
"EventName": "UNC_M_CLOCKTICKS",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "UNC_M_POWER_CHANNEL_PPD",
"MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x86",
"EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
"MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
"Counter": "0,1,2,3",
"EventCode": "0x43",
"EventName": "UNC_M_POWER_SELF_REFRESH",
"MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "iMC"
}
]

249
tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json 100644
View File

@ -0,0 +1,249 @@
[
{
"BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
"Counter": "0,1,2,3",
"EventName": "UNC_P_CLOCKTICKS",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xb",
"EventName": "UNC_P_FREQ_BAND0_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xc",
"EventName": "UNC_P_FREQ_BAND1_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xd",
"EventName": "UNC_P_FREQ_BAND2_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xe",
"EventName": "UNC_P_FREQ_BAND3_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xb",
"EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xc",
"EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xd",
"EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xe",
"EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
"Filter": "occ_sel=1",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
"Filter": "occ_sel=2",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c6",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
"Filter": "occ_sel=3",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xa",
"EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
"MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles when thermal conditions are the upper limit on frequency. This is related to the THERMAL_THROTTLE CYCLES_ABOVE_TEMP event, which always counts cycles when we are above the thermal temperature. This event (STRONGEST_UPPER_LIMIT) is sampled at the output of the algorithm that determines the actual frequency, while THERMAL_THROTTLE looks at the input. Derived from unc_p_freq_max_limit_thermal_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x6",
"EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x5",
"EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x7",
"EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles when the system is changing frequency. This can not be filtered by thread ID. One can also use it with the occupancy counter that monitors number of threads in C0 to estimate the performance impact that frequency transitions had on the system. Derived from unc_p_freq_trans_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x60",
"EventName": "UNC_P_FREQ_TRANS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xb",
"EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
"Filter": "filter_band0=1200",
"MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xc",
"EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
"Filter": "filter_band1=2000",
"MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xd",
"EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
"Filter": "filter_band2=3000",
"MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xe",
"EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
"Filter": "filter_band3=4000",
"MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xb",
"EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band0=1200",
"MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xc",
"EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band1=2000",
"MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xd",
"EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band2=4000",
"MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xe",
"EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band3=4000",
"MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
}
]

209
tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json 100644
View File

@ -0,0 +1,209 @@
[
{
"BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
"Counter": "0,1,2,3",
"EventName": "UNC_C_CLOCKTICKS",
"PerPkg": "1",
"Unit": "CBO"
},
{
"BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_C_LLC_LOOKUP.ANY",
"Filter": "filter_state=0x1",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x11",
"Unit": "CBO"
},
{
"BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
"Counter": "0,1",
"EventCode": "0x37",
"EventName": "UNC_C_LLC_VICTIMS.M_STATE",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_MISSES.DATA_READ",
"Filter": "filter_opc=0x182",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_MISSES.UNCACHEABLE",
"Filter": "filter_opc=0x187",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_MISSES.PCIE_WRITE",
"Filter": "filter_opc=0x19c",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_MISSES.ITOM_WRITE",
"Filter": "filter_opc=0x1c8",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.STREAMING_FULL",
"Filter": "filter_opc=0x18c",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
"Filter": "filter_opc=0x18d",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ",
"Filter": "filter_opc=0x195",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_WRITE",
"Filter": "filter_opc=0x19c",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_READ",
"Filter": "filter_opc=0x19e",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.ITOM_WRITE",
"Filter": "filter_opc=0x1c8",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_NS_READ",
"Filter": "filter_opc=0x1e4",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
"Filter": "filter_opc=0x1e5",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write",
"Counter": "0,1",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.PCIE_NS_WRITE",
"Filter": "filter_opc=0x1e6",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x1",
"Unit": "CBO"
},
{
"BriefDescription": "Occupancy counter for all LLC misses; we divide this by UNC_C_CLOCKTICKS to get average Q depth. Derived from unc_c_tor_occupancy.miss_all",
"EventCode": "0x36",
"EventName": "UNC_C_TOR_OCCUPANCY.MISS_ALL",
"Filter": "filter_opc=0x182",
"MetricExpr": "(UNC_C_TOR_OCCUPANCY.MISS_ALL / UNC_C_CLOCKTICKS) * 100.",
"PerPkg": "1",
"UMask": "0xa",
"Unit": "CBO"
},
{
"BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read",
"EventCode": "0x36",
"EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
"PerPkg": "1",
"UMask": "0x3",
"Unit": "CBO"
},
{
"BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS",
"PerPkg": "1",
"UMask": "0x3",
"Unit": "HA"
},
{
"BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES",
"PerPkg": "1",
"UMask": "0xc",
"Unit": "HA"
}
]

46
tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json 100644
View File

@ -0,0 +1,46 @@
[
{
"BriefDescription": "QPI clock ticks. Used to get percentages of QPI cycles events. Derived from unc_q_clockticks",
"Counter": "0,1,2,3",
"EventCode": "0x14",
"EventName": "UNC_Q_CLOCKTICKS",
"PerPkg": "1",
"Unit": "QPI LL"
},
{
"BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x10",
"EventName": "UNC_Q_RxL0P_POWER_CYCLES",
"MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "QPI LL"
},
{
"BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xd",
"EventName": "UNC_Q_TxL0P_POWER_CYCLES",
"MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "QPI LL"
},
{
"BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
"Counter": "0,1,2,3",
"EventName": "UNC_Q_TxL_FLITS_G0.DATA",
"PerPkg": "1",
"ScaleUnit": "8Bytes",
"UMask": "0x2",
"Unit": "QPI LL"
},
{
"BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
"Counter": "0,1,2,3",
"EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
"PerPkg": "1",
"ScaleUnit": "8Bytes",
"UMask": "0x4",
"Unit": "QPI LL"
}
]

79
tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json 100644
View File

@ -0,0 +1,79 @@
[
{
"BriefDescription": "Memory page activates. Derived from unc_m_act_count",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_M_ACT_COUNT",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_M_CAS_COUNT.RD",
"PerPkg": "1",
"UMask": "0x3",
"Unit": "iMC"
},
{
"BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_M_CAS_COUNT.WR",
"PerPkg": "1",
"UMask": "0xc",
"Unit": "iMC"
},
{
"BriefDescription": "Memory controller clock ticks. Used to get percentages of memory controller cycles events. Derived from unc_m_clockticks",
"Counter": "0,1,2,3",
"EventName": "UNC_M_CLOCKTICKS",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "UNC_M_POWER_CHANNEL_PPD",
"MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x86",
"EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
"MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
"Counter": "0,1,2,3",
"EventCode": "0x43",
"EventName": "UNC_M_POWER_SELF_REFRESH",
"MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "iMC"
},
{
"BriefDescription": "Occupancy counter for memory read queue. Derived from unc_m_rpq_occupancy",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_M_RPQ_OCCUPANCY",
"PerPkg": "1",
"Unit": "iMC"
}
]

248
tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json 100644
View File

@ -0,0 +1,248 @@
[
{
"BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
"Counter": "0,1,2,3",
"EventName": "UNC_P_CLOCKTICKS",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xb",
"EventName": "UNC_P_FREQ_BAND0_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xc",
"EventName": "UNC_P_FREQ_BAND1_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xd",
"EventName": "UNC_P_FREQ_BAND2_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xe",
"EventName": "UNC_P_FREQ_BAND3_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xb",
"EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of times that the uncore transistioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xc",
"EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xd",
"EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xe",
"EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
"Filter": "occ_sel=1",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
"Filter": "occ_sel=2",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events . Derived from unc_p_power_state_occupancy.cores_c6",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
"Filter": "occ_sel=3",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xa",
"EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
"MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency. Derived from unc_p_freq_max_limit_thermal_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x6",
"EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x5",
"EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
"Counter": "0,1,2,3",
"EventCode": "0x7",
"EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
"Counter": "0,1,2,3",
"EventName": "UNC_P_FREQ_TRANS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xb",
"EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
"Filter": "filter_band0=1200",
"MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xc",
"EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
"Filter": "filter_band1=2000",
"MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xd",
"EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
"Filter": "filter_band2=3000",
"MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xe",
"EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
"Filter": "filter_band3=4000",
"MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xb",
"EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band0=1200",
"MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xc",
"EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band1=2000",
"MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xd",
"EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band2=4000",
"MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
},
{
"BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
"Counter": "0,1,2,3",
"EventCode": "0xe",
"EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band3=4000",
"MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
"PerPkg": "1",
"Unit": "PCU"
}
]

42
tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json 100644
View File

@ -0,0 +1,42 @@
[
{
"BriefDescription": "ddr bandwidth read (CPU traffic only) (MB/sec). ",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "UNC_M_CAS_COUNT.RD",
"PerPkg": "1",
"ScaleUnit": "6.4e-05MiB",
"UMask": "0x01",
"Unit": "imc"
},
{
"BriefDescription": "ddr bandwidth write (CPU traffic only) (MB/sec). ",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "UNC_M_CAS_COUNT.WR",
"PerPkg": "1",
"ScaleUnit": "6.4e-05MiB",
"UMask": "0x02",
"Unit": "imc"
},
{
"BriefDescription": "mcdram bandwidth read (CPU traffic only) (MB/sec). ",
"Counter": "0,1,2,3",
"EventCode": "0x01",
"EventName": "UNC_E_RPQ_INSERTS",
"PerPkg": "1",
"ScaleUnit": "6.4e-05MiB",
"UMask": "0x01",
"Unit": "edc_eclk"
},
{
"BriefDescription": "mcdram bandwidth write (CPU traffic only) (MB/sec). ",
"Counter": "0,1,2,3",
"EventCode": "0x02",
"EventName": "UNC_E_WPQ_INSERTS",
"PerPkg": "1",
"ScaleUnit": "6.4e-05MiB",
"UMask": "0x01",
"Unit": "edc_eclk"
}
]

84
tools/perf/pmu-events/jevents.c
View File

@ -135,7 +135,6 @@ static struct field {
const char *field;
const char *kernel;
} fields[] = {
{ "EventCode", "event=" },
{ "UMask", "umask=" },
{ "CounterMask", "cmask=" },
{ "Invert", "inv=" },
@ -189,6 +188,27 @@ static struct msrmap *lookup_msr(char *map, jsmntok_t *val)
return NULL;
}
static struct map {
const char *json;
const char *perf;
} unit_to_pmu[] = {
{ "CBO", "uncore_cbox" },
{ "QPI LL", "uncore_qpi" },
{ "SBO", "uncore_sbox" },
{}
};
static const char *field_to_perf(struct map *table, char *map, jsmntok_t *val)
{
int i;
for (i = 0; table[i].json; i++) {
if (json_streq(map, val, table[i].json))
return table[i].perf;
}
return NULL;
}
#define EXPECT(e, t, m) do { if (!(e)) { \
jsmntok_t *loc = (t); \
if (!(t)->start && (t) > tokens) \
@ -270,7 +290,8 @@ static void print_events_table_prefix(FILE *fp, const char *tblname)
}
static int print_events_table_entry(void *data, char *name, char *event,
char *desc, char *long_desc)
char *desc, char *long_desc,
char *pmu, char *unit, char *perpkg)
{
struct perf_entry_data *pd = data;
FILE *outfp = pd->outfp;
@ -288,7 +309,12 @@ static int print_events_table_entry(void *data, char *name, char *event,
fprintf(outfp, "\t.topic = \"%s\",\n", topic);
if (long_desc && long_desc[0])
fprintf(outfp, "\t.long_desc = \"%s\",\n", long_desc);
if (pmu)
fprintf(outfp, "\t.pmu = \"%s\",\n", pmu);
if (unit)
fprintf(outfp, "\t.unit = \"%s\",\n", unit);
if (perpkg)
fprintf(outfp, "\t.perpkg = \"%s\",\n", perpkg);
fprintf(outfp, "},\n");
return 0;
@ -335,7 +361,8 @@ static char *real_event(const char *name, char *event)
/* Call func with each event in the json file */
int json_events(const char *fn,
int (*func)(void *data, char *name, char *event, char *desc,
char *long_desc),
char *long_desc,
char *pmu, char *unit, char *perpkg),
void *data)
{
int err = -EIO;
@ -343,6 +370,7 @@ int json_events(const char *fn,
jsmntok_t *tokens, *tok;
int i, j, len;
char *map;
char buf[128];
if (!fn)
return -ENOENT;
@ -356,6 +384,11 @@ int json_events(const char *fn,
char *event = NULL, *desc = NULL, *name = NULL;
char *long_desc = NULL;
char *extra_desc = NULL;
char *pmu = NULL;
char *filter = NULL;
char *perpkg = NULL;
char *unit = NULL;
unsigned long long eventcode = 0;
struct msrmap *msr = NULL;
jsmntok_t *msrval = NULL;
jsmntok_t *precise = NULL;
@ -376,6 +409,16 @@ int json_events(const char *fn,
nz = !json_streq(map, val, "0");
if (match_field(map, field, nz, &event, val)) {
/* ok */
} else if (json_streq(map, field, "EventCode")) {
char *code = NULL;
addfield(map, &code, "", "", val);
eventcode |= strtoul(code, NULL, 0);
free(code);
} else if (json_streq(map, field, "ExtSel")) {
char *code = NULL;
addfield(map, &code, "", "", val);
eventcode |= strtoul(code, NULL, 0) << 21;
free(code);
} else if (json_streq(map, field, "EventName")) {
addfield(map, &name, "", "", val);
} else if (json_streq(map, field, "BriefDescription")) {
@ -399,6 +442,28 @@ int json_events(const char *fn,
addfield(map, &extra_desc, ". ",
" Supports address when precise",
NULL);
} else if (json_streq(map, field, "Unit")) {
const char *ppmu;
char *s;
ppmu = field_to_perf(unit_to_pmu, map, val);
if (ppmu) {
pmu = strdup(ppmu);
} else {
if (!pmu)
pmu = strdup("uncore_");
addfield(map, &pmu, "", "", val);
for (s = pmu; *s; s++)
*s = tolower(*s);
}
addfield(map, &desc, ". ", "Unit: ", NULL);
addfield(map, &desc, "", pmu, NULL);
} else if (json_streq(map, field, "Filter")) {
addfield(map, &filter, "", "", val);
} else if (json_streq(map, field, "ScaleUnit")) {
addfield(map, &unit, "", "", val);
} else if (json_streq(map, field, "PerPkg")) {
addfield(map, &perpkg, "", "", val);
}
/* ignore unknown fields */
}
@ -410,20 +475,29 @@ int json_events(const char *fn,
addfield(map, &extra_desc, " ",
"(Precise event)", NULL);
}
snprintf(buf, sizeof buf, "event=%#llx", eventcode);
addfield(map, &event, ",", buf, NULL);
if (desc && extra_desc)
addfield(map, &desc, " ", extra_desc, NULL);
if (long_desc && extra_desc)
addfield(map, &long_desc, " ", extra_desc, NULL);
if (filter)
addfield(map, &event, ",", filter, NULL);
if (msr != NULL)
addfield(map, &event, ",", msr->pname, msrval);
fixname(name);
err = func(data, name, real_event(name, event), desc, long_desc);
err = func(data, name, real_event(name, event), desc, long_desc,
pmu, unit, perpkg);
free(event);
free(desc);
free(name);
free(long_desc);
free(extra_desc);
free(pmu);
free(filter);
free(perpkg);
free(unit);
if (err)
break;
tok += j;

4
tools/perf/pmu-events/jevents.h
View File

@ -3,7 +3,9 @@
int json_events(const char *fn,
int (*func)(void *data, char *name, char *event, char *desc,
char *long_desc),
char *long_desc,
char *pmu,
char *unit, char *perpkg),
void *data);
char *get_cpu_str(void);

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