This attribute is present for all online CPUs supporting the
Intel EPB feature.
+
+What: /sys/devices/system/cpu/umwait_control
+ /sys/devices/system/cpu/umwait_control/enable_c02
+ /sys/devices/system/cpu/umwait_control/max_time
+Date: May 2019
+Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description: Umwait control
+
+ enable_c02: Read/write interface to control umwait C0.2 state
+ Read returns C0.2 state status:
+ 0: C0.2 is disabled
+ 1: C0.2 is enabled
+
+ Write 'y' or '1' or 'on' to enable C0.2 state.
+ Write 'n' or '0' or 'off' to disable C0.2 state.
+
+ The interface is case insensitive.
+
+ max_time: Read/write interface to control umwait maximum time
+ in TSC-quanta that the CPU can reside in either C0.1
+ or C0.2 state. The time is an unsigned 32-bit number.
+ Note that a value of zero means there is no limit.
+ Low order two bits must be zero.
socket number, but the actual value is architecture and platform
dependent.
+die_id:
+
+ the CPU die ID of cpuX. Typically it is the hardware platform's
+ identifier (rather than the kernel's). The actual value is
+ architecture and platform dependent.
+
core_id:
the CPU core ID of cpuX. Typically it is the hardware platform's
identifier (rather than the kernel's). The actual value is
architecture and platform dependent.
-thread_siblings:
+core_cpus:
- internal kernel map of cpuX's hardware threads within the same
- core as cpuX.
+ internal kernel map of CPUs within the same core.
+ (deprecated name: "thread_siblings")
-thread_siblings_list:
+core_cpus_list:
- human-readable list of cpuX's hardware threads within the same
- core as cpuX.
+ human-readable list of CPUs within the same core.
+ (deprecated name: "thread_siblings_list");
-core_siblings:
+package_cpus:
- internal kernel map of cpuX's hardware threads within the same
- physical_package_id.
+ internal kernel map of the CPUs sharing the same physical_package_id.
+ (deprecated name: "core_siblings")
-core_siblings_list:
+package_cpus_list:
- human-readable list of cpuX's hardware threads within the same
- physical_package_id.
+ human-readable list of CPUs sharing the same physical_package_id.
+ (deprecated name: "core_siblings_list")
+
+die_cpus:
+
+ internal kernel map of CPUs within the same die.
+
+die_cpus_list:
+
+ human-readable list of CPUs within the same die.
book_siblings:
these macros in include/asm-XXX/topology.h::
#define topology_physical_package_id(cpu)
+ #define topology_die_id(cpu)
#define topology_core_id(cpu)
#define topology_book_id(cpu)
#define topology_drawer_id(cpu)
#define topology_sibling_cpumask(cpu)
#define topology_core_cpumask(cpu)
+ #define topology_die_cpumask(cpu)
#define topology_book_cpumask(cpu)
#define topology_drawer_cpumask(cpu)
not defined by include/asm-XXX/topology.h:
1) topology_physical_package_id: -1
-2) topology_core_id: 0
-3) topology_sibling_cpumask: just the given CPU
-4) topology_core_cpumask: just the given CPU
+2) topology_die_id: -1
+3) topology_core_id: 0
+4) topology_sibling_cpumask: just the given CPU
+5) topology_core_cpumask: just the given CPU
+6) topology_die_cpumask: just the given CPU
For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
default definitions for topology_book_id() and topology_book_cpumask().
====================== =============== ========================================
GNU C 4.6 gcc --version
GNU make 3.81 make --version
-binutils 2.20 ld -v
+binutils 2.21 ld -v
flex 2.5.35 flex --version
bison 2.0 bison --version
util-linux 2.10o fdformat --version
Binutils
--------
-The build system has, as of 4.13, switched to using thin archives (`ar T`)
-rather than incremental linking (`ld -r`) for built-in.a intermediate steps.
-This requires binutils 2.20 or newer.
+Binutils 2.21 or newer is needed to build the kernel.
pkg-config
----------
The number of cores in a package. This information is retrieved via CPUID.
+ - cpuinfo_x86.x86_max_dies:
+
+ The number of dies in a package. This information is retrieved via CPUID.
+
- cpuinfo_x86.phys_proc_id:
The physical ID of the package. This information is retrieved via CPUID
S: Maintained
F: drivers/media/dvb-frontends/zd1301_demod*
+ZHAOXIN PROCESSOR SUPPORT
+M: Tony W Wang-oc <TonyWWang-oc@zhaoxin.com>
+L: linux-kernel@vger.kernel.org
+S: Maintained
+F: arch/x86/kernel/cpu/zhaoxin.c
+
ZPOOL COMPRESSED PAGE STORAGE API
M: Dan Streetman <ddstreet@ieee.org>
L: linux-mm@kvack.org
CPU might render the kernel unbootable.
If unsure, say N.
+
+config CPU_SUP_ZHAOXIN
+ default y
+ bool "Support Zhaoxin processors" if PROCESSOR_SELECT
+ help
+ This enables detection, tunings and quirks for Zhaoxin processors
+
+ You need this enabled if you want your kernel to run on a
+ Zhaoxin CPU. Disabling this option on other types of CPUs
+ makes the kernel a tiny bit smaller. Disabling it on a Zhaoxin
+ CPU might render the kernel unbootable.
+
+ If unsure, say N.
iretq
END(nmi)
+#ifndef CONFIG_IA32_EMULATION
+/*
+ * This handles SYSCALL from 32-bit code. There is no way to program
+ * MSRs to fully disable 32-bit SYSCALL.
+ */
ENTRY(ignore_sysret)
UNWIND_HINT_EMPTY
mov $-ENOSYS, %eax
sysret
END(ignore_sysret)
+#endif
ENTRY(rewind_stack_do_exit)
UNWIND_HINT_FUNC
# SPDX-License-Identifier: GPL-2.0-only
-obj-y += core.o
+obj-y += core.o probe.o
obj-y += amd/
obj-$(CONFIG_X86_LOCAL_APIC) += msr.o
obj-$(CONFIG_CPU_SUP_INTEL) += intel/
.attrs = NULL,
};
-/*
- * Remove all undefined events (x86_pmu.event_map(id) == 0)
- * out of events_attr attributes.
- */
-static void __init filter_events(struct attribute **attrs)
-{
- struct device_attribute *d;
- struct perf_pmu_events_attr *pmu_attr;
- int offset = 0;
- int i, j;
-
- for (i = 0; attrs[i]; i++) {
- d = (struct device_attribute *)attrs[i];
- pmu_attr = container_of(d, struct perf_pmu_events_attr, attr);
- /* str trumps id */
- if (pmu_attr->event_str)
- continue;
- if (x86_pmu.event_map(i + offset))
- continue;
-
- for (j = i; attrs[j]; j++)
- attrs[j] = attrs[j + 1];
-
- /* Check the shifted attr. */
- i--;
-
- /*
- * event_map() is index based, the attrs array is organized
- * by increasing event index. If we shift the events, then
- * we need to compensate for the event_map(), otherwise
- * we are looking up the wrong event in the map
- */
- offset++;
- }
-}
-
-/* Merge two pointer arrays */
-__init struct attribute **merge_attr(struct attribute **a, struct attribute **b)
-{
- struct attribute **new;
- int j, i;
-
- for (j = 0; a && a[j]; j++)
- ;
- for (i = 0; b && b[i]; i++)
- j++;
- j++;
-
- new = kmalloc_array(j, sizeof(struct attribute *), GFP_KERNEL);
- if (!new)
- return NULL;
-
- j = 0;
- for (i = 0; a && a[i]; i++)
- new[j++] = a[i];
- for (i = 0; b && b[i]; i++)
- new[j++] = b[i];
- new[j] = NULL;
-
- return new;
-}
-
ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page)
{
struct perf_pmu_events_attr *pmu_attr = \
NULL,
};
+/*
+ * Remove all undefined events (x86_pmu.event_map(id) == 0)
+ * out of events_attr attributes.
+ */
+static umode_t
+is_visible(struct kobject *kobj, struct attribute *attr, int idx)
+{
+ struct perf_pmu_events_attr *pmu_attr;
+
+ pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr);
+ /* str trumps id */
+ return pmu_attr->event_str || x86_pmu.event_map(idx) ? attr->mode : 0;
+}
+
static struct attribute_group x86_pmu_events_group __ro_after_init = {
.name = "events",
.attrs = events_attr,
+ .is_visible = is_visible,
};
ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event)
x86_pmu_format_group.attrs = x86_pmu.format_attrs;
- if (x86_pmu.caps_attrs) {
- struct attribute **tmp;
-
- tmp = merge_attr(x86_pmu_caps_group.attrs, x86_pmu.caps_attrs);
- if (!WARN_ON(!tmp))
- x86_pmu_caps_group.attrs = tmp;
- }
-
- if (x86_pmu.event_attrs)
- x86_pmu_events_group.attrs = x86_pmu.event_attrs;
-
if (!x86_pmu.events_sysfs_show)
x86_pmu_events_group.attrs = &empty_attrs;
- else
- filter_events(x86_pmu_events_group.attrs);
- if (x86_pmu.cpu_events) {
- struct attribute **tmp;
-
- tmp = merge_attr(x86_pmu_events_group.attrs, x86_pmu.cpu_events);
- if (!WARN_ON(!tmp))
- x86_pmu_events_group.attrs = tmp;
- }
-
- if (x86_pmu.attrs) {
- struct attribute **tmp;
-
- tmp = merge_attr(x86_pmu_attr_group.attrs, x86_pmu.attrs);
- if (!WARN_ON(!tmp))
- x86_pmu_attr_group.attrs = tmp;
- }
+ pmu.attr_update = x86_pmu.attr_update;
pr_info("... version: %d\n", x86_pmu.version);
pr_info("... bit width: %d\n", x86_pmu.cntval_bits);
#include <asm/intel-family.h>
#include <asm/apic.h>
#include <asm/cpu_device_id.h>
+#include <asm/hypervisor.h>
#include "../perf_event.h"
.check_period = intel_pmu_check_period,
};
-static struct attribute *intel_pmu_attrs[];
-
static __initconst const struct x86_pmu intel_pmu = {
.name = "Intel",
.handle_irq = intel_pmu_handle_irq,
.format_attrs = intel_arch3_formats_attr,
.events_sysfs_show = intel_event_sysfs_show,
- .attrs = intel_pmu_attrs,
-
.cpu_prepare = intel_pmu_cpu_prepare,
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
{
u64 val_old, val_new, val_tmp;
+ /*
+ * Disable the check for real HW, so we don't
+ * mess with potentionaly enabled registers:
+ */
+ if (hypervisor_is_type(X86_HYPER_NATIVE))
+ return true;
+
/*
* Read the current value, change it and read it back to see if it
* matches, this is needed to detect certain hardware emulators
NULL,
};
-static __init struct attribute **get_icl_events_attrs(void)
-{
- return boot_cpu_has(X86_FEATURE_RTM) ?
- merge_attr(icl_events_attrs, icl_tsx_events_attrs) :
- icl_events_attrs;
-}
-
static ssize_t freeze_on_smi_show(struct device *cdev,
struct device_attribute *attr,
char *buf)
static struct attribute *intel_pmu_attrs[] = {
&dev_attr_freeze_on_smi.attr,
- NULL, /* &dev_attr_allow_tsx_force_abort.attr.attr */
+ &dev_attr_allow_tsx_force_abort.attr,
NULL,
};
-static __init struct attribute **
-get_events_attrs(struct attribute **base,
- struct attribute **mem,
- struct attribute **tsx)
+static umode_t
+tsx_is_visible(struct kobject *kobj, struct attribute *attr, int i)
{
- struct attribute **attrs = base;
- struct attribute **old;
+ return boot_cpu_has(X86_FEATURE_RTM) ? attr->mode : 0;
+}
- if (mem && x86_pmu.pebs)
- attrs = merge_attr(attrs, mem);
+static umode_t
+pebs_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return x86_pmu.pebs ? attr->mode : 0;
+}
- if (tsx && boot_cpu_has(X86_FEATURE_RTM)) {
- old = attrs;
- attrs = merge_attr(attrs, tsx);
- if (old != base)
- kfree(old);
- }
+static umode_t
+lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return x86_pmu.lbr_nr ? attr->mode : 0;
+}
- return attrs;
+static umode_t
+exra_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return x86_pmu.version >= 2 ? attr->mode : 0;
}
+static umode_t
+default_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ if (attr == &dev_attr_allow_tsx_force_abort.attr)
+ return x86_pmu.flags & PMU_FL_TFA ? attr->mode : 0;
+
+ return attr->mode;
+}
+
+static struct attribute_group group_events_td = {
+ .name = "events",
+};
+
+static struct attribute_group group_events_mem = {
+ .name = "events",
+ .is_visible = pebs_is_visible,
+};
+
+static struct attribute_group group_events_tsx = {
+ .name = "events",
+ .is_visible = tsx_is_visible,
+};
+
+static struct attribute_group group_caps_gen = {
+ .name = "caps",
+ .attrs = intel_pmu_caps_attrs,
+};
+
+static struct attribute_group group_caps_lbr = {
+ .name = "caps",
+ .attrs = lbr_attrs,
+ .is_visible = lbr_is_visible,
+};
+
+static struct attribute_group group_format_extra = {
+ .name = "format",
+ .is_visible = exra_is_visible,
+};
+
+static struct attribute_group group_format_extra_skl = {
+ .name = "format",
+ .is_visible = exra_is_visible,
+};
+
+static struct attribute_group group_default = {
+ .attrs = intel_pmu_attrs,
+ .is_visible = default_is_visible,
+};
+
+static const struct attribute_group *attr_update[] = {
+ &group_events_td,
+ &group_events_mem,
+ &group_events_tsx,
+ &group_caps_gen,
+ &group_caps_lbr,
+ &group_format_extra,
+ &group_format_extra_skl,
+ &group_default,
+ NULL,
+};
+
+static struct attribute *empty_attrs;
+
__init int intel_pmu_init(void)
{
- struct attribute **extra_attr = NULL;
- struct attribute **mem_attr = NULL;
- struct attribute **tsx_attr = NULL;
- struct attribute **to_free = NULL;
+ struct attribute **extra_skl_attr = &empty_attrs;
+ struct attribute **extra_attr = &empty_attrs;
+ struct attribute **td_attr = &empty_attrs;
+ struct attribute **mem_attr = &empty_attrs;
+ struct attribute **tsx_attr = &empty_attrs;
union cpuid10_edx edx;
union cpuid10_eax eax;
union cpuid10_ebx ebx;
struct event_constraint *c;
unsigned int unused;
struct extra_reg *er;
+ bool pmem = false;
int version, i;
char *name;
x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
x86_pmu.extra_regs = intel_slm_extra_regs;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
- x86_pmu.cpu_events = slm_events_attrs;
+ td_attr = slm_events_attrs;
extra_attr = slm_format_attr;
pr_cont("Silvermont events, ");
name = "silvermont";
x86_pmu.pebs_prec_dist = true;
x86_pmu.lbr_pt_coexist = true;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
- x86_pmu.cpu_events = glm_events_attrs;
+ td_attr = glm_events_attrs;
extra_attr = slm_format_attr;
pr_cont("Goldmont events, ");
name = "goldmont";
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_PEBS_ALL;
x86_pmu.get_event_constraints = glp_get_event_constraints;
- x86_pmu.cpu_events = glm_events_attrs;
+ td_attr = glm_events_attrs;
/* Goldmont Plus has 4-wide pipeline */
event_attr_td_total_slots_scale_glm.event_str = "4";
extra_attr = slm_format_attr;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
- x86_pmu.cpu_events = snb_events_attrs;
+ td_attr = snb_events_attrs;
mem_attr = snb_mem_events_attrs;
/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
- x86_pmu.cpu_events = snb_events_attrs;
+ td_attr = snb_events_attrs;
mem_attr = snb_mem_events_attrs;
/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
- x86_pmu.cpu_events = hsw_events_attrs;
x86_pmu.lbr_double_abort = true;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
+ td_attr = hsw_events_attrs;
mem_attr = hsw_mem_events_attrs;
tsx_attr = hsw_tsx_events_attrs;
pr_cont("Haswell events, ");
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
- x86_pmu.cpu_events = hsw_events_attrs;
x86_pmu.limit_period = bdw_limit_period;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
+ td_attr = hsw_events_attrs;
mem_attr = hsw_mem_events_attrs;
tsx_attr = hsw_tsx_events_attrs;
pr_cont("Broadwell events, ");
name = "knights-landing";
break;
+ case INTEL_FAM6_SKYLAKE_X:
+ pmem = true;
case INTEL_FAM6_SKYLAKE_MOBILE:
case INTEL_FAM6_SKYLAKE_DESKTOP:
- case INTEL_FAM6_SKYLAKE_X:
case INTEL_FAM6_KABYLAKE_MOBILE:
case INTEL_FAM6_KABYLAKE_DESKTOP:
x86_add_quirk(intel_pebs_isolation_quirk);
x86_pmu.get_event_constraints = hsw_get_event_constraints;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
- extra_attr = merge_attr(extra_attr, skl_format_attr);
- to_free = extra_attr;
- x86_pmu.cpu_events = hsw_events_attrs;
+ extra_skl_attr = skl_format_attr;
+ td_attr = hsw_events_attrs;
mem_attr = hsw_mem_events_attrs;
tsx_attr = hsw_tsx_events_attrs;
- intel_pmu_pebs_data_source_skl(
- boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
+ intel_pmu_pebs_data_source_skl(pmem);
if (boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) {
x86_pmu.flags |= PMU_FL_TFA;
x86_pmu.get_event_constraints = tfa_get_event_constraints;
x86_pmu.enable_all = intel_tfa_pmu_enable_all;
x86_pmu.commit_scheduling = intel_tfa_commit_scheduling;
- intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr;
}
pr_cont("Skylake events, ");
name = "skylake";
break;
+ case INTEL_FAM6_ICELAKE_X:
+ case INTEL_FAM6_ICELAKE_XEON_D:
+ pmem = true;
case INTEL_FAM6_ICELAKE_MOBILE:
+ case INTEL_FAM6_ICELAKE_DESKTOP:
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
x86_pmu.get_event_constraints = icl_get_event_constraints;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
- extra_attr = merge_attr(extra_attr, skl_format_attr);
- x86_pmu.cpu_events = get_icl_events_attrs();
+ extra_skl_attr = skl_format_attr;
+ mem_attr = icl_events_attrs;
+ tsx_attr = icl_tsx_events_attrs;
x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
x86_pmu.lbr_pt_coexist = true;
- intel_pmu_pebs_data_source_skl(false);
+ intel_pmu_pebs_data_source_skl(pmem);
pr_cont("Icelake events, ");
name = "icelake";
break;
snprintf(pmu_name_str, sizeof(pmu_name_str), "%s", name);
- if (version >= 2 && extra_attr) {
- x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr,
- extra_attr);
- WARN_ON(!x86_pmu.format_attrs);
- }
- x86_pmu.cpu_events = get_events_attrs(x86_pmu.cpu_events,
- mem_attr, tsx_attr);
+ group_events_td.attrs = td_attr;
+ group_events_mem.attrs = mem_attr;
+ group_events_tsx.attrs = tsx_attr;
+ group_format_extra.attrs = extra_attr;
+ group_format_extra_skl.attrs = extra_skl_attr;
+
+ x86_pmu.attr_update = attr_update;
if (x86_pmu.num_counters > INTEL_PMC_MAX_GENERIC) {
WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
x86_pmu.lbr_nr = 0;
}
- x86_pmu.caps_attrs = intel_pmu_caps_attrs;
-
- if (x86_pmu.lbr_nr) {
- x86_pmu.caps_attrs = merge_attr(x86_pmu.caps_attrs, lbr_attrs);
+ if (x86_pmu.lbr_nr)
pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr);
- }
/*
* Access extra MSR may cause #GP under certain circumstances.
if (x86_pmu.counter_freezing)
x86_pmu.handle_irq = intel_pmu_handle_irq_v4;
- kfree(to_free);
return 0;
}
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#include "../perf_event.h"
+#include "../probe.h"
MODULE_LICENSE("GPL");
PERF_CSTATE_CORE_EVENT_MAX,
};
-PMU_EVENT_ATTR_STRING(c1-residency, evattr_cstate_core_c1, "event=0x00");
-PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_core_c3, "event=0x01");
-PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_core_c6, "event=0x02");
-PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_core_c7, "event=0x03");
+PMU_EVENT_ATTR_STRING(c1-residency, attr_cstate_core_c1, "event=0x00");
+PMU_EVENT_ATTR_STRING(c3-residency, attr_cstate_core_c3, "event=0x01");
+PMU_EVENT_ATTR_STRING(c6-residency, attr_cstate_core_c6, "event=0x02");
+PMU_EVENT_ATTR_STRING(c7-residency, attr_cstate_core_c7, "event=0x03");
-static struct perf_cstate_msr core_msr[] = {
- [PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &evattr_cstate_core_c1 },
- [PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &evattr_cstate_core_c3 },
- [PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &evattr_cstate_core_c6 },
- [PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &evattr_cstate_core_c7 },
+static unsigned long core_msr_mask;
+
+PMU_EVENT_GROUP(events, cstate_core_c1);
+PMU_EVENT_GROUP(events, cstate_core_c3);
+PMU_EVENT_GROUP(events, cstate_core_c6);
+PMU_EVENT_GROUP(events, cstate_core_c7);
+
+static bool test_msr(int idx, void *data)
+{
+ return test_bit(idx, (unsigned long *) data);
+}
+
+static struct perf_msr core_msr[] = {
+ [PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &group_cstate_core_c1, test_msr },
+ [PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &group_cstate_core_c3, test_msr },
+ [PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &group_cstate_core_c6, test_msr },
+ [PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &group_cstate_core_c7, test_msr },
};
-static struct attribute *core_events_attrs[PERF_CSTATE_CORE_EVENT_MAX + 1] = {
+static struct attribute *attrs_empty[] = {
NULL,
};
+/*
+ * There are no default events, but we need to create
+ * "events" group (with empty attrs) before updating
+ * it with detected events.
+ */
static struct attribute_group core_events_attr_group = {
.name = "events",
- .attrs = core_events_attrs,
+ .attrs = attrs_empty,
};
DEFINE_CSTATE_FORMAT_ATTR(core_event, event, "config:0-63");
PERF_CSTATE_PKG_EVENT_MAX,
};
-PMU_EVENT_ATTR_STRING(c2-residency, evattr_cstate_pkg_c2, "event=0x00");
-PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_pkg_c3, "event=0x01");
-PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_pkg_c6, "event=0x02");
-PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_pkg_c7, "event=0x03");
-PMU_EVENT_ATTR_STRING(c8-residency, evattr_cstate_pkg_c8, "event=0x04");
-PMU_EVENT_ATTR_STRING(c9-residency, evattr_cstate_pkg_c9, "event=0x05");
-PMU_EVENT_ATTR_STRING(c10-residency, evattr_cstate_pkg_c10, "event=0x06");
-
-static struct perf_cstate_msr pkg_msr[] = {
- [PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &evattr_cstate_pkg_c2 },
- [PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &evattr_cstate_pkg_c3 },
- [PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &evattr_cstate_pkg_c6 },
- [PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &evattr_cstate_pkg_c7 },
- [PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &evattr_cstate_pkg_c8 },
- [PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &evattr_cstate_pkg_c9 },
- [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &evattr_cstate_pkg_c10 },
-};
-
-static struct attribute *pkg_events_attrs[PERF_CSTATE_PKG_EVENT_MAX + 1] = {
- NULL,
+PMU_EVENT_ATTR_STRING(c2-residency, attr_cstate_pkg_c2, "event=0x00");
+PMU_EVENT_ATTR_STRING(c3-residency, attr_cstate_pkg_c3, "event=0x01");
+PMU_EVENT_ATTR_STRING(c6-residency, attr_cstate_pkg_c6, "event=0x02");
+PMU_EVENT_ATTR_STRING(c7-residency, attr_cstate_pkg_c7, "event=0x03");
+PMU_EVENT_ATTR_STRING(c8-residency, attr_cstate_pkg_c8, "event=0x04");
+PMU_EVENT_ATTR_STRING(c9-residency, attr_cstate_pkg_c9, "event=0x05");
+PMU_EVENT_ATTR_STRING(c10-residency, attr_cstate_pkg_c10, "event=0x06");
+
+static unsigned long pkg_msr_mask;
+
+PMU_EVENT_GROUP(events, cstate_pkg_c2);
+PMU_EVENT_GROUP(events, cstate_pkg_c3);
+PMU_EVENT_GROUP(events, cstate_pkg_c6);
+PMU_EVENT_GROUP(events, cstate_pkg_c7);
+PMU_EVENT_GROUP(events, cstate_pkg_c8);
+PMU_EVENT_GROUP(events, cstate_pkg_c9);
+PMU_EVENT_GROUP(events, cstate_pkg_c10);
+
+static struct perf_msr pkg_msr[] = {
+ [PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &group_cstate_pkg_c2, test_msr },
+ [PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &group_cstate_pkg_c3, test_msr },
+ [PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &group_cstate_pkg_c6, test_msr },
+ [PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &group_cstate_pkg_c7, test_msr },
+ [PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &group_cstate_pkg_c8, test_msr },
+ [PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &group_cstate_pkg_c9, test_msr },
+ [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &group_cstate_pkg_c10, test_msr },
};
static struct attribute_group pkg_events_attr_group = {
.name = "events",
- .attrs = pkg_events_attrs,
+ .attrs = attrs_empty,
};
DEFINE_CSTATE_FORMAT_ATTR(pkg_event, event, "config:0-63");
if (event->pmu == &cstate_core_pmu) {
if (cfg >= PERF_CSTATE_CORE_EVENT_MAX)
return -EINVAL;
- if (!core_msr[cfg].attr)
+ cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_CORE_EVENT_MAX);
+ if (!(core_msr_mask & (1 << cfg)))
return -EINVAL;
event->hw.event_base = core_msr[cfg].msr;
cpu = cpumask_any_and(&cstate_core_cpu_mask,
if (cfg >= PERF_CSTATE_PKG_EVENT_MAX)
return -EINVAL;
cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX);
- if (!pkg_msr[cfg].attr)
+ if (!(pkg_msr_mask & (1 << cfg)))
return -EINVAL;
event->hw.event_base = pkg_msr[cfg].msr;
cpu = cpumask_any_and(&cstate_pkg_cpu_mask,
- topology_core_cpumask(event->cpu));
+ topology_die_cpumask(event->cpu));
} else {
return -ENOENT;
}
if (has_cstate_pkg &&
cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask)) {
- target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
+ target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
/* Migrate events if there is a valid target */
if (target < nr_cpu_ids) {
cpumask_set_cpu(target, &cstate_pkg_cpu_mask);
* in the package cpu mask as the designated reader.
*/
target = cpumask_any_and(&cstate_pkg_cpu_mask,
- topology_core_cpumask(cpu));
+ topology_die_cpumask(cpu));
if (has_cstate_pkg && target >= nr_cpu_ids)
cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask);
return 0;
}
+const struct attribute_group *core_attr_update[] = {
+ &group_cstate_core_c1,
+ &group_cstate_core_c3,
+ &group_cstate_core_c6,
+ &group_cstate_core_c7,
+ NULL,
+};
+
+const struct attribute_group *pkg_attr_update[] = {
+ &group_cstate_pkg_c2,
+ &group_cstate_pkg_c3,
+ &group_cstate_pkg_c6,
+ &group_cstate_pkg_c7,
+ &group_cstate_pkg_c8,
+ &group_cstate_pkg_c9,
+ &group_cstate_pkg_c10,
+ NULL,
+};
+
static struct pmu cstate_core_pmu = {
.attr_groups = core_attr_groups,
+ .attr_update = core_attr_update,
.name = "cstate_core",
.task_ctx_nr = perf_invalid_context,
.event_init = cstate_pmu_event_init,
static struct pmu cstate_pkg_pmu = {
.attr_groups = pkg_attr_groups,
+ .attr_update = pkg_attr_update,
.name = "cstate_pkg",
.task_ctx_nr = perf_invalid_context,
.event_init = cstate_pmu_event_init,
X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_MOBILE, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_DESKTOP, snb_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
-/*
- * Probe the cstate events and insert the available one into sysfs attrs
- * Return false if there are no available events.
- */
-static bool __init cstate_probe_msr(const unsigned long evmsk, int max,
- struct perf_cstate_msr *msr,
- struct attribute **attrs)
-{
- bool found = false;
- unsigned int bit;
- u64 val;
-
- for (bit = 0; bit < max; bit++) {
- if (test_bit(bit, &evmsk) && !rdmsrl_safe(msr[bit].msr, &val)) {
- *attrs++ = &msr[bit].attr->attr.attr;
- found = true;
- } else {
- msr[bit].attr = NULL;
- }
- }
- *attrs = NULL;
-
- return found;
-}
-
static int __init cstate_probe(const struct cstate_model *cm)
{
/* SLM has different MSR for PKG C6 */
pkg_msr[PERF_CSTATE_CORE_C6_RES].msr = MSR_KNL_CORE_C6_RESIDENCY;
- has_cstate_core = cstate_probe_msr(cm->core_events,
- PERF_CSTATE_CORE_EVENT_MAX,
- core_msr, core_events_attrs);
+ core_msr_mask = perf_msr_probe(core_msr, PERF_CSTATE_CORE_EVENT_MAX,
+ true, (void *) &cm->core_events);
- has_cstate_pkg = cstate_probe_msr(cm->pkg_events,
- PERF_CSTATE_PKG_EVENT_MAX,
- pkg_msr, pkg_events_attrs);
+ pkg_msr_mask = perf_msr_probe(pkg_msr, PERF_CSTATE_PKG_EVENT_MAX,
+ true, (void *) &cm->pkg_events);
+
+ has_cstate_core = !!core_msr_mask;
+ has_cstate_pkg = !!pkg_msr_mask;
return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV;
}
}
if (has_cstate_pkg) {
- err = perf_pmu_register(&cstate_pkg_pmu, cstate_pkg_pmu.name, -1);
+ if (topology_max_die_per_package() > 1) {
+ err = perf_pmu_register(&cstate_pkg_pmu,
+ "cstate_die", -1);
+ } else {
+ err = perf_pmu_register(&cstate_pkg_pmu,
+ cstate_pkg_pmu.name, -1);
+ }
if (err) {
has_cstate_pkg = false;
pr_info("Failed to register cstate pkg pmu\n");
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/perf_event.h>
+#include <linux/nospec.h>
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#include "../perf_event.h"
+#include "../probe.h"
MODULE_LICENSE("GPL");
/*
* RAPL energy status counters
*/
-#define RAPL_IDX_PP0_NRG_STAT 0 /* all cores */
-#define INTEL_RAPL_PP0 0x1 /* pseudo-encoding */
-#define RAPL_IDX_PKG_NRG_STAT 1 /* entire package */
-#define INTEL_RAPL_PKG 0x2 /* pseudo-encoding */
-#define RAPL_IDX_RAM_NRG_STAT 2 /* DRAM */
-#define INTEL_RAPL_RAM 0x3 /* pseudo-encoding */
-#define RAPL_IDX_PP1_NRG_STAT 3 /* gpu */
-#define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */
-#define RAPL_IDX_PSYS_NRG_STAT 4 /* psys */
-#define INTEL_RAPL_PSYS 0x5 /* pseudo-encoding */
-
-#define NR_RAPL_DOMAINS 0x5
+enum perf_rapl_events {
+ PERF_RAPL_PP0 = 0, /* all cores */
+ PERF_RAPL_PKG, /* entire package */
+ PERF_RAPL_RAM, /* DRAM */
+ PERF_RAPL_PP1, /* gpu */
+ PERF_RAPL_PSYS, /* psys */
+
+ PERF_RAPL_MAX,
+ NR_RAPL_DOMAINS = PERF_RAPL_MAX,
+};
+
static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
"pp0-core",
"package",
"psys",
};
-/* Clients have PP0, PKG */
-#define RAPL_IDX_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\
- 1<<RAPL_IDX_PKG_NRG_STAT|\
- 1<<RAPL_IDX_PP1_NRG_STAT)
-
-/* Servers have PP0, PKG, RAM */
-#define RAPL_IDX_SRV (1<<RAPL_IDX_PP0_NRG_STAT|\
- 1<<RAPL_IDX_PKG_NRG_STAT|\
- 1<<RAPL_IDX_RAM_NRG_STAT)
-
-/* Servers have PP0, PKG, RAM, PP1 */
-#define RAPL_IDX_HSW (1<<RAPL_IDX_PP0_NRG_STAT|\
- 1<<RAPL_IDX_PKG_NRG_STAT|\
- 1<<RAPL_IDX_RAM_NRG_STAT|\
- 1<<RAPL_IDX_PP1_NRG_STAT)
-
-/* SKL clients have PP0, PKG, RAM, PP1, PSYS */
-#define RAPL_IDX_SKL_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\
- 1<<RAPL_IDX_PKG_NRG_STAT|\
- 1<<RAPL_IDX_RAM_NRG_STAT|\
- 1<<RAPL_IDX_PP1_NRG_STAT|\
- 1<<RAPL_IDX_PSYS_NRG_STAT)
-
-/* Knights Landing has PKG, RAM */
-#define RAPL_IDX_KNL (1<<RAPL_IDX_PKG_NRG_STAT|\
- 1<<RAPL_IDX_RAM_NRG_STAT)
-
/*
* event code: LSB 8 bits, passed in attr->config
* any other bit is reserved
struct rapl_pmus {
struct pmu pmu;
- unsigned int maxpkg;
+ unsigned int maxdie;
struct rapl_pmu *pmus[];
};
+struct rapl_model {
+ unsigned long events;
+ bool apply_quirk;
+};
+
/* 1/2^hw_unit Joule */
static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly;
static struct rapl_pmus *rapl_pmus;
static cpumask_t rapl_cpu_mask;
static unsigned int rapl_cntr_mask;
static u64 rapl_timer_ms;
+static struct perf_msr rapl_msrs[];
static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
{
- unsigned int pkgid = topology_logical_package_id(cpu);
+ unsigned int dieid = topology_logical_die_id(cpu);
/*
* The unsigned check also catches the '-1' return value for non
* existent mappings in the topology map.
*/
- return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL;
+ return dieid < rapl_pmus->maxdie ? rapl_pmus->pmus[dieid] : NULL;
}
static inline u64 rapl_read_counter(struct perf_event *event)
static int rapl_pmu_event_init(struct perf_event *event)
{
u64 cfg = event->attr.config & RAPL_EVENT_MASK;
- int bit, msr, ret = 0;
+ int bit, ret = 0;
struct rapl_pmu *pmu;
/* only look at RAPL events */
event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
- /*
- * check event is known (determines counter)
- */
- switch (cfg) {
- case INTEL_RAPL_PP0:
- bit = RAPL_IDX_PP0_NRG_STAT;
- msr = MSR_PP0_ENERGY_STATUS;
- break;
- case INTEL_RAPL_PKG:
- bit = RAPL_IDX_PKG_NRG_STAT;
- msr = MSR_PKG_ENERGY_STATUS;
- break;
- case INTEL_RAPL_RAM:
- bit = RAPL_IDX_RAM_NRG_STAT;
- msr = MSR_DRAM_ENERGY_STATUS;
- break;
- case INTEL_RAPL_PP1:
- bit = RAPL_IDX_PP1_NRG_STAT;
- msr = MSR_PP1_ENERGY_STATUS;
- break;
- case INTEL_RAPL_PSYS:
- bit = RAPL_IDX_PSYS_NRG_STAT;
- msr = MSR_PLATFORM_ENERGY_STATUS;
- break;
- default:
+ if (!cfg || cfg >= NR_RAPL_DOMAINS + 1)
return -EINVAL;
- }
+
+ cfg = array_index_nospec((long)cfg, NR_RAPL_DOMAINS + 1);
+ bit = cfg - 1;
+
/* check event supported */
if (!(rapl_cntr_mask & (1 << bit)))
return -EINVAL;
return -EINVAL;
event->cpu = pmu->cpu;
event->pmu_private = pmu;
- event->hw.event_base = msr;
+ event->hw.event_base = rapl_msrs[bit].msr;
event->hw.config = cfg;
event->hw.idx = bit;
RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10");
RAPL_EVENT_ATTR_STR(energy-psys.scale, rapl_psys_scale, "2.3283064365386962890625e-10");
-static struct attribute *rapl_events_srv_attr[] = {
- EVENT_PTR(rapl_cores),
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_ram),
+/*
+ * There are no default events, but we need to create
+ * "events" group (with empty attrs) before updating
+ * it with detected events.
+ */
+static struct attribute *attrs_empty[] = {
+ NULL,
+};
- EVENT_PTR(rapl_cores_unit),
- EVENT_PTR(rapl_pkg_unit),
- EVENT_PTR(rapl_ram_unit),
+static struct attribute_group rapl_pmu_events_group = {
+ .name = "events",
+ .attrs = attrs_empty,
+};
- EVENT_PTR(rapl_cores_scale),
- EVENT_PTR(rapl_pkg_scale),
- EVENT_PTR(rapl_ram_scale),
+DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7");
+static struct attribute *rapl_formats_attr[] = {
+ &format_attr_event.attr,
NULL,
};
-static struct attribute *rapl_events_cln_attr[] = {
- EVENT_PTR(rapl_cores),
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_gpu),
-
- EVENT_PTR(rapl_cores_unit),
- EVENT_PTR(rapl_pkg_unit),
- EVENT_PTR(rapl_gpu_unit),
+static struct attribute_group rapl_pmu_format_group = {
+ .name = "format",
+ .attrs = rapl_formats_attr,
+};
- EVENT_PTR(rapl_cores_scale),
- EVENT_PTR(rapl_pkg_scale),
- EVENT_PTR(rapl_gpu_scale),
+static const struct attribute_group *rapl_attr_groups[] = {
+ &rapl_pmu_attr_group,
+ &rapl_pmu_format_group,
+ &rapl_pmu_events_group,
NULL,
};
-static struct attribute *rapl_events_hsw_attr[] = {
+static struct attribute *rapl_events_cores[] = {
EVENT_PTR(rapl_cores),
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_gpu),
- EVENT_PTR(rapl_ram),
-
EVENT_PTR(rapl_cores_unit),
- EVENT_PTR(rapl_pkg_unit),
- EVENT_PTR(rapl_gpu_unit),
- EVENT_PTR(rapl_ram_unit),
-
EVENT_PTR(rapl_cores_scale),
- EVENT_PTR(rapl_pkg_scale),
- EVENT_PTR(rapl_gpu_scale),
- EVENT_PTR(rapl_ram_scale),
NULL,
};
-static struct attribute *rapl_events_skl_attr[] = {
- EVENT_PTR(rapl_cores),
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_gpu),
- EVENT_PTR(rapl_ram),
- EVENT_PTR(rapl_psys),
+static struct attribute_group rapl_events_cores_group = {
+ .name = "events",
+ .attrs = rapl_events_cores,
+};
- EVENT_PTR(rapl_cores_unit),
+static struct attribute *rapl_events_pkg[] = {
+ EVENT_PTR(rapl_pkg),
EVENT_PTR(rapl_pkg_unit),
- EVENT_PTR(rapl_gpu_unit),
- EVENT_PTR(rapl_ram_unit),
- EVENT_PTR(rapl_psys_unit),
-
- EVENT_PTR(rapl_cores_scale),
EVENT_PTR(rapl_pkg_scale),
- EVENT_PTR(rapl_gpu_scale),
- EVENT_PTR(rapl_ram_scale),
- EVENT_PTR(rapl_psys_scale),
NULL,
};
-static struct attribute *rapl_events_knl_attr[] = {
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_ram),
+static struct attribute_group rapl_events_pkg_group = {
+ .name = "events",
+ .attrs = rapl_events_pkg,
+};
- EVENT_PTR(rapl_pkg_unit),
+static struct attribute *rapl_events_ram[] = {
+ EVENT_PTR(rapl_ram),
EVENT_PTR(rapl_ram_unit),
-
- EVENT_PTR(rapl_pkg_scale),
EVENT_PTR(rapl_ram_scale),
NULL,
};
-static struct attribute_group rapl_pmu_events_group = {
- .name = "events",
- .attrs = NULL, /* patched at runtime */
+static struct attribute_group rapl_events_ram_group = {
+ .name = "events",
+ .attrs = rapl_events_ram,
};
-DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7");
-static struct attribute *rapl_formats_attr[] = {
- &format_attr_event.attr,
+static struct attribute *rapl_events_gpu[] = {
+ EVENT_PTR(rapl_gpu),
+ EVENT_PTR(rapl_gpu_unit),
+ EVENT_PTR(rapl_gpu_scale),
NULL,
};
-static struct attribute_group rapl_pmu_format_group = {
- .name = "format",
- .attrs = rapl_formats_attr,
+static struct attribute_group rapl_events_gpu_group = {
+ .name = "events",
+ .attrs = rapl_events_gpu,
};
-static const struct attribute_group *rapl_attr_groups[] = {
- &rapl_pmu_attr_group,
- &rapl_pmu_format_group,
- &rapl_pmu_events_group,
+static struct attribute *rapl_events_psys[] = {
+ EVENT_PTR(rapl_psys),
+ EVENT_PTR(rapl_psys_unit),
+ EVENT_PTR(rapl_psys_scale),
NULL,
};
+static struct attribute_group rapl_events_psys_group = {
+ .name = "events",
+ .attrs = rapl_events_psys,
+};
+
+static bool test_msr(int idx, void *data)
+{
+ return test_bit(idx, (unsigned long *) data);
+}
+
+static struct perf_msr rapl_msrs[] = {
+ [PERF_RAPL_PP0] = { MSR_PP0_ENERGY_STATUS, &rapl_events_cores_group, test_msr },
+ [PERF_RAPL_PKG] = { MSR_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr },
+ [PERF_RAPL_RAM] = { MSR_DRAM_ENERGY_STATUS, &rapl_events_ram_group, test_msr },
+ [PERF_RAPL_PP1] = { MSR_PP1_ENERGY_STATUS, &rapl_events_gpu_group, test_msr },
+ [PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group, test_msr },
+};
+
static int rapl_cpu_offline(unsigned int cpu)
{
struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
pmu->cpu = -1;
/* Find a new cpu to collect rapl events */
- target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
+ target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
/* Migrate rapl events to the new target */
if (target < nr_cpu_ids) {
pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
rapl_hrtimer_init(pmu);
- rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
+ rapl_pmus->pmus[topology_logical_die_id(cpu)] = pmu;
}
/*
* Check if there is an online cpu in the package which collects rapl
* events already.
*/
- target = cpumask_any_and(&rapl_cpu_mask, topology_core_cpumask(cpu));
+ target = cpumask_any_and(&rapl_cpu_mask, topology_die_cpumask(cpu));
if (target < nr_cpu_ids)
return 0;
* of 2. Datasheet, September 2014, Reference Number: 330784-001 "
*/
if (apply_quirk)
- rapl_hw_unit[RAPL_IDX_RAM_NRG_STAT] = 16;
+ rapl_hw_unit[PERF_RAPL_RAM] = 16;
/*
* Calculate the timer rate:
{
int i;
- for (i = 0; i < rapl_pmus->maxpkg; i++)
+ for (i = 0; i < rapl_pmus->maxdie; i++)
kfree(rapl_pmus->pmus[i]);
kfree(rapl_pmus);
}
+const struct attribute_group *rapl_attr_update[] = {
+ &rapl_events_cores_group,
+ &rapl_events_pkg_group,
+ &rapl_events_ram_group,
+ &rapl_events_gpu_group,
+ &rapl_events_gpu_group,
+ NULL,
+};
+
static int __init init_rapl_pmus(void)
{
- int maxpkg = topology_max_packages();
+ int maxdie = topology_max_packages() * topology_max_die_per_package();
size_t size;
- size = sizeof(*rapl_pmus) + maxpkg * sizeof(struct rapl_pmu *);
+ size = sizeof(*rapl_pmus) + maxdie * sizeof(struct rapl_pmu *);
rapl_pmus = kzalloc(size, GFP_KERNEL);
if (!rapl_pmus)
return -ENOMEM;
- rapl_pmus->maxpkg = maxpkg;
+ rapl_pmus->maxdie = maxdie;
rapl_pmus->pmu.attr_groups = rapl_attr_groups;
+ rapl_pmus->pmu.attr_update = rapl_attr_update;
rapl_pmus->pmu.task_ctx_nr = perf_invalid_context;
rapl_pmus->pmu.event_init = rapl_pmu_event_init;
rapl_pmus->pmu.add = rapl_pmu_event_add;
#define X86_RAPL_MODEL_MATCH(model, init) \
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
-struct intel_rapl_init_fun {
- bool apply_quirk;
- int cntr_mask;
- struct attribute **attrs;
-};
-
-static const struct intel_rapl_init_fun snb_rapl_init __initconst = {
- .apply_quirk = false,
- .cntr_mask = RAPL_IDX_CLN,
- .attrs = rapl_events_cln_attr,
+static struct rapl_model model_snb = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_PP1),
+ .apply_quirk = false,
};
-static const struct intel_rapl_init_fun hsx_rapl_init __initconst = {
- .apply_quirk = true,
- .cntr_mask = RAPL_IDX_SRV,
- .attrs = rapl_events_srv_attr,
+static struct rapl_model model_snbep = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM),
+ .apply_quirk = false,
};
-static const struct intel_rapl_init_fun hsw_rapl_init __initconst = {
- .apply_quirk = false,
- .cntr_mask = RAPL_IDX_HSW,
- .attrs = rapl_events_hsw_attr,
+static struct rapl_model model_hsw = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM) |
+ BIT(PERF_RAPL_PP1),
+ .apply_quirk = false,
};
-static const struct intel_rapl_init_fun snbep_rapl_init __initconst = {
- .apply_quirk = false,
- .cntr_mask = RAPL_IDX_SRV,
- .attrs = rapl_events_srv_attr,
+static struct rapl_model model_hsx = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM),
+ .apply_quirk = true,
};
-static const struct intel_rapl_init_fun knl_rapl_init __initconst = {
- .apply_quirk = true,
- .cntr_mask = RAPL_IDX_KNL,
- .attrs = rapl_events_knl_attr,
+static struct rapl_model model_knl = {
+ .events = BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM),
+ .apply_quirk = true,
};
-static const struct intel_rapl_init_fun skl_rapl_init __initconst = {
- .apply_quirk = false,
- .cntr_mask = RAPL_IDX_SKL_CLN,
- .attrs = rapl_events_skl_attr,
+static struct rapl_model model_skl = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM) |
+ BIT(PERF_RAPL_PP1) |
+ BIT(PERF_RAPL_PSYS),
+ .apply_quirk = false,
};
-static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE, snb_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, snbep_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, snb_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, snbep_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hsx_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, hsw_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, hsx_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsx_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, hsx_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_MOBILE, skl_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, hsw_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, skl_rapl_init),
+static const struct x86_cpu_id rapl_model_match[] __initconst = {
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE, model_snb),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, model_snbep),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, model_snb),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, model_snbep),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, model_knl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, model_knl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_MOBILE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_DESKTOP, model_skl),
{},
};
-MODULE_DEVICE_TABLE(x86cpu, rapl_cpu_match);
+MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
static int __init rapl_pmu_init(void)
{
const struct x86_cpu_id *id;
- struct intel_rapl_init_fun *rapl_init;
- bool apply_quirk;
+ struct rapl_model *rm;
int ret;
- id = x86_match_cpu(rapl_cpu_match);
+ id = x86_match_cpu(rapl_model_match);
if (!id)
return -ENODEV;
- rapl_init = (struct intel_rapl_init_fun *)id->driver_data;
- apply_quirk = rapl_init->apply_quirk;
- rapl_cntr_mask = rapl_init->cntr_mask;
- rapl_pmu_events_group.attrs = rapl_init->attrs;
+ rm = (struct rapl_model *) id->driver_data;
+ rapl_cntr_mask = perf_msr_probe(rapl_msrs, PERF_RAPL_MAX,
+ false, (void *) &rm->events);
- ret = rapl_check_hw_unit(apply_quirk);
+ ret = rapl_check_hw_unit(rm->apply_quirk);
if (ret)
return ret;
static struct intel_uncore_type *empty_uncore[] = { NULL, };
struct intel_uncore_type **uncore_msr_uncores = empty_uncore;
struct intel_uncore_type **uncore_pci_uncores = empty_uncore;
+struct intel_uncore_type **uncore_mmio_uncores = empty_uncore;
static bool pcidrv_registered;
struct pci_driver *uncore_pci_driver;
DEFINE_RAW_SPINLOCK(pci2phy_map_lock);
struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head);
struct pci_extra_dev *uncore_extra_pci_dev;
-static int max_packages;
+static int max_dies;
/* mask of cpus that collect uncore events */
static cpumask_t uncore_cpu_mask;
MODULE_LICENSE("GPL");
-static int uncore_pcibus_to_physid(struct pci_bus *bus)
+int uncore_pcibus_to_physid(struct pci_bus *bus)
{
struct pci2phy_map *map;
int phys_id = -1;
struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
{
- unsigned int pkgid = topology_logical_package_id(cpu);
+ unsigned int dieid = topology_logical_die_id(cpu);
/*
* The unsigned check also catches the '-1' return value for non
* existent mappings in the topology map.
*/
- return pkgid < max_packages ? pmu->boxes[pkgid] : NULL;
+ return dieid < max_dies ? pmu->boxes[dieid] : NULL;
}
u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
return count;
}
+void uncore_mmio_exit_box(struct intel_uncore_box *box)
+{
+ if (box->io_addr)
+ iounmap(box->io_addr);
+}
+
+u64 uncore_mmio_read_counter(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ if (!box->io_addr)
+ return 0;
+
+ return readq(box->io_addr + event->hw.event_base);
+}
+
/*
* generic get constraint function for shared match/mask registers.
*/
uncore_pmu_init_hrtimer(box);
box->cpu = -1;
box->pci_phys_id = -1;
- box->pkgid = -1;
+ box->dieid = -1;
/* set default hrtimer timeout */
box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL;
static void uncore_free_boxes(struct intel_uncore_pmu *pmu)
{
- int pkg;
+ int die;
- for (pkg = 0; pkg < max_packages; pkg++)
- kfree(pmu->boxes[pkg]);
+ for (die = 0; die < max_dies; die++)
+ kfree(pmu->boxes[die]);
kfree(pmu->boxes);
}
if (!pmus)
return -ENOMEM;
- size = max_packages * sizeof(struct intel_uncore_box *);
+ size = max_dies * sizeof(struct intel_uncore_box *);
for (i = 0; i < type->num_boxes; i++) {
pmus[i].func_id = setid ? i : -1;
struct intel_uncore_type *type;
struct intel_uncore_pmu *pmu = NULL;
struct intel_uncore_box *box;
- int phys_id, pkg, ret;
+ int phys_id, die, ret;
phys_id = uncore_pcibus_to_physid(pdev->bus);
if (phys_id < 0)
return -ENODEV;
- pkg = topology_phys_to_logical_pkg(phys_id);
- if (pkg < 0)
+ die = (topology_max_die_per_package() > 1) ? phys_id :
+ topology_phys_to_logical_pkg(phys_id);
+ if (die < 0)
return -EINVAL;
if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) {
int idx = UNCORE_PCI_DEV_IDX(id->driver_data);
- uncore_extra_pci_dev[pkg].dev[idx] = pdev;
+ uncore_extra_pci_dev[die].dev[idx] = pdev;
pci_set_drvdata(pdev, NULL);
return 0;
}
pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
}
- if (WARN_ON_ONCE(pmu->boxes[pkg] != NULL))
+ if (WARN_ON_ONCE(pmu->boxes[die] != NULL))
return -EINVAL;
box = uncore_alloc_box(type, NUMA_NO_NODE);
atomic_inc(&box->refcnt);
box->pci_phys_id = phys_id;
- box->pkgid = pkg;
+ box->dieid = die;
box->pci_dev = pdev;
box->pmu = pmu;
uncore_box_init(box);
pci_set_drvdata(pdev, box);
- pmu->boxes[pkg] = box;
+ pmu->boxes[die] = box;
if (atomic_inc_return(&pmu->activeboxes) > 1)
return 0;
ret = uncore_pmu_register(pmu);
if (ret) {
pci_set_drvdata(pdev, NULL);
- pmu->boxes[pkg] = NULL;
+ pmu->boxes[die] = NULL;
uncore_box_exit(box);
kfree(box);
}
{
struct intel_uncore_box *box;
struct intel_uncore_pmu *pmu;
- int i, phys_id, pkg;
+ int i, phys_id, die;
phys_id = uncore_pcibus_to_physid(pdev->bus);
box = pci_get_drvdata(pdev);
if (!box) {
- pkg = topology_phys_to_logical_pkg(phys_id);
+ die = (topology_max_die_per_package() > 1) ? phys_id :
+ topology_phys_to_logical_pkg(phys_id);
for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
- if (uncore_extra_pci_dev[pkg].dev[i] == pdev) {
- uncore_extra_pci_dev[pkg].dev[i] = NULL;
+ if (uncore_extra_pci_dev[die].dev[i] == pdev) {
+ uncore_extra_pci_dev[die].dev[i] = NULL;
break;
}
}
return;
pci_set_drvdata(pdev, NULL);
- pmu->boxes[box->pkgid] = NULL;
+ pmu->boxes[box->dieid] = NULL;
if (atomic_dec_return(&pmu->activeboxes) == 0)
uncore_pmu_unregister(pmu);
uncore_box_exit(box);
size_t size;
int ret;
- size = max_packages * sizeof(struct pci_extra_dev);
+ size = max_dies * sizeof(struct pci_extra_dev);
uncore_extra_pci_dev = kzalloc(size, GFP_KERNEL);
if (!uncore_extra_pci_dev) {
ret = -ENOMEM;
{
struct intel_uncore_pmu *pmu = type->pmus;
struct intel_uncore_box *box;
- int i, pkg;
+ int i, die;
- pkg = topology_logical_package_id(old_cpu < 0 ? new_cpu : old_cpu);
+ die = topology_logical_die_id(old_cpu < 0 ? new_cpu : old_cpu);
for (i = 0; i < type->num_boxes; i++, pmu++) {
- box = pmu->boxes[pkg];
+ box = pmu->boxes[die];
if (!box)
continue;
uncore_change_type_ctx(*uncores, old_cpu, new_cpu);
}
-static int uncore_event_cpu_offline(unsigned int cpu)
+static void uncore_box_unref(struct intel_uncore_type **types, int id)
{
- struct intel_uncore_type *type, **types = uncore_msr_uncores;
+ struct intel_uncore_type *type;
struct intel_uncore_pmu *pmu;
struct intel_uncore_box *box;
- int i, pkg, target;
+ int i;
+
+ for (; *types; types++) {
+ type = *types;
+ pmu = type->pmus;
+ for (i = 0; i < type->num_boxes; i++, pmu++) {
+ box = pmu->boxes[id];
+ if (box && atomic_dec_return(&box->refcnt) == 0)
+ uncore_box_exit(box);
+ }
+ }
+}
+
+static int uncore_event_cpu_offline(unsigned int cpu)
+{
+ int die, target;
/* Check if exiting cpu is used for collecting uncore events */
if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
goto unref;
/* Find a new cpu to collect uncore events */
- target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
+ target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
/* Migrate uncore events to the new target */
if (target < nr_cpu_ids)
target = -1;
uncore_change_context(uncore_msr_uncores, cpu, target);
+ uncore_change_context(uncore_mmio_uncores, cpu, target);
uncore_change_context(uncore_pci_uncores, cpu, target);
unref:
/* Clear the references */
- pkg = topology_logical_package_id(cpu);
- for (; *types; types++) {
- type = *types;
- pmu = type->pmus;
- for (i = 0; i < type->num_boxes; i++, pmu++) {
- box = pmu->boxes[pkg];
- if (box && atomic_dec_return(&box->refcnt) == 0)
- uncore_box_exit(box);
- }
- }
+ die = topology_logical_die_id(cpu);
+ uncore_box_unref(uncore_msr_uncores, die);
+ uncore_box_unref(uncore_mmio_uncores, die);
return 0;
}
static int allocate_boxes(struct intel_uncore_type **types,
- unsigned int pkg, unsigned int cpu)
+ unsigned int die, unsigned int cpu)
{
struct intel_uncore_box *box, *tmp;
struct intel_uncore_type *type;
type = *types;
pmu = type->pmus;
for (i = 0; i < type->num_boxes; i++, pmu++) {
- if (pmu->boxes[pkg])
+ if (pmu->boxes[die])
continue;
box = uncore_alloc_box(type, cpu_to_node(cpu));
if (!box)
goto cleanup;
box->pmu = pmu;
- box->pkgid = pkg;
+ box->dieid = die;
list_add(&box->active_list, &allocated);
}
}
/* Install them in the pmus */
list_for_each_entry_safe(box, tmp, &allocated, active_list) {
list_del_init(&box->active_list);
- box->pmu->boxes[pkg] = box;
+ box->pmu->boxes[die] = box;
}
return 0;
return -ENOMEM;
}
-static int uncore_event_cpu_online(unsigned int cpu)
+static int uncore_box_ref(struct intel_uncore_type **types,
+ int id, unsigned int cpu)
{
- struct intel_uncore_type *type, **types = uncore_msr_uncores;
+ struct intel_uncore_type *type;
struct intel_uncore_pmu *pmu;
struct intel_uncore_box *box;
- int i, ret, pkg, target;
+ int i, ret;
- pkg = topology_logical_package_id(cpu);
- ret = allocate_boxes(types, pkg, cpu);
+ ret = allocate_boxes(types, id, cpu);
if (ret)
return ret;
type = *types;
pmu = type->pmus;
for (i = 0; i < type->num_boxes; i++, pmu++) {
- box = pmu->boxes[pkg];
+ box = pmu->boxes[id];
if (box && atomic_inc_return(&box->refcnt) == 1)
uncore_box_init(box);
}
}
+ return 0;
+}
+
+static int uncore_event_cpu_online(unsigned int cpu)
+{
+ int die, target, msr_ret, mmio_ret;
+
+ die = topology_logical_die_id(cpu);
+ msr_ret = uncore_box_ref(uncore_msr_uncores, die, cpu);
+ mmio_ret = uncore_box_ref(uncore_mmio_uncores, die, cpu);
+ if (msr_ret && mmio_ret)
+ return -ENOMEM;
/*
* Check if there is an online cpu in the package
* which collects uncore events already.
*/
- target = cpumask_any_and(&uncore_cpu_mask, topology_core_cpumask(cpu));
+ target = cpumask_any_and(&uncore_cpu_mask, topology_die_cpumask(cpu));
if (target < nr_cpu_ids)
return 0;
cpumask_set_cpu(cpu, &uncore_cpu_mask);
- uncore_change_context(uncore_msr_uncores, -1, cpu);
+ if (!msr_ret)
+ uncore_change_context(uncore_msr_uncores, -1, cpu);
+ if (!mmio_ret)
+ uncore_change_context(uncore_mmio_uncores, -1, cpu);
uncore_change_context(uncore_pci_uncores, -1, cpu);
return 0;
}
return ret;
}
+static int __init uncore_mmio_init(void)
+{
+ struct intel_uncore_type **types = uncore_mmio_uncores;
+ int ret;
+
+ ret = uncore_types_init(types, true);
+ if (ret)
+ goto err;
+
+ for (; *types; types++) {
+ ret = type_pmu_register(*types);
+ if (ret)
+ goto err;
+ }
+ return 0;
+err:
+ uncore_types_exit(uncore_mmio_uncores);
+ uncore_mmio_uncores = empty_uncore;
+ return ret;
+}
+
+
#define X86_UNCORE_MODEL_MATCH(model, init) \
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
struct intel_uncore_init_fun {
void (*cpu_init)(void);
int (*pci_init)(void);
+ void (*mmio_init)(void);
};
static const struct intel_uncore_init_fun nhm_uncore_init __initconst = {
.pci_init = skl_uncore_pci_init,
};
+static const struct intel_uncore_init_fun snr_uncore_init __initconst = {
+ .cpu_init = snr_uncore_cpu_init,
+ .pci_init = snr_uncore_pci_init,
+ .mmio_init = snr_uncore_mmio_init,
+};
+
static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP, nhm_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM, nhm_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, icl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_NNPI, icl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_DESKTOP, icl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ATOM_TREMONT_X, snr_uncore_init),
{},
};
{
const struct x86_cpu_id *id;
struct intel_uncore_init_fun *uncore_init;
- int pret = 0, cret = 0, ret;
+ int pret = 0, cret = 0, mret = 0, ret;
id = x86_match_cpu(intel_uncore_match);
if (!id)
if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
return -ENODEV;
- max_packages = topology_max_packages();
+ max_dies = topology_max_packages() * topology_max_die_per_package();
uncore_init = (struct intel_uncore_init_fun *)id->driver_data;
if (uncore_init->pci_init) {
cret = uncore_cpu_init();
}
- if (cret && pret)
+ if (uncore_init->mmio_init) {
+ uncore_init->mmio_init();
+ mret = uncore_mmio_init();
+ }
+
+ if (cret && pret && mret)
return -ENODEV;
/* Install hotplug callbacks to setup the targets for each package */
err:
uncore_types_exit(uncore_msr_uncores);
+ uncore_types_exit(uncore_mmio_uncores);
uncore_pci_exit();
return ret;
}
{
cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
uncore_types_exit(uncore_msr_uncores);
+ uncore_types_exit(uncore_mmio_uncores);
uncore_pci_exit();
}
module_exit(intel_uncore_exit);
#include <linux/slab.h>
#include <linux/pci.h>
#include <asm/apicdef.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/perf_event.h>
#include "../perf_event.h"
unsigned fixed_ctr;
unsigned fixed_ctl;
unsigned box_ctl;
- unsigned msr_offset;
+ union {
+ unsigned msr_offset;
+ unsigned mmio_offset;
+ };
unsigned num_shared_regs:8;
unsigned single_fixed:1;
unsigned pair_ctr_ctl:1;
struct intel_uncore_box {
int pci_phys_id;
- int pkgid; /* Logical package ID */
+ int dieid; /* Logical die ID */
int n_active; /* number of active events */
int n_events;
int cpu; /* cpu to collect events */
struct hrtimer hrtimer;
struct list_head list;
struct list_head active_list;
- void *io_addr;
+ void __iomem *io_addr;
struct intel_uncore_extra_reg shared_regs[0];
};
};
struct pci2phy_map *__find_pci2phy_map(int segment);
+int uncore_pcibus_to_physid(struct pci_bus *bus);
ssize_t uncore_event_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf);
return idx == UNCORE_PMC_IDX_FREERUNNING;
}
+static inline
+unsigned int uncore_mmio_box_ctl(struct intel_uncore_box *box)
+{
+ return box->pmu->type->box_ctl +
+ box->pmu->type->mmio_offset * box->pmu->pmu_idx;
+}
+
static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box)
{
return box->pmu->type->box_ctl;
static inline
unsigned uncore_fixed_ctl(struct intel_uncore_box *box)
{
- if (box->pci_dev)
+ if (box->pci_dev || box->io_addr)
return uncore_pci_fixed_ctl(box);
else
return uncore_msr_fixed_ctl(box);
static inline
unsigned uncore_fixed_ctr(struct intel_uncore_box *box)
{
- if (box->pci_dev)
+ if (box->pci_dev || box->io_addr)
return uncore_pci_fixed_ctr(box);
else
return uncore_msr_fixed_ctr(box);
static inline
unsigned uncore_event_ctl(struct intel_uncore_box *box, int idx)
{
- if (box->pci_dev)
+ if (box->pci_dev || box->io_addr)
return uncore_pci_event_ctl(box, idx);
else
return uncore_msr_event_ctl(box, idx);
static inline
unsigned uncore_perf_ctr(struct intel_uncore_box *box, int idx)
{
- if (box->pci_dev)
+ if (box->pci_dev || box->io_addr)
return uncore_pci_perf_ctr(box, idx);
else
return uncore_msr_perf_ctr(box, idx);
(((cfg >> 8) & 0xff) >= UNCORE_FREERUNNING_UMASK_START);
}
+/* Check and reject invalid config */
+static inline int uncore_freerunning_hw_config(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ if (is_freerunning_event(event))
+ return 0;
+
+ return -EINVAL;
+}
+
static inline void uncore_disable_box(struct intel_uncore_box *box)
{
if (box->pmu->type->ops->disable_box)
static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
{
- return (box->pkgid < 0);
+ return (box->dieid < 0);
}
static inline struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu);
u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event);
+void uncore_mmio_exit_box(struct intel_uncore_box *box);
+u64 uncore_mmio_read_counter(struct intel_uncore_box *box,
+ struct perf_event *event);
void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
void uncore_pmu_event_start(struct perf_event *event, int flags);
extern struct intel_uncore_type **uncore_msr_uncores;
extern struct intel_uncore_type **uncore_pci_uncores;
+extern struct intel_uncore_type **uncore_mmio_uncores;
extern struct pci_driver *uncore_pci_driver;
extern raw_spinlock_t pci2phy_map_lock;
extern struct list_head pci2phy_map_head;
void knl_uncore_cpu_init(void);
int skx_uncore_pci_init(void);
void skx_uncore_cpu_init(void);
+int snr_uncore_pci_init(void);
+void snr_uncore_cpu_init(void);
+void snr_uncore_mmio_init(void);
/* uncore_nhmex.c */
void nhmex_uncore_cpu_init(void);
#include "uncore.h"
/* Uncore IMC PCI IDs */
-#define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100
-#define PCI_DEVICE_ID_INTEL_IVB_IMC 0x0154
-#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150
-#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00
-#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04
-#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604
-#define PCI_DEVICE_ID_INTEL_SKL_U_IMC 0x1904
-#define PCI_DEVICE_ID_INTEL_SKL_Y_IMC 0x190c
-#define PCI_DEVICE_ID_INTEL_SKL_HD_IMC 0x1900
-#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910
-#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f
-#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f
-#define PCI_DEVICE_ID_INTEL_KBL_Y_IMC 0x590c
-#define PCI_DEVICE_ID_INTEL_KBL_U_IMC 0x5904
-#define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC 0x5914
-#define PCI_DEVICE_ID_INTEL_KBL_SD_IMC 0x590f
-#define PCI_DEVICE_ID_INTEL_KBL_SQ_IMC 0x591f
-#define PCI_DEVICE_ID_INTEL_CFL_2U_IMC 0x3ecc
-#define PCI_DEVICE_ID_INTEL_CFL_4U_IMC 0x3ed0
-#define PCI_DEVICE_ID_INTEL_CFL_4H_IMC 0x3e10
-#define PCI_DEVICE_ID_INTEL_CFL_6H_IMC 0x3ec4
+#define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100
+#define PCI_DEVICE_ID_INTEL_IVB_IMC 0x0154
+#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150
+#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00
+#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04
+#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604
+#define PCI_DEVICE_ID_INTEL_SKL_U_IMC 0x1904
+#define PCI_DEVICE_ID_INTEL_SKL_Y_IMC 0x190c
+#define PCI_DEVICE_ID_INTEL_SKL_HD_IMC 0x1900
+#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910
+#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f
+#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f
+#define PCI_DEVICE_ID_INTEL_KBL_Y_IMC 0x590c
+#define PCI_DEVICE_ID_INTEL_KBL_U_IMC 0x5904
+#define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC 0x5914
+#define PCI_DEVICE_ID_INTEL_KBL_SD_IMC 0x590f
+#define PCI_DEVICE_ID_INTEL_KBL_SQ_IMC 0x591f
+#define PCI_DEVICE_ID_INTEL_KBL_HQ_IMC 0x5910
+#define PCI_DEVICE_ID_INTEL_KBL_WQ_IMC 0x5918
+#define PCI_DEVICE_ID_INTEL_CFL_2U_IMC 0x3ecc
+#define PCI_DEVICE_ID_INTEL_CFL_4U_IMC 0x3ed0
+#define PCI_DEVICE_ID_INTEL_CFL_4H_IMC 0x3e10
+#define PCI_DEVICE_ID_INTEL_CFL_6H_IMC 0x3ec4
#define PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC 0x3e0f
#define PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC 0x3e1f
#define PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC 0x3ec2
#define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC 0x3e33
#define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC 0x3eca
#define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC 0x3e32
+#define PCI_DEVICE_ID_INTEL_AML_YD_IMC 0x590c
+#define PCI_DEVICE_ID_INTEL_AML_YQ_IMC 0x590d
+#define PCI_DEVICE_ID_INTEL_WHL_UQ_IMC 0x3ed0
+#define PCI_DEVICE_ID_INTEL_WHL_4_UQ_IMC 0x3e34
+#define PCI_DEVICE_ID_INTEL_WHL_UD_IMC 0x3e35
#define PCI_DEVICE_ID_INTEL_ICL_U_IMC 0x8a02
#define PCI_DEVICE_ID_INTEL_ICL_U2_IMC 0x8a12
+
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
#define SNB_UNC_CTL_UMASK_MASK 0x0000ff00
box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
}
-static void snb_uncore_imc_exit_box(struct intel_uncore_box *box)
-{
- iounmap(box->io_addr);
-}
-
static void snb_uncore_imc_enable_box(struct intel_uncore_box *box)
{}
static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event)
{}
-static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
-
- return (u64)*(unsigned int *)(box->io_addr + hwc->event_base);
-}
-
/*
* Keep the custom event_init() function compatible with old event
* encoding for free running counters.
static struct intel_uncore_ops snb_uncore_imc_ops = {
.init_box = snb_uncore_imc_init_box,
- .exit_box = snb_uncore_imc_exit_box,
+ .exit_box = uncore_mmio_exit_box,
.enable_box = snb_uncore_imc_enable_box,
.disable_box = snb_uncore_imc_disable_box,
.disable_event = snb_uncore_imc_disable_event,
.enable_event = snb_uncore_imc_enable_event,
.hw_config = snb_uncore_imc_hw_config,
- .read_counter = snb_uncore_imc_read_counter,
+ .read_counter = uncore_mmio_read_counter,
};
static struct intel_uncore_type snb_uncore_imc = {
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SQ_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_HQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_WQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
{ /* IMC */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2U_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_AML_YD_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_AML_YQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_UQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_4_UQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_UD_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
{ /* end: all zeroes */ },
};
IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U Quad Core */
IMC_DEV(KBL_SD_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S Dual Core */
IMC_DEV(KBL_SQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S Quad Core */
+ IMC_DEV(KBL_HQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core H Quad Core */
+ IMC_DEV(KBL_WQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S 4 cores Work Station */
IMC_DEV(CFL_2U_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U 2 Cores */
IMC_DEV(CFL_4U_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U 4 Cores */
IMC_DEV(CFL_4H_IMC, &skl_uncore_pci_driver), /* 8th Gen Core H 4 Cores */
IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Server */
IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Server */
IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Server */
+ IMC_DEV(AML_YD_IMC, &skl_uncore_pci_driver), /* 8th Gen Core Y Mobile Dual Core */
+ IMC_DEV(AML_YQ_IMC, &skl_uncore_pci_driver), /* 8th Gen Core Y Mobile Quad Core */
+ IMC_DEV(WHL_UQ_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U Mobile Quad Core */
+ IMC_DEV(WHL_4_UQ_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U Mobile Quad Core */
+ IMC_DEV(WHL_UD_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U Mobile Dual Core */
IMC_DEV(ICL_U_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
IMC_DEV(ICL_U2_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
{ /* end marker */ }
#define SKX_M2M_PCI_PMON_CTR0 0x200
#define SKX_M2M_PCI_PMON_BOX_CTL 0x258
+/* SNR Ubox */
+#define SNR_U_MSR_PMON_CTR0 0x1f98
+#define SNR_U_MSR_PMON_CTL0 0x1f91
+#define SNR_U_MSR_PMON_UCLK_FIXED_CTL 0x1f93
+#define SNR_U_MSR_PMON_UCLK_FIXED_CTR 0x1f94
+
+/* SNR CHA */
+#define SNR_CHA_RAW_EVENT_MASK_EXT 0x3ffffff
+#define SNR_CHA_MSR_PMON_CTL0 0x1c01
+#define SNR_CHA_MSR_PMON_CTR0 0x1c08
+#define SNR_CHA_MSR_PMON_BOX_CTL 0x1c00
+#define SNR_C0_MSR_PMON_BOX_FILTER0 0x1c05
+
+
+/* SNR IIO */
+#define SNR_IIO_MSR_PMON_CTL0 0x1e08
+#define SNR_IIO_MSR_PMON_CTR0 0x1e01
+#define SNR_IIO_MSR_PMON_BOX_CTL 0x1e00
+#define SNR_IIO_MSR_OFFSET 0x10
+#define SNR_IIO_PMON_RAW_EVENT_MASK_EXT 0x7ffff
+
+/* SNR IRP */
+#define SNR_IRP0_MSR_PMON_CTL0 0x1ea8
+#define SNR_IRP0_MSR_PMON_CTR0 0x1ea1
+#define SNR_IRP0_MSR_PMON_BOX_CTL 0x1ea0
+#define SNR_IRP_MSR_OFFSET 0x10
+
+/* SNR M2PCIE */
+#define SNR_M2PCIE_MSR_PMON_CTL0 0x1e58
+#define SNR_M2PCIE_MSR_PMON_CTR0 0x1e51
+#define SNR_M2PCIE_MSR_PMON_BOX_CTL 0x1e50
+#define SNR_M2PCIE_MSR_OFFSET 0x10
+
+/* SNR PCU */
+#define SNR_PCU_MSR_PMON_CTL0 0x1ef1
+#define SNR_PCU_MSR_PMON_CTR0 0x1ef8
+#define SNR_PCU_MSR_PMON_BOX_CTL 0x1ef0
+#define SNR_PCU_MSR_PMON_BOX_FILTER 0x1efc
+
+/* SNR M2M */
+#define SNR_M2M_PCI_PMON_CTL0 0x468
+#define SNR_M2M_PCI_PMON_CTR0 0x440
+#define SNR_M2M_PCI_PMON_BOX_CTL 0x438
+#define SNR_M2M_PCI_PMON_UMASK_EXT 0xff
+
+/* SNR PCIE3 */
+#define SNR_PCIE3_PCI_PMON_CTL0 0x508
+#define SNR_PCIE3_PCI_PMON_CTR0 0x4e8
+#define SNR_PCIE3_PCI_PMON_BOX_CTL 0x4e4
+
+/* SNR IMC */
+#define SNR_IMC_MMIO_PMON_FIXED_CTL 0x54
+#define SNR_IMC_MMIO_PMON_FIXED_CTR 0x38
+#define SNR_IMC_MMIO_PMON_CTL0 0x40
+#define SNR_IMC_MMIO_PMON_CTR0 0x8
+#define SNR_IMC_MMIO_PMON_BOX_CTL 0x22800
+#define SNR_IMC_MMIO_OFFSET 0x4000
+#define SNR_IMC_MMIO_SIZE 0x4000
+#define SNR_IMC_MMIO_BASE_OFFSET 0xd0
+#define SNR_IMC_MMIO_BASE_MASK 0x1FFFFFFF
+#define SNR_IMC_MMIO_MEM0_OFFSET 0xd8
+#define SNR_IMC_MMIO_MEM0_MASK 0x7FF
+
DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6");
DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7");
DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55");
+DEFINE_UNCORE_FORMAT_ATTR(umask_ext2, umask, "config:8-15,32-57");
+DEFINE_UNCORE_FORMAT_ATTR(umask_ext3, umask, "config:8-15,32-39");
DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16");
DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
DEFINE_UNCORE_FORMAT_ATTR(occ_edge_det, occ_edge_det, "config:31");
DEFINE_UNCORE_FORMAT_ATTR(ch_mask, ch_mask, "config:36-43");
+DEFINE_UNCORE_FORMAT_ATTR(ch_mask2, ch_mask, "config:36-47");
DEFINE_UNCORE_FORMAT_ATTR(fc_mask, fc_mask, "config:44-46");
+DEFINE_UNCORE_FORMAT_ATTR(fc_mask2, fc_mask, "config:48-50");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid4, filter_tid, "config1:0-8");
+DEFINE_UNCORE_FORMAT_ATTR(filter_tid5, filter_tid, "config1:0-9");
DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5");
DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8");
if (reg1->idx != EXTRA_REG_NONE) {
int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
- int pkg = box->pkgid;
- struct pci_dev *filter_pdev = uncore_extra_pci_dev[pkg].dev[idx];
+ int die = box->dieid;
+ struct pci_dev *filter_pdev = uncore_extra_pci_dev[die].dev[idx];
if (filter_pdev) {
pci_write_config_dword(filter_pdev, reg1->reg,
static struct intel_uncore_ops skx_uncore_iio_freerunning_ops = {
.read_counter = uncore_msr_read_counter,
+ .hw_config = uncore_freerunning_hw_config,
};
static struct attribute *skx_uncore_iio_freerunning_formats_attr[] = {
}
/* end of SKX uncore support */
+
+/* SNR uncore support */
+
+static struct intel_uncore_type snr_uncore_ubox = {
+ .name = "ubox",
+ .num_counters = 2,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .perf_ctr = SNR_U_MSR_PMON_CTR0,
+ .event_ctl = SNR_U_MSR_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .fixed_ctr = SNR_U_MSR_PMON_UCLK_FIXED_CTR,
+ .fixed_ctl = SNR_U_MSR_PMON_UCLK_FIXED_CTL,
+ .ops = &ivbep_uncore_msr_ops,
+ .format_group = &ivbep_uncore_format_group,
+};
+
+static struct attribute *snr_uncore_cha_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask_ext2.attr,
+ &format_attr_edge.attr,
+ &format_attr_tid_en.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ &format_attr_filter_tid5.attr,
+ NULL,
+};
+static const struct attribute_group snr_uncore_chabox_format_group = {
+ .name = "format",
+ .attrs = snr_uncore_cha_formats_attr,
+};
+
+static int snr_cha_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+
+ reg1->reg = SNR_C0_MSR_PMON_BOX_FILTER0 +
+ box->pmu->type->msr_offset * box->pmu->pmu_idx;
+ reg1->config = event->attr.config1 & SKX_CHA_MSR_PMON_BOX_FILTER_TID;
+ reg1->idx = 0;
+
+ return 0;
+}
+
+static void snr_cha_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE)
+ wrmsrl(reg1->reg, reg1->config);
+
+ wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops snr_uncore_chabox_ops = {
+ .init_box = ivbep_uncore_msr_init_box,
+ .disable_box = snbep_uncore_msr_disable_box,
+ .enable_box = snbep_uncore_msr_enable_box,
+ .disable_event = snbep_uncore_msr_disable_event,
+ .enable_event = snr_cha_enable_event,
+ .read_counter = uncore_msr_read_counter,
+ .hw_config = snr_cha_hw_config,
+};
+
+static struct intel_uncore_type snr_uncore_chabox = {
+ .name = "cha",
+ .num_counters = 4,
+ .num_boxes = 6,
+ .perf_ctr_bits = 48,
+ .event_ctl = SNR_CHA_MSR_PMON_CTL0,
+ .perf_ctr = SNR_CHA_MSR_PMON_CTR0,
+ .box_ctl = SNR_CHA_MSR_PMON_BOX_CTL,
+ .msr_offset = HSWEP_CBO_MSR_OFFSET,
+ .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
+ .event_mask_ext = SNR_CHA_RAW_EVENT_MASK_EXT,
+ .ops = &snr_uncore_chabox_ops,
+ .format_group = &snr_uncore_chabox_format_group,
+};
+
+static struct attribute *snr_uncore_iio_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh9.attr,
+ &format_attr_ch_mask2.attr,
+ &format_attr_fc_mask2.attr,
+ NULL,
+};
+
+static const struct attribute_group snr_uncore_iio_format_group = {
+ .name = "format",
+ .attrs = snr_uncore_iio_formats_attr,
+};
+
+static struct intel_uncore_type snr_uncore_iio = {
+ .name = "iio",
+ .num_counters = 4,
+ .num_boxes = 5,
+ .perf_ctr_bits = 48,
+ .event_ctl = SNR_IIO_MSR_PMON_CTL0,
+ .perf_ctr = SNR_IIO_MSR_PMON_CTR0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .event_mask_ext = SNR_IIO_PMON_RAW_EVENT_MASK_EXT,
+ .box_ctl = SNR_IIO_MSR_PMON_BOX_CTL,
+ .msr_offset = SNR_IIO_MSR_OFFSET,
+ .ops = &ivbep_uncore_msr_ops,
+ .format_group = &snr_uncore_iio_format_group,
+};
+
+static struct intel_uncore_type snr_uncore_irp = {
+ .name = "irp",
+ .num_counters = 2,
+ .num_boxes = 5,
+ .perf_ctr_bits = 48,
+ .event_ctl = SNR_IRP0_MSR_PMON_CTL0,
+ .perf_ctr = SNR_IRP0_MSR_PMON_CTR0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNR_IRP0_MSR_PMON_BOX_CTL,
+ .msr_offset = SNR_IRP_MSR_OFFSET,
+ .ops = &ivbep_uncore_msr_ops,
+ .format_group = &ivbep_uncore_format_group,
+};
+
+static struct intel_uncore_type snr_uncore_m2pcie = {
+ .name = "m2pcie",
+ .num_counters = 4,
+ .num_boxes = 5,
+ .perf_ctr_bits = 48,
+ .event_ctl = SNR_M2PCIE_MSR_PMON_CTL0,
+ .perf_ctr = SNR_M2PCIE_MSR_PMON_CTR0,
+ .box_ctl = SNR_M2PCIE_MSR_PMON_BOX_CTL,
+ .msr_offset = SNR_M2PCIE_MSR_OFFSET,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .ops = &ivbep_uncore_msr_ops,
+ .format_group = &ivbep_uncore_format_group,
+};
+
+static int snr_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK;
+
+ if (ev_sel >= 0xb && ev_sel <= 0xe) {
+ reg1->reg = SNR_PCU_MSR_PMON_BOX_FILTER;
+ reg1->idx = ev_sel - 0xb;
+ reg1->config = event->attr.config1 & (0xff << reg1->idx);
+ }
+ return 0;
+}
+
+static struct intel_uncore_ops snr_uncore_pcu_ops = {
+ IVBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+ .hw_config = snr_pcu_hw_config,
+ .get_constraint = snbep_pcu_get_constraint,
+ .put_constraint = snbep_pcu_put_constraint,
+};
+
+static struct intel_uncore_type snr_uncore_pcu = {
+ .name = "pcu",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNR_PCU_MSR_PMON_CTR0,
+ .event_ctl = SNR_PCU_MSR_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNR_PCU_MSR_PMON_BOX_CTL,
+ .num_shared_regs = 1,
+ .ops = &snr_uncore_pcu_ops,
+ .format_group = &skx_uncore_pcu_format_group,
+};
+
+enum perf_uncore_snr_iio_freerunning_type_id {
+ SNR_IIO_MSR_IOCLK,
+ SNR_IIO_MSR_BW_IN,
+
+ SNR_IIO_FREERUNNING_TYPE_MAX,
+};
+
+static struct freerunning_counters snr_iio_freerunning[] = {
+ [SNR_IIO_MSR_IOCLK] = { 0x1eac, 0x1, 0x10, 1, 48 },
+ [SNR_IIO_MSR_BW_IN] = { 0x1f00, 0x1, 0x10, 8, 48 },
+};
+
+static struct uncore_event_desc snr_uncore_iio_freerunning_events[] = {
+ /* Free-Running IIO CLOCKS Counter */
+ INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"),
+ /* Free-Running IIO BANDWIDTH IN Counters */
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type snr_uncore_iio_free_running = {
+ .name = "iio_free_running",
+ .num_counters = 9,
+ .num_boxes = 5,
+ .num_freerunning_types = SNR_IIO_FREERUNNING_TYPE_MAX,
+ .freerunning = snr_iio_freerunning,
+ .ops = &skx_uncore_iio_freerunning_ops,
+ .event_descs = snr_uncore_iio_freerunning_events,
+ .format_group = &skx_uncore_iio_freerunning_format_group,
+};
+
+static struct intel_uncore_type *snr_msr_uncores[] = {
+ &snr_uncore_ubox,
+ &snr_uncore_chabox,
+ &snr_uncore_iio,
+ &snr_uncore_irp,
+ &snr_uncore_m2pcie,
+ &snr_uncore_pcu,
+ &snr_uncore_iio_free_running,
+ NULL,
+};
+
+void snr_uncore_cpu_init(void)
+{
+ uncore_msr_uncores = snr_msr_uncores;
+}
+
+static void snr_m2m_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ int box_ctl = uncore_pci_box_ctl(box);
+
+ __set_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags);
+ pci_write_config_dword(pdev, box_ctl, IVBEP_PMON_BOX_CTL_INT);
+}
+
+static struct intel_uncore_ops snr_m2m_uncore_pci_ops = {
+ .init_box = snr_m2m_uncore_pci_init_box,
+ .disable_box = snbep_uncore_pci_disable_box,
+ .enable_box = snbep_uncore_pci_enable_box,
+ .disable_event = snbep_uncore_pci_disable_event,
+ .enable_event = snbep_uncore_pci_enable_event,
+ .read_counter = snbep_uncore_pci_read_counter,
+};
+
+static struct attribute *snr_m2m_uncore_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask_ext3.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ NULL,
+};
+
+static const struct attribute_group snr_m2m_uncore_format_group = {
+ .name = "format",
+ .attrs = snr_m2m_uncore_formats_attr,
+};
+
+static struct intel_uncore_type snr_uncore_m2m = {
+ .name = "m2m",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNR_M2M_PCI_PMON_CTR0,
+ .event_ctl = SNR_M2M_PCI_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .event_mask_ext = SNR_M2M_PCI_PMON_UMASK_EXT,
+ .box_ctl = SNR_M2M_PCI_PMON_BOX_CTL,
+ .ops = &snr_m2m_uncore_pci_ops,
+ .format_group = &snr_m2m_uncore_format_group,
+};
+
+static struct intel_uncore_type snr_uncore_pcie3 = {
+ .name = "pcie3",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNR_PCIE3_PCI_PMON_CTR0,
+ .event_ctl = SNR_PCIE3_PCI_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNR_PCIE3_PCI_PMON_BOX_CTL,
+ .ops = &ivbep_uncore_pci_ops,
+ .format_group = &ivbep_uncore_format_group,
+};
+
+enum {
+ SNR_PCI_UNCORE_M2M,
+ SNR_PCI_UNCORE_PCIE3,
+};
+
+static struct intel_uncore_type *snr_pci_uncores[] = {
+ [SNR_PCI_UNCORE_M2M] = &snr_uncore_m2m,
+ [SNR_PCI_UNCORE_PCIE3] = &snr_uncore_pcie3,
+ NULL,
+};
+
+static const struct pci_device_id snr_uncore_pci_ids[] = {
+ { /* M2M */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 0, SNR_PCI_UNCORE_M2M, 0),
+ },
+ { /* PCIe3 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x334a),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(4, 0, SNR_PCI_UNCORE_PCIE3, 0),
+ },
+ { /* end: all zeroes */ }
+};
+
+static struct pci_driver snr_uncore_pci_driver = {
+ .name = "snr_uncore",
+ .id_table = snr_uncore_pci_ids,
+};
+
+int snr_uncore_pci_init(void)
+{
+ /* SNR UBOX DID */
+ int ret = snbep_pci2phy_map_init(0x3460, SKX_CPUNODEID,
+ SKX_GIDNIDMAP, true);
+
+ if (ret)
+ return ret;
+
+ uncore_pci_uncores = snr_pci_uncores;
+ uncore_pci_driver = &snr_uncore_pci_driver;
+ return 0;
+}
+
+static struct pci_dev *snr_uncore_get_mc_dev(int id)
+{
+ struct pci_dev *mc_dev = NULL;
+ int phys_id, pkg;
+
+ while (1) {
+ mc_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x3451, mc_dev);
+ if (!mc_dev)
+ break;
+ phys_id = uncore_pcibus_to_physid(mc_dev->bus);
+ if (phys_id < 0)
+ continue;
+ pkg = topology_phys_to_logical_pkg(phys_id);
+ if (pkg < 0)
+ continue;
+ else if (pkg == id)
+ break;
+ }
+ return mc_dev;
+}
+
+static void snr_uncore_mmio_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = snr_uncore_get_mc_dev(box->dieid);
+ unsigned int box_ctl = uncore_mmio_box_ctl(box);
+ resource_size_t addr;
+ u32 pci_dword;
+
+ if (!pdev)
+ return;
+
+ pci_read_config_dword(pdev, SNR_IMC_MMIO_BASE_OFFSET, &pci_dword);
+ addr = (pci_dword & SNR_IMC_MMIO_BASE_MASK) << 23;
+
+ pci_read_config_dword(pdev, SNR_IMC_MMIO_MEM0_OFFSET, &pci_dword);
+ addr |= (pci_dword & SNR_IMC_MMIO_MEM0_MASK) << 12;
+
+ addr += box_ctl;
+
+ box->io_addr = ioremap(addr, SNR_IMC_MMIO_SIZE);
+ if (!box->io_addr)
+ return;
+
+ writel(IVBEP_PMON_BOX_CTL_INT, box->io_addr);
+}
+
+static void snr_uncore_mmio_disable_box(struct intel_uncore_box *box)
+{
+ u32 config;
+
+ if (!box->io_addr)
+ return;
+
+ config = readl(box->io_addr);
+ config |= SNBEP_PMON_BOX_CTL_FRZ;
+ writel(config, box->io_addr);
+}
+
+static void snr_uncore_mmio_enable_box(struct intel_uncore_box *box)
+{
+ u32 config;
+
+ if (!box->io_addr)
+ return;
+
+ config = readl(box->io_addr);
+ config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+ writel(config, box->io_addr);
+}
+
+static void snr_uncore_mmio_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!box->io_addr)
+ return;
+
+ writel(hwc->config | SNBEP_PMON_CTL_EN,
+ box->io_addr + hwc->config_base);
+}
+
+static void snr_uncore_mmio_disable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!box->io_addr)
+ return;
+
+ writel(hwc->config, box->io_addr + hwc->config_base);
+}
+
+static struct intel_uncore_ops snr_uncore_mmio_ops = {
+ .init_box = snr_uncore_mmio_init_box,
+ .exit_box = uncore_mmio_exit_box,
+ .disable_box = snr_uncore_mmio_disable_box,
+ .enable_box = snr_uncore_mmio_enable_box,
+ .disable_event = snr_uncore_mmio_disable_event,
+ .enable_event = snr_uncore_mmio_enable_event,
+ .read_counter = uncore_mmio_read_counter,
+};
+
+static struct uncore_event_desc snr_uncore_imc_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x00,umask=0x00"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x0f"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x30"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type snr_uncore_imc = {
+ .name = "imc",
+ .num_counters = 4,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR,
+ .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL,
+ .event_descs = snr_uncore_imc_events,
+ .perf_ctr = SNR_IMC_MMIO_PMON_CTR0,
+ .event_ctl = SNR_IMC_MMIO_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNR_IMC_MMIO_PMON_BOX_CTL,
+ .mmio_offset = SNR_IMC_MMIO_OFFSET,
+ .ops = &snr_uncore_mmio_ops,
+ .format_group = &skx_uncore_format_group,
+};
+
+enum perf_uncore_snr_imc_freerunning_type_id {
+ SNR_IMC_DCLK,
+ SNR_IMC_DDR,
+
+ SNR_IMC_FREERUNNING_TYPE_MAX,
+};
+
+static struct freerunning_counters snr_imc_freerunning[] = {
+ [SNR_IMC_DCLK] = { 0x22b0, 0x0, 0, 1, 48 },
+ [SNR_IMC_DDR] = { 0x2290, 0x8, 0, 2, 48 },
+};
+
+static struct uncore_event_desc snr_uncore_imc_freerunning_events[] = {
+ INTEL_UNCORE_EVENT_DESC(dclk, "event=0xff,umask=0x10"),
+
+ INTEL_UNCORE_EVENT_DESC(read, "event=0xff,umask=0x20"),
+ INTEL_UNCORE_EVENT_DESC(read.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(read.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(write, "event=0xff,umask=0x21"),
+ INTEL_UNCORE_EVENT_DESC(write.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(write.unit, "MiB"),
+};
+
+static struct intel_uncore_ops snr_uncore_imc_freerunning_ops = {
+ .init_box = snr_uncore_mmio_init_box,
+ .exit_box = uncore_mmio_exit_box,
+ .read_counter = uncore_mmio_read_counter,
+ .hw_config = uncore_freerunning_hw_config,
+};
+
+static struct intel_uncore_type snr_uncore_imc_free_running = {
+ .name = "imc_free_running",
+ .num_counters = 3,
+ .num_boxes = 1,
+ .num_freerunning_types = SNR_IMC_FREERUNNING_TYPE_MAX,
+ .freerunning = snr_imc_freerunning,
+ .ops = &snr_uncore_imc_freerunning_ops,
+ .event_descs = snr_uncore_imc_freerunning_events,
+ .format_group = &skx_uncore_iio_freerunning_format_group,
+};
+
+static struct intel_uncore_type *snr_mmio_uncores[] = {
+ &snr_uncore_imc,
+ &snr_uncore_imc_free_running,
+ NULL,
+};
+
+void snr_uncore_mmio_init(void)
+{
+ uncore_mmio_uncores = snr_mmio_uncores;
+}
+
+/* end of SNR uncore support */
// SPDX-License-Identifier: GPL-2.0
#include <linux/perf_event.h>
+#include <linux/sysfs.h>
#include <linux/nospec.h>
#include <asm/intel-family.h>
+#include "probe.h"
enum perf_msr_id {
PERF_MSR_TSC = 0,
PERF_MSR_PTSC = 5,
PERF_MSR_IRPERF = 6,
PERF_MSR_THERM = 7,
- PERF_MSR_THERM_SNAP = 8,
- PERF_MSR_THERM_UNIT = 9,
PERF_MSR_EVENT_MAX,
};
-static bool test_aperfmperf(int idx)
+static bool test_aperfmperf(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_APERFMPERF);
}
-static bool test_ptsc(int idx)
+static bool test_ptsc(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_PTSC);
}
-static bool test_irperf(int idx)
+static bool test_irperf(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_IRPERF);
}
-static bool test_therm_status(int idx)
+static bool test_therm_status(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_DTHERM);
}
-static bool test_intel(int idx)
+static bool test_intel(int idx, void *data)
{
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
boot_cpu_data.x86 != 6)
return false;
}
-struct perf_msr {
- u64 msr;
- struct perf_pmu_events_attr *attr;
- bool (*test)(int idx);
+PMU_EVENT_ATTR_STRING(tsc, attr_tsc, "event=0x00" );
+PMU_EVENT_ATTR_STRING(aperf, attr_aperf, "event=0x01" );
+PMU_EVENT_ATTR_STRING(mperf, attr_mperf, "event=0x02" );
+PMU_EVENT_ATTR_STRING(pperf, attr_pperf, "event=0x03" );
+PMU_EVENT_ATTR_STRING(smi, attr_smi, "event=0x04" );
+PMU_EVENT_ATTR_STRING(ptsc, attr_ptsc, "event=0x05" );
+PMU_EVENT_ATTR_STRING(irperf, attr_irperf, "event=0x06" );
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin, attr_therm, "event=0x07" );
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin.snapshot, attr_therm_snap, "1" );
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin.unit, attr_therm_unit, "C" );
+
+static unsigned long msr_mask;
+
+PMU_EVENT_GROUP(events, aperf);
+PMU_EVENT_GROUP(events, mperf);
+PMU_EVENT_GROUP(events, pperf);
+PMU_EVENT_GROUP(events, smi);
+PMU_EVENT_GROUP(events, ptsc);
+PMU_EVENT_GROUP(events, irperf);
+
+static struct attribute *attrs_therm[] = {
+ &attr_therm.attr.attr,
+ &attr_therm_snap.attr.attr,
+ &attr_therm_unit.attr.attr,
+ NULL,
};
-PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00" );
-PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01" );
-PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02" );
-PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03" );
-PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04" );
-PMU_EVENT_ATTR_STRING(ptsc, evattr_ptsc, "event=0x05" );
-PMU_EVENT_ATTR_STRING(irperf, evattr_irperf, "event=0x06" );
-PMU_EVENT_ATTR_STRING(cpu_thermal_margin, evattr_therm, "event=0x07" );
-PMU_EVENT_ATTR_STRING(cpu_thermal_margin.snapshot, evattr_therm_snap, "1" );
-PMU_EVENT_ATTR_STRING(cpu_thermal_margin.unit, evattr_therm_unit, "C" );
+static struct attribute_group group_therm = {
+ .name = "events",
+ .attrs = attrs_therm,
+};
static struct perf_msr msr[] = {
- [PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, },
- [PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, },
- [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, },
- [PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, },
- [PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, },
- [PERF_MSR_PTSC] = { MSR_F15H_PTSC, &evattr_ptsc, test_ptsc, },
- [PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &evattr_irperf, test_irperf, },
- [PERF_MSR_THERM] = { MSR_IA32_THERM_STATUS, &evattr_therm, test_therm_status, },
- [PERF_MSR_THERM_SNAP] = { MSR_IA32_THERM_STATUS, &evattr_therm_snap, test_therm_status, },
- [PERF_MSR_THERM_UNIT] = { MSR_IA32_THERM_STATUS, &evattr_therm_unit, test_therm_status, },
+ [PERF_MSR_TSC] = { .no_check = true, },
+ [PERF_MSR_APERF] = { MSR_IA32_APERF, &group_aperf, test_aperfmperf, },
+ [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &group_mperf, test_aperfmperf, },
+ [PERF_MSR_PPERF] = { MSR_PPERF, &group_pperf, test_intel, },
+ [PERF_MSR_SMI] = { MSR_SMI_COUNT, &group_smi, test_intel, },
+ [PERF_MSR_PTSC] = { MSR_F15H_PTSC, &group_ptsc, test_ptsc, },
+ [PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &group_irperf, test_irperf, },
+ [PERF_MSR_THERM] = { MSR_IA32_THERM_STATUS, &group_therm, test_therm_status, },
};
-static struct attribute *events_attrs[PERF_MSR_EVENT_MAX + 1] = {
+static struct attribute *events_attrs[] = {
+ &attr_tsc.attr.attr,
NULL,
};
NULL,
};
+const struct attribute_group *attr_update[] = {
+ &group_aperf,
+ &group_mperf,
+ &group_pperf,
+ &group_smi,
+ &group_ptsc,
+ &group_irperf,
+ &group_therm,
+ NULL,
+};
+
static int msr_event_init(struct perf_event *event)
{
u64 cfg = event->attr.config;
cfg = array_index_nospec((unsigned long)cfg, PERF_MSR_EVENT_MAX);
- if (!msr[cfg].attr)
+ if (!(msr_mask & (1 << cfg)))
return -EINVAL;
event->hw.idx = -1;
.stop = msr_event_stop,
.read = msr_event_update,
.capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE,
+ .attr_update = attr_update,
};
static int __init msr_init(void)
{
- int i, j = 0;
-
if (!boot_cpu_has(X86_FEATURE_TSC)) {
pr_cont("no MSR PMU driver.\n");
return 0;
}
- /* Probe the MSRs. */
- for (i = PERF_MSR_TSC + 1; i < PERF_MSR_EVENT_MAX; i++) {
- u64 val;
-
- /* Virt sucks; you cannot tell if a R/O MSR is present :/ */
- if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val))
- msr[i].attr = NULL;
- }
-
- /* List remaining MSRs in the sysfs attrs. */
- for (i = 0; i < PERF_MSR_EVENT_MAX; i++) {
- if (msr[i].attr)
- events_attrs[j++] = &msr[i].attr->attr.attr;
- }
- events_attrs[j] = NULL;
+ msr_mask = perf_msr_probe(msr, PERF_MSR_EVENT_MAX, true, NULL);
perf_pmu_register(&pmu_msr, "msr", -1);
int attr_rdpmc_broken;
int attr_rdpmc;
struct attribute **format_attrs;
- struct attribute **event_attrs;
- struct attribute **caps_attrs;
ssize_t (*events_sysfs_show)(char *page, u64 config);
- struct attribute **cpu_events;
+ const struct attribute_group **attr_update;
unsigned long attr_freeze_on_smi;
- struct attribute **attrs;
/*
* CPU Hotplug hooks
ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event);
ssize_t intel_event_sysfs_show(char *page, u64 config);
-struct attribute **merge_attr(struct attribute **a, struct attribute **b);
-
ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
char *page);
ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/bits.h>
+#include "probe.h"
+
+static umode_t
+not_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return 0;
+}
+
+unsigned long
+perf_msr_probe(struct perf_msr *msr, int cnt, bool zero, void *data)
+{
+ unsigned long avail = 0;
+ unsigned int bit;
+ u64 val;
+
+ if (cnt >= BITS_PER_LONG)
+ return 0;
+
+ for (bit = 0; bit < cnt; bit++) {
+ if (!msr[bit].no_check) {
+ struct attribute_group *grp = msr[bit].grp;
+
+ grp->is_visible = not_visible;
+
+ if (msr[bit].test && !msr[bit].test(bit, data))
+ continue;
+ /* Virt sucks; you cannot tell if a R/O MSR is present :/ */
+ if (rdmsrl_safe(msr[bit].msr, &val))
+ continue;
+ /* Disable zero counters if requested. */
+ if (!zero && !val)
+ continue;
+
+ grp->is_visible = NULL;
+ }
+ avail |= BIT(bit);
+ }
+
+ return avail;
+}
+EXPORT_SYMBOL_GPL(perf_msr_probe);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ARCH_X86_EVENTS_PROBE_H__
+#define __ARCH_X86_EVENTS_PROBE_H__
+#include <linux/sysfs.h>
+
+struct perf_msr {
+ u64 msr;
+ struct attribute_group *grp;
+ bool (*test)(int idx, void *data);
+ bool no_check;
+};
+
+unsigned long
+perf_msr_probe(struct perf_msr *msr, int cnt, bool no_zero, void *data);
+
+#define __PMU_EVENT_GROUP(_name) \
+static struct attribute *attrs_##_name[] = { \
+ &attr_##_name.attr.attr, \
+ NULL, \
+}
+
+#define PMU_EVENT_GROUP(_grp, _name) \
+__PMU_EVENT_GROUP(_name); \
+static struct attribute_group group_##_name = { \
+ .name = #_grp, \
+ .attrs = attrs_##_name, \
+}
+
+#endif /* __ARCH_X86_EVENTS_PROBE_H__ */
CPUID_LNX_3,
CPUID_7_0_EBX,
CPUID_D_1_EAX,
- CPUID_F_0_EDX,
- CPUID_F_1_EDX,
+ CPUID_LNX_4,
+ CPUID_7_1_EAX,
CPUID_8000_0008_EBX,
CPUID_6_EAX,
CPUID_8000_000A_EDX,
#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */
#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */
#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* "" FPU data pointer updated only on x87 exceptions */
#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */
#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */
#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */
#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */
#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */
#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */
+#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* "" Zero out FPU CS and FPU DS */
#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */
#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */
#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */
#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */
#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */
-#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */
+/*
+ * Extended auxiliary flags: Linux defined - for features scattered in various
+ * CPUID levels like 0xf, etc.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+#define X86_FEATURE_CQM_LLC (11*32+ 0) /* LLC QoS if 1 */
+#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring */
+#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring */
+#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */
-#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring */
-#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */
-#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */
+/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
#define X86_FEATURE_UMIP (16*32+ 2) /* User Mode Instruction Protection */
#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */
#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_WAITPKG (16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */
#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
#define X86_FEATURE_GFNI (16*32+ 8) /* Galois Field New Instructions */
#define X86_FEATURE_VAES (16*32+ 9) /* Vector AES */
#define INTEL_FAM6_ICELAKE_XEON_D 0x6C
#define INTEL_FAM6_ICELAKE_DESKTOP 0x7D
#define INTEL_FAM6_ICELAKE_MOBILE 0x7E
+#define INTEL_FAM6_ICELAKE_NNPI 0x9D
/* "Small Core" Processors (Atom) */
#define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */
#define INTEL_FAM6_ATOM_GOLDMONT_X 0x5F /* Denverton */
#define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */
+
#define INTEL_FAM6_ATOM_TREMONT_X 0x86 /* Jacobsville */
/* Xeon Phi */
#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT 31
#define MSR_PLATFORM_INFO_CPUID_FAULT BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT)
+#define MSR_IA32_UMWAIT_CONTROL 0xe1
+#define MSR_IA32_UMWAIT_CONTROL_C02_DISABLE BIT(0)
+#define MSR_IA32_UMWAIT_CONTROL_RESERVED BIT(1)
+/*
+ * The time field is bit[31:2], but representing a 32bit value with
+ * bit[1:0] zero.
+ */
+#define MSR_IA32_UMWAIT_CONTROL_TIME_MASK (~0x03U)
+
#define MSR_PKG_CST_CONFIG_CONTROL 0x000000e2
#define NHM_C3_AUTO_DEMOTE (1UL << 25)
#define NHM_C1_AUTO_DEMOTE (1UL << 26)
int x86_power;
unsigned long loops_per_jiffy;
/* cpuid returned max cores value: */
- u16 x86_max_cores;
+ u16 x86_max_cores;
u16 apicid;
u16 initial_apicid;
u16 x86_clflush_size;
u16 logical_proc_id;
/* Core id: */
u16 cpu_core_id;
+ u16 cpu_die_id;
+ u16 logical_die_id;
/* Index into per_cpu list: */
u16 cpu_index;
u32 microcode;
#define X86_VENDOR_TRANSMETA 7
#define X86_VENDOR_NSC 8
#define X86_VENDOR_HYGON 9
-#define X86_VENDOR_NUM 10
+#define X86_VENDOR_ZHAOXIN 10
+#define X86_VENDOR_NUM 11
#define X86_VENDOR_UNKNOWN 0xff
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
+DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
/* cpus sharing the last level cache: */
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
#define topology_logical_package_id(cpu) (cpu_data(cpu).logical_proc_id)
#define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id)
+#define topology_logical_die_id(cpu) (cpu_data(cpu).logical_die_id)
+#define topology_die_id(cpu) (cpu_data(cpu).cpu_die_id)
#define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id)
#ifdef CONFIG_SMP
+#define topology_die_cpumask(cpu) (per_cpu(cpu_die_map, cpu))
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
extern unsigned int __max_logical_packages;
#define topology_max_packages() (__max_logical_packages)
+extern unsigned int __max_die_per_package;
+
+static inline int topology_max_die_per_package(void)
+{
+ return __max_die_per_package;
+}
+
extern int __max_smt_threads;
static inline int topology_max_smt_threads(void)
}
int topology_update_package_map(unsigned int apicid, unsigned int cpu);
+int topology_update_die_map(unsigned int dieid, unsigned int cpu);
int topology_phys_to_logical_pkg(unsigned int pkg);
+int topology_phys_to_logical_die(unsigned int die, unsigned int cpu);
bool topology_is_primary_thread(unsigned int cpu);
bool topology_smt_supported(void);
#else
#define topology_max_packages() (1)
static inline int
topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
+static inline int
+topology_update_die_map(unsigned int dieid, unsigned int cpu) { return 0; }
static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
+static inline int topology_phys_to_logical_die(unsigned int die,
+ unsigned int cpu) { return 0; }
+static inline int topology_max_die_per_package(void) { return 1; }
static inline int topology_max_smt_threads(void) { return 1; }
static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
static inline bool topology_smt_supported(void) { return false; }
c->x86_stepping >= 0x0e))
flags->bm_check = 1;
}
+
+ if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
+ /*
+ * All Zhaoxin CPUs that support C3 share cache.
+ * And caches should not be flushed by software while
+ * entering C3 type state.
+ */
+ flags->bm_check = 1;
+ /*
+ * On all recent Zhaoxin platforms, ARB_DISABLE is a nop.
+ * So, set bm_control to zero to indicate that ARB_DISABLE
+ * is not required while entering C3 type state.
+ */
+ flags->bm_control = 0;
+ }
}
EXPORT_SYMBOL(acpi_processor_power_init_bm_check);
obj-y += bugs.o
obj-y += aperfmperf.o
obj-y += cpuid-deps.o
+obj-y += umwait.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o
obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o
obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o
+obj-$(CONFIG_CPU_SUP_ZHAOXIN) += zhaoxin.o
obj-$(CONFIG_X86_MCE) += mce/
obj-$(CONFIG_MTRR) += mtrr/
#include <linux/percpu.h>
#include <linux/cpufreq.h>
#include <linux/smp.h>
+#include <linux/sched/isolation.h>
#include "cpu.h"
if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
+ if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+ return 0;
+
aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
return per_cpu(samples.khz, cpu);
}
if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return;
- for_each_online_cpu(cpu)
+ for_each_online_cpu(cpu) {
+ if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+ continue;
if (!aperfmperf_snapshot_cpu(cpu, now, false))
wait = true;
+ }
if (wait)
msleep(APERFMPERF_REFRESH_DELAY_MS);
if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
+ if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+ return 0;
+
if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
return per_cpu(samples.khz, cpu);
if (c->x86 < 0x17) {
/* LLC is at the node level. */
per_cpu(cpu_llc_id, cpu) = node_id;
- } else if (c->x86 == 0x17 &&
- c->x86_model >= 0 && c->x86_model <= 0x1F) {
+ } else if (c->x86 == 0x17 && c->x86_model <= 0x1F) {
/*
* LLC is at the core complex level.
* Core complex ID is ApicId[3] for these processors.
}
}
+static void init_cqm(struct cpuinfo_x86 *c)
+{
+ if (!cpu_has(c, X86_FEATURE_CQM_LLC)) {
+ c->x86_cache_max_rmid = -1;
+ c->x86_cache_occ_scale = -1;
+ return;
+ }
+
+ /* will be overridden if occupancy monitoring exists */
+ c->x86_cache_max_rmid = cpuid_ebx(0xf);
+
+ if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) ||
+ cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) ||
+ cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) {
+ u32 eax, ebx, ecx, edx;
+
+ /* QoS sub-leaf, EAX=0Fh, ECX=1 */
+ cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx);
+
+ c->x86_cache_max_rmid = ecx;
+ c->x86_cache_occ_scale = ebx;
+ }
+}
+
void get_cpu_cap(struct cpuinfo_x86 *c)
{
u32 eax, ebx, ecx, edx;
c->x86_capability[CPUID_7_0_EBX] = ebx;
c->x86_capability[CPUID_7_ECX] = ecx;
c->x86_capability[CPUID_7_EDX] = edx;
+
+ /* Check valid sub-leaf index before accessing it */
+ if (eax >= 1) {
+ cpuid_count(0x00000007, 1, &eax, &ebx, &ecx, &edx);
+ c->x86_capability[CPUID_7_1_EAX] = eax;
+ }
}
/* Extended state features: level 0x0000000d */
c->x86_capability[CPUID_D_1_EAX] = eax;
}
- /* Additional Intel-defined flags: level 0x0000000F */
- if (c->cpuid_level >= 0x0000000F) {
-
- /* QoS sub-leaf, EAX=0Fh, ECX=0 */
- cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
- c->x86_capability[CPUID_F_0_EDX] = edx;
-
- if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
- /* will be overridden if occupancy monitoring exists */
- c->x86_cache_max_rmid = ebx;
-
- /* QoS sub-leaf, EAX=0Fh, ECX=1 */
- cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
- c->x86_capability[CPUID_F_1_EDX] = edx;
-
- if ((cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) ||
- ((cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL)) ||
- (cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)))) {
- c->x86_cache_max_rmid = ecx;
- c->x86_cache_occ_scale = ebx;
- }
- } else {
- c->x86_cache_max_rmid = -1;
- c->x86_cache_occ_scale = -1;
- }
- }
-
/* AMD-defined flags: level 0x80000001 */
eax = cpuid_eax(0x80000000);
c->extended_cpuid_level = eax;
init_scattered_cpuid_features(c);
init_speculation_control(c);
+ init_cqm(c);
/*
* Clear/Set all flags overridden by options, after probe.
cpu, apicid, c->initial_apicid);
}
BUG_ON(topology_update_package_map(c->phys_proc_id, cpu));
+ BUG_ON(topology_update_die_map(c->cpu_die_id, cpu));
#else
c->logical_proc_id = 0;
#endif
{ X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F },
{ X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F },
{ X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F },
+ { X86_FEATURE_CQM_OCCUP_LLC, X86_FEATURE_CQM_LLC },
+ { X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC },
+ { X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC },
+ { X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL },
{}
};
}
}
+/*
+ * Processors which have self-snooping capability can handle conflicting
+ * memory type across CPUs by snooping its own cache. However, there exists
+ * CPU models in which having conflicting memory types still leads to
+ * unpredictable behavior, machine check errors, or hangs. Clear this
+ * feature to prevent its use on machines with known erratas.
+ */
+static void check_memory_type_self_snoop_errata(struct cpuinfo_x86 *c)
+{
+ switch (c->x86_model) {
+ case INTEL_FAM6_CORE_YONAH:
+ case INTEL_FAM6_CORE2_MEROM:
+ case INTEL_FAM6_CORE2_MEROM_L:
+ case INTEL_FAM6_CORE2_PENRYN:
+ case INTEL_FAM6_CORE2_DUNNINGTON:
+ case INTEL_FAM6_NEHALEM:
+ case INTEL_FAM6_NEHALEM_G:
+ case INTEL_FAM6_NEHALEM_EP:
+ case INTEL_FAM6_NEHALEM_EX:
+ case INTEL_FAM6_WESTMERE:
+ case INTEL_FAM6_WESTMERE_EP:
+ case INTEL_FAM6_SANDYBRIDGE:
+ setup_clear_cpu_cap(X86_FEATURE_SELFSNOOP);
+ }
+}
+
static bool ring3mwait_disabled __read_mostly;
static int __init ring3mwait_disable(char *__unused)
}
check_mpx_erratum(c);
+ check_memory_type_self_snoop_errata(c);
/*
* Get the number of SMT siblings early from the extended topology
/* Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */
cr0 = read_cr0() | X86_CR0_CD;
write_cr0(cr0);
- wbinvd();
+
+ /*
+ * Cache flushing is the most time-consuming step when programming
+ * the MTRRs. Fortunately, as per the Intel Software Development
+ * Manual, we can skip it if the processor supports cache self-
+ * snooping.
+ */
+ if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
+ wbinvd();
/* Save value of CR4 and clear Page Global Enable (bit 7) */
if (boot_cpu_has(X86_FEATURE_PGE)) {
/* Disable MTRRs, and set the default type to uncached */
mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi);
- wbinvd();
+
+ /* Again, only flush caches if we have to. */
+ if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
+ wbinvd();
}
static void post_set(void) __releases(set_atomicity_lock)
static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 },
{ X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 },
+ { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 },
+ { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 },
+ { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 },
+ { X86_FEATURE_CQM_MBM_LOCAL, CPUID_EDX, 2, 0x0000000f, 1 },
{ X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 },
{ X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 },
{ X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 },
/* leaf 0xb SMT level */
#define SMT_LEVEL 0
-/* leaf 0xb sub-leaf types */
+/* extended topology sub-leaf types */
#define INVALID_TYPE 0
#define SMT_TYPE 1
#define CORE_TYPE 2
+#define DIE_TYPE 5
#define LEAFB_SUBTYPE(ecx) (((ecx) >> 8) & 0xff)
#define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f)
#define LEVEL_MAX_SIBLINGS(ebx) ((ebx) & 0xffff)
-int detect_extended_topology_early(struct cpuinfo_x86 *c)
-{
#ifdef CONFIG_SMP
+unsigned int __max_die_per_package __read_mostly = 1;
+EXPORT_SYMBOL(__max_die_per_package);
+
+/*
+ * Check if given CPUID extended toplogy "leaf" is implemented
+ */
+static int check_extended_topology_leaf(int leaf)
+{
unsigned int eax, ebx, ecx, edx;
- if (c->cpuid_level < 0xb)
+ cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+
+ if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
return -1;
- cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+ return 0;
+}
+/*
+ * Return best CPUID Extended Toplogy Leaf supported
+ */
+static int detect_extended_topology_leaf(struct cpuinfo_x86 *c)
+{
+ if (c->cpuid_level >= 0x1f) {
+ if (check_extended_topology_leaf(0x1f) == 0)
+ return 0x1f;
+ }
- /*
- * check if the cpuid leaf 0xb is actually implemented.
- */
- if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
+ if (c->cpuid_level >= 0xb) {
+ if (check_extended_topology_leaf(0xb) == 0)
+ return 0xb;
+ }
+
+ return -1;
+}
+#endif
+
+int detect_extended_topology_early(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+ unsigned int eax, ebx, ecx, edx;
+ int leaf;
+
+ leaf = detect_extended_topology_leaf(c);
+ if (leaf < 0)
return -1;
set_cpu_cap(c, X86_FEATURE_XTOPOLOGY);
+ cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
/*
* initial apic id, which also represents 32-bit extended x2apic id.
*/
}
/*
- * Check for extended topology enumeration cpuid leaf 0xb and if it
+ * Check for extended topology enumeration cpuid leaf, and if it
* exists, use it for populating initial_apicid and cpu topology
* detection.
*/
{
#ifdef CONFIG_SMP
unsigned int eax, ebx, ecx, edx, sub_index;
- unsigned int ht_mask_width, core_plus_mask_width;
+ unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width;
unsigned int core_select_mask, core_level_siblings;
+ unsigned int die_select_mask, die_level_siblings;
+ int leaf;
- if (detect_extended_topology_early(c) < 0)
+ leaf = detect_extended_topology_leaf(c);
+ if (leaf < 0)
return -1;
/*
* Populate HT related information from sub-leaf level 0.
*/
- cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+ cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+ c->initial_apicid = edx;
core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+ die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
+ die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
sub_index = 1;
do {
- cpuid_count(0xb, sub_index, &eax, &ebx, &ecx, &edx);
+ cpuid_count(leaf, sub_index, &eax, &ebx, &ecx, &edx);
/*
* Check for the Core type in the implemented sub leaves.
if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) {
core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
core_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
- break;
+ die_level_siblings = core_level_siblings;
+ die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+ }
+ if (LEAFB_SUBTYPE(ecx) == DIE_TYPE) {
+ die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
+ die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
}
sub_index++;
} while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width;
-
- c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, ht_mask_width)
- & core_select_mask;
- c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, core_plus_mask_width);
+ die_select_mask = (~(-1 << die_plus_mask_width)) >>
+ core_plus_mask_width;
+
+ c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid,
+ ht_mask_width) & core_select_mask;
+ c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid,
+ core_plus_mask_width) & die_select_mask;
+ c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid,
+ die_plus_mask_width);
/*
* Reinit the apicid, now that we have extended initial_apicid.
*/
c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
c->x86_max_cores = (core_level_siblings / smp_num_siblings);
+ __max_die_per_package = (die_level_siblings / core_level_siblings);
#endif
return 0;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/syscore_ops.h>
+#include <linux/suspend.h>
+#include <linux/cpu.h>
+
+#include <asm/msr.h>
+
+#define UMWAIT_C02_ENABLE 0
+
+#define UMWAIT_CTRL_VAL(max_time, c02_disable) \
+ (((max_time) & MSR_IA32_UMWAIT_CONTROL_TIME_MASK) | \
+ ((c02_disable) & MSR_IA32_UMWAIT_CONTROL_C02_DISABLE))
+
+/*
+ * Cache IA32_UMWAIT_CONTROL MSR. This is a systemwide control. By default,
+ * umwait max time is 100000 in TSC-quanta and C0.2 is enabled
+ */
+static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE);
+
+/*
+ * Serialize access to umwait_control_cached and IA32_UMWAIT_CONTROL MSR in
+ * the sysfs write functions.
+ */
+static DEFINE_MUTEX(umwait_lock);
+
+static void umwait_update_control_msr(void * unused)
+{
+ lockdep_assert_irqs_disabled();
+ wrmsr(MSR_IA32_UMWAIT_CONTROL, READ_ONCE(umwait_control_cached), 0);
+}
+
+/*
+ * The CPU hotplug callback sets the control MSR to the global control
+ * value.
+ *
+ * Disable interrupts so the read of umwait_control_cached and the WRMSR
+ * are protected against a concurrent sysfs write. Otherwise the sysfs
+ * write could update the cached value after it had been read on this CPU
+ * and issue the IPI before the old value had been written. The IPI would
+ * interrupt, write the new value and after return from IPI the previous
+ * value would be written by this CPU.
+ *
+ * With interrupts disabled the upcoming CPU either sees the new control
+ * value or the IPI is updating this CPU to the new control value after
+ * interrupts have been reenabled.
+ */
+static int umwait_cpu_online(unsigned int cpu)
+{
+ local_irq_disable();
+ umwait_update_control_msr(NULL);
+ local_irq_enable();
+ return 0;
+}
+
+/*
+ * On resume, restore IA32_UMWAIT_CONTROL MSR on the boot processor which
+ * is the only active CPU at this time. The MSR is set up on the APs via the
+ * CPU hotplug callback.
+ *
+ * This function is invoked on resume from suspend and hibernation. On
+ * resume from suspend the restore should be not required, but we neither
+ * trust the firmware nor does it matter if the same value is written
+ * again.
+ */
+static void umwait_syscore_resume(void)
+{
+ umwait_update_control_msr(NULL);
+}
+
+static struct syscore_ops umwait_syscore_ops = {
+ .resume = umwait_syscore_resume,
+};
+
+/* sysfs interface */
+
+/*
+ * When bit 0 in IA32_UMWAIT_CONTROL MSR is 1, C0.2 is disabled.
+ * Otherwise, C0.2 is enabled.
+ */
+static inline bool umwait_ctrl_c02_enabled(u32 ctrl)
+{
+ return !(ctrl & MSR_IA32_UMWAIT_CONTROL_C02_DISABLE);
+}
+
+static inline u32 umwait_ctrl_max_time(u32 ctrl)
+{
+ return ctrl & MSR_IA32_UMWAIT_CONTROL_TIME_MASK;
+}
+
+static inline void umwait_update_control(u32 maxtime, bool c02_enable)
+{
+ u32 ctrl = maxtime & MSR_IA32_UMWAIT_CONTROL_TIME_MASK;
+
+ if (!c02_enable)
+ ctrl |= MSR_IA32_UMWAIT_CONTROL_C02_DISABLE;
+
+ WRITE_ONCE(umwait_control_cached, ctrl);
+ /* Propagate to all CPUs */
+ on_each_cpu(umwait_update_control_msr, NULL, 1);
+}
+
+static ssize_t
+enable_c02_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ u32 ctrl = READ_ONCE(umwait_control_cached);
+
+ return sprintf(buf, "%d\n", umwait_ctrl_c02_enabled(ctrl));
+}
+
+static ssize_t enable_c02_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ bool c02_enable;
+ u32 ctrl;
+ int ret;
+
+ ret = kstrtobool(buf, &c02_enable);
+ if (ret)
+ return ret;
+
+ mutex_lock(&umwait_lock);
+
+ ctrl = READ_ONCE(umwait_control_cached);
+ if (c02_enable != umwait_ctrl_c02_enabled(ctrl))
+ umwait_update_control(ctrl, c02_enable);
+
+ mutex_unlock(&umwait_lock);
+
+ return count;
+}
+static DEVICE_ATTR_RW(enable_c02);
+
+static ssize_t
+max_time_show(struct device *kobj, struct device_attribute *attr, char *buf)
+{
+ u32 ctrl = READ_ONCE(umwait_control_cached);
+
+ return sprintf(buf, "%u\n", umwait_ctrl_max_time(ctrl));
+}
+
+static ssize_t max_time_store(struct device *kobj,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ u32 max_time, ctrl;
+ int ret;
+
+ ret = kstrtou32(buf, 0, &max_time);
+ if (ret)
+ return ret;
+
+ /* bits[1:0] must be zero */
+ if (max_time & ~MSR_IA32_UMWAIT_CONTROL_TIME_MASK)
+ return -EINVAL;
+
+ mutex_lock(&umwait_lock);
+
+ ctrl = READ_ONCE(umwait_control_cached);
+ if (max_time != umwait_ctrl_max_time(ctrl))
+ umwait_update_control(max_time, umwait_ctrl_c02_enabled(ctrl));
+
+ mutex_unlock(&umwait_lock);
+
+ return count;
+}
+static DEVICE_ATTR_RW(max_time);
+
+static struct attribute *umwait_attrs[] = {
+ &dev_attr_enable_c02.attr,
+ &dev_attr_max_time.attr,
+ NULL
+};
+
+static struct attribute_group umwait_attr_group = {
+ .attrs = umwait_attrs,
+ .name = "umwait_control",
+};
+
+static int __init umwait_init(void)
+{
+ struct device *dev;
+ int ret;
+
+ if (!boot_cpu_has(X86_FEATURE_WAITPKG))
+ return -ENODEV;
+
+ ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "umwait:online",
+ umwait_cpu_online, NULL);
+
+ register_syscore_ops(&umwait_syscore_ops);
+
+ /*
+ * Add umwait control interface. Ignore failure, so at least the
+ * default values are set up in case the machine manages to boot.
+ */
+ dev = cpu_subsys.dev_root;
+ return sysfs_create_group(&dev->kobj, &umwait_attr_group);
+}
+device_initcall(umwait_init);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
+
+#include <asm/cpufeature.h>
+
+#include "cpu.h"
+
+#define MSR_ZHAOXIN_FCR57 0x00001257
+
+#define ACE_PRESENT (1 << 6)
+#define ACE_ENABLED (1 << 7)
+#define ACE_FCR (1 << 7) /* MSR_ZHAOXIN_FCR */
+
+#define RNG_PRESENT (1 << 2)
+#define RNG_ENABLED (1 << 3)
+#define RNG_ENABLE (1 << 8) /* MSR_ZHAOXIN_RNG */
+
+#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW 0x00200000
+#define X86_VMX_FEATURE_PROC_CTLS_VNMI 0x00400000
+#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS 0x80000000
+#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001
+#define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002
+#define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020
+
+static void init_zhaoxin_cap(struct cpuinfo_x86 *c)
+{
+ u32 lo, hi;
+
+ /* Test for Extended Feature Flags presence */
+ if (cpuid_eax(0xC0000000) >= 0xC0000001) {
+ u32 tmp = cpuid_edx(0xC0000001);
+
+ /* Enable ACE unit, if present and disabled */
+ if ((tmp & (ACE_PRESENT | ACE_ENABLED)) == ACE_PRESENT) {
+ rdmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+ /* Enable ACE unit */
+ lo |= ACE_FCR;
+ wrmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+ pr_info("CPU: Enabled ACE h/w crypto\n");
+ }
+
+ /* Enable RNG unit, if present and disabled */
+ if ((tmp & (RNG_PRESENT | RNG_ENABLED)) == RNG_PRESENT) {
+ rdmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+ /* Enable RNG unit */
+ lo |= RNG_ENABLE;
+ wrmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+ pr_info("CPU: Enabled h/w RNG\n");
+ }
+
+ /*
+ * Store Extended Feature Flags as word 5 of the CPU
+ * capability bit array
+ */
+ c->x86_capability[CPUID_C000_0001_EDX] = cpuid_edx(0xC0000001);
+ }
+
+ if (c->x86 >= 0x6)
+ set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+ cpu_detect_cache_sizes(c);
+}
+
+static void early_init_zhaoxin(struct cpuinfo_x86 *c)
+{
+ if (c->x86 >= 0x6)
+ set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+#ifdef CONFIG_X86_64
+ set_cpu_cap(c, X86_FEATURE_SYSENTER32);
+#endif
+ if (c->x86_power & (1 << 8)) {
+ set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+ set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+ }
+
+ if (c->cpuid_level >= 0x00000001) {
+ u32 eax, ebx, ecx, edx;
+
+ cpuid(0x00000001, &eax, &ebx, &ecx, &edx);
+ /*
+ * If HTT (EDX[28]) is set EBX[16:23] contain the number of
+ * apicids which are reserved per package. Store the resulting
+ * shift value for the package management code.
+ */
+ if (edx & (1U << 28))
+ c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff);
+ }
+
+}
+
+static void zhaoxin_detect_vmx_virtcap(struct cpuinfo_x86 *c)
+{
+ u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
+
+ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
+ msr_ctl = vmx_msr_high | vmx_msr_low;
+
+ if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)
+ set_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
+ if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI)
+ set_cpu_cap(c, X86_FEATURE_VNMI);
+ if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) {
+ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
+ vmx_msr_low, vmx_msr_high);
+ msr_ctl2 = vmx_msr_high | vmx_msr_low;
+ if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
+ (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
+ set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
+ if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
+ set_cpu_cap(c, X86_FEATURE_EPT);
+ if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
+ set_cpu_cap(c, X86_FEATURE_VPID);
+ }
+}
+
+static void init_zhaoxin(struct cpuinfo_x86 *c)
+{
+ early_init_zhaoxin(c);
+ init_intel_cacheinfo(c);
+ detect_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+ detect_ht(c);
+#endif
+
+ if (c->cpuid_level > 9) {
+ unsigned int eax = cpuid_eax(10);
+
+ /*
+ * Check for version and the number of counters
+ * Version(eax[7:0]) can't be 0;
+ * Counters(eax[15:8]) should be greater than 1;
+ */
+ if ((eax & 0xff) && (((eax >> 8) & 0xff) > 1))
+ set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
+ }
+
+ if (c->x86 >= 0x6)
+ init_zhaoxin_cap(c);
+#ifdef CONFIG_X86_64
+ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+#endif
+
+ if (cpu_has(c, X86_FEATURE_VMX))
+ zhaoxin_detect_vmx_virtcap(c);
+}
+
+#ifdef CONFIG_X86_32
+static unsigned int
+zhaoxin_size_cache(struct cpuinfo_x86 *c, unsigned int size)
+{
+ return size;
+}
+#endif
+
+static const struct cpu_dev zhaoxin_cpu_dev = {
+ .c_vendor = "zhaoxin",
+ .c_ident = { " Shanghai " },
+ .c_early_init = early_init_zhaoxin,
+ .c_init = init_zhaoxin,
+#ifdef CONFIG_X86_32
+ .legacy_cache_size = zhaoxin_size_cache,
+#endif
+ .c_x86_vendor = X86_VENDOR_ZHAOXIN,
+};
+
+cpu_dev_register(zhaoxin_cpu_dev);
case offsetof(struct user_regs_struct,fs_base):
if (value >= TASK_SIZE_MAX)
return -EIO;
- /*
- * When changing the FS base, use do_arch_prctl_64()
- * to set the index to zero and to set the base
- * as requested.
- */
- if (child->thread.fsbase != value)
- return do_arch_prctl_64(child, ARCH_SET_FS, value);
+ x86_fsbase_write_task(child, value);
return 0;
case offsetof(struct user_regs_struct,gs_base):
- /*
- * Exactly the same here as the %fs handling above.
- */
if (value >= TASK_SIZE_MAX)
return -EIO;
- if (child->thread.gsbase != value)
- return do_arch_prctl_64(child, ARCH_SET_GS, value);
+ x86_gsbase_write_task(child, value);
return 0;
#endif
}
DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
+/* representing HT, core, and die siblings of each logical CPU */
+DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
+EXPORT_PER_CPU_SYMBOL(cpu_die_map);
+
DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
/* Per CPU bogomips and other parameters */
unsigned int __max_logical_packages __read_mostly;
EXPORT_SYMBOL(__max_logical_packages);
static unsigned int logical_packages __read_mostly;
+static unsigned int logical_die __read_mostly;
/* Maximum number of SMT threads on any online core */
int __read_mostly __max_smt_threads = 1;
return -1;
}
EXPORT_SYMBOL(topology_phys_to_logical_pkg);
+/**
+ * topology_phys_to_logical_die - Map a physical die id to logical
+ *
+ * Returns logical die id or -1 if not found
+ */
+int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu)
+{
+ int cpu;
+ int proc_id = cpu_data(cur_cpu).phys_proc_id;
+
+ for_each_possible_cpu(cpu) {
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+ if (c->initialized && c->cpu_die_id == die_id &&
+ c->phys_proc_id == proc_id)
+ return c->logical_die_id;
+ }
+ return -1;
+}
+EXPORT_SYMBOL(topology_phys_to_logical_die);
/**
* topology_update_package_map - Update the physical to logical package map
cpu_data(cpu).logical_proc_id = new;
return 0;
}
+/**
+ * topology_update_die_map - Update the physical to logical die map
+ * @die: The die id as retrieved via CPUID
+ * @cpu: The cpu for which this is updated
+ */
+int topology_update_die_map(unsigned int die, unsigned int cpu)
+{
+ int new;
+
+ /* Already available somewhere? */
+ new = topology_phys_to_logical_die(die, cpu);
+ if (new >= 0)
+ goto found;
+
+ new = logical_die++;
+ if (new != die) {
+ pr_info("CPU %u Converting physical %u to logical die %u\n",
+ cpu, die, new);
+ }
+found:
+ cpu_data(cpu).logical_die_id = new;
+ return 0;
+}
void __init smp_store_boot_cpu_info(void)
{
*c = boot_cpu_data;
c->cpu_index = id;
topology_update_package_map(c->phys_proc_id, id);
+ topology_update_die_map(c->cpu_die_id, id);
c->initialized = true;
}
int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
if (c->phys_proc_id == o->phys_proc_id &&
+ c->cpu_die_id == o->cpu_die_id &&
per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
if (c->cpu_core_id == o->cpu_core_id)
return topology_sane(c, o, "smt");
}
} else if (c->phys_proc_id == o->phys_proc_id &&
+ c->cpu_die_id == o->cpu_die_id &&
c->cpu_core_id == o->cpu_core_id) {
return topology_sane(c, o, "smt");
}
return false;
}
+static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+{
+ if ((c->phys_proc_id == o->phys_proc_id) &&
+ (c->cpu_die_id == o->cpu_die_id))
+ return true;
+ return false;
+}
+
+
#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC)
static inline int x86_sched_itmt_flags(void)
{
cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu));
cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
cpumask_set_cpu(cpu, topology_core_cpumask(cpu));
+ cpumask_set_cpu(cpu, topology_die_cpumask(cpu));
c->booted_cores = 1;
return;
}
}
if (match_pkg(c, o) && !topology_same_node(c, o))
x86_has_numa_in_package = true;
+
+ if ((i == cpu) || (has_mp && match_die(c, o)))
+ link_mask(topology_die_cpumask, cpu, i);
}
threads = cpumask_weight(topology_sibling_cpumask(cpu));
physid_set_mask_of_physid(0, &phys_cpu_present_map);
cpumask_set_cpu(0, topology_sibling_cpumask(0));
cpumask_set_cpu(0, topology_core_cpumask(0));
+ cpumask_set_cpu(0, topology_die_cpumask(0));
}
/*
for_each_possible_cpu(i) {
zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+ zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
}
cpu_data(sibling).booted_cores--;
}
+ for_each_cpu(sibling, topology_die_cpumask(cpu))
+ cpumask_clear_cpu(cpu, topology_die_cpumask(sibling));
for_each_cpu(sibling, topology_sibling_cpumask(cpu))
cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
cpumask_clear(cpu_llc_shared_mask(cpu));
cpumask_clear(topology_sibling_cpumask(cpu));
cpumask_clear(topology_core_cpumask(cpu));
+ cpumask_clear(topology_die_cpumask(cpu));
c->cpu_core_id = 0;
c->booted_cores = 0;
cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
[CPUID_8000_0001_ECX] = {0x80000001, 0, CPUID_ECX},
[CPUID_7_0_EBX] = { 7, 0, CPUID_EBX},
[CPUID_D_1_EAX] = { 0xd, 1, CPUID_EAX},
- [CPUID_F_0_EDX] = { 0xf, 0, CPUID_EDX},
- [CPUID_F_1_EDX] = { 0xf, 1, CPUID_EDX},
[CPUID_8000_0008_EBX] = {0x80000008, 0, CPUID_EBX},
[CPUID_6_EAX] = { 6, 0, CPUID_EAX},
[CPUID_8000_000A_EDX] = {0x8000000a, 0, CPUID_EDX},
for_each_possible_cpu(i) {
zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+ zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
}
set_cpu_sibling_map(0);
case X86_VENDOR_HYGON:
case X86_VENDOR_AMD:
case X86_VENDOR_INTEL:
+ case X86_VENDOR_ZHAOXIN:
/*
* AMD Fam10h TSC will tick in all
* C/P/S0/S1 states when this bit is set.
case X86_VENDOR_AMD:
case X86_VENDOR_INTEL:
case X86_VENDOR_CENTAUR:
+ case X86_VENDOR_ZHAOXIN:
/*
* AMD Fam10h TSC will tick in all
* C/P/S0/S1 states when this bit is set.
define_id_show_func(physical_package_id);
static DEVICE_ATTR_RO(physical_package_id);
+define_id_show_func(die_id);
+static DEVICE_ATTR_RO(die_id);
+
define_id_show_func(core_id);
static DEVICE_ATTR_RO(core_id);
static DEVICE_ATTR_RO(thread_siblings);
static DEVICE_ATTR_RO(thread_siblings_list);
+define_siblings_show_func(core_cpus, sibling_cpumask);
+static DEVICE_ATTR_RO(core_cpus);
+static DEVICE_ATTR_RO(core_cpus_list);
+
define_siblings_show_func(core_siblings, core_cpumask);
static DEVICE_ATTR_RO(core_siblings);
static DEVICE_ATTR_RO(core_siblings_list);
+define_siblings_show_func(die_cpus, die_cpumask);
+static DEVICE_ATTR_RO(die_cpus);
+static DEVICE_ATTR_RO(die_cpus_list);
+
+define_siblings_show_func(package_cpus, core_cpumask);
+static DEVICE_ATTR_RO(package_cpus);
+static DEVICE_ATTR_RO(package_cpus_list);
+
#ifdef CONFIG_SCHED_BOOK
define_id_show_func(book_id);
static DEVICE_ATTR_RO(book_id);
static struct attribute *default_attrs[] = {
&dev_attr_physical_package_id.attr,
+ &dev_attr_die_id.attr,
&dev_attr_core_id.attr,
&dev_attr_thread_siblings.attr,
&dev_attr_thread_siblings_list.attr,
+ &dev_attr_core_cpus.attr,
+ &dev_attr_core_cpus_list.attr,
&dev_attr_core_siblings.attr,
&dev_attr_core_siblings_list.attr,
+ &dev_attr_die_cpus.attr,
+ &dev_attr_die_cpus_list.attr,
+ &dev_attr_package_cpus.attr,
+ &dev_attr_package_cpus_list.attr,
#ifdef CONFIG_SCHED_BOOK
&dev_attr_book_id.attr,
&dev_attr_book_siblings.attr,
struct device_attribute name_attr;
};
-/* Keep track of how many package pointers we allocated in init() */
-static int max_packages __read_mostly;
-/* Array of package pointers. Serialized by cpu hotplug lock */
-static struct platform_device **pkg_devices;
+/* Keep track of how many zone pointers we allocated in init() */
+static int max_zones __read_mostly;
+/* Array of zone pointers. Serialized by cpu hotplug lock */
+static struct platform_device **zone_devices;
static ssize_t show_label(struct device *dev,
struct device_attribute *devattr, char *buf)
static struct platform_device *coretemp_get_pdev(unsigned int cpu)
{
- int pkgid = topology_logical_package_id(cpu);
+ int id = topology_logical_die_id(cpu);
- if (pkgid >= 0 && pkgid < max_packages)
- return pkg_devices[pkgid];
+ if (id >= 0 && id < max_zones)
+ return zone_devices[id];
return NULL;
}
struct device *dev = &pdev->dev;
struct platform_data *pdata;
- /* Initialize the per-package data structures */
+ /* Initialize the per-zone data structures */
pdata = devm_kzalloc(dev, sizeof(struct platform_data), GFP_KERNEL);
if (!pdata)
return -ENOMEM;
static struct platform_device *coretemp_device_add(unsigned int cpu)
{
- int err, pkgid = topology_logical_package_id(cpu);
+ int err, zoneid = topology_logical_die_id(cpu);
struct platform_device *pdev;
- if (pkgid < 0)
+ if (zoneid < 0)
return ERR_PTR(-ENOMEM);
- pdev = platform_device_alloc(DRVNAME, pkgid);
+ pdev = platform_device_alloc(DRVNAME, zoneid);
if (!pdev)
return ERR_PTR(-ENOMEM);
return ERR_PTR(err);
}
- pkg_devices[pkgid] = pdev;
+ zone_devices[zoneid] = pdev;
return pdev;
}
* the rest.
*/
if (cpumask_empty(&pd->cpumask)) {
- pkg_devices[topology_logical_package_id(cpu)] = NULL;
+ zone_devices[topology_logical_die_id(cpu)] = NULL;
platform_device_unregister(pdev);
return 0;
}
if (!x86_match_cpu(coretemp_ids))
return -ENODEV;
- max_packages = topology_max_packages();
- pkg_devices = kcalloc(max_packages, sizeof(struct platform_device *),
+ max_zones = topology_max_packages() * topology_max_die_per_package();
+ zone_devices = kcalloc(max_zones, sizeof(struct platform_device *),
GFP_KERNEL);
- if (!pkg_devices)
+ if (!zone_devices)
return -ENOMEM;
err = platform_driver_register(&coretemp_driver);
outdrv:
platform_driver_unregister(&coretemp_driver);
- kfree(pkg_devices);
+ kfree(zone_devices);
return err;
}
module_init(coretemp_init)
{
cpuhp_remove_state(coretemp_hp_online);
platform_driver_unregister(&coretemp_driver);
- kfree(pkg_devices);
+ kfree(zone_devices);
}
module_exit(coretemp_exit)
#define power_zone_to_rapl_domain(_zone) \
container_of(_zone, struct rapl_domain, power_zone)
+/* maximum rapl package domain name: package-%d-die-%d */
+#define PACKAGE_DOMAIN_NAME_LENGTH 30
-/* Each physical package contains multiple domains, these are the common
+
+/* Each rapl package contains multiple domains, these are the common
* data across RAPL domains within a package.
*/
struct rapl_package {
- unsigned int id; /* physical package/socket id */
+ unsigned int id; /* logical die id, equals physical 1-die systems */
unsigned int nr_domains;
unsigned long domain_map; /* bit map of active domains */
unsigned int power_unit;
int lead_cpu; /* one active cpu per package for access */
/* Track active cpus */
struct cpumask cpumask;
+ char name[PACKAGE_DOMAIN_NAME_LENGTH];
};
struct rapl_defaults {
static struct rapl_domain *platform_rapl_domain; /* Platform (PSys) domain */
/* caller to ensure CPU hotplug lock is held */
-static struct rapl_package *find_package_by_id(int id)
+static struct rapl_package *rapl_find_package_domain(int cpu)
{
+ int id = topology_logical_die_id(cpu);
struct rapl_package *rp;
list_for_each_entry(rp, &rapl_packages, plist) {
value = (msr_val & TIME_UNIT_MASK) >> TIME_UNIT_OFFSET;
rp->time_unit = 1000000 / (1 << value);
- pr_debug("Core CPU package %d energy=%dpJ, time=%dus, power=%duW\n",
- rp->id, rp->energy_unit, rp->time_unit, rp->power_unit);
+ pr_debug("Core CPU %s energy=%dpJ, time=%dus, power=%duW\n",
+ rp->name, rp->energy_unit, rp->time_unit, rp->power_unit);
return 0;
}
value = (msr_val & TIME_UNIT_MASK) >> TIME_UNIT_OFFSET;
rp->time_unit = 1000000 / (1 << value);
- pr_debug("Atom package %d energy=%dpJ, time=%dus, power=%duW\n",
- rp->id, rp->energy_unit, rp->time_unit, rp->power_unit);
+ pr_debug("Atom %s energy=%dpJ, time=%dus, power=%duW\n",
+ rp->name, rp->energy_unit, rp->time_unit, rp->power_unit);
return 0;
}
u64 val;
for (dmn = 0; dmn < rp->nr_domains; dmn++) {
- pr_debug("update package %d domain %s data\n", rp->id,
+ pr_debug("update %s domain %s data\n", rp->name,
rp->domains[dmn].name);
/* exclude non-raw primitives */
for (prim = 0; prim < NR_RAW_PRIMITIVES; prim++) {
static int rapl_package_register_powercap(struct rapl_package *rp)
{
struct rapl_domain *rd;
- char dev_name[17]; /* max domain name = 7 + 1 + 8 for int + 1 for null*/
struct powercap_zone *power_zone = NULL;
int nr_pl, ret;
for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) {
if (rd->id == RAPL_DOMAIN_PACKAGE) {
nr_pl = find_nr_power_limit(rd);
- pr_debug("register socket %d package domain %s\n",
- rp->id, rd->name);
- memset(dev_name, 0, sizeof(dev_name));
- snprintf(dev_name, sizeof(dev_name), "%s-%d",
- rd->name, rp->id);
+ pr_debug("register package domain %s\n", rp->name);
power_zone = powercap_register_zone(&rd->power_zone,
control_type,
- dev_name, NULL,
+ rp->name, NULL,
&zone_ops[rd->id],
nr_pl,
&constraint_ops);
if (IS_ERR(power_zone)) {
- pr_debug("failed to register package, %d\n",
- rp->id);
+ pr_debug("failed to register power zone %s\n",
+ rp->name);
return PTR_ERR(power_zone);
}
/* track parent zone in per package/socket data */
&constraint_ops);
if (IS_ERR(power_zone)) {
- pr_debug("failed to register power_zone, %d:%s:%s\n",
- rp->id, rd->name, dev_name);
+ pr_debug("failed to register power_zone, %s:%s\n",
+ rp->name, rd->name);
ret = PTR_ERR(power_zone);
goto err_cleanup;
}
* failed after the first domain setup.
*/
while (--rd >= rp->domains) {
- pr_debug("unregister package %d domain %s\n", rp->id, rd->name);
+ pr_debug("unregister %s domain %s\n", rp->name, rd->name);
powercap_unregister_zone(control_type, &rd->power_zone);
}
rd->rpl[0].name = pl1_name;
rd->rpl[1].prim_id = PL2_ENABLE;
rd->rpl[1].name = pl2_name;
- rd->rp = find_package_by_id(0);
+ rd->rp = rapl_find_package_domain(0);
power_zone = powercap_register_zone(&rd->power_zone, control_type,
"psys", NULL,
/* check if the domain is locked by BIOS, ignore if MSR doesn't exist */
if (!rapl_read_data_raw(rd, FW_LOCK, false, &val64)) {
if (val64) {
- pr_info("RAPL package %d domain %s locked by BIOS\n",
- rd->rp->id, rd->name);
+ pr_info("RAPL %s domain %s locked by BIOS\n",
+ rd->rp->name, rd->name);
rd->state |= DOMAIN_STATE_BIOS_LOCKED;
}
}
}
rp->nr_domains = bitmap_weight(&rp->domain_map, RAPL_DOMAIN_MAX);
if (!rp->nr_domains) {
- pr_debug("no valid rapl domains found in package %d\n", rp->id);
+ pr_debug("no valid rapl domains found in %s\n", rp->name);
return -ENODEV;
}
- pr_debug("found %d domains on package %d\n", rp->nr_domains, rp->id);
+ pr_debug("found %d domains on %s\n", rp->nr_domains, rp->name);
rp->domains = kcalloc(rp->nr_domains + 1, sizeof(struct rapl_domain),
GFP_KERNEL);
rd_package = rd;
continue;
}
- pr_debug("remove package, undo power limit on %d: %s\n",
- rp->id, rd->name);
+ pr_debug("remove package, undo power limit on %s: %s\n",
+ rp->name, rd->name);
powercap_unregister_zone(control_type, &rd->power_zone);
}
/* do parent zone last */
}
/* called from CPU hotplug notifier, hotplug lock held */
-static struct rapl_package *rapl_add_package(int cpu, int pkgid)
+static struct rapl_package *rapl_add_package(int cpu)
{
+ int id = topology_logical_die_id(cpu);
struct rapl_package *rp;
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
int ret;
rp = kzalloc(sizeof(struct rapl_package), GFP_KERNEL);
return ERR_PTR(-ENOMEM);
/* add the new package to the list */
- rp->id = pkgid;
+ rp->id = id;
rp->lead_cpu = cpu;
+ if (topology_max_die_per_package() > 1)
+ snprintf(rp->name, PACKAGE_DOMAIN_NAME_LENGTH,
+ "package-%d-die-%d", c->phys_proc_id, c->cpu_die_id);
+ else
+ snprintf(rp->name, PACKAGE_DOMAIN_NAME_LENGTH, "package-%d",
+ c->phys_proc_id);
+
/* check if the package contains valid domains */
if (rapl_detect_domains(rp, cpu) ||
rapl_defaults->check_unit(rp, cpu)) {
*/
static int rapl_cpu_online(unsigned int cpu)
{
- int pkgid = topology_physical_package_id(cpu);
struct rapl_package *rp;
- rp = find_package_by_id(pkgid);
+ rp = rapl_find_package_domain(cpu);
if (!rp) {
- rp = rapl_add_package(cpu, pkgid);
+ rp = rapl_add_package(cpu);
if (IS_ERR(rp))
return PTR_ERR(rp);
}
static int rapl_cpu_down_prep(unsigned int cpu)
{
- int pkgid = topology_physical_package_id(cpu);
struct rapl_package *rp;
int lead_cpu;
- rp = find_package_by_id(pkgid);
+ rp = rapl_find_package_domain(cpu);
if (!rp)
return 0;
*/
#define MAX_NUMBER_OF_TRIPS 2
-struct pkg_device {
+struct zone_device {
int cpu;
bool work_scheduled;
u32 tj_max;
.no_hwmon = true,
};
-/* Keep track of how many package pointers we allocated in init() */
-static int max_packages __read_mostly;
-/* Array of package pointers */
-static struct pkg_device **packages;
+/* Keep track of how many zone pointers we allocated in init() */
+static int max_id __read_mostly;
+/* Array of zone pointers */
+static struct zone_device **zones;
/* Serializes interrupt notification, work and hotplug */
static DEFINE_SPINLOCK(pkg_temp_lock);
/* Protects zone operation in the work function against hotplug removal */
*
* - Other callsites: Must hold pkg_temp_lock
*/
-static struct pkg_device *pkg_temp_thermal_get_dev(unsigned int cpu)
+static struct zone_device *pkg_temp_thermal_get_dev(unsigned int cpu)
{
- int pkgid = topology_logical_package_id(cpu);
+ int id = topology_logical_die_id(cpu);
- if (pkgid >= 0 && pkgid < max_packages)
- return packages[pkgid];
+ if (id >= 0 && id < max_id)
+ return zones[id];
return NULL;
}
static int sys_get_curr_temp(struct thermal_zone_device *tzd, int *temp)
{
- struct pkg_device *pkgdev = tzd->devdata;
+ struct zone_device *zonedev = tzd->devdata;
u32 eax, edx;
- rdmsr_on_cpu(pkgdev->cpu, MSR_IA32_PACKAGE_THERM_STATUS, &eax, &edx);
+ rdmsr_on_cpu(zonedev->cpu, MSR_IA32_PACKAGE_THERM_STATUS,
+ &eax, &edx);
if (eax & 0x80000000) {
- *temp = pkgdev->tj_max - ((eax >> 16) & 0x7f) * 1000;
+ *temp = zonedev->tj_max - ((eax >> 16) & 0x7f) * 1000;
pr_debug("sys_get_curr_temp %d\n", *temp);
return 0;
}
static int sys_get_trip_temp(struct thermal_zone_device *tzd,
int trip, int *temp)
{
- struct pkg_device *pkgdev = tzd->devdata;
+ struct zone_device *zonedev = tzd->devdata;
unsigned long thres_reg_value;
u32 mask, shift, eax, edx;
int ret;
shift = THERM_SHIFT_THRESHOLD0;
}
- ret = rdmsr_on_cpu(pkgdev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT,
+ ret = rdmsr_on_cpu(zonedev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT,
&eax, &edx);
if (ret < 0)
return ret;
thres_reg_value = (eax & mask) >> shift;
if (thres_reg_value)
- *temp = pkgdev->tj_max - thres_reg_value * 1000;
+ *temp = zonedev->tj_max - thres_reg_value * 1000;
else
*temp = 0;
pr_debug("sys_get_trip_temp %d\n", *temp);
static int
sys_set_trip_temp(struct thermal_zone_device *tzd, int trip, int temp)
{
- struct pkg_device *pkgdev = tzd->devdata;
+ struct zone_device *zonedev = tzd->devdata;
u32 l, h, mask, shift, intr;
int ret;
- if (trip >= MAX_NUMBER_OF_TRIPS || temp >= pkgdev->tj_max)
+ if (trip >= MAX_NUMBER_OF_TRIPS || temp >= zonedev->tj_max)
return -EINVAL;
- ret = rdmsr_on_cpu(pkgdev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT,
+ ret = rdmsr_on_cpu(zonedev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT,
&l, &h);
if (ret < 0)
return ret;
if (!temp) {
l &= ~intr;
} else {
- l |= (pkgdev->tj_max - temp)/1000 << shift;
+ l |= (zonedev->tj_max - temp)/1000 << shift;
l |= intr;
}
- return wrmsr_on_cpu(pkgdev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
+ return wrmsr_on_cpu(zonedev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT,
+ l, h);
}
static int sys_get_trip_type(struct thermal_zone_device *thermal, int trip,
{
struct thermal_zone_device *tzone = NULL;
int cpu = smp_processor_id();
- struct pkg_device *pkgdev;
+ struct zone_device *zonedev;
u64 msr_val, wr_val;
mutex_lock(&thermal_zone_mutex);
spin_lock_irq(&pkg_temp_lock);
++pkg_work_cnt;
- pkgdev = pkg_temp_thermal_get_dev(cpu);
- if (!pkgdev) {
+ zonedev = pkg_temp_thermal_get_dev(cpu);
+ if (!zonedev) {
spin_unlock_irq(&pkg_temp_lock);
mutex_unlock(&thermal_zone_mutex);
return;
}
- pkgdev->work_scheduled = false;
+ zonedev->work_scheduled = false;
rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val);
wr_val = msr_val & ~(THERM_LOG_THRESHOLD0 | THERM_LOG_THRESHOLD1);
if (wr_val != msr_val) {
wrmsrl(MSR_IA32_PACKAGE_THERM_STATUS, wr_val);
- tzone = pkgdev->tzone;
+ tzone = zonedev->tzone;
}
enable_pkg_thres_interrupt();
static int pkg_thermal_notify(u64 msr_val)
{
int cpu = smp_processor_id();
- struct pkg_device *pkgdev;
+ struct zone_device *zonedev;
unsigned long flags;
spin_lock_irqsave(&pkg_temp_lock, flags);
disable_pkg_thres_interrupt();
/* Work is per package, so scheduling it once is enough. */
- pkgdev = pkg_temp_thermal_get_dev(cpu);
- if (pkgdev && !pkgdev->work_scheduled) {
- pkgdev->work_scheduled = true;
- pkg_thermal_schedule_work(pkgdev->cpu, &pkgdev->work);
+ zonedev = pkg_temp_thermal_get_dev(cpu);
+ if (zonedev && !zonedev->work_scheduled) {
+ zonedev->work_scheduled = true;
+ pkg_thermal_schedule_work(zonedev->cpu, &zonedev->work);
}
spin_unlock_irqrestore(&pkg_temp_lock, flags);
static int pkg_temp_thermal_device_add(unsigned int cpu)
{
- int pkgid = topology_logical_package_id(cpu);
+ int id = topology_logical_die_id(cpu);
u32 tj_max, eax, ebx, ecx, edx;
- struct pkg_device *pkgdev;
+ struct zone_device *zonedev;
int thres_count, err;
- if (pkgid >= max_packages)
+ if (id >= max_id)
return -ENOMEM;
cpuid(6, &eax, &ebx, &ecx, &edx);
if (err)
return err;
- pkgdev = kzalloc(sizeof(*pkgdev), GFP_KERNEL);
- if (!pkgdev)
+ zonedev = kzalloc(sizeof(*zonedev), GFP_KERNEL);
+ if (!zonedev)
return -ENOMEM;
- INIT_DELAYED_WORK(&pkgdev->work, pkg_temp_thermal_threshold_work_fn);
- pkgdev->cpu = cpu;
- pkgdev->tj_max = tj_max;
- pkgdev->tzone = thermal_zone_device_register("x86_pkg_temp",
+ INIT_DELAYED_WORK(&zonedev->work, pkg_temp_thermal_threshold_work_fn);
+ zonedev->cpu = cpu;
+ zonedev->tj_max = tj_max;
+ zonedev->tzone = thermal_zone_device_register("x86_pkg_temp",
thres_count,
(thres_count == MAX_NUMBER_OF_TRIPS) ? 0x03 : 0x01,
- pkgdev, &tzone_ops, &pkg_temp_tz_params, 0, 0);
- if (IS_ERR(pkgdev->tzone)) {
- err = PTR_ERR(pkgdev->tzone);
- kfree(pkgdev);
+ zonedev, &tzone_ops, &pkg_temp_tz_params, 0, 0);
+ if (IS_ERR(zonedev->tzone)) {
+ err = PTR_ERR(zonedev->tzone);
+ kfree(zonedev);
return err;
}
/* Store MSR value for package thermal interrupt, to restore at exit */
- rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, pkgdev->msr_pkg_therm_low,
- pkgdev->msr_pkg_therm_high);
+ rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, zonedev->msr_pkg_therm_low,
+ zonedev->msr_pkg_therm_high);
- cpumask_set_cpu(cpu, &pkgdev->cpumask);
+ cpumask_set_cpu(cpu, &zonedev->cpumask);
spin_lock_irq(&pkg_temp_lock);
- packages[pkgid] = pkgdev;
+ zones[id] = zonedev;
spin_unlock_irq(&pkg_temp_lock);
return 0;
}
static int pkg_thermal_cpu_offline(unsigned int cpu)
{
- struct pkg_device *pkgdev = pkg_temp_thermal_get_dev(cpu);
+ struct zone_device *zonedev = pkg_temp_thermal_get_dev(cpu);
bool lastcpu, was_target;
int target;
- if (!pkgdev)
+ if (!zonedev)
return 0;
- target = cpumask_any_but(&pkgdev->cpumask, cpu);
- cpumask_clear_cpu(cpu, &pkgdev->cpumask);
+ target = cpumask_any_but(&zonedev->cpumask, cpu);
+ cpumask_clear_cpu(cpu, &zonedev->cpumask);
lastcpu = target >= nr_cpu_ids;
/*
* Remove the sysfs files, if this is the last cpu in the package
* before doing further cleanups.
*/
if (lastcpu) {
- struct thermal_zone_device *tzone = pkgdev->tzone;
+ struct thermal_zone_device *tzone = zonedev->tzone;
/*
* We must protect against a work function calling
* won't try to call.
*/
mutex_lock(&thermal_zone_mutex);
- pkgdev->tzone = NULL;
+ zonedev->tzone = NULL;
mutex_unlock(&thermal_zone_mutex);
thermal_zone_device_unregister(tzone);
* one. When we drop the lock, then the interrupt notify function
* will see the new target.
*/
- was_target = pkgdev->cpu == cpu;
- pkgdev->cpu = target;
+ was_target = zonedev->cpu == cpu;
+ zonedev->cpu = target;
/*
* If this is the last CPU in the package remove the package
* worker will see the package anymore.
*/
if (lastcpu) {
- packages[topology_logical_package_id(cpu)] = NULL;
+ zones[topology_logical_die_id(cpu)] = NULL;
/* After this point nothing touches the MSR anymore. */
wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT,
- pkgdev->msr_pkg_therm_low, pkgdev->msr_pkg_therm_high);
+ zonedev->msr_pkg_therm_low, zonedev->msr_pkg_therm_high);
}
/*
* Check whether there is work scheduled and whether the work is
* targeted at the outgoing CPU.
*/
- if (pkgdev->work_scheduled && was_target) {
+ if (zonedev->work_scheduled && was_target) {
/*
* To cancel the work we need to drop the lock, otherwise
* we might deadlock if the work needs to be flushed.
*/
spin_unlock_irq(&pkg_temp_lock);
- cancel_delayed_work_sync(&pkgdev->work);
+ cancel_delayed_work_sync(&zonedev->work);
spin_lock_irq(&pkg_temp_lock);
/*
* If this is not the last cpu in the package and the work
* need to reschedule the work, otherwise the interrupt
* stays disabled forever.
*/
- if (!lastcpu && pkgdev->work_scheduled)
- pkg_thermal_schedule_work(target, &pkgdev->work);
+ if (!lastcpu && zonedev->work_scheduled)
+ pkg_thermal_schedule_work(target, &zonedev->work);
}
spin_unlock_irq(&pkg_temp_lock);
/* Final cleanup if this is the last cpu */
if (lastcpu)
- kfree(pkgdev);
+ kfree(zonedev);
return 0;
}
static int pkg_thermal_cpu_online(unsigned int cpu)
{
- struct pkg_device *pkgdev = pkg_temp_thermal_get_dev(cpu);
+ struct zone_device *zonedev = pkg_temp_thermal_get_dev(cpu);
struct cpuinfo_x86 *c = &cpu_data(cpu);
/* Paranoia check */
return -ENODEV;
/* If the package exists, nothing to do */
- if (pkgdev) {
- cpumask_set_cpu(cpu, &pkgdev->cpumask);
+ if (zonedev) {
+ cpumask_set_cpu(cpu, &zonedev->cpumask);
return 0;
}
return pkg_temp_thermal_device_add(cpu);
if (!x86_match_cpu(pkg_temp_thermal_ids))
return -ENODEV;
- max_packages = topology_max_packages();
- packages = kcalloc(max_packages, sizeof(struct pkg_device *),
+ max_id = topology_max_packages() * topology_max_die_per_package();
+ zones = kcalloc(max_id, sizeof(struct zone_device *),
GFP_KERNEL);
- if (!packages)
+ if (!zones)
return -ENOMEM;
ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "thermal/x86_pkg:online",
return 0;
err:
- kfree(packages);
+ kfree(zones);
return ret;
}
module_init(pkg_temp_thermal_init)
cpuhp_remove_state(pkg_thermal_hp_state);
debugfs_remove_recursive(debugfs);
- kfree(packages);
+ kfree(zones);
}
module_exit(pkg_temp_thermal_exit)
}
EXPORT_SYMBOL_GPL(sysfs_create_group);
+static int internal_create_groups(struct kobject *kobj, int update,
+ const struct attribute_group **groups)
+{
+ int error = 0;
+ int i;
+
+ if (!groups)
+ return 0;
+
+ for (i = 0; groups[i]; i++) {
+ error = internal_create_group(kobj, update, groups[i]);
+ if (error) {
+ while (--i >= 0)
+ sysfs_remove_group(kobj, groups[i]);
+ break;
+ }
+ }
+ return error;
+}
+
/**
* sysfs_create_groups - given a directory kobject, create a bunch of attribute groups
* @kobj: The kobject to create the group on
int sysfs_create_groups(struct kobject *kobj,
const struct attribute_group **groups)
{
- int error = 0;
- int i;
-
- if (!groups)
- return 0;
-
- for (i = 0; groups[i]; i++) {
- error = sysfs_create_group(kobj, groups[i]);
- if (error) {
- while (--i >= 0)
- sysfs_remove_group(kobj, groups[i]);
- break;
- }
- }
- return error;
+ return internal_create_groups(kobj, 0, groups);
}
EXPORT_SYMBOL_GPL(sysfs_create_groups);
+/**
+ * sysfs_update_groups - given a directory kobject, create a bunch of attribute groups
+ * @kobj: The kobject to update the group on
+ * @groups: The attribute groups to update, NULL terminated
+ *
+ * This function update a bunch of attribute groups. If an error occurs when
+ * updating a group, all previously updated groups will be removed together
+ * with already existing (not updated) attributes.
+ *
+ * Returns 0 on success or error code from sysfs_update_group on failure.
+ */
+int sysfs_update_groups(struct kobject *kobj,
+ const struct attribute_group **groups)
+{
+ return internal_create_groups(kobj, 1, groups);
+}
+EXPORT_SYMBOL_GPL(sysfs_update_groups);
+
/**
* sysfs_update_group - given a directory kobject, update an attribute group
* @kobj: The kobject to update the group on
struct module *module;
struct device *dev;
const struct attribute_group **attr_groups;
+ const struct attribute_group **attr_update;
const char *name;
int type;
int nr_stat;
int nr_freq;
int rotate_disable;
+ /*
+ * Set when nr_events != nr_active, except tolerant to events not
+ * necessary to be active due to scheduling constraints, such as cgroups.
+ */
+ int rotate_necessary;
refcount_t refcount;
struct task_struct *task;
const struct attribute_group *grp);
int __must_check sysfs_create_groups(struct kobject *kobj,
const struct attribute_group **groups);
+int __must_check sysfs_update_groups(struct kobject *kobj,
+ const struct attribute_group **groups);
int sysfs_update_group(struct kobject *kobj,
const struct attribute_group *grp);
void sysfs_remove_group(struct kobject *kobj,
return 0;
}
+static inline int sysfs_update_groups(struct kobject *kobj,
+ const struct attribute_group **groups)
+{
+ return 0;
+}
+
static inline int sysfs_update_group(struct kobject *kobj,
const struct attribute_group *grp)
{
#ifndef topology_physical_package_id
#define topology_physical_package_id(cpu) ((void)(cpu), -1)
#endif
+#ifndef topology_die_id
+#define topology_die_id(cpu) ((void)(cpu), -1)
+#endif
#ifndef topology_core_id
#define topology_core_id(cpu) ((void)(cpu), 0)
#endif
#ifndef topology_core_cpumask
#define topology_core_cpumask(cpu) cpumask_of(cpu)
#endif
+#ifndef topology_die_cpumask
+#define topology_die_cpumask(cpu) cpumask_of(cpu)
+#endif
#ifdef CONFIG_SCHED_SMT
static inline const struct cpumask *cpu_smt_mask(int cpu)
if (!ctx->nr_active || !(is_active & EVENT_ALL))
return;
+ /*
+ * If we had been multiplexing, no rotations are necessary, now no events
+ * are active.
+ */
+ ctx->rotate_necessary = 0;
+
perf_pmu_disable(ctx->pmu);
if (is_active & EVENT_PINNED) {
list_for_each_entry_safe(event, tmp, &ctx->pinned_active, active_list)
return 0;
if (group_can_go_on(event, sid->cpuctx, sid->can_add_hw)) {
- if (!group_sched_in(event, sid->cpuctx, sid->ctx))
- list_add_tail(&event->active_list, &sid->ctx->flexible_active);
- else
+ int ret = group_sched_in(event, sid->cpuctx, sid->ctx);
+ if (ret) {
sid->can_add_hw = 0;
+ sid->ctx->rotate_necessary = 1;
+ return 0;
+ }
+ list_add_tail(&event->active_list, &sid->ctx->flexible_active);
}
return 0;
static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
{
struct perf_event *cpu_event = NULL, *task_event = NULL;
- bool cpu_rotate = false, task_rotate = false;
- struct perf_event_context *ctx = NULL;
+ struct perf_event_context *task_ctx = NULL;
+ int cpu_rotate, task_rotate;
/*
* Since we run this from IRQ context, nobody can install new
* events, thus the event count values are stable.
*/
- if (cpuctx->ctx.nr_events) {
- if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
- cpu_rotate = true;
- }
-
- ctx = cpuctx->task_ctx;
- if (ctx && ctx->nr_events) {
- if (ctx->nr_events != ctx->nr_active)
- task_rotate = true;
- }
+ cpu_rotate = cpuctx->ctx.rotate_necessary;
+ task_ctx = cpuctx->task_ctx;
+ task_rotate = task_ctx ? task_ctx->rotate_necessary : 0;
if (!(cpu_rotate || task_rotate))
return false;
perf_pmu_disable(cpuctx->ctx.pmu);
if (task_rotate)
- task_event = ctx_first_active(ctx);
+ task_event = ctx_first_active(task_ctx);
if (cpu_rotate)
cpu_event = ctx_first_active(&cpuctx->ctx);
* As per the order given at ctx_resched() first 'pop' task flexible
* and then, if needed CPU flexible.
*/
- if (task_event || (ctx && cpu_event))
- ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
+ if (task_event || (task_ctx && cpu_event))
+ ctx_sched_out(task_ctx, cpuctx, EVENT_FLEXIBLE);
if (cpu_event)
cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
if (task_event)
- rotate_ctx(ctx, task_event);
+ rotate_ctx(task_ctx, task_event);
if (cpu_event)
rotate_ctx(&cpuctx->ctx, cpu_event);
- perf_event_sched_in(cpuctx, ctx, current);
+ perf_event_sched_in(cpuctx, task_ctx, current);
perf_pmu_enable(cpuctx->ctx.pmu);
perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
if (event->hw.state & PERF_HES_STOPPED)
return 0;
/*
- * All tracepoints are from kernel-space.
+ * If exclude_kernel, only trace user-space tracepoints (uprobes)
*/
- if (event->attr.exclude_kernel)
+ if (event->attr.exclude_kernel && !user_mode(regs))
return 0;
if (!perf_tp_filter_match(event, data))
if (ret)
goto del_dev;
+ if (pmu->attr_update)
+ ret = sysfs_update_groups(&pmu->dev->kobj, pmu->attr_update);
+
+ if (ret)
+ goto del_dev;
+
out:
return ret;
call->event.funcs = &uprobe_funcs;
call->class->define_fields = uprobe_event_define_fields;
- call->flags = TRACE_EVENT_FL_UPROBE;
+ call->flags = TRACE_EVENT_FL_UPROBE | TRACE_EVENT_FL_CAP_ANY;
call->class->reg = trace_uprobe_register;
call->data = tu;
}
fortify-source \
sync-compare-and-swap \
get_current_dir_name \
+ gettid \
glibc \
gtk2 \
gtk2-infobar \
libpython \
libpython-version \
libslang \
+ libslang-include-subdir \
libcrypto \
libunwind \
pthread-attr-setaffinity-np \
numa_num_possible_cpus \
libperl \
libpython \
- libslang \
libcrypto \
libunwind \
libdw-dwarf-unwind \
test-libpython.bin \
test-libpython-version.bin \
test-libslang.bin \
+ test-libslang-include-subdir.bin \
test-libcrypto.bin \
test-libunwind.bin \
test-libunwind-debug-frame.bin \
test-get_cpuid.bin \
test-sdt.bin \
test-cxx.bin \
+ test-gettid.bin \
test-jvmti.bin \
test-jvmti-cmlr.bin \
test-sched_getcpu.bin \
$(BUILD) -laudit
$(OUTPUT)test-libslang.bin:
- $(BUILD) -I/usr/include/slang -lslang
+ $(BUILD) -lslang
+
+$(OUTPUT)test-libslang-include-subdir.bin:
+ $(BUILD) -lslang
$(OUTPUT)test-libcrypto.bin:
$(BUILD) -lcrypto
$(OUTPUT)test-cxx.bin:
$(BUILDXX) -std=gnu++11
+$(OUTPUT)test-gettid.bin:
+ $(BUILD)
+
$(OUTPUT)test-jvmti.bin:
$(BUILD)
# include "test-get_current_dir_name.c"
#undef main
+#define main main_test_gettid
+# include "test-gettid.c"
+#undef main
+
#define main main_test_glibc
# include "test-glibc.c"
#undef main
# include "test-disassembler-four-args.c"
#undef main
-#define main main_test_zstd
+#define main main_test_libzstd
# include "test-libzstd.c"
#undef main
main_test_libelf();
main_test_libelf_mmap();
main_test_get_current_dir_name();
+ main_test_gettid();
main_test_glibc();
main_test_dwarf();
main_test_dwarf_getlocations();
+// SPDX-License-Identifier: GPL-2.0
#include <stdio.h>
int main(void)
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+#define _GNU_SOURCE
+#include <unistd.h>
+
+int main(void)
+{
+ return gettid();
+}
+
+#undef _GNU_SOURCE
+// SPDX-License-Identifier: GPL-2.0
#include <stdio.h>
int main(void)
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <slang/slang.h>
+
+int main(void)
+{
+ return SLsmg_init_smg();
+}
+// SPDX-License-Identifier: GPL-2.0
#define _GNU_SOURCE
#include <sched.h>
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_CTYPE_H
+#define _LINUX_CTYPE_H
+
+/*
+ * NOTE! This ctype does not handle EOF like the standard C
+ * library is required to.
+ */
+
+#define _U 0x01 /* upper */
+#define _L 0x02 /* lower */
+#define _D 0x04 /* digit */
+#define _C 0x08 /* cntrl */
+#define _P 0x10 /* punct */
+#define _S 0x20 /* white space (space/lf/tab) */
+#define _X 0x40 /* hex digit */
+#define _SP 0x80 /* hard space (0x20) */
+
+extern const unsigned char _ctype[];
+
+#define __ismask(x) (_ctype[(int)(unsigned char)(x)])
+
+#define isalnum(c) ((__ismask(c)&(_U|_L|_D)) != 0)
+#define isalpha(c) ((__ismask(c)&(_U|_L)) != 0)
+#define iscntrl(c) ((__ismask(c)&(_C)) != 0)
+static inline int __isdigit(int c)
+{
+ return '0' <= c && c <= '9';
+}
+#define isdigit(c) __isdigit(c)
+#define isgraph(c) ((__ismask(c)&(_P|_U|_L|_D)) != 0)
+#define islower(c) ((__ismask(c)&(_L)) != 0)
+#define isprint(c) ((__ismask(c)&(_P|_U|_L|_D|_SP)) != 0)
+#define ispunct(c) ((__ismask(c)&(_P)) != 0)
+/* Note: isspace() must return false for %NUL-terminator */
+#define isspace(c) ((__ismask(c)&(_S)) != 0)
+#define isupper(c) ((__ismask(c)&(_U)) != 0)
+#define isxdigit(c) ((__ismask(c)&(_D|_X)) != 0)
+
+#define isascii(c) (((unsigned char)(c))<=0x7f)
+#define toascii(c) (((unsigned char)(c))&0x7f)
+
+static inline unsigned char __tolower(unsigned char c)
+{
+ if (isupper(c))
+ c -= 'A'-'a';
+ return c;
+}
+
+static inline unsigned char __toupper(unsigned char c)
+{
+ if (islower(c))
+ c -= 'a'-'A';
+ return c;
+}
+
+#define tolower(c) __tolower(c)
+#define toupper(c) __toupper(c)
+
+/*
+ * Fast implementation of tolower() for internal usage. Do not use in your
+ * code.
+ */
+static inline char _tolower(const char c)
+{
+ return c | 0x20;
+}
+
+/* Fast check for octal digit */
+static inline int isodigit(const char c)
+{
+ return c >= '0' && c <= '7';
+}
+
+#endif
int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
int scnprintf(char * buf, size_t size, const char * fmt, ...);
+int scnprintf_pad(char * buf, size_t size, const char * fmt, ...);
#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
void *memdup(const void *src, size_t len);
+char **argv_split(const char *str, int *argcp);
+void argv_free(char **argv);
+
int strtobool(const char *s, bool *res);
/*
char *str_error_r(int errnum, char *buf, size_t buflen);
+char *strreplace(char *s, char old, char new);
+
/**
* strstarts - does @str start with @prefix?
* @str: string to examine
return strncmp(str, prefix, strlen(prefix)) == 0;
}
-#endif /* _LINUX_STRING_H_ */
+extern char * __must_check skip_spaces(const char *);
+
+extern char *strim(char *);
+
+#endif /* _TOOLS_LINUX_STRING_H_ */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Helper function for splitting a string into an argv-like array.
+ */
+
+#include <stdlib.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/string.h>
+
+static const char *skip_arg(const char *cp)
+{
+ while (*cp && !isspace(*cp))
+ cp++;
+
+ return cp;
+}
+
+static int count_argc(const char *str)
+{
+ int count = 0;
+
+ while (*str) {
+ str = skip_spaces(str);
+ if (*str) {
+ count++;
+ str = skip_arg(str);
+ }
+ }
+
+ return count;
+}
+
+/**
+ * argv_free - free an argv
+ * @argv - the argument vector to be freed
+ *
+ * Frees an argv and the strings it points to.
+ */
+void argv_free(char **argv)
+{
+ char **p;
+ for (p = argv; *p; p++) {
+ free(*p);
+ *p = NULL;
+ }
+
+ free(argv);
+}
+
+/**
+ * argv_split - split a string at whitespace, returning an argv
+ * @str: the string to be split
+ * @argcp: returned argument count
+ *
+ * Returns an array of pointers to strings which are split out from
+ * @str. This is performed by strictly splitting on white-space; no
+ * quote processing is performed. Multiple whitespace characters are
+ * considered to be a single argument separator. The returned array
+ * is always NULL-terminated. Returns NULL on memory allocation
+ * failure.
+ */
+char **argv_split(const char *str, int *argcp)
+{
+ int argc = count_argc(str);
+ char **argv = calloc(argc + 1, sizeof(*argv));
+ char **argvp;
+
+ if (argv == NULL)
+ goto out;
+
+ if (argcp)
+ *argcp = argc;
+
+ argvp = argv;
+
+ while (*str) {
+ str = skip_spaces(str);
+
+ if (*str) {
+ const char *p = str;
+ char *t;
+
+ str = skip_arg(str);
+
+ t = strndup(p, str-p);
+ if (t == NULL)
+ goto fail;
+ *argvp++ = t;
+ }
+ }
+ *argvp = NULL;
+
+out:
+ return argv;
+
+fail:
+ argv_free(argv);
+ return NULL;
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/lib/ctype.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+#include <linux/ctype.h>
+#include <linux/compiler.h>
+
+const unsigned char _ctype[] = {
+_C,_C,_C,_C,_C,_C,_C,_C, /* 0-7 */
+_C,_C|_S,_C|_S,_C|_S,_C|_S,_C|_S,_C,_C, /* 8-15 */
+_C,_C,_C,_C,_C,_C,_C,_C, /* 16-23 */
+_C,_C,_C,_C,_C,_C,_C,_C, /* 24-31 */
+_S|_SP,_P,_P,_P,_P,_P,_P,_P, /* 32-39 */
+_P,_P,_P,_P,_P,_P,_P,_P, /* 40-47 */
+_D,_D,_D,_D,_D,_D,_D,_D, /* 48-55 */
+_D,_D,_P,_P,_P,_P,_P,_P, /* 56-63 */
+_P,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U, /* 64-71 */
+_U,_U,_U,_U,_U,_U,_U,_U, /* 72-79 */
+_U,_U,_U,_U,_U,_U,_U,_U, /* 80-87 */
+_U,_U,_U,_P,_P,_P,_P,_P, /* 88-95 */
+_P,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L, /* 96-103 */
+_L,_L,_L,_L,_L,_L,_L,_L, /* 104-111 */
+_L,_L,_L,_L,_L,_L,_L,_L, /* 112-119 */
+_L,_L,_L,_P,_P,_P,_P,_C, /* 120-127 */
+0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 128-143 */
+0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 144-159 */
+_S|_SP,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P, /* 160-175 */
+_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P, /* 176-191 */
+_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U, /* 192-207 */
+_U,_U,_U,_U,_U,_U,_U,_P,_U,_U,_U,_U,_U,_U,_U,_L, /* 208-223 */
+_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L, /* 224-239 */
+_L,_L,_L,_L,_L,_L,_L,_P,_L,_L,_L,_L,_L,_L,_L,_L}; /* 240-255 */
#include <string.h>
#include <errno.h>
#include <linux/string.h>
+#include <linux/ctype.h>
#include <linux/compiler.h>
/**
}
return ret;
}
+
+/**
+ * skip_spaces - Removes leading whitespace from @str.
+ * @str: The string to be stripped.
+ *
+ * Returns a pointer to the first non-whitespace character in @str.
+ */
+char *skip_spaces(const char *str)
+{
+ while (isspace(*str))
+ ++str;
+ return (char *)str;
+}
+
+/**
+ * strim - Removes leading and trailing whitespace from @s.
+ * @s: The string to be stripped.
+ *
+ * Note that the first trailing whitespace is replaced with a %NUL-terminator
+ * in the given string @s. Returns a pointer to the first non-whitespace
+ * character in @s.
+ */
+char *strim(char *s)
+{
+ size_t size;
+ char *end;
+
+ size = strlen(s);
+ if (!size)
+ return s;
+
+ end = s + size - 1;
+ while (end >= s && isspace(*end))
+ end--;
+ *(end + 1) = '\0';
+
+ return skip_spaces(s);
+}
+
+/**
+ * strreplace - Replace all occurrences of character in string.
+ * @s: The string to operate on.
+ * @old: The character being replaced.
+ * @new: The character @old is replaced with.
+ *
+ * Returns pointer to the nul byte at the end of @s.
+ */
+char *strreplace(char *s, char old, char new)
+{
+ for (; *s; ++s)
+ if (*s == old)
+ *s = new;
+ return s;
+}
// SPDX-License-Identifier: GPL-2.0
-#include <ctype.h>
#include "symbol/kallsyms.h"
#include <stdio.h>
#include <stdlib.h>
return symbol_type == 'T' || symbol_type == 'W';
}
+/*
+ * While we find nice hex chars, build a long_val.
+ * Return number of chars processed.
+ */
+int hex2u64(const char *ptr, u64 *long_val)
+{
+ char *p;
+
+ *long_val = strtoull(ptr, &p, 16);
+
+ return p - ptr;
+}
+
int kallsyms__parse(const char *filename, void *arg,
int (*process_symbol)(void *arg, const char *name,
char type, u64 start))
return isupper(type) ? STB_GLOBAL : STB_LOCAL;
}
+int hex2u64(const char *ptr, u64 *long_val);
+
u8 kallsyms2elf_type(char type);
bool kallsyms__is_function(char symbol_type);
return (i >= ssize) ? (ssize - 1) : i;
}
+
+int scnprintf_pad(char * buf, size_t size, const char * fmt, ...)
+{
+ ssize_t ssize = size;
+ va_list args;
+ int i;
+
+ va_start(args, fmt);
+ i = vscnprintf(buf, size, fmt, args);
+ va_end(args);
+
+ if (i < (int) size) {
+ for (; i < (int) size; i++)
+ buf[i] = ' ';
+ buf[i] = 0x0;
+ }
+
+ return (i >= ssize) ? (ssize - 1) : i;
+}
objtool-y += objtool.o
objtool-y += libstring.o
+objtool-y += libctype.o
objtool-y += str_error_r.o
CFLAGS += -I$(srctree)/tools/lib
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
+$(OUTPUT)libctype.o: ../lib/ctype.c FORCE
+ $(call rule_mkdir)
+ $(call if_changed_dep,cc_o_c)
+
$(OUTPUT)str_error_r.o: ../lib/str_error_r.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
--- /dev/null
+Database Export
+===============
+
+perf tool's python scripting engine:
+
+ tools/perf/util/scripting-engines/trace-event-python.c
+
+supports scripts:
+
+ tools/perf/scripts/python/export-to-sqlite.py
+ tools/perf/scripts/python/export-to-postgresql.py
+
+which export data to a SQLite3 or PostgreSQL database.
+
+The export process provides records with unique sequential ids which allows the
+data to be imported directly to a database and provides the relationships
+between tables.
+
+Over time it is possible to continue to expand the export while maintaining
+backward and forward compatibility, by following some simple rules:
+
+1. Because of the nature of SQL, existing tables and columns can continue to be
+used so long as the names and meanings (and to some extent data types) remain
+the same.
+
+2. New tables and columns can be added, without affecting existing SQL queries,
+so long as the new names are unique.
+
+3. Scripts that use a database (e.g. exported-sql-viewer.py) can maintain
+backward compatibility by testing for the presence of new tables and columns
+before using them. e.g. function IsSelectable() in exported-sql-viewer.py
+
+4. The export scripts themselves maintain forward compatibility (i.e. an existing
+script will continue to work with new versions of perf) by accepting a variable
+number of arguments (e.g. def call_return_table(*x)) i.e. perf can pass more
+arguments which old scripts will ignore.
+
+5. The scripting engine tests for the existence of script handler functions
+before calling them. The scripting engine can also test for the support of new
+or optional features by checking for the existence and value of script global
+variables.
To represent software control flow, "branches" samples are produced. By default
a branch sample is synthesized for every single branch. To get an idea what
-data is available you can use the 'perf script' tool with no parameters, which
-will list all the samples.
+data is available you can use the 'perf script' tool with all itrace sampling
+options, which will list all the samples.
perf record -e intel_pt//u ls
- perf script
+ perf script --itrace=ibxwpe
An interesting field that is not printed by default is 'flags' which can be
displayed as follows:
- perf script -Fcomm,tid,pid,time,cpu,event,trace,ip,sym,dso,addr,symoff,flags
+ perf script --itrace=ibxwpe -F+flags
The flags are "bcrosyiABEx" which stand for branch, call, return, conditional,
system, asynchronous, interrupt, transaction abort, trace begin, trace end, and
in transaction, respectively.
+Another interesting field that is not printed by default is 'ipc' which can be
+displayed as follows:
+
+ perf script --itrace=be -F+ipc
+
+There are two ways that instructions-per-cycle (IPC) can be calculated depending
+on the recording.
+
+If the 'cyc' config term (see config terms section below) was used, then IPC is
+calculated using the cycle count from CYC packets, otherwise MTC packets are
+used - refer to the 'mtc' config term. When MTC is used, however, the values
+are less accurate because the timing is less accurate.
+
+Because Intel PT does not update the cycle count on every branch or instruction,
+the values will often be zero. When there are values, they will be the number
+of instructions and number of cycles since the last update, and thus represent
+the average IPC since the last IPC for that event type. Note IPC for "branches"
+events is calculated separately from IPC for "instructions" events.
+
+Also note that the IPC instruction count may or may not include the current
+instruction. If the cycle count is associated with an asynchronous branch
+(e.g. page fault or interrupt), then the instruction count does not include the
+current instruction, otherwise it does. That is consistent with whether or not
+that instruction has retired when the cycle count is updated.
+
+Another note, in the case of "branches" events, non-taken branches are not
+presently sampled, so IPC values for them do not appear e.g. a CYC packet with a
+TNT packet that starts with a non-taken branch. To see every possible IPC
+value, "instructions" events can be used e.g. --itrace=i0ns
+
While it is possible to create scripts to analyze the data, an alternative
approach is available to export the data to a sqlite or postgresql database.
Refer to script export-to-sqlite.py or export-to-postgresql.py for more details,
which, in turn, is the same as
- --itrace=ibxwpe
+ --itrace=cepwx
The letters are:
llvm.clang-bpf-cmd-template::
Cmdline template. Below lines show its default value. Environment
variable is used to pass options.
- "$CLANG_EXEC -D__KERNEL__ $CLANG_OPTIONS $KERNEL_INC_OPTIONS \
- -Wno-unused-value -Wno-pointer-sign -working-directory \
- $WORKING_DIR -c $CLANG_SOURCE -target bpf -O2 -o -"
+ "$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
+ "-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE " \
+ "$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
+ "-Wno-unused-value -Wno-pointer-sign " \
+ "-working-directory $WORKING_DIR " \
+ "-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
llvm.clang-opt::
Options passed to clang.
-c::
--compute::
- Differential computation selection - delta, ratio, wdiff, delta-abs
- (default is delta-abs). Default can be changed using diff.compute
- config option. See COMPARISON METHODS section for more info.
+ Differential computation selection - delta, ratio, wdiff, cycles,
+ delta-abs (default is delta-abs). Default can be changed using
+ diff.compute config option. See COMPARISON METHODS section for
+ more info.
-p::
--period::
perf diff --time 0%-10%,30%-40%
It also supports analyzing samples within a given time window
- <start>,<stop>. Times have the format seconds.microseconds. If 'start'
- is not given (i.e., time string is ',x.y') then analysis starts at
- the beginning of the file. If stop time is not given (i.e, time
- string is 'x.y,') then analysis goes to the end of the file. Time string is
- 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different
- perf.data files.
+ <start>,<stop>. Times have the format seconds.nanoseconds. If 'start'
+ is not given (i.e. time string is ',x.y') then analysis starts at
+ the beginning of the file. If stop time is not given (i.e. time
+ string is 'x.y,') then analysis goes to the end of the file.
+ Multiple ranges can be separated by spaces, which requires the argument
+ to be quoted e.g. --time "1234.567,1234.789 1235,"
+ Time string is'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps
+ for different perf.data files.
For example, we get the timestamp information from 'perf script'.
- WEIGHT-A being the weight of the data file
- WEIGHT-B being the weight of the baseline data file
+cycles
+~~~~~~
+If specified the '[Program Block Range] Cycles Diff' column is displayed.
+It displays the cycles difference of same program basic block amongst
+two perf.data. The program basic block is the code between two branches.
+
+'[Program Block Range]' indicates the range of a program basic block.
+Source line is reported if it can be found otherwise uses symbol+offset
+instead.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-report[1]
--all-user::
Configure all used events to run in user space.
+--kernel-callchains::
+Collect callchains only from kernel space. I.e. this option sets
+perf_event_attr.exclude_callchain_user to 1.
+
+--user-callchains::
+Collect callchains only from user space. I.e. this option sets
+perf_event_attr.exclude_callchain_kernel to 1.
+
+Don't use both --kernel-callchains and --user-callchains at the same time or no
+callchains will be collected.
+
--timestamp-filename
Append timestamp to output file name.
- socket: processor socket number the task ran at the time of sample
- srcline: filename and line number executed at the time of sample. The
DWARF debugging info must be provided.
- - srcfile: file name of the source file of the same. Requires dwarf
+ - srcfile: file name of the source file of the samples. Requires dwarf
information.
- weight: Event specific weight, e.g. memory latency or transaction
abort cost. This is the global weight.
--time::
Only analyze samples within given time window: <start>,<stop>. Times
- have the format seconds.microseconds. If start is not given (i.e., time
+ have the format seconds.nanoseconds. If start is not given (i.e. time
string is ',x.y') then analysis starts at the beginning of the file. If
- stop time is not given (i.e, time string is 'x.y,') then analysis goes
- to end of file.
+ stop time is not given (i.e. time string is 'x.y,') then analysis goes
+ to end of file. Multiple ranges can be separated by spaces, which
+ requires the argument to be quoted e.g. --time "1234.567,1234.789 1235,"
- Also support time percent with multiple time range. Time string is
+ Also support time percent with multiple time ranges. Time string is
'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'.
For example:
Comma separated list of fields to print. Options are:
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
- brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc, srccode.
+ brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc, srccode, ipc.
Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace
The synth field is used by synthesized events which may be created when
Instruction Trace decoding.
+ The ipc (instructions per cycle) field is synthesized and may have a value when
+ Instruction Trace decoding.
+
Finally, a user may not set fields to none for all event types.
i.e., -F "" is not allowed.
--show-round-events
Display finished round events i.e. events of type PERF_RECORD_FINISHED_ROUND.
+--show-bpf-events
+ Display bpf events i.e. events of type PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT.
+
--demangle::
Demangle symbol names to human readable form. It's enabled by default,
disable with --no-demangle.
--time::
Only analyze samples within given time window: <start>,<stop>. Times
- have the format seconds.microseconds. If start is not given (i.e., time
+ have the format seconds.nanoseconds. If start is not given (i.e. time
string is ',x.y') then analysis starts at the beginning of the file. If
- stop time is not given (i.e, time string is 'x.y,') then analysis goes
- to end of file.
+ stop time is not given (i.e. time string is 'x.y,') then analysis goes
+ to end of file. Multiple ranges can be separated by spaces, which
+ requires the argument to be quoted e.g. --time "1234.567,1234.789 1235,"
- Also support time percent with multipe time range. Time string is
+ Also support time percent with multiple time ranges. Time string is
'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'.
For example:
socket number and the number of online processors on that socket. This is
useful to gauge the amount of aggregation.
+--per-die::
+Aggregate counts per processor die for system-wide mode measurements. This
+is a useful mode to detect imbalance between dies. To enable this mode,
+use --per-die in addition to -a. (system-wide). The output includes the
+die number and the number of online processors on that die. This is
+useful to gauge the amount of aggregation.
+
--per-core::
Aggregate counts per physical processor for system-wide mode measurements. This
is a useful mode to detect imbalance between physical cores. To enable this mode,
--per-socket::
Aggregate counts per processor socket for system-wide mode measurements.
+--per-die::
+Aggregate counts per processor die for system-wide mode measurements.
+
--per-core::
Aggregate counts per physical processor for system-wide mode measurements.
The number of threads to run when synthesizing events for existing processes.
By default, the number of threads equals to the number of online CPUs.
+--namespaces::
+ Record events of type PERF_RECORD_NAMESPACES and display it with the
+ 'cgroup_id' sort key.
+
+
INTERACTIVE PROMPTING KEYS
--------------------------
HEADER_CPU_TOPOLOGY = 13,
-String lists defining the core and CPU threads topology.
-The string lists are followed by a variable length array
-which contains core_id and socket_id of each cpu.
-The number of entries can be determined by the size of the
-section minus the sizes of both string lists.
-
struct {
+ /*
+ * First revision of HEADER_CPU_TOPOLOGY
+ *
+ * See 'struct perf_header_string_list' definition earlier
+ * in this file.
+ */
+
struct perf_header_string_list cores; /* Variable length */
struct perf_header_string_list threads; /* Variable length */
+
+ /*
+ * Second revision of HEADER_CPU_TOPOLOGY, older tools
+ * will not consider what comes next
+ */
+
struct {
uint32_t core_id;
uint32_t socket_id;
} cpus[nr]; /* Variable length records */
+ /* 'nr' comes from previously processed HEADER_NRCPUS's nr_cpu_avail */
+
+ /*
+ * Third revision of HEADER_CPU_TOPOLOGY, older tools
+ * will not consider what comes next
+ */
+
+ struct perf_header_string_list dies; /* Variable length */
+ uint32_t die_id[nr_cpus_avail]; /* from previously processed HEADER_NR_CPUS, VLA */
};
Example:
- sibling cores : 0-3
+ sibling sockets : 0-8
+ sibling dies : 0-3
+ sibling dies : 4-7
sibling threads : 0-1
sibling threads : 2-3
+ sibling threads : 4-5
+ sibling threads : 6-7
HEADER_NUMA_TOPOLOGY = 14,
Two uint64_t for the time of first sample and the time of last sample.
+ HEADER_SAMPLE_TOPOLOGY = 22,
+
+Physical memory map and its node assignments.
+
+The format of data in MEM_TOPOLOGY is as follows:
+
+ 0 - version | for future changes
+ 8 - block_size_bytes | /sys/devices/system/memory/block_size_bytes
+ 16 - count | number of nodes
+
+For each node we store map of physical indexes:
+
+ 32 - node id | node index
+ 40 - size | size of bitmap
+ 48 - bitmap | bitmap of memory indexes that belongs to node
+ | /sys/devices/system/node/node<NODE>/memory<INDEX>
+
+The MEM_TOPOLOGY can be displayed with following command:
+
+$ perf report --header-only -I
+...
+# memory nodes (nr 1, block size 0x8000000):
+# 0 [7G]: 0-23,32-69
+
+ HEADER_CLOCKID = 23,
+
+One uint64_t for the clockid frequency, specified, for instance, via 'perf
+record -k' (see clock_gettime()), to enable timestamps derived metrics
+conversion into wall clock time on the reporting stage.
+
+ HEADER_DIR_FORMAT = 24,
+
+The data files layout is described by HEADER_DIR_FORMAT feature. Currently it
+holds only version number (1):
+
+ uint64_t version;
+
+The current version holds only version value (1) means that data files:
+
+- Follow the 'data.*' name format.
+
+- Contain raw events data in standard perf format as read from kernel (and need
+ to be sorted)
+
+Future versions are expected to describe different data files layout according
+to special needs.
+
+ HEADER_BPF_PROG_INFO = 25,
+
+struct bpf_prog_info_linear, which contains detailed information about
+a BPF program, including type, id, tag, jited/xlated instructions, etc.
+
+ HEADER_BPF_BTF = 26,
+
+Contains BPF Type Format (BTF). For more information about BTF, please
+refer to Documentation/bpf/btf.rst.
+
+struct {
+ u32 id;
+ u32 data_size;
+ char data[];
+};
+
HEADER_COMPRESSED = 27,
struct {
To browse sample contexts use perf report --sample 10 and select in context menu
To separate samples by time use perf report --sort time,overhead,sym
To set sample time separation other than 100ms with --sort time use --time-quantum
-Add -I to perf report to sample register values visible in perf report context.
+Add -I to perf record to sample register values, which will be visible in perf report sample context.
To show IPC for sampling periods use perf record -e '{cycles,instructions}:S' and then browse context
To show context switches in perf report sample context add --switch-events to perf record.
tools/lib/api
tools/lib/bpf
tools/lib/subcmd
+tools/lib/argv_split.c
+tools/lib/ctype.c
tools/lib/hweight.c
tools/lib/rbtree.c
tools/lib/string.c
CFLAGS += -DHAVE_GET_CURRENT_DIR_NAME
endif
+ifeq ($(feature-gettid), 1)
+ CFLAGS += -DHAVE_GETTID
+endif
+
ifdef NO_LIBELF
NO_DWARF := 1
NO_DEMANGLE := 1
$(call feature_check,libopencsd)
ifeq ($(feature-libopencsd), 1)
CFLAGS += -DHAVE_CSTRACE_SUPPORT $(LIBOPENCSD_CFLAGS)
+ ifeq ($(feature-reallocarray), 0)
+ CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
+ endif
LDFLAGS += $(LIBOPENCSD_LDFLAGS)
EXTLIBS += $(OPENCSDLIBS)
$(call detected,CONFIG_LIBOPENCSD)
ifndef NO_SLANG
ifneq ($(feature-libslang), 1)
- msg := $(warning slang not found, disables TUI support. Please install slang-devel, libslang-dev or libslang2-dev);
- NO_SLANG := 1
- else
+ ifneq ($(feature-libslang-include-subdir), 1)
+ msg := $(warning slang not found, disables TUI support. Please install slang-devel, libslang-dev or libslang2-dev);
+ NO_SLANG := 1
+ else
+ CFLAGS += -DHAVE_SLANG_INCLUDE_SUBDIR
+ endif
+ endif
+ ifndef NO_SLANG
# Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
- CFLAGS += -I/usr/include/slang
CFLAGS += -DHAVE_SLANG_SUPPORT
EXTLIBS += -lslang
$(call detected,CONFIG_SLANG)
$(fadvise_advice_array): $(linux_uapi_dir)/in.h $(fadvise_advice_tbl)
$(Q)$(SHELL) '$(fadvise_advice_tbl)' $(linux_uapi_dir) > $@
+fsmount_arrays := $(beauty_outdir)/fsmount_arrays.c
+fsmount_tbls := $(srctree)/tools/perf/trace/beauty/fsmount.sh
+
+$(fsmount_arrays): $(linux_uapi_dir)/fs.h $(fsmount_tbls)
+ $(Q)$(SHELL) '$(fsmount_tbls)' $(linux_uapi_dir) > $@
+
+fspick_arrays := $(beauty_outdir)/fspick_arrays.c
+fspick_tbls := $(srctree)/tools/perf/trace/beauty/fspick.sh
+
+$(fspick_arrays): $(linux_uapi_dir)/fs.h $(fspick_tbls)
+ $(Q)$(SHELL) '$(fspick_tbls)' $(linux_uapi_dir) > $@
+
+fsconfig_arrays := $(beauty_outdir)/fsconfig_arrays.c
+fsconfig_tbls := $(srctree)/tools/perf/trace/beauty/fsconfig.sh
+
+$(fsconfig_arrays): $(linux_uapi_dir)/fs.h $(fsconfig_tbls)
+ $(Q)$(SHELL) '$(fsconfig_tbls)' $(linux_uapi_dir) > $@
+
pkey_alloc_access_rights_array := $(beauty_outdir)/pkey_alloc_access_rights_array.c
asm_generic_hdr_dir := $(srctree)/tools/include/uapi/asm-generic/
pkey_alloc_access_rights_tbl := $(srctree)/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
$(mount_flags_array): $(linux_uapi_dir)/fs.h $(mount_flags_tbl)
$(Q)$(SHELL) '$(mount_flags_tbl)' $(linux_uapi_dir) > $@
+move_mount_flags_array := $(beauty_outdir)/move_mount_flags_array.c
+move_mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/move_mount_flags.sh
+
+$(move_mount_flags_array): $(linux_uapi_dir)/fs.h $(move_mount_flags_tbl)
+ $(Q)$(SHELL) '$(move_mount_flags_tbl)' $(linux_uapi_dir) > $@
+
prctl_option_array := $(beauty_outdir)/prctl_option_array.c
prctl_hdr_dir := $(srctree)/tools/include/uapi/linux/
prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh
$(arch_errno_name_array): $(arch_errno_tbl)
$(Q)$(SHELL) '$(arch_errno_tbl)' $(CC) $(arch_errno_hdr_dir) > $@
+sync_file_range_arrays := $(beauty_outdir)/sync_file_range_arrays.c
+sync_file_range_tbls := $(srctree)/tools/perf/trace/beauty/sync_file_range.sh
+
+$(sync_file_range_arrays): $(linux_uapi_dir)/fs.h $(sync_file_range_tbls)
+ $(Q)$(SHELL) '$(sync_file_range_tbls)' $(linux_uapi_dir) > $@
+
all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
# Create python binding output directory if not already present
prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioctl_array) \
$(fadvise_advice_array) \
+ $(fsconfig_arrays) \
+ $(fsmount_arrays) \
+ $(fspick_arrays) \
$(pkey_alloc_access_rights_array) \
$(sndrv_pcm_ioctl_array) \
$(sndrv_ctl_ioctl_array) \
$(madvise_behavior_array) \
$(mmap_flags_array) \
$(mount_flags_array) \
+ $(move_mount_flags_array) \
$(perf_ioctl_array) \
$(prctl_option_array) \
$(usbdevfs_ioctl_array) \
$(x86_arch_prctl_code_array) \
$(rename_flags_array) \
- $(arch_errno_name_array)
+ $(arch_errno_name_array) \
+ $(sync_file_range_arrays)
$(OUTPUT)%.o: %.c prepare FORCE
$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
$(OUTPUT)pmu-events/pmu-events.c \
$(OUTPUT)$(fadvise_advice_array) \
+ $(OUTPUT)$(fsconfig_arrays) \
+ $(OUTPUT)$(fsmount_arrays) \
+ $(OUTPUT)$(fspick_arrays) \
$(OUTPUT)$(madvise_behavior_array) \
$(OUTPUT)$(mmap_flags_array) \
$(OUTPUT)$(mount_flags_array) \
+ $(OUTPUT)$(move_mount_flags_array) \
$(OUTPUT)$(drm_ioctl_array) \
$(OUTPUT)$(pkey_alloc_access_rights_array) \
$(OUTPUT)$(sndrv_ctl_ioctl_array) \
$(OUTPUT)$(usbdevfs_ioctl_array) \
$(OUTPUT)$(x86_arch_prctl_code_array) \
$(OUTPUT)$(rename_flags_array) \
- $(OUTPUT)$(arch_errno_name_array)
+ $(OUTPUT)$(arch_errno_name_array) \
+ $(OUTPUT)$(sync_file_range_arrays)
$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
#
#include "../../util/pmu.h"
#include "../../util/thread_map.h"
#include "../../util/cs-etm.h"
+#include "../../util/util.h"
#include <errno.h>
#include <stdlib.h>
struct auxtrace_record itr;
struct perf_pmu *cs_etm_pmu;
struct perf_evlist *evlist;
+ int wrapped_cnt;
+ bool *wrapped;
bool snapshot_mode;
size_t snapshot_size;
};
+static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = {
+ [CS_ETM_ETMCCER] = "mgmt/etmccer",
+ [CS_ETM_ETMIDR] = "mgmt/etmidr",
+};
+
+static const char *metadata_etmv4_ro[CS_ETMV4_PRIV_MAX] = {
+ [CS_ETMV4_TRCIDR0] = "trcidr/trcidr0",
+ [CS_ETMV4_TRCIDR1] = "trcidr/trcidr1",
+ [CS_ETMV4_TRCIDR2] = "trcidr/trcidr2",
+ [CS_ETMV4_TRCIDR8] = "trcidr/trcidr8",
+ [CS_ETMV4_TRCAUTHSTATUS] = "mgmt/trcauthstatus",
+};
+
static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu);
+static int cs_etm_set_context_id(struct auxtrace_record *itr,
+ struct perf_evsel *evsel, int cpu)
+{
+ struct cs_etm_recording *ptr;
+ struct perf_pmu *cs_etm_pmu;
+ char path[PATH_MAX];
+ int err = -EINVAL;
+ u32 val;
+
+ ptr = container_of(itr, struct cs_etm_recording, itr);
+ cs_etm_pmu = ptr->cs_etm_pmu;
+
+ if (!cs_etm_is_etmv4(itr, cpu))
+ goto out;
+
+ /* Get a handle on TRCIRD2 */
+ snprintf(path, PATH_MAX, "cpu%d/%s",
+ cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR2]);
+ err = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val);
+
+ /* There was a problem reading the file, bailing out */
+ if (err != 1) {
+ pr_err("%s: can't read file %s\n",
+ CORESIGHT_ETM_PMU_NAME, path);
+ goto out;
+ }
+
+ /*
+ * TRCIDR2.CIDSIZE, bit [9-5], indicates whether contextID tracing
+ * is supported:
+ * 0b00000 Context ID tracing is not supported.
+ * 0b00100 Maximum of 32-bit Context ID size.
+ * All other values are reserved.
+ */
+ val = BMVAL(val, 5, 9);
+ if (!val || val != 0x4) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ /* All good, let the kernel know */
+ evsel->attr.config |= (1 << ETM_OPT_CTXTID);
+ err = 0;
+
+out:
+
+ return err;
+}
+
+static int cs_etm_set_timestamp(struct auxtrace_record *itr,
+ struct perf_evsel *evsel, int cpu)
+{
+ struct cs_etm_recording *ptr;
+ struct perf_pmu *cs_etm_pmu;
+ char path[PATH_MAX];
+ int err = -EINVAL;
+ u32 val;
+
+ ptr = container_of(itr, struct cs_etm_recording, itr);
+ cs_etm_pmu = ptr->cs_etm_pmu;
+
+ if (!cs_etm_is_etmv4(itr, cpu))
+ goto out;
+
+ /* Get a handle on TRCIRD0 */
+ snprintf(path, PATH_MAX, "cpu%d/%s",
+ cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR0]);
+ err = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val);
+
+ /* There was a problem reading the file, bailing out */
+ if (err != 1) {
+ pr_err("%s: can't read file %s\n",
+ CORESIGHT_ETM_PMU_NAME, path);
+ goto out;
+ }
+
+ /*
+ * TRCIDR0.TSSIZE, bit [28-24], indicates whether global timestamping
+ * is supported:
+ * 0b00000 Global timestamping is not implemented
+ * 0b00110 Implementation supports a maximum timestamp of 48bits.
+ * 0b01000 Implementation supports a maximum timestamp of 64bits.
+ */
+ val &= GENMASK(28, 24);
+ if (!val) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ /* All good, let the kernel know */
+ evsel->attr.config |= (1 << ETM_OPT_TS);
+ err = 0;
+
+out:
+ return err;
+}
+
+static int cs_etm_set_option(struct auxtrace_record *itr,
+ struct perf_evsel *evsel, u32 option)
+{
+ int i, err = -EINVAL;
+ struct cpu_map *event_cpus = evsel->evlist->cpus;
+ struct cpu_map *online_cpus = cpu_map__new(NULL);
+
+ /* Set option of each CPU we have */
+ for (i = 0; i < cpu__max_cpu(); i++) {
+ if (!cpu_map__has(event_cpus, i) ||
+ !cpu_map__has(online_cpus, i))
+ continue;
+
+ if (option & ETM_OPT_CTXTID) {
+ err = cs_etm_set_context_id(itr, evsel, i);
+ if (err)
+ goto out;
+ }
+ if (option & ETM_OPT_TS) {
+ err = cs_etm_set_timestamp(itr, evsel, i);
+ if (err)
+ goto out;
+ }
+ if (option & ~(ETM_OPT_CTXTID | ETM_OPT_TS))
+ /* Nothing else is currently supported */
+ goto out;
+ }
+
+ err = 0;
+out:
+ cpu_map__put(online_cpus);
+ return err;
+}
+
static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr,
struct record_opts *opts,
const char *str)
container_of(itr, struct cs_etm_recording, itr);
struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
struct perf_evsel *evsel, *cs_etm_evsel = NULL;
- const struct cpu_map *cpus = evlist->cpus;
+ struct cpu_map *cpus = evlist->cpus;
bool privileged = (geteuid() == 0 || perf_event_paranoid() < 0);
+ int err = 0;
ptr->evlist = evlist;
ptr->snapshot_mode = opts->auxtrace_snapshot_mode;
+ if (perf_can_record_switch_events())
+ opts->record_switch_events = true;
+
evlist__for_each_entry(evlist, evsel) {
if (evsel->attr.type == cs_etm_pmu->type) {
if (cs_etm_evsel) {
/*
* In the case of per-cpu mmaps, we need the CPU on the
- * AUX event.
+ * AUX event. We also need the contextID in order to be notified
+ * when a context switch happened.
*/
- if (!cpu_map__empty(cpus))
+ if (!cpu_map__empty(cpus)) {
perf_evsel__set_sample_bit(cs_etm_evsel, CPU);
+ err = cs_etm_set_option(itr, cs_etm_evsel,
+ ETM_OPT_CTXTID | ETM_OPT_TS);
+ if (err)
+ goto out;
+ }
+
/* Add dummy event to keep tracking */
if (opts->full_auxtrace) {
struct perf_evsel *tracking_evsel;
- int err;
err = parse_events(evlist, "dummy:u", NULL);
if (err)
- return err;
+ goto out;
tracking_evsel = perf_evlist__last(evlist);
perf_evlist__set_tracking_event(evlist, tracking_evsel);
perf_evsel__set_sample_bit(tracking_evsel, TIME);
}
- return 0;
+out:
+ return err;
}
static u64 cs_etm_get_config(struct auxtrace_record *itr)
config_opts = cs_etm_get_config(itr);
if (config_opts & BIT(ETM_OPT_CYCACC))
config |= BIT(ETM4_CFG_BIT_CYCACC);
+ if (config_opts & BIT(ETM_OPT_CTXTID))
+ config |= BIT(ETM4_CFG_BIT_CTXTID);
if (config_opts & BIT(ETM_OPT_TS))
config |= BIT(ETM4_CFG_BIT_TS);
if (config_opts & BIT(ETM_OPT_RETSTK))
(etmv3 * CS_ETMV3_PRIV_SIZE));
}
-static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = {
- [CS_ETM_ETMCCER] = "mgmt/etmccer",
- [CS_ETM_ETMIDR] = "mgmt/etmidr",
-};
-
-static const char *metadata_etmv4_ro[CS_ETMV4_PRIV_MAX] = {
- [CS_ETMV4_TRCIDR0] = "trcidr/trcidr0",
- [CS_ETMV4_TRCIDR1] = "trcidr/trcidr1",
- [CS_ETMV4_TRCIDR2] = "trcidr/trcidr2",
- [CS_ETMV4_TRCIDR8] = "trcidr/trcidr8",
- [CS_ETMV4_TRCAUTHSTATUS] = "mgmt/trcauthstatus",
-};
-
static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu)
{
bool ret = false;
return 0;
}
-static int cs_etm_find_snapshot(struct auxtrace_record *itr __maybe_unused,
+static int cs_etm_alloc_wrapped_array(struct cs_etm_recording *ptr, int idx)
+{
+ bool *wrapped;
+ int cnt = ptr->wrapped_cnt;
+
+ /* Make @ptr->wrapped as big as @idx */
+ while (cnt <= idx)
+ cnt++;
+
+ /*
+ * Free'ed in cs_etm_recording_free(). Using realloc() to avoid
+ * cross compilation problems where the host's system supports
+ * reallocarray() but not the target.
+ */
+ wrapped = realloc(ptr->wrapped, cnt * sizeof(bool));
+ if (!wrapped)
+ return -ENOMEM;
+
+ wrapped[cnt - 1] = false;
+ ptr->wrapped_cnt = cnt;
+ ptr->wrapped = wrapped;
+
+ return 0;
+}
+
+static bool cs_etm_buffer_has_wrapped(unsigned char *buffer,
+ size_t buffer_size, u64 head)
+{
+ u64 i, watermark;
+ u64 *buf = (u64 *)buffer;
+ size_t buf_size = buffer_size;
+
+ /*
+ * We want to look the very last 512 byte (chosen arbitrarily) in
+ * the ring buffer.
+ */
+ watermark = buf_size - 512;
+
+ /*
+ * @head is continuously increasing - if its value is equal or greater
+ * than the size of the ring buffer, it has wrapped around.
+ */
+ if (head >= buffer_size)
+ return true;
+
+ /*
+ * The value of @head is somewhere within the size of the ring buffer.
+ * This can be that there hasn't been enough data to fill the ring
+ * buffer yet or the trace time was so long that @head has numerically
+ * wrapped around. To find we need to check if we have data at the very
+ * end of the ring buffer. We can reliably do this because mmap'ed
+ * pages are zeroed out and there is a fresh mapping with every new
+ * session.
+ */
+
+ /* @head is less than 512 byte from the end of the ring buffer */
+ if (head > watermark)
+ watermark = head;
+
+ /*
+ * Speed things up by using 64 bit transactions (see "u64 *buf" above)
+ */
+ watermark >>= 3;
+ buf_size >>= 3;
+
+ /*
+ * If we find trace data at the end of the ring buffer, @head has
+ * been there and has numerically wrapped around at least once.
+ */
+ for (i = watermark; i < buf_size; i++)
+ if (buf[i])
+ return true;
+
+ return false;
+}
+
+static int cs_etm_find_snapshot(struct auxtrace_record *itr,
int idx, struct auxtrace_mmap *mm,
- unsigned char *data __maybe_unused,
+ unsigned char *data,
u64 *head, u64 *old)
{
+ int err;
+ bool wrapped;
+ struct cs_etm_recording *ptr =
+ container_of(itr, struct cs_etm_recording, itr);
+
+ /*
+ * Allocate memory to keep track of wrapping if this is the first
+ * time we deal with this *mm.
+ */
+ if (idx >= ptr->wrapped_cnt) {
+ err = cs_etm_alloc_wrapped_array(ptr, idx);
+ if (err)
+ return err;
+ }
+
+ /*
+ * Check to see if *head has wrapped around. If it hasn't only the
+ * amount of data between *head and *old is snapshot'ed to avoid
+ * bloating the perf.data file with zeros. But as soon as *head has
+ * wrapped around the entire size of the AUX ring buffer it taken.
+ */
+ wrapped = ptr->wrapped[idx];
+ if (!wrapped && cs_etm_buffer_has_wrapped(data, mm->len, *head)) {
+ wrapped = true;
+ ptr->wrapped[idx] = true;
+ }
+
pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n",
__func__, idx, (size_t)*old, (size_t)*head, mm->len);
- *old = *head;
- *head += mm->len;
+ /* No wrap has occurred, we can just use *head and *old. */
+ if (!wrapped)
+ return 0;
+
+ /*
+ * *head has wrapped around - adjust *head and *old to pickup the
+ * entire content of the AUX buffer.
+ */
+ if (*head >= mm->len) {
+ *old = *head - mm->len;
+ } else {
+ *head += mm->len;
+ *old = *head - mm->len;
+ }
return 0;
}
{
struct cs_etm_recording *ptr =
container_of(itr, struct cs_etm_recording, itr);
+
+ zfree(&ptr->wrapped);
free(ptr);
}
perf-y += util/
-perf-$(CONFIG_DWARF_UNWIND) += tests/
+perf-y += tests/
perf-y += regs_load.o
-perf-y += dwarf-unwind.o
+perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
perf-y += arch-tests.o
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/compiler.h>
+
+static struct ins_ops *csky__associate_ins_ops(struct arch *arch,
+ const char *name)
+{
+ struct ins_ops *ops = NULL;
+
+ /* catch all kind of jumps */
+ if (!strcmp(name, "bt") ||
+ !strcmp(name, "bf") ||
+ !strcmp(name, "bez") ||
+ !strcmp(name, "bnez") ||
+ !strcmp(name, "bnezad") ||
+ !strcmp(name, "bhsz") ||
+ !strcmp(name, "bhz") ||
+ !strcmp(name, "blsz") ||
+ !strcmp(name, "blz") ||
+ !strcmp(name, "br") ||
+ !strcmp(name, "jmpi") ||
+ !strcmp(name, "jmp"))
+ ops = &jump_ops;
+
+ /* catch function call */
+ if (!strcmp(name, "bsr") ||
+ !strcmp(name, "jsri") ||
+ !strcmp(name, "jsr"))
+ ops = &call_ops;
+
+ /* catch function return */
+ if (!strcmp(name, "rts"))
+ ops = &ret_ops;
+
+ if (ops)
+ arch__associate_ins_ops(arch, name, ops);
+ return ops;
+}
+
+static int csky__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
+{
+ arch->initialized = true;
+ arch->objdump.comment_char = '/';
+ arch->associate_instruction_ops = csky__associate_ins_ops;
+
+ return 0;
+}
#include <unistd.h>
#include <stdio.h>
#include <string.h>
-#include <ctype.h>
+#include <linux/ctype.h>
#include "../../util/header.h"
#include "../../util/util.h"
int test__rdpmc(struct test *test __maybe_unused, int subtest);
int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest);
int test__insn_x86(struct test *test __maybe_unused, int subtest);
+int test__intel_pt_pkt_decoder(struct test *test, int subtest);
int test__bp_modify(struct test *test, int subtest);
#ifdef HAVE_DWARF_UNWIND_SUPPORT
perf-y += arch-tests.o
perf-y += rdpmc.o
perf-y += perf-time-to-tsc.o
-perf-$(CONFIG_AUXTRACE) += insn-x86.o
+perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-pkt-decoder-test.o
perf-$(CONFIG_X86_64) += bp-modify.o
.desc = "x86 instruction decoder - new instructions",
.func = test__insn_x86,
},
+ {
+ .desc = "Intel PT packet decoder",
+ .func = test__intel_pt_pkt_decoder,
+ },
#endif
#if defined(__x86_64__)
{
#include "evlist.h"
#include "evsel.h"
#include "arch-tests.h"
+#include "util.h"
#include <signal.h>
#include <sys/mman.h>
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include <string.h>
+
+#include "intel-pt-decoder/intel-pt-pkt-decoder.h"
+
+#include "debug.h"
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+/**
+ * struct test_data - Test data.
+ * @len: number of bytes to decode
+ * @bytes: bytes to decode
+ * @ctx: packet context to decode
+ * @packet: expected packet
+ * @new_ctx: expected new packet context
+ * @ctx_unchanged: the packet context must not change
+ */
+struct test_data {
+ int len;
+ u8 bytes[INTEL_PT_PKT_MAX_SZ];
+ enum intel_pt_pkt_ctx ctx;
+ struct intel_pt_pkt packet;
+ enum intel_pt_pkt_ctx new_ctx;
+ int ctx_unchanged;
+} data[] = {
+ /* Padding Packet */
+ {1, {0}, 0, {INTEL_PT_PAD, 0, 0}, 0, 1 },
+ /* Short Taken/Not Taken Packet */
+ {1, {4}, 0, {INTEL_PT_TNT, 1, 0}, 0, 0 },
+ {1, {6}, 0, {INTEL_PT_TNT, 1, 0x20ULL << 58}, 0, 0 },
+ {1, {0x80}, 0, {INTEL_PT_TNT, 6, 0}, 0, 0 },
+ {1, {0xfe}, 0, {INTEL_PT_TNT, 6, 0x3fULL << 58}, 0, 0 },
+ /* Long Taken/Not Taken Packet */
+ {8, {0x02, 0xa3, 2}, 0, {INTEL_PT_TNT, 1, 0xa302ULL << 47}, 0, 0 },
+ {8, {0x02, 0xa3, 3}, 0, {INTEL_PT_TNT, 1, 0x1a302ULL << 47}, 0, 0 },
+ {8, {0x02, 0xa3, 0, 0, 0, 0, 0, 0x80}, 0, {INTEL_PT_TNT, 47, 0xa302ULL << 1}, 0, 0 },
+ {8, {0x02, 0xa3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff}, 0, {INTEL_PT_TNT, 47, 0xffffffffffffa302ULL << 1}, 0, 0 },
+ /* Target IP Packet */
+ {1, {0x0d}, 0, {INTEL_PT_TIP, 0, 0}, 0, 0 },
+ {3, {0x2d, 1, 2}, 0, {INTEL_PT_TIP, 1, 0x201}, 0, 0 },
+ {5, {0x4d, 1, 2, 3, 4}, 0, {INTEL_PT_TIP, 2, 0x4030201}, 0, 0 },
+ {7, {0x6d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP, 3, 0x60504030201}, 0, 0 },
+ {7, {0x8d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP, 4, 0x60504030201}, 0, 0 },
+ {9, {0xcd, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_TIP, 6, 0x807060504030201}, 0, 0 },
+ /* Packet Generation Enable */
+ {1, {0x11}, 0, {INTEL_PT_TIP_PGE, 0, 0}, 0, 0 },
+ {3, {0x31, 1, 2}, 0, {INTEL_PT_TIP_PGE, 1, 0x201}, 0, 0 },
+ {5, {0x51, 1, 2, 3, 4}, 0, {INTEL_PT_TIP_PGE, 2, 0x4030201}, 0, 0 },
+ {7, {0x71, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGE, 3, 0x60504030201}, 0, 0 },
+ {7, {0x91, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGE, 4, 0x60504030201}, 0, 0 },
+ {9, {0xd1, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_TIP_PGE, 6, 0x807060504030201}, 0, 0 },
+ /* Packet Generation Disable */
+ {1, {0x01}, 0, {INTEL_PT_TIP_PGD, 0, 0}, 0, 0 },
+ {3, {0x21, 1, 2}, 0, {INTEL_PT_TIP_PGD, 1, 0x201}, 0, 0 },
+ {5, {0x41, 1, 2, 3, 4}, 0, {INTEL_PT_TIP_PGD, 2, 0x4030201}, 0, 0 },
+ {7, {0x61, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGD, 3, 0x60504030201}, 0, 0 },
+ {7, {0x81, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGD, 4, 0x60504030201}, 0, 0 },
+ {9, {0xc1, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_TIP_PGD, 6, 0x807060504030201}, 0, 0 },
+ /* Flow Update Packet */
+ {1, {0x1d}, 0, {INTEL_PT_FUP, 0, 0}, 0, 0 },
+ {3, {0x3d, 1, 2}, 0, {INTEL_PT_FUP, 1, 0x201}, 0, 0 },
+ {5, {0x5d, 1, 2, 3, 4}, 0, {INTEL_PT_FUP, 2, 0x4030201}, 0, 0 },
+ {7, {0x7d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_FUP, 3, 0x60504030201}, 0, 0 },
+ {7, {0x9d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_FUP, 4, 0x60504030201}, 0, 0 },
+ {9, {0xdd, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_FUP, 6, 0x807060504030201}, 0, 0 },
+ /* Paging Information Packet */
+ {8, {0x02, 0x43, 2, 4, 6, 8, 10, 12}, 0, {INTEL_PT_PIP, 0, 0x60504030201}, 0, 0 },
+ {8, {0x02, 0x43, 3, 4, 6, 8, 10, 12}, 0, {INTEL_PT_PIP, 0, 0x60504030201 | (1ULL << 63)}, 0, 0 },
+ /* Mode Exec Packet */
+ {2, {0x99, 0x00}, 0, {INTEL_PT_MODE_EXEC, 0, 16}, 0, 0 },
+ {2, {0x99, 0x01}, 0, {INTEL_PT_MODE_EXEC, 0, 64}, 0, 0 },
+ {2, {0x99, 0x02}, 0, {INTEL_PT_MODE_EXEC, 0, 32}, 0, 0 },
+ /* Mode TSX Packet */
+ {2, {0x99, 0x20}, 0, {INTEL_PT_MODE_TSX, 0, 0}, 0, 0 },
+ {2, {0x99, 0x21}, 0, {INTEL_PT_MODE_TSX, 0, 1}, 0, 0 },
+ {2, {0x99, 0x22}, 0, {INTEL_PT_MODE_TSX, 0, 2}, 0, 0 },
+ /* Trace Stop Packet */
+ {2, {0x02, 0x83}, 0, {INTEL_PT_TRACESTOP, 0, 0}, 0, 0 },
+ /* Core:Bus Ratio Packet */
+ {4, {0x02, 0x03, 0x12, 0}, 0, {INTEL_PT_CBR, 0, 0x12}, 0, 1 },
+ /* Timestamp Counter Packet */
+ {8, {0x19, 1, 2, 3, 4, 5, 6, 7}, 0, {INTEL_PT_TSC, 0, 0x7060504030201}, 0, 1 },
+ /* Mini Time Counter Packet */
+ {2, {0x59, 0x12}, 0, {INTEL_PT_MTC, 0, 0x12}, 0, 1 },
+ /* TSC / MTC Alignment Packet */
+ {7, {0x02, 0x73}, 0, {INTEL_PT_TMA, 0, 0}, 0, 1 },
+ {7, {0x02, 0x73, 1, 2}, 0, {INTEL_PT_TMA, 0, 0x201}, 0, 1 },
+ {7, {0x02, 0x73, 0, 0, 0, 0xff, 1}, 0, {INTEL_PT_TMA, 0x1ff, 0}, 0, 1 },
+ {7, {0x02, 0x73, 0x80, 0xc0, 0, 0xff, 1}, 0, {INTEL_PT_TMA, 0x1ff, 0xc080}, 0, 1 },
+ /* Cycle Count Packet */
+ {1, {0x03}, 0, {INTEL_PT_CYC, 0, 0}, 0, 1 },
+ {1, {0x0b}, 0, {INTEL_PT_CYC, 0, 1}, 0, 1 },
+ {1, {0xfb}, 0, {INTEL_PT_CYC, 0, 0x1f}, 0, 1 },
+ {2, {0x07, 2}, 0, {INTEL_PT_CYC, 0, 0x20}, 0, 1 },
+ {2, {0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0xfff}, 0, 1 },
+ {3, {0x07, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x1000}, 0, 1 },
+ {3, {0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x7ffff}, 0, 1 },
+ {4, {0x07, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x80000}, 0, 1 },
+ {4, {0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x3ffffff}, 0, 1 },
+ {5, {0x07, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x4000000}, 0, 1 },
+ {5, {0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x1ffffffff}, 0, 1 },
+ {6, {0x07, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x200000000}, 0, 1 },
+ {6, {0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0xffffffffff}, 0, 1 },
+ {7, {0x07, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x10000000000}, 0, 1 },
+ {7, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x7fffffffffff}, 0, 1 },
+ {8, {0x07, 1, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x800000000000}, 0, 1 },
+ {8, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x3fffffffffffff}, 0, 1 },
+ {9, {0x07, 1, 1, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x40000000000000}, 0, 1 },
+ {9, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x1fffffffffffffff}, 0, 1 },
+ {10, {0x07, 1, 1, 1, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x2000000000000000}, 0, 1 },
+ {10, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xe}, 0, {INTEL_PT_CYC, 0, 0xffffffffffffffff}, 0, 1 },
+ /* Virtual-Machine Control Structure Packet */
+ {7, {0x02, 0xc8, 1, 2, 3, 4, 5}, 0, {INTEL_PT_VMCS, 5, 0x504030201}, 0, 0 },
+ /* Overflow Packet */
+ {2, {0x02, 0xf3}, 0, {INTEL_PT_OVF, 0, 0}, 0, 0 },
+ {2, {0x02, 0xf3}, INTEL_PT_BLK_4_CTX, {INTEL_PT_OVF, 0, 0}, 0, 0 },
+ {2, {0x02, 0xf3}, INTEL_PT_BLK_8_CTX, {INTEL_PT_OVF, 0, 0}, 0, 0 },
+ /* Packet Stream Boundary*/
+ {16, {0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82}, 0, {INTEL_PT_PSB, 0, 0}, 0, 0 },
+ {16, {0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82}, INTEL_PT_BLK_4_CTX, {INTEL_PT_PSB, 0, 0}, 0, 0 },
+ {16, {0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82}, INTEL_PT_BLK_8_CTX, {INTEL_PT_PSB, 0, 0}, 0, 0 },
+ /* PSB End Packet */
+ {2, {0x02, 0x23}, 0, {INTEL_PT_PSBEND, 0, 0}, 0, 0 },
+ /* Maintenance Packet */
+ {11, {0x02, 0xc3, 0x88, 1, 2, 3, 4, 5, 6, 7}, 0, {INTEL_PT_MNT, 0, 0x7060504030201}, 0, 1 },
+ /* Write Data to PT Packet */
+ {6, {0x02, 0x12, 1, 2, 3, 4}, 0, {INTEL_PT_PTWRITE, 0, 0x4030201}, 0, 0 },
+ {10, {0x02, 0x32, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_PTWRITE, 1, 0x807060504030201}, 0, 0 },
+ {6, {0x02, 0x92, 1, 2, 3, 4}, 0, {INTEL_PT_PTWRITE_IP, 0, 0x4030201}, 0, 0 },
+ {10, {0x02, 0xb2, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_PTWRITE_IP, 1, 0x807060504030201}, 0, 0 },
+ /* Execution Stop Packet */
+ {2, {0x02, 0x62}, 0, {INTEL_PT_EXSTOP, 0, 0}, 0, 1 },
+ {2, {0x02, 0xe2}, 0, {INTEL_PT_EXSTOP_IP, 0, 0}, 0, 1 },
+ /* Monitor Wait Packet */
+ {10, {0x02, 0xc2}, 0, {INTEL_PT_MWAIT, 0, 0}, 0, 0 },
+ {10, {0x02, 0xc2, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_MWAIT, 0, 0x807060504030201}, 0, 0 },
+ {10, {0x02, 0xc2, 0xff, 2, 3, 4, 7, 6, 7, 8}, 0, {INTEL_PT_MWAIT, 0, 0x8070607040302ff}, 0, 0 },
+ /* Power Entry Packet */
+ {4, {0x02, 0x22}, 0, {INTEL_PT_PWRE, 0, 0}, 0, 1 },
+ {4, {0x02, 0x22, 1, 2}, 0, {INTEL_PT_PWRE, 0, 0x0201}, 0, 1 },
+ {4, {0x02, 0x22, 0x80, 0x34}, 0, {INTEL_PT_PWRE, 0, 0x3480}, 0, 1 },
+ {4, {0x02, 0x22, 0x00, 0x56}, 0, {INTEL_PT_PWRE, 0, 0x5600}, 0, 1 },
+ /* Power Exit Packet */
+ {7, {0x02, 0xa2}, 0, {INTEL_PT_PWRX, 0, 0}, 0, 1 },
+ {7, {0x02, 0xa2, 1, 2, 3, 4, 5}, 0, {INTEL_PT_PWRX, 0, 0x504030201}, 0, 1 },
+ {7, {0x02, 0xa2, 0xff, 0xff, 0xff, 0xff, 0xff}, 0, {INTEL_PT_PWRX, 0, 0xffffffffff}, 0, 1 },
+ /* Block Begin Packet */
+ {3, {0x02, 0x63, 0x00}, 0, {INTEL_PT_BBP, 0, 0}, INTEL_PT_BLK_8_CTX, 0 },
+ {3, {0x02, 0x63, 0x80}, 0, {INTEL_PT_BBP, 1, 0}, INTEL_PT_BLK_4_CTX, 0 },
+ {3, {0x02, 0x63, 0x1f}, 0, {INTEL_PT_BBP, 0, 0x1f}, INTEL_PT_BLK_8_CTX, 0 },
+ {3, {0x02, 0x63, 0x9f}, 0, {INTEL_PT_BBP, 1, 0x1f}, INTEL_PT_BLK_4_CTX, 0 },
+ /* 4-byte Block Item Packet */
+ {5, {0x04}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0, 0}, INTEL_PT_BLK_4_CTX, 0 },
+ {5, {0xfc}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0x1f, 0}, INTEL_PT_BLK_4_CTX, 0 },
+ {5, {0x04, 1, 2, 3, 4}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0, 0x04030201}, INTEL_PT_BLK_4_CTX, 0 },
+ {5, {0xfc, 1, 2, 3, 4}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0x1f, 0x04030201}, INTEL_PT_BLK_4_CTX, 0 },
+ /* 8-byte Block Item Packet */
+ {9, {0x04}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0, 0}, INTEL_PT_BLK_8_CTX, 0 },
+ {9, {0xfc}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0x1f, 0}, INTEL_PT_BLK_8_CTX, 0 },
+ {9, {0x04, 1, 2, 3, 4, 5, 6, 7, 8}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0, 0x0807060504030201}, INTEL_PT_BLK_8_CTX, 0 },
+ {9, {0xfc, 1, 2, 3, 4, 5, 6, 7, 8}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0x1f, 0x0807060504030201}, INTEL_PT_BLK_8_CTX, 0 },
+ /* Block End Packet */
+ {2, {0x02, 0x33}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BEP, 0, 0}, 0, 0 },
+ {2, {0x02, 0xb3}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BEP_IP, 0, 0}, 0, 0 },
+ {2, {0x02, 0x33}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BEP, 0, 0}, 0, 0 },
+ {2, {0x02, 0xb3}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BEP_IP, 0, 0}, 0, 0 },
+ /* Terminator */
+ {0, {0}, 0, {0, 0, 0}, 0, 0 },
+};
+
+static int dump_packet(struct intel_pt_pkt *packet, u8 *bytes, int len)
+{
+ char desc[INTEL_PT_PKT_DESC_MAX];
+ int ret, i;
+
+ for (i = 0; i < len; i++)
+ pr_debug(" %02x", bytes[i]);
+ for (; i < INTEL_PT_PKT_MAX_SZ; i++)
+ pr_debug(" ");
+ pr_debug(" ");
+ ret = intel_pt_pkt_desc(packet, desc, INTEL_PT_PKT_DESC_MAX);
+ if (ret < 0) {
+ pr_debug("intel_pt_pkt_desc failed!\n");
+ return TEST_FAIL;
+ }
+ pr_debug("%s\n", desc);
+
+ return TEST_OK;
+}
+
+static void decoding_failed(struct test_data *d)
+{
+ pr_debug("Decoding failed!\n");
+ pr_debug("Decoding: ");
+ dump_packet(&d->packet, d->bytes, d->len);
+}
+
+static int fail(struct test_data *d, struct intel_pt_pkt *packet, int len,
+ enum intel_pt_pkt_ctx new_ctx)
+{
+ decoding_failed(d);
+
+ if (len != d->len)
+ pr_debug("Expected length: %d Decoded length %d\n",
+ d->len, len);
+
+ if (packet->type != d->packet.type)
+ pr_debug("Expected type: %d Decoded type %d\n",
+ d->packet.type, packet->type);
+
+ if (packet->count != d->packet.count)
+ pr_debug("Expected count: %d Decoded count %d\n",
+ d->packet.count, packet->count);
+
+ if (packet->payload != d->packet.payload)
+ pr_debug("Expected payload: 0x%llx Decoded payload 0x%llx\n",
+ (unsigned long long)d->packet.payload,
+ (unsigned long long)packet->payload);
+
+ if (new_ctx != d->new_ctx)
+ pr_debug("Expected packet context: %d Decoded packet context %d\n",
+ d->new_ctx, new_ctx);
+
+ return TEST_FAIL;
+}
+
+static int test_ctx_unchanged(struct test_data *d, struct intel_pt_pkt *packet,
+ enum intel_pt_pkt_ctx ctx)
+{
+ enum intel_pt_pkt_ctx old_ctx = ctx;
+
+ intel_pt_upd_pkt_ctx(packet, &ctx);
+
+ if (ctx != old_ctx) {
+ decoding_failed(d);
+ pr_debug("Packet context changed!\n");
+ return TEST_FAIL;
+ }
+
+ return TEST_OK;
+}
+
+static int test_one(struct test_data *d)
+{
+ struct intel_pt_pkt packet;
+ enum intel_pt_pkt_ctx ctx = d->ctx;
+ int ret;
+
+ memset(&packet, 0xff, sizeof(packet));
+
+ /* Decode a packet */
+ ret = intel_pt_get_packet(d->bytes, d->len, &packet, &ctx);
+ if (ret < 0 || ret > INTEL_PT_PKT_MAX_SZ) {
+ decoding_failed(d);
+ pr_debug("intel_pt_get_packet returned %d\n", ret);
+ return TEST_FAIL;
+ }
+
+ /* Some packets must always leave the packet context unchanged */
+ if (d->ctx_unchanged) {
+ int err;
+
+ err = test_ctx_unchanged(d, &packet, INTEL_PT_NO_CTX);
+ if (err)
+ return err;
+ err = test_ctx_unchanged(d, &packet, INTEL_PT_BLK_4_CTX);
+ if (err)
+ return err;
+ err = test_ctx_unchanged(d, &packet, INTEL_PT_BLK_8_CTX);
+ if (err)
+ return err;
+ }
+
+ /* Compare to the expected values */
+ if (ret != d->len || packet.type != d->packet.type ||
+ packet.count != d->packet.count ||
+ packet.payload != d->packet.payload || ctx != d->new_ctx)
+ return fail(d, &packet, ret, ctx);
+
+ pr_debug("Decoded ok:");
+ ret = dump_packet(&d->packet, d->bytes, d->len);
+
+ return ret;
+}
+
+/*
+ * This test feeds byte sequences to the Intel PT packet decoder and checks the
+ * results. Changes to the packet context are also checked.
+ */
+int test__intel_pt_pkt_decoder(struct test *test __maybe_unused, int subtest __maybe_unused)
+{
+ struct test_data *d = data;
+ int ret;
+
+ for (d = data; d->len; d++) {
+ ret = test_one(d);
+ if (ret)
+ return ret;
+ }
+
+ return TEST_OK;
+}
#include "../../util/auxtrace.h"
#include "../../util/tsc.h"
#include "../../util/intel-pt.h"
+#include "../../util/util.h"
#define KiB(x) ((x) * 1024)
#define MiB(x) ((x) * 1024 * 1024)
#include <linux/string.h>
#include <stdlib.h>
+#include "../../util/util.h"
#include "../../util/machine.h"
#include "../../util/map.h"
#include "../../util/symbol.h"
-#include "../../util/sane_ctype.h"
+#include <linux/ctype.h>
#include <symbol/kallsyms.h>
#include "util/data.h"
#include "util/config.h"
#include "util/time-utils.h"
+#include "util/annotate.h"
+#include "util/map.h"
#include <errno.h>
#include <inttypes.h>
struct perf_time_interval *ptime_range;
int range_size;
int range_num;
+ bool has_br_stack;
};
/* Diff command specific HPP columns. */
PERF_HPP_DIFF__WEIGHTED_DIFF,
PERF_HPP_DIFF__FORMULA,
PERF_HPP_DIFF__DELTA_ABS,
+ PERF_HPP_DIFF__CYCLES,
PERF_HPP_DIFF__MAX_INDEX
};
static const char *cpu_list;
static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+static struct addr_location dummy_al;
+
enum {
COMPUTE_DELTA,
COMPUTE_RATIO,
COMPUTE_WEIGHTED_DIFF,
COMPUTE_DELTA_ABS,
+ COMPUTE_CYCLES,
COMPUTE_MAX,
};
[COMPUTE_DELTA_ABS] = "delta-abs",
[COMPUTE_RATIO] = "ratio",
[COMPUTE_WEIGHTED_DIFF] = "wdiff",
+ [COMPUTE_CYCLES] = "cycles",
};
static int compute = COMPUTE_DELTA_ABS;
[COMPUTE_DELTA_ABS] = PERF_HPP_DIFF__DELTA_ABS,
[COMPUTE_RATIO] = PERF_HPP_DIFF__RATIO,
[COMPUTE_WEIGHTED_DIFF] = PERF_HPP_DIFF__WEIGHTED_DIFF,
+ [COMPUTE_CYCLES] = PERF_HPP_DIFF__CYCLES,
};
#define MAX_COL_WIDTH 70
[PERF_HPP_DIFF__FORMULA] = {
.name = "Formula",
.width = MAX_COL_WIDTH,
+ },
+ [PERF_HPP_DIFF__CYCLES] = {
+ .name = "[Program Block Range] Cycles Diff",
+ .width = 70,
}
};
return -1;
}
+static void *block_hist_zalloc(size_t size)
+{
+ struct block_hist *bh;
+
+ bh = zalloc(size + sizeof(*bh));
+ if (!bh)
+ return NULL;
+
+ return &bh->he;
+}
+
+static void block_hist_free(void *he)
+{
+ struct block_hist *bh;
+
+ bh = container_of(he, struct block_hist, he);
+ hists__delete_entries(&bh->block_hists);
+ free(bh);
+}
+
+struct hist_entry_ops block_hist_ops = {
+ .new = block_hist_zalloc,
+ .free = block_hist_free,
+};
+
static int diff__process_sample_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
goto out_put;
}
- if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample, true)) {
- pr_warning("problem incrementing symbol period, skipping event\n");
- goto out_put;
+ if (compute != COMPUTE_CYCLES) {
+ if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample,
+ true)) {
+ pr_warning("problem incrementing symbol period, "
+ "skipping event\n");
+ goto out_put;
+ }
+ } else {
+ if (!hists__add_entry_ops(hists, &block_hist_ops, &al, NULL,
+ NULL, NULL, sample, true)) {
+ pr_warning("problem incrementing symbol period, "
+ "skipping event\n");
+ goto out_put;
+ }
+
+ hist__account_cycles(sample->branch_stack, &al, sample, false);
}
/*
}
}
+static int64_t block_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ struct block_info *bi_l = left->block_info;
+ struct block_info *bi_r = right->block_info;
+ int cmp;
+
+ if (!bi_l->sym || !bi_r->sym) {
+ if (!bi_l->sym && !bi_r->sym)
+ return 0;
+ else if (!bi_l->sym)
+ return -1;
+ else
+ return 1;
+ }
+
+ if (bi_l->sym == bi_r->sym) {
+ if (bi_l->start == bi_r->start) {
+ if (bi_l->end == bi_r->end)
+ return 0;
+ else
+ return (int64_t)(bi_r->end - bi_l->end);
+ } else
+ return (int64_t)(bi_r->start - bi_l->start);
+ } else {
+ cmp = strcmp(bi_l->sym->name, bi_r->sym->name);
+ return cmp;
+ }
+
+ if (bi_l->sym->start != bi_r->sym->start)
+ return (int64_t)(bi_r->sym->start - bi_l->sym->start);
+
+ return (int64_t)(bi_r->sym->end - bi_l->sym->end);
+}
+
+static int64_t block_cycles_diff_cmp(struct hist_entry *left,
+ struct hist_entry *right)
+{
+ bool pairs_left = hist_entry__has_pairs(left);
+ bool pairs_right = hist_entry__has_pairs(right);
+ s64 l, r;
+
+ if (!pairs_left && !pairs_right)
+ return 0;
+
+ l = labs(left->diff.cycles);
+ r = labs(right->diff.cycles);
+ return r - l;
+}
+
+static int64_t block_sort(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ return block_cycles_diff_cmp(right, left);
+}
+
+static void init_block_hist(struct block_hist *bh)
+{
+ __hists__init(&bh->block_hists, &bh->block_list);
+ perf_hpp_list__init(&bh->block_list);
+
+ INIT_LIST_HEAD(&bh->block_fmt.list);
+ INIT_LIST_HEAD(&bh->block_fmt.sort_list);
+ bh->block_fmt.cmp = block_cmp;
+ bh->block_fmt.sort = block_sort;
+ perf_hpp_list__register_sort_field(&bh->block_list,
+ &bh->block_fmt);
+ bh->valid = true;
+}
+
+static void init_block_info(struct block_info *bi, struct symbol *sym,
+ struct cyc_hist *ch, int offset)
+{
+ bi->sym = sym;
+ bi->start = ch->start;
+ bi->end = offset;
+ bi->cycles = ch->cycles;
+ bi->cycles_aggr = ch->cycles_aggr;
+ bi->num = ch->num;
+ bi->num_aggr = ch->num_aggr;
+}
+
+static int process_block_per_sym(struct hist_entry *he)
+{
+ struct annotation *notes;
+ struct cyc_hist *ch;
+ struct block_hist *bh;
+
+ if (!he->ms.map || !he->ms.sym)
+ return 0;
+
+ notes = symbol__annotation(he->ms.sym);
+ if (!notes || !notes->src || !notes->src->cycles_hist)
+ return 0;
+
+ bh = container_of(he, struct block_hist, he);
+ init_block_hist(bh);
+
+ ch = notes->src->cycles_hist;
+ for (unsigned int i = 0; i < symbol__size(he->ms.sym); i++) {
+ if (ch[i].num_aggr) {
+ struct block_info *bi;
+ struct hist_entry *he_block;
+
+ bi = block_info__new();
+ if (!bi)
+ return -1;
+
+ init_block_info(bi, he->ms.sym, &ch[i], i);
+ he_block = hists__add_entry_block(&bh->block_hists,
+ &dummy_al, bi);
+ if (!he_block) {
+ block_info__put(bi);
+ return -1;
+ }
+ }
+ }
+
+ return 0;
+}
+
+static int block_pair_cmp(struct hist_entry *a, struct hist_entry *b)
+{
+ struct block_info *bi_a = a->block_info;
+ struct block_info *bi_b = b->block_info;
+ int cmp;
+
+ if (!bi_a->sym || !bi_b->sym)
+ return -1;
+
+ cmp = strcmp(bi_a->sym->name, bi_b->sym->name);
+
+ if ((!cmp) && (bi_a->start == bi_b->start) && (bi_a->end == bi_b->end))
+ return 0;
+
+ return -1;
+}
+
+static struct hist_entry *get_block_pair(struct hist_entry *he,
+ struct hists *hists_pair)
+{
+ struct rb_root_cached *root = hists_pair->entries_in;
+ struct rb_node *next = rb_first_cached(root);
+ int cmp;
+
+ while (next != NULL) {
+ struct hist_entry *he_pair = rb_entry(next, struct hist_entry,
+ rb_node_in);
+
+ next = rb_next(&he_pair->rb_node_in);
+
+ cmp = block_pair_cmp(he_pair, he);
+ if (!cmp)
+ return he_pair;
+ }
+
+ return NULL;
+}
+
+static void compute_cycles_diff(struct hist_entry *he,
+ struct hist_entry *pair)
+{
+ pair->diff.computed = true;
+ if (pair->block_info->num && he->block_info->num) {
+ pair->diff.cycles =
+ pair->block_info->cycles_aggr / pair->block_info->num_aggr -
+ he->block_info->cycles_aggr / he->block_info->num_aggr;
+ }
+}
+
+static void block_hists_match(struct hists *hists_base,
+ struct hists *hists_pair)
+{
+ struct rb_root_cached *root = hists_base->entries_in;
+ struct rb_node *next = rb_first_cached(root);
+
+ while (next != NULL) {
+ struct hist_entry *he = rb_entry(next, struct hist_entry,
+ rb_node_in);
+ struct hist_entry *pair = get_block_pair(he, hists_pair);
+
+ next = rb_next(&he->rb_node_in);
+
+ if (pair) {
+ hist_entry__add_pair(pair, he);
+ compute_cycles_diff(he, pair);
+ }
+ }
+}
+
+static int filter_cb(struct hist_entry *he, void *arg __maybe_unused)
+{
+ /* Skip the calculation of column length in output_resort */
+ he->filtered = true;
+ return 0;
+}
+
static void hists__precompute(struct hists *hists)
{
struct rb_root_cached *root;
next = rb_first_cached(root);
while (next != NULL) {
+ struct block_hist *bh, *pair_bh;
struct hist_entry *he, *pair;
struct data__file *d;
int i;
he = rb_entry(next, struct hist_entry, rb_node_in);
next = rb_next(&he->rb_node_in);
+ if (compute == COMPUTE_CYCLES)
+ process_block_per_sym(he);
+
data__for_each_file_new(i, d) {
pair = get_pair_data(he, d);
if (!pair)
case COMPUTE_WEIGHTED_DIFF:
compute_wdiff(he, pair);
break;
+ case COMPUTE_CYCLES:
+ process_block_per_sym(pair);
+ bh = container_of(he, struct block_hist, he);
+ pair_bh = container_of(pair, struct block_hist,
+ he);
+
+ if (bh->valid && pair_bh->valid) {
+ block_hists_match(&bh->block_hists,
+ &pair_bh->block_hists);
+ hists__output_resort_cb(&pair_bh->block_hists,
+ NULL, filter_cb);
+ }
+ break;
default:
BUG_ON(1);
}
hists__precompute(hists);
hists__output_resort(hists, NULL);
+ if (compute == COMPUTE_CYCLES)
+ symbol_conf.report_block = true;
+
hists__fprintf(hists, !quiet, 0, 0, 0, stdout,
!symbol_conf.use_callchain);
}
return ret;
}
+static int check_file_brstack(void)
+{
+ struct data__file *d;
+ bool has_br_stack;
+ int i;
+
+ data__for_each_file(i, d) {
+ d->session = perf_session__new(&d->data, false, &pdiff.tool);
+ if (!d->session) {
+ pr_err("Failed to open %s\n", d->data.path);
+ return -1;
+ }
+
+ has_br_stack = perf_header__has_feat(&d->session->header,
+ HEADER_BRANCH_STACK);
+ perf_session__delete(d->session);
+ if (!has_br_stack)
+ return 0;
+ }
+
+ /* Set only all files having branch stacks */
+ pdiff.has_br_stack = true;
+ return 0;
+}
+
static int __cmd_diff(void)
{
struct data__file *d;
OPT_BOOLEAN('b', "baseline-only", &show_baseline_only,
"Show only items with match in baseline"),
OPT_CALLBACK('c', "compute", &compute,
- "delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs)",
+ "delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs),cycles",
"Entries differential computation selection",
setup_compute),
OPT_BOOLEAN('p', "period", &show_period,
return ret;
}
+static int cycles_printf(struct hist_entry *he, struct hist_entry *pair,
+ struct perf_hpp *hpp, int width)
+{
+ struct block_hist *bh = container_of(he, struct block_hist, he);
+ struct block_hist *bh_pair = container_of(pair, struct block_hist, he);
+ struct hist_entry *block_he;
+ struct block_info *bi;
+ char buf[128];
+ char *start_line, *end_line;
+
+ block_he = hists__get_entry(&bh_pair->block_hists, bh->block_idx);
+ if (!block_he) {
+ hpp->skip = true;
+ return 0;
+ }
+
+ /*
+ * Avoid printing the warning "addr2line_init failed for ..."
+ */
+ symbol_conf.disable_add2line_warn = true;
+
+ bi = block_he->block_info;
+
+ start_line = map__srcline(he->ms.map, bi->sym->start + bi->start,
+ he->ms.sym);
+
+ end_line = map__srcline(he->ms.map, bi->sym->start + bi->end,
+ he->ms.sym);
+
+ if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) {
+ scnprintf(buf, sizeof(buf), "[%s -> %s] %4ld",
+ start_line, end_line, block_he->diff.cycles);
+ } else {
+ scnprintf(buf, sizeof(buf), "[%7lx -> %7lx] %4ld",
+ bi->start, bi->end, block_he->diff.cycles);
+ }
+
+ free_srcline(start_line);
+ free_srcline(end_line);
+
+ return scnprintf(hpp->buf, hpp->size, "%*s", width, buf);
+}
+
static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
struct perf_hpp *hpp, struct hist_entry *he,
int comparison_method)
s64 wdiff;
char pfmt[20] = " ";
- if (!pair)
+ if (!pair) {
+ if (comparison_method == COMPUTE_CYCLES) {
+ struct block_hist *bh;
+
+ bh = container_of(he, struct block_hist, he);
+ if (bh->block_idx)
+ hpp->skip = true;
+ }
+
goto no_print;
+ }
switch (comparison_method) {
case COMPUTE_DELTA:
return color_snprintf(hpp->buf, hpp->size,
get_percent_color(wdiff),
pfmt, wdiff);
+ case COMPUTE_CYCLES:
+ return cycles_printf(he, pair, hpp, dfmt->header_width);
default:
BUG_ON(1);
}
return __hpp__color_compare(fmt, hpp, he, COMPUTE_WEIGHTED_DIFF);
}
+static int hpp__color_cycles(struct perf_hpp_fmt *fmt,
+ struct perf_hpp *hpp, struct hist_entry *he)
+{
+ return __hpp__color_compare(fmt, hpp, he, COMPUTE_CYCLES);
+}
+
static void
hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
{
fmt->color = hpp__color_delta;
fmt->sort = hist_entry__cmp_delta_abs;
break;
+ case PERF_HPP_DIFF__CYCLES:
+ fmt->color = hpp__color_cycles;
+ fmt->sort = hist_entry__cmp_nop;
+ break;
default:
fmt->sort = hist_entry__cmp_nop;
break;
case COMPUTE_DELTA_ABS:
fmt->sort = hist_entry__cmp_delta_abs_idx;
break;
+ case COMPUTE_CYCLES:
+ /*
+ * Should set since 'fmt->sort' is called without
+ * checking valid during sorting
+ */
+ fmt->sort = hist_entry__cmp_nop;
+ break;
default:
BUG_ON(1);
}
if (quiet)
perf_quiet_option();
+ symbol__annotation_init();
+
if (symbol__init(NULL) < 0)
return -1;
if (data_init(argc, argv) < 0)
return -1;
+ if (check_file_brstack() < 0)
+ return -1;
+
+ if (compute == COMPUTE_CYCLES && !pdiff.has_br_stack)
+ return -1;
+
if (ui_init() < 0)
return -1;
#include "util/cpumap.h"
#include "util/debug.h"
+#include "util/string2.h"
#include <linux/kernel.h>
#include <linux/rbtree.h>
#include <locale.h>
#include <regex.h>
-#include "sane_ctype.h"
+#include <linux/ctype.h>
static int kmem_slab;
static int kmem_page;
OPT_BOOLEAN_FLAG(0, "all-user", &record.opts.all_user,
"Configure all used events to run in user space.",
PARSE_OPT_EXCLUSIVE),
+ OPT_BOOLEAN(0, "kernel-callchains", &record.opts.kernel_callchains,
+ "collect kernel callchains"),
+ OPT_BOOLEAN(0, "user-callchains", &record.opts.user_callchains,
+ "collect user callchains"),
OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path",
"clang binary to use for compiling BPF scriptlets"),
OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options",
#include <errno.h>
#include <inttypes.h>
#include <regex.h>
-#include "sane_ctype.h"
+#include <linux/ctype.h>
#include <signal.h>
#include <linux/bitmap.h>
#include <linux/stringify.h>
pr_err("time quantum cannot be 0");
return -1;
}
- while (isspace(*end))
- end++;
+ end = skip_spaces(end);
if (*end == 0)
return 0;
if (!strcmp(end, "s")) {
&report.range_num);
if (ret < 0)
goto error;
+
+ itrace_synth_opts__set_time_range(&itrace_synth_opts,
+ report.ptime_range,
+ report.range_num);
}
if (session->tevent.pevent &&
ret = 0;
error:
- if (report.ptime_range)
+ if (report.ptime_range) {
+ itrace_synth_opts__clear_time_range(&itrace_synth_opts);
zfree(&report.ptime_range);
+ }
zstd_fini(&(session->zstd_data));
perf_session__delete(session);
return ret;
#include "util/thread_map.h"
#include "util/color.h"
#include "util/stat.h"
+#include "util/string2.h"
#include "util/callchain.h"
#include "util/time-utils.h"
#include <api/fs/fs.h>
#include <linux/time64.h>
-#include "sane_ctype.h"
+#include <linux/ctype.h>
#define PR_SET_NAME 15 /* Set process name */
#define MAX_CPUS 4096
#include <unistd.h>
#include <subcmd/pager.h>
-#include "sane_ctype.h"
+#include <linux/ctype.h>
static char const *script_name;
static char const *generate_script_lang;
PERF_OUTPUT_METRIC = 1U << 28,
PERF_OUTPUT_MISC = 1U << 29,
PERF_OUTPUT_SRCCODE = 1U << 30,
+ PERF_OUTPUT_IPC = 1U << 31,
};
struct output_option {
{.str = "metric", .field = PERF_OUTPUT_METRIC},
{.str = "misc", .field = PERF_OUTPUT_MISC},
{.str = "srccode", .field = PERF_OUTPUT_SRCCODE},
+ {.str = "ipc", .field = PERF_OUTPUT_IPC},
};
enum {
return printed;
}
+static int perf_sample__fprintf_ipc(struct perf_sample *sample,
+ struct perf_event_attr *attr, FILE *fp)
+{
+ unsigned int ipc;
+
+ if (!PRINT_FIELD(IPC) || !sample->cyc_cnt || !sample->insn_cnt)
+ return 0;
+
+ ipc = (sample->insn_cnt * 100) / sample->cyc_cnt;
+
+ return fprintf(fp, " \t IPC: %u.%02u (%" PRIu64 "/%" PRIu64 ") ",
+ ipc / 100, ipc % 100, sample->insn_cnt, sample->cyc_cnt);
+}
+
static int perf_sample__fprintf_bts(struct perf_sample *sample,
struct perf_evsel *evsel,
struct thread *thread,
printed += perf_sample__fprintf_addr(sample, thread, attr, fp);
}
+ printed += perf_sample__fprintf_ipc(sample, attr, fp);
+
if (print_srcline_last)
printed += map__fprintf_srcline(al->map, al->addr, "\n ", fp);
bool show_namespace_events;
bool show_lost_events;
bool show_round_events;
+ bool show_bpf_events;
bool allocated;
bool per_event_dump;
struct cpu_map *cpus;
if (PRINT_FIELD(PHYS_ADDR))
fprintf(fp, "%16" PRIx64, sample->phys_addr);
+
+ perf_sample__fprintf_ipc(sample, attr, fp);
+
fprintf(fp, "\n");
if (PRINT_FIELD(SRCCODE)) {
return 0;
}
+static int
+process_bpf_events(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ struct thread *thread;
+ struct perf_script *script = container_of(tool, struct perf_script, tool);
+ struct perf_session *session = script->session;
+ struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+
+ if (machine__process_ksymbol(machine, event, sample) < 0)
+ return -1;
+
+ if (!evsel->attr.sample_id_all) {
+ perf_event__fprintf(event, stdout);
+ return 0;
+ }
+
+ thread = machine__findnew_thread(machine, sample->pid, sample->tid);
+ if (thread == NULL) {
+ pr_debug("problem processing MMAP event, skipping it.\n");
+ return -1;
+ }
+
+ if (!filter_cpu(sample)) {
+ perf_sample__fprintf_start(sample, thread, evsel,
+ event->header.type, stdout);
+ perf_event__fprintf(event, stdout);
+ }
+
+ thread__put(thread);
+ return 0;
+}
+
static void sig_handler(int sig __maybe_unused)
{
session_done = 1;
script->tool.ordered_events = false;
script->tool.finished_round = process_finished_round_event;
}
+ if (script->show_bpf_events) {
+ script->tool.ksymbol = process_bpf_events;
+ script->tool.bpf_event = process_bpf_events;
+ }
if (perf_script__setup_per_event_dump(script)) {
pr_err("Couldn't create the per event dump files\n");
return -1;
while (fgets(line, sizeof(line), fp)) {
- p = ltrim(line);
+ p = skip_spaces(line);
if (strlen(p) == 0)
continue;
if (*p != '#')
if (strlen(p) && *p == '!')
continue;
- p = ltrim(p);
+ p = skip_spaces(p);
if (strlen(p) && p[strlen(p) - 1] == '\n')
p[strlen(p) - 1] = '\0';
if (!strncmp(p, "description:", strlen("description:"))) {
p += strlen("description:");
- desc->half_liner = strdup(ltrim(p));
+ desc->half_liner = strdup(skip_spaces(p));
continue;
}
if (!strncmp(p, "args:", strlen("args:"))) {
p += strlen("args:");
- desc->args = strdup(ltrim(p));
+ desc->args = strdup(skip_spaces(p));
continue;
}
}
return -1;
while (fgets(line, sizeof(line), fp)) {
- p = ltrim(line);
+ p = skip_spaces(line);
if (*p == '#')
continue;
break;
p += 2;
- p = ltrim(p);
+ p = skip_spaces(p);
len = strcspn(p, " \t");
if (!len)
break;
parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0);
itrace_parse_synth_opts(opt, "cewp", 0);
symbol_conf.nanosecs = true;
+ symbol_conf.pad_output_len_dso = 50;
return 0;
}
"Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
"addr,symoff,srcline,period,iregs,uregs,brstack,"
"brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
- "callindent,insn,insnlen,synth,phys_addr,metric,misc",
+ "callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc",
parse_output_fields),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
"Show lost events (if recorded)"),
OPT_BOOLEAN('\0', "show-round-events", &script.show_round_events,
"Show round events (if recorded)"),
+ OPT_BOOLEAN('\0', "show-bpf-events", &script.show_bpf_events,
+ "Show bpf related events (if recorded)"),
OPT_BOOLEAN('\0', "per-event-dump", &script.per_event_dump,
"Dump trace output to files named by the monitored events"),
OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
"Time span of interest (start,stop)"),
OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name,
"Show inline function"),
+ OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory",
+ "guest mount directory under which every guest os"
+ " instance has a subdir"),
+ OPT_STRING(0, "guestvmlinux", &symbol_conf.default_guest_vmlinux_name,
+ "file", "file saving guest os vmlinux"),
+ OPT_STRING(0, "guestkallsyms", &symbol_conf.default_guest_kallsyms,
+ "file", "file saving guest os /proc/kallsyms"),
+ OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules,
+ "file", "file saving guest os /proc/modules"),
OPT_END()
};
const char * const script_subcommands[] = { "record", "report", NULL };
argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
+ if (symbol_conf.guestmount ||
+ symbol_conf.default_guest_vmlinux_name ||
+ symbol_conf.default_guest_kallsyms ||
+ symbol_conf.default_guest_modules) {
+ /*
+ * Enable guest sample processing.
+ */
+ perf_guest = true;
+ }
+
data.path = input_name;
data.force = symbol_conf.force;
&script.range_num);
if (err < 0)
goto out_delete;
+
+ itrace_synth_opts__set_time_range(&itrace_synth_opts,
+ script.ptime_range,
+ script.range_num);
}
err = __cmd_script(&script);
flush_scripting();
out_delete:
- if (script.ptime_range)
+ if (script.ptime_range) {
+ itrace_synth_opts__clear_time_range(&itrace_synth_opts);
zfree(&script.ptime_range);
+ }
perf_evlist__free_stats(session->evlist);
perf_session__delete(session);
#include <sys/time.h>
#include <sys/resource.h>
-#include "sane_ctype.h"
+#include <linux/ctype.h>
#define DEFAULT_SEPARATOR " "
#define FREEZE_ON_SMI_PATH "devices/cpu/freeze_on_smi"
"stop workload and print counts after a timeout period in ms (>= 10ms)"),
OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
"aggregate counts per processor socket", AGGR_SOCKET),
+ OPT_SET_UINT(0, "per-die", &stat_config.aggr_mode,
+ "aggregate counts per processor die", AGGR_DIE),
OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode,
"aggregate counts per physical processor core", AGGR_CORE),
OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode,
return cpu_map__get_socket(map, cpu, NULL);
}
+static int perf_stat__get_die(struct perf_stat_config *config __maybe_unused,
+ struct cpu_map *map, int cpu)
+{
+ return cpu_map__get_die(map, cpu, NULL);
+}
+
static int perf_stat__get_core(struct perf_stat_config *config __maybe_unused,
struct cpu_map *map, int cpu)
{
return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx);
}
+static int perf_stat__get_die_cached(struct perf_stat_config *config,
+ struct cpu_map *map, int idx)
+{
+ return perf_stat__get_aggr(config, perf_stat__get_die, map, idx);
+}
+
static int perf_stat__get_core_cached(struct perf_stat_config *config,
struct cpu_map *map, int idx)
{
}
stat_config.aggr_get_id = perf_stat__get_socket_cached;
break;
+ case AGGR_DIE:
+ if (cpu_map__build_die_map(evsel_list->cpus, &stat_config.aggr_map)) {
+ perror("cannot build die map");
+ return -1;
+ }
+ stat_config.aggr_get_id = perf_stat__get_die_cached;
+ break;
case AGGR_CORE:
if (cpu_map__build_core_map(evsel_list->cpus, &stat_config.aggr_map)) {
perror("cannot build core map");
return cpu == -1 ? -1 : env->cpu[cpu].socket_id;
}
+static int perf_env__get_die(struct cpu_map *map, int idx, void *data)
+{
+ struct perf_env *env = data;
+ int die_id = -1, cpu = perf_env__get_cpu(env, map, idx);
+
+ if (cpu != -1) {
+ /*
+ * Encode socket in bit range 15:8
+ * die_id is relative to socket,
+ * we need a global id. So we combine
+ * socket + die id
+ */
+ if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.\n"))
+ return -1;
+
+ if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n"))
+ return -1;
+
+ die_id = (env->cpu[cpu].socket_id << 8) | (env->cpu[cpu].die_id & 0xff);
+ }
+
+ return die_id;
+}
+
static int perf_env__get_core(struct cpu_map *map, int idx, void *data)
{
struct perf_env *env = data;
int core = -1, cpu = perf_env__get_cpu(env, map, idx);
if (cpu != -1) {
- int socket_id = env->cpu[cpu].socket_id;
-
/*
- * Encode socket in upper 16 bits
- * core_id is relative to socket, and
+ * Encode socket in bit range 31:24
+ * encode die id in bit range 23:16
+ * core_id is relative to socket and die,
* we need a global id. So we combine
- * socket + core id.
+ * socket + die id + core id
*/
- core = (socket_id << 16) | (env->cpu[cpu].core_id & 0xffff);
+ if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.\n"))
+ return -1;
+
+ if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n"))
+ return -1;
+
+ if (WARN_ONCE(env->cpu[cpu].core_id >> 16, "The core id number is too big.\n"))
+ return -1;
+
+ core = (env->cpu[cpu].socket_id << 24) |
+ (env->cpu[cpu].die_id << 16) |
+ (env->cpu[cpu].core_id & 0xffff);
}
return core;
return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env);
}
+static int perf_env__build_die_map(struct perf_env *env, struct cpu_map *cpus,
+ struct cpu_map **diep)
+{
+ return cpu_map__build_map(cpus, diep, perf_env__get_die, env);
+}
+
static int perf_env__build_core_map(struct perf_env *env, struct cpu_map *cpus,
struct cpu_map **corep)
{
{
return perf_env__get_socket(map, idx, &perf_stat.session->header.env);
}
+static int perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused,
+ struct cpu_map *map, int idx)
+{
+ return perf_env__get_die(map, idx, &perf_stat.session->header.env);
+}
static int perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused,
struct cpu_map *map, int idx)
}
stat_config.aggr_get_id = perf_stat__get_socket_file;
break;
+ case AGGR_DIE:
+ if (perf_env__build_die_map(env, evsel_list->cpus, &stat_config.aggr_map)) {
+ perror("cannot build die map");
+ return -1;
+ }
+ stat_config.aggr_get_id = perf_stat__get_die_file;
+ break;
case AGGR_CORE:
if (perf_env__build_core_map(env, evsel_list->cpus, &stat_config.aggr_map)) {
perror("cannot build core map");
OPT_STRING('i', "input", &input_name, "file", "input file name"),
OPT_SET_UINT(0, "per-socket", &perf_stat.aggr_mode,
"aggregate counts per processor socket", AGGR_SOCKET),
+ OPT_SET_UINT(0, "per-die", &perf_stat.aggr_mode,
+ "aggregate counts per processor die", AGGR_DIE),
OPT_SET_UINT(0, "per-core", &perf_stat.aggr_mode,
"aggregate counts per physical processor core", AGGR_CORE),
OPT_SET_UINT('A', "no-aggr", &perf_stat.aggr_mode,
#include "util/cpumap.h"
#include "util/xyarray.h"
#include "util/sort.h"
+#include "util/string2.h"
#include "util/term.h"
#include "util/intlist.h"
#include "util/parse-branch-options.h"
#include <linux/time64.h>
#include <linux/types.h>
-#include "sane_ctype.h"
+#include <linux/ctype.h>
static volatile int done;
static volatile int resize;
init_process_thread(top);
+ if (opts->record_namespaces)
+ top->tool.namespace_events = true;
+
ret = perf_event__synthesize_bpf_events(top->session, perf_event__process,
&top->session->machines.host,
&top->record_opts);
if (ret < 0)
- pr_warning("Couldn't synthesize bpf events.\n");
+ pr_debug("Couldn't synthesize BPF events: Pre-existing BPF programs won't have symbols resolved.\n");
machine__synthesize_threads(&top->session->machines.host, &opts->target,
top->evlist->threads, false,
OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"),
OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize,
"number of thread to run event synthesize"),
+ OPT_BOOLEAN(0, "namespaces", &opts->record_namespaces,
+ "Record namespaces events"),
OPT_END()
};
struct perf_evlist *sb_evlist = NULL;
#include <fcntl.h>
#include <sys/sysmacros.h>
-#include "sane_ctype.h"
+#include <linux/ctype.h>
#ifndef O_CLOEXEC
# define O_CLOEXEC 02000000
#define SCA_STRARRAY syscall_arg__scnprintf_strarray
+size_t syscall_arg__scnprintf_strarray_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+ return strarray__scnprintf_flags(arg->parm, bf, size, arg->show_string_prefix, arg->val);
+}
+
size_t strarrays__scnprintf(struct strarrays *sas, char *bf, size_t size, const char *intfmt, bool show_prefix, int val)
{
size_t printed;
};
static DEFINE_STRARRAY(bpf_cmd, "BPF_");
+static const char *fsmount_flags[] = {
+ [1] = "CLOEXEC",
+};
+static DEFINE_STRARRAY(fsmount_flags, "FSMOUNT_");
+
+#include "trace/beauty/generated/fsconfig_arrays.c"
+
+static DEFINE_STRARRAY(fsconfig_cmds, "FSCONFIG_");
+
static const char *epoll_ctl_ops[] = { "ADD", "DEL", "MOD", };
static DEFINE_STRARRAY_OFFSET(epoll_ctl_ops, "EPOLL_CTL_", 1);
{ .scnprintf = SCA_STRARRAY, \
.parm = &strarray__##array, }
+#define STRARRAY_FLAGS(name, array) \
+ { .scnprintf = SCA_STRARRAY_FLAGS, \
+ .parm = &strarray__##array, }
+
#include "trace/beauty/arch_errno_names.c"
#include "trace/beauty/eventfd.c"
#include "trace/beauty/futex_op.c"
[2] = { .scnprintf = SCA_FCNTL_ARG, /* arg */ }, }, },
{ .name = "flock",
.arg = { [1] = { .scnprintf = SCA_FLOCK, /* cmd */ }, }, },
+ { .name = "fsconfig",
+ .arg = { [1] = STRARRAY(cmd, fsconfig_cmds), }, },
+ { .name = "fsmount",
+ .arg = { [1] = STRARRAY_FLAGS(flags, fsmount_flags),
+ [2] = { .scnprintf = SCA_FSMOUNT_ATTR_FLAGS, /* attr_flags */ }, }, },
+ { .name = "fspick",
+ .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ },
+ [1] = { .scnprintf = SCA_FILENAME, /* path */ },
+ [2] = { .scnprintf = SCA_FSPICK_FLAGS, /* flags */ }, }, },
{ .name = "fstat", .alias = "newfstat", },
{ .name = "fstatat", .alias = "newfstatat", },
{ .name = "futex",
.arg = { [0] = { .scnprintf = SCA_FILENAME, /* dev_name */ },
[3] = { .scnprintf = SCA_MOUNT_FLAGS, /* flags */
.mask_val = SCAMV_MOUNT_FLAGS, /* flags */ }, }, },
+ { .name = "move_mount",
+ .arg = { [0] = { .scnprintf = SCA_FDAT, /* from_dfd */ },
+ [1] = { .scnprintf = SCA_FILENAME, /* from_pathname */ },
+ [2] = { .scnprintf = SCA_FDAT, /* to_dfd */ },
+ [3] = { .scnprintf = SCA_FILENAME, /* to_pathname */ },
+ [4] = { .scnprintf = SCA_MOVE_MOUNT_FLAGS, /* flags */ }, }, },
{ .name = "mprotect",
.arg = { [0] = { .scnprintf = SCA_HEX, /* start */ },
[2] = { .scnprintf = SCA_MMAP_PROT, /* prot */ }, }, },
.arg = { [0] = { .scnprintf = SCA_FILENAME, /* specialfile */ }, }, },
{ .name = "symlinkat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
+ { .name = "sync_file_range",
+ .arg = { [3] = { .scnprintf = SCA_SYNC_FILE_RANGE_FLAGS, /* flags */ }, }, },
{ .name = "tgkill",
.arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
{ .name = "tkill",
struct syscall_arg_fmt *arg_fmt;
};
+/*
+ * Must match what is in the BPF program:
+ *
+ * tools/perf/examples/bpf/augmented_raw_syscalls.c
+ */
struct bpf_map_syscall_entry {
bool enabled;
+ u16 string_args_len[6];
};
/*
static size_t syscall_arg__scnprintf_augmented_string(struct syscall_arg *arg, char *bf, size_t size)
{
struct augmented_arg *augmented_arg = arg->augmented.args;
+ size_t printed = scnprintf(bf, size, "\"%.*s\"", augmented_arg->size, augmented_arg->value);
+ /*
+ * So that the next arg with a payload can consume its augmented arg, i.e. for rename* syscalls
+ * we would have two strings, each prefixed by its size.
+ */
+ int consumed = sizeof(*augmented_arg) + augmented_arg->size;
+
+ arg->augmented.args = ((void *)arg->augmented.args) + consumed;
+ arg->augmented.size -= consumed;
- return scnprintf(bf, size, "\"%.*s\"", augmented_arg->size, augmented_arg->value);
+ return printed;
}
static size_t syscall_arg__scnprintf_filename(char *bf, size_t size,
if (sc->fmt && sc->fmt->arg[idx].scnprintf)
continue;
+ len = strlen(field->name);
+
if (strcmp(field->type, "const char *") == 0 &&
- (strcmp(field->name, "filename") == 0 ||
- strcmp(field->name, "path") == 0 ||
- strcmp(field->name, "pathname") == 0))
+ ((len >= 4 && strcmp(field->name + len - 4, "name") == 0) ||
+ strstr(field->name, "path") != NULL))
sc->arg_fmt[idx].scnprintf = SCA_FILENAME;
else if ((field->flags & TEP_FIELD_IS_POINTER) || strstr(field->name, "addr"))
sc->arg_fmt[idx].scnprintf = SCA_PTR;
else if ((strcmp(field->type, "int") == 0 ||
strcmp(field->type, "unsigned int") == 0 ||
strcmp(field->type, "long") == 0) &&
- (len = strlen(field->name)) >= 2 &&
- strcmp(field->name + len - 2, "fd") == 0) {
+ len >= 2 && strcmp(field->name + len - 2, "fd") == 0) {
/*
* /sys/kernel/tracing/events/syscalls/sys_enter*
* egrep 'field:.*fd;' .../format|sed -r 's/.*field:([a-z ]+) [a-z_]*fd.+/\1/g'|sort|uniq -c
static int trace__validate_ev_qualifier(struct trace *trace)
{
- int err = 0, i;
- size_t nr_allocated;
+ int err = 0;
+ bool printed_invalid_prefix = false;
struct str_node *pos;
+ size_t nr_used = 0, nr_allocated = strlist__nr_entries(trace->ev_qualifier);
- trace->ev_qualifier_ids.nr = strlist__nr_entries(trace->ev_qualifier);
- trace->ev_qualifier_ids.entries = malloc(trace->ev_qualifier_ids.nr *
+ trace->ev_qualifier_ids.entries = malloc(nr_allocated *
sizeof(trace->ev_qualifier_ids.entries[0]));
if (trace->ev_qualifier_ids.entries == NULL) {
goto out;
}
- nr_allocated = trace->ev_qualifier_ids.nr;
- i = 0;
-
strlist__for_each_entry(pos, trace->ev_qualifier) {
const char *sc = pos->s;
int id = syscalltbl__id(trace->sctbl, sc), match_next = -1;
if (id >= 0)
goto matches;
- if (err == 0) {
- fputs("Error:\tInvalid syscall ", trace->output);
- err = -EINVAL;
+ if (!printed_invalid_prefix) {
+ pr_debug("Skipping unknown syscalls: ");
+ printed_invalid_prefix = true;
} else {
- fputs(", ", trace->output);
+ pr_debug(", ");
}
- fputs(sc, trace->output);
+ pr_debug("%s", sc);
+ continue;
}
matches:
- trace->ev_qualifier_ids.entries[i++] = id;
+ trace->ev_qualifier_ids.entries[nr_used++] = id;
if (match_next == -1)
continue;
id = syscalltbl__strglobmatch_next(trace->sctbl, sc, &match_next);
if (id < 0)
break;
- if (nr_allocated == trace->ev_qualifier_ids.nr) {
+ if (nr_allocated == nr_used) {
void *entries;
nr_allocated += 8;
}
trace->ev_qualifier_ids.entries = entries;
}
- trace->ev_qualifier_ids.nr++;
- trace->ev_qualifier_ids.entries[i++] = id;
+ trace->ev_qualifier_ids.entries[nr_used++] = id;
}
}
- if (err < 0) {
- fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'"
- "\nHint:\tand: 'man syscalls'\n", trace->output);
-out_free:
- zfree(&trace->ev_qualifier_ids.entries);
- trace->ev_qualifier_ids.nr = 0;
- }
+ trace->ev_qualifier_ids.nr = nr_used;
out:
+ if (printed_invalid_prefix)
+ pr_debug("\n");
return err;
+out_free:
+ zfree(&trace->ev_qualifier_ids.entries);
+ trace->ev_qualifier_ids.nr = 0;
+ goto out;
}
/*
}
#ifdef HAVE_LIBBPF_SUPPORT
+static void trace__init_bpf_map_syscall_args(struct trace *trace, int id, struct bpf_map_syscall_entry *entry)
+{
+ struct syscall *sc = trace__syscall_info(trace, NULL, id);
+ int arg = 0;
+
+ if (sc == NULL)
+ goto out;
+
+ for (; arg < sc->nr_args; ++arg) {
+ entry->string_args_len[arg] = 0;
+ if (sc->arg_fmt[arg].scnprintf == SCA_FILENAME) {
+ /* Should be set like strace -s strsize */
+ entry->string_args_len[arg] = PATH_MAX;
+ }
+ }
+out:
+ for (; arg < 6; ++arg)
+ entry->string_args_len[arg] = 0;
+}
static int trace__set_ev_qualifier_bpf_filter(struct trace *trace)
{
int fd = bpf_map__fd(trace->syscalls.map);
for (i = 0; i < trace->ev_qualifier_ids.nr; ++i) {
int key = trace->ev_qualifier_ids.entries[i];
+ if (value.enabled)
+ trace__init_bpf_map_syscall_args(trace, key, &value);
+
err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST);
if (err)
break;
int err = 0, key;
for (key = 0; key < trace->sctbl->syscalls.nr_entries; ++key) {
+ if (enabled)
+ trace__init_bpf_map_syscall_args(trace, key, &value);
+
err = bpf_map_update_elem(fd, &key, &value, BPF_ANY);
if (err)
break;
struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
"event selector. use 'perf list' to list available events",
parse_events_option);
- err = parse_events_option(&o, value, 0);
+ /*
+ * We can't propagate parse_event_option() return, as it is 1
+ * for failure while perf_config() expects -1.
+ */
+ if (parse_events_option(&o, value, 0))
+ err = -1;
} else if (!strcmp(var, "trace.show_timestamp")) {
trace->show_tstamp = perf_config_bool(var, value);
} else if (!strcmp(var, "trace.show_duration")) {
check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"'
+check include/linux/ctype.h '-I "isdigit("'
+check lib/ctype.c '-I "^EXPORT_SYMBOL" -I "^#include <linux/export.h>" -B'
# diff non-symmetric files
check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl
/* bpf-output associated map */
bpf_map(__augmented_syscalls__, PERF_EVENT_ARRAY, int, u32, __NR_CPUS__);
+/*
+ * string_args_len: one per syscall arg, 0 means not a string or don't copy it,
+ * PATH_MAX for copying everything, any other value to limit
+ * it a la 'strace -s strsize'.
+ */
struct syscall {
bool enabled;
+ u16 string_args_len[6];
};
bpf_map(syscalls, ARRAY, int, struct syscall, 512);
struct augmented_filename {
unsigned int size;
- int reserved;
+ int err;
char value[PATH_MAX];
};
-/* syscalls where the first arg is a string */
-#define SYS_OPEN 2
-#define SYS_STAT 4
-#define SYS_LSTAT 6
-#define SYS_ACCESS 21
-#define SYS_EXECVE 59
-#define SYS_TRUNCATE 76
-#define SYS_CHDIR 80
-#define SYS_RENAME 82
-#define SYS_MKDIR 83
-#define SYS_RMDIR 84
-#define SYS_CREAT 85
-#define SYS_LINK 86
-#define SYS_UNLINK 87
-#define SYS_SYMLINK 88
-#define SYS_READLINK 89
-#define SYS_CHMOD 90
-#define SYS_CHOWN 92
-#define SYS_LCHOWN 94
-#define SYS_MKNOD 133
-#define SYS_STATFS 137
-#define SYS_PIVOT_ROOT 155
-#define SYS_CHROOT 161
-#define SYS_ACCT 163
-#define SYS_SWAPON 167
-#define SYS_SWAPOFF 168
-#define SYS_DELETE_MODULE 176
-#define SYS_SETXATTR 188
-#define SYS_LSETXATTR 189
-#define SYS_GETXATTR 191
-#define SYS_LGETXATTR 192
-#define SYS_LISTXATTR 194
-#define SYS_LLISTXATTR 195
-#define SYS_REMOVEXATTR 197
-#define SYS_LREMOVEXATTR 198
-#define SYS_MQ_OPEN 240
-#define SYS_MQ_UNLINK 241
-#define SYS_ADD_KEY 248
-#define SYS_REQUEST_KEY 249
-#define SYS_SYMLINKAT 266
-#define SYS_MEMFD_CREATE 319
-
-/* syscalls where the first arg is a string */
-
-#define SYS_PWRITE64 18
-#define SYS_EXECVE 59
-#define SYS_RENAME 82
-#define SYS_QUOTACTL 179
-#define SYS_FSETXATTR 190
-#define SYS_FGETXATTR 193
-#define SYS_FREMOVEXATTR 199
-#define SYS_MQ_TIMEDSEND 242
-#define SYS_REQUEST_KEY 249
-#define SYS_INOTIFY_ADD_WATCH 254
-#define SYS_OPENAT 257
-#define SYS_MKDIRAT 258
-#define SYS_MKNODAT 259
-#define SYS_FCHOWNAT 260
-#define SYS_FUTIMESAT 261
-#define SYS_NEWFSTATAT 262
-#define SYS_UNLINKAT 263
-#define SYS_RENAMEAT 264
-#define SYS_LINKAT 265
-#define SYS_READLINKAT 267
-#define SYS_FCHMODAT 268
-#define SYS_FACCESSAT 269
-#define SYS_UTIMENSAT 280
-#define SYS_NAME_TO_HANDLE_AT 303
-#define SYS_FINIT_MODULE 313
-#define SYS_RENAMEAT2 316
-#define SYS_EXECVEAT 322
-#define SYS_STATX 332
-
pid_filter(pids_filtered);
struct augmented_args_filename {
bpf_map(augmented_filename_map, PERCPU_ARRAY, int, struct augmented_args_filename, 1);
+static inline
+unsigned int augmented_filename__read(struct augmented_filename *augmented_filename,
+ const void *filename_arg, unsigned int filename_len)
+{
+ unsigned int len = sizeof(*augmented_filename);
+ int size = probe_read_str(&augmented_filename->value, filename_len, filename_arg);
+
+ augmented_filename->size = augmented_filename->err = 0;
+ /*
+ * probe_read_str may return < 0, e.g. -EFAULT
+ * So we leave that in the augmented_filename->size that userspace will
+ */
+ if (size > 0) {
+ len -= sizeof(augmented_filename->value) - size;
+ len &= sizeof(augmented_filename->value) - 1;
+ augmented_filename->size = size;
+ } else {
+ /*
+ * So that username notice the error while still being able
+ * to skip this augmented arg record
+ */
+ augmented_filename->err = size;
+ len = offsetof(struct augmented_filename, value);
+ }
+
+ return len;
+}
+
SEC("raw_syscalls:sys_enter")
int sys_enter(struct syscall_enter_args *args)
{
struct augmented_args_filename *augmented_args;
- unsigned int len = sizeof(*augmented_args);
- const void *filename_arg = NULL;
+ /*
+ * We start len, the amount of data that will be in the perf ring
+ * buffer, if this is not filtered out by one of pid_filter__has(),
+ * syscall->enabled, etc, with the non-augmented raw syscall payload,
+ * i.e. sizeof(augmented_args->args).
+ *
+ * We'll add to this as we add augmented syscalls right after that
+ * initial, non-augmented raw_syscalls:sys_enter payload.
+ */
+ unsigned int len = sizeof(augmented_args->args);
struct syscall *syscall;
int key = 0;
* after the ctx memory access to prevent their down stream merging.
*/
/*
- * This table of what args are strings will be provided by userspace,
- * in the syscalls map, i.e. we will already have to do the lookup to
- * see if this specific syscall is filtered, so we can as well get more
- * info about what syscall args are strings or pointers, and how many
- * bytes to copy, per arg, etc.
+ * For now copy just the first string arg, we need to improve the protocol
+ * and have more than one.
*
- * For now hard code it, till we have all the basic mechanisms in place
- * to automate everything and make the kernel part be completely driven
- * by information obtained in userspace for each kernel version and
- * processor architecture, making the kernel part the same no matter what
- * kernel version or processor architecture it runs on.
- */
- switch (augmented_args->args.syscall_nr) {
- case SYS_ACCT:
- case SYS_ADD_KEY:
- case SYS_CHDIR:
- case SYS_CHMOD:
- case SYS_CHOWN:
- case SYS_CHROOT:
- case SYS_CREAT:
- case SYS_DELETE_MODULE:
- case SYS_EXECVE:
- case SYS_GETXATTR:
- case SYS_LCHOWN:
- case SYS_LGETXATTR:
- case SYS_LINK:
- case SYS_LISTXATTR:
- case SYS_LLISTXATTR:
- case SYS_LREMOVEXATTR:
- case SYS_LSETXATTR:
- case SYS_LSTAT:
- case SYS_MEMFD_CREATE:
- case SYS_MKDIR:
- case SYS_MKNOD:
- case SYS_MQ_OPEN:
- case SYS_MQ_UNLINK:
- case SYS_PIVOT_ROOT:
- case SYS_READLINK:
- case SYS_REMOVEXATTR:
- case SYS_RENAME:
- case SYS_REQUEST_KEY:
- case SYS_RMDIR:
- case SYS_SETXATTR:
- case SYS_STAT:
- case SYS_STATFS:
- case SYS_SWAPOFF:
- case SYS_SWAPON:
- case SYS_SYMLINK:
- case SYS_SYMLINKAT:
- case SYS_TRUNCATE:
- case SYS_UNLINK:
- case SYS_ACCESS:
- case SYS_OPEN: filename_arg = (const void *)args->args[0];
+ * Using the unrolled loop is not working, only when we do it manually,
+ * check this out later...
+
+ u8 arg;
+#pragma clang loop unroll(full)
+ for (arg = 0; arg < 6; ++arg) {
+ if (syscall->string_args_len[arg] != 0) {
+ filename_len = syscall->string_args_len[arg];
+ filename_arg = (const void *)args->args[arg];
__asm__ __volatile__("": : :"memory");
- break;
- case SYS_EXECVEAT:
- case SYS_FACCESSAT:
- case SYS_FCHMODAT:
- case SYS_FCHOWNAT:
- case SYS_FGETXATTR:
- case SYS_FINIT_MODULE:
- case SYS_FREMOVEXATTR:
- case SYS_FSETXATTR:
- case SYS_FUTIMESAT:
- case SYS_INOTIFY_ADD_WATCH:
- case SYS_LINKAT:
- case SYS_MKDIRAT:
- case SYS_MKNODAT:
- case SYS_MQ_TIMEDSEND:
- case SYS_NAME_TO_HANDLE_AT:
- case SYS_NEWFSTATAT:
- case SYS_PWRITE64:
- case SYS_QUOTACTL:
- case SYS_READLINKAT:
- case SYS_RENAMEAT:
- case SYS_RENAMEAT2:
- case SYS_STATX:
- case SYS_UNLINKAT:
- case SYS_UTIMENSAT:
- case SYS_OPENAT: filename_arg = (const void *)args->args[1];
- break;
- }
-
- if (filename_arg != NULL) {
- augmented_args->filename.reserved = 0;
- augmented_args->filename.size = probe_read_str(&augmented_args->filename.value,
- sizeof(augmented_args->filename.value),
- filename_arg);
- if (augmented_args->filename.size < sizeof(augmented_args->filename.value)) {
- len -= sizeof(augmented_args->filename.value) - augmented_args->filename.size;
- len &= sizeof(augmented_args->filename.value) - 1;
+ break;
}
- } else {
- len = sizeof(augmented_args->args);
}
+ verifier log:
+
+; if (syscall->string_args_len[arg] != 0) {
+37: (69) r3 = *(u16 *)(r0 +2)
+ R0=map_value(id=0,off=0,ks=4,vs=14,imm=0) R1_w=inv0 R2_w=map_value(id=0,off=2,ks=4,vs=14,imm=0) R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=4168,imm=0) R10=fp0,call_-1 fp-8=mmmmmmmm
+; if (syscall->string_args_len[arg] != 0) {
+38: (55) if r3 != 0x0 goto pc+5
+ R0=map_value(id=0,off=0,ks=4,vs=14,imm=0) R1=inv0 R2=map_value(id=0,off=2,ks=4,vs=14,imm=0) R3=inv0 R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=4168,imm=0) R10=fp0,call_-1 fp-8=mmmmmmmm
+39: (b7) r1 = 1
+; if (syscall->string_args_len[arg] != 0) {
+40: (bf) r2 = r0
+41: (07) r2 += 4
+42: (69) r3 = *(u16 *)(r0 +4)
+ R0=map_value(id=0,off=0,ks=4,vs=14,imm=0) R1_w=inv1 R2_w=map_value(id=0,off=4,ks=4,vs=14,imm=0) R3_w=inv0 R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=4168,imm=0) R10=fp0,call_-1 fp-8=mmmmmmmm
+; if (syscall->string_args_len[arg] != 0) {
+43: (15) if r3 == 0x0 goto pc+32
+ R0=map_value(id=0,off=0,ks=4,vs=14,imm=0) R1=inv1 R2=map_value(id=0,off=4,ks=4,vs=14,imm=0) R3=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff)) R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=4168,imm=0) R10=fp0,call_-1 fp-8=mmmmmmmm
+; filename_arg = (const void *)args->args[arg];
+44: (67) r1 <<= 3
+45: (bf) r3 = r6
+46: (0f) r3 += r1
+47: (b7) r5 = 64
+48: (79) r3 = *(u64 *)(r3 +16)
+dereference of modified ctx ptr R3 off=8 disallowed
+processed 46 insns (limit 1000000) max_states_per_insn 0 total_states 12 peak_states 12 mark_read 7
+ */
+
+#define __loop_iter(arg) \
+ if (syscall->string_args_len[arg] != 0) { \
+ unsigned int filename_len = syscall->string_args_len[arg]; \
+ const void *filename_arg = (const void *)args->args[arg]; \
+ if (filename_len <= sizeof(augmented_args->filename.value)) \
+ len += augmented_filename__read(&augmented_args->filename, filename_arg, filename_len);
+#define loop_iter_first() __loop_iter(0); }
+#define loop_iter(arg) else __loop_iter(arg); }
+#define loop_iter_last(arg) else __loop_iter(arg); __asm__ __volatile__("": : :"memory"); }
+
+ loop_iter_first()
+ loop_iter(1)
+ loop_iter(2)
+ loop_iter(3)
+ loop_iter(4)
+ loop_iter_last(5)
+
/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len);
}
static char jit_path[PATH_MAX];
static void *marker_addr;
+#ifndef HAVE_GETTID
static inline pid_t gettid(void)
{
return (pid_t)syscall(__NR_gettid);
}
+#endif
static int get_e_machine(struct jitheader *hdr)
{
// SPDX-License-Identifier: GPL-2.0
#include <linux/compiler.h>
+#include <linux/string.h>
#include <sys/types.h>
#include <stdio.h>
#include <string.h>
result[i] = '\0';
} else {
/* fallback case */
- size_t file_name_len = strlen(file_name);
- strncpy(result, file_name, file_name_len < max_length ? file_name_len : max_length);
+ strlcpy(result, file_name, max_length);
}
}
USER_HOME=$(bash <<< "echo ~$SUDO_USER")
- if [ "$HOME" != "$USER_HOME" ] ; then
- echo "Fix unnecessary because root has a home: $HOME" >&2
- exit 1
- fi
-
echo "Fixing buildid cache permissions"
find "$USER_HOME/.debug" -xdev -type d ! -user "$SUDO_USER" -ls -exec chown "$SUDO_USER" \{\} \;
#include "util/bpf-loader.h"
#include "util/debug.h"
#include "util/event.h"
+#include "util/util.h"
#include <api/fs/fs.h>
#include <api/fs/tracing_path.h>
#include <errno.h>
}
#ifndef MAX_NR_CPUS
-#define MAX_NR_CPUS 1024
+#define MAX_NR_CPUS 2048
#endif
extern const char *input_name;
bool record_switch_events;
bool all_kernel;
bool all_user;
+ bool kernel_callchains;
+ bool user_callchains;
bool tail_synthesize;
bool overwrite;
bool ignore_missing_thread;
--- /dev/null
+[
+ {
+ "EventCode": "0x02",
+ "EventName": "uncore_hisi_ddrc.flux_wcmd",
+ "BriefDescription": "DDRC write commands",
+ "PublicDescription": "DDRC write commands",
+ "Unit": "hisi_sccl,ddrc",
+ },
+ {
+ "EventCode": "0x03",
+ "EventName": "uncore_hisi_ddrc.flux_rcmd",
+ "BriefDescription": "DDRC read commands",
+ "PublicDescription": "DDRC read commands",
+ "Unit": "hisi_sccl,ddrc",
+ },
+ {
+ "EventCode": "0x04",
+ "EventName": "uncore_hisi_ddrc.flux_wr",
+ "BriefDescription": "DDRC precharge commands",
+ "PublicDescription": "DDRC precharge commands",
+ "Unit": "hisi_sccl,ddrc",
+ },
+ {
+ "EventCode": "0x05",
+ "EventName": "uncore_hisi_ddrc.act_cmd",
+ "BriefDescription": "DDRC active commands",
+ "PublicDescription": "DDRC active commands",
+ "Unit": "hisi_sccl,ddrc",
+ },
+ {
+ "EventCode": "0x06",
+ "EventName": "uncore_hisi_ddrc.rnk_chg",
+ "BriefDescription": "DDRC rank commands",
+ "PublicDescription": "DDRC rank commands",
+ "Unit": "hisi_sccl,ddrc",
+ },
+ {
+ "EventCode": "0x07",
+ "EventName": "uncore_hisi_ddrc.rw_chg",
+ "BriefDescription": "DDRC read and write changes",
+ "PublicDescription": "DDRC read and write changes",
+ "Unit": "hisi_sccl,ddrc",
+ },
+]
--- /dev/null
+[
+ {
+ "EventCode": "0x00",
+ "EventName": "uncore_hisi_hha.rx_ops_num",
+ "BriefDescription": "The number of all operations received by the HHA",
+ "PublicDescription": "The number of all operations received by the HHA",
+ "Unit": "hisi_sccl,hha",
+ },
+ {
+ "EventCode": "0x01",
+ "EventName": "uncore_hisi_hha.rx_outer",
+ "BriefDescription": "The number of all operations received by the HHA from another socket",
+ "PublicDescription": "The number of all operations received by the HHA from another socket",
+ "Unit": "hisi_sccl,hha",
+ },
+ {
+ "EventCode": "0x02",
+ "EventName": "uncore_hisi_hha.rx_sccl",
+ "BriefDescription": "The number of all operations received by the HHA from another SCCL in this socket",
+ "PublicDescription": "The number of all operations received by the HHA from another SCCL in this socket",
+ "Unit": "hisi_sccl,hha",
+ },
+ {
+ "EventCode": "0x1c",
+ "EventName": "uncore_hisi_hha.rd_ddr_64b",
+ "BriefDescription": "The number of read operations sent by HHA to DDRC which size is 64 bytes",
+ "PublicDescription": "The number of read operations sent by HHA to DDRC which size is 64bytes",
+ "Unit": "hisi_sccl,hha",
+ },
+ {
+ "EventCode": "0x1d",
+ "EventName": "uncore_hisi_hha.wr_dr_64b",
+ "BriefDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes",
+ "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes",
+ "Unit": "hisi_sccl,hha",
+ },
+ {
+ "EventCode": "0x1e",
+ "EventName": "uncore_hisi_hha.rd_ddr_128b",
+ "BriefDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes",
+ "PublicDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes",
+ "Unit": "hisi_sccl,hha",
+ },
+ {
+ "EventCode": "0x1f",
+ "EventName": "uncore_hisi_hha.wr_ddr_128b",
+ "BriefDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes",
+ "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes",
+ "Unit": "hisi_sccl,hha",
+ },
+]
--- /dev/null
+[
+ {
+ "EventCode": "0x00",
+ "EventName": "uncore_hisi_l3c.rd_cpipe",
+ "BriefDescription": "Total read accesses",
+ "PublicDescription": "Total read accesses",
+ "Unit": "hisi_sccl,l3c",
+ },
+ {
+ "EventCode": "0x01",
+ "EventName": "uncore_hisi_l3c.wr_cpipe",
+ "BriefDescription": "Total write accesses",
+ "PublicDescription": "Total write accesses",
+ "Unit": "hisi_sccl,l3c",
+ },
+ {
+ "EventCode": "0x02",
+ "EventName": "uncore_hisi_l3c.rd_hit_cpipe",
+ "BriefDescription": "Total read hits",
+ "PublicDescription": "Total read hits",
+ "Unit": "hisi_sccl,l3c",
+ },
+ {
+ "EventCode": "0x03",
+ "EventName": "uncore_hisi_l3c.wr_hit_cpipe",
+ "BriefDescription": "Total write hits",
+ "PublicDescription": "Total write hits",
+ "Unit": "hisi_sccl,l3c",
+ },
+ {
+ "EventCode": "0x04",
+ "EventName": "uncore_hisi_l3c.victim_num",
+ "BriefDescription": "l3c precharge commands",
+ "PublicDescription": "l3c precharge commands",
+ "Unit": "hisi_sccl,l3c",
+ },
+]
"MetricName": "DRAM_BW_Use"
},
{
- "MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x35\\\\\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )",
+ "MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,config\\=0x40433@ / cha@event\\=0x35\\\\\\,umask\\=0x21\\\\\\,config\\=0x40433@ ) / ( cha_0@event\\=0x0@ / duration_time )",
"BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
"MetricGroup": "Memory_Lat",
"MetricName": "DRAM_Read_Latency"
},
{
- "MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1@",
+ "MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,config\\=0x40433@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1\\\\\\,config\\=0x40433@",
"BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
"MetricGroup": "Memory_BW",
"MetricName": "DRAM_Parallel_Reads"
"MetricName": "DRAM_BW_Use"
},
{
- "MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x35\\\\\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )",
+ "MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,config\\=0x40433@ / cha@event\\=0x35\\\\\\,umask\\=0x21\\\\\\,config\\=0x40433@ ) / ( cha_0@event\\=0x0@ / duration_time )",
"BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
"MetricGroup": "Memory_Lat",
"MetricName": "DRAM_Read_Latency"
},
{
- "MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1@",
+ "MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,config\\=0x40433@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1\\\\\\,config\\=0x40433@",
"BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
"MetricGroup": "Memory_BW",
"MetricName": "DRAM_Parallel_Reads"
},
- {
- "MetricExpr": "( 1000000000 * ( imc@event\\=0xe0\\\\\\,umask\\=0x1@ / imc@event\\=0xe3@ ) / imc_0@event\\=0x0@ ) if 1 if 0 == 1 else 0 else 0",
- "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches",
- "MetricGroup": "Memory_Lat",
- "MetricName": "MEM_PMM_Read_Latency"
- },
- {
- "MetricExpr": "( ( 64 * imc@event\\=0xe3@ / 1000000000 ) / duration_time ) if 1 if 0 == 1 else 0 else 0",
- "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]",
- "MetricGroup": "Memory_BW",
- "MetricName": "PMM_Read_BW"
- },
- {
- "MetricExpr": "( ( 64 * imc@event\\=0xe7@ / 1000000000 ) / duration_time ) if 1 if 0 == 1 else 0 else 0",
- "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]",
- "MetricGroup": "Memory_BW",
- "MetricName": "PMM_Write_BW"
- },
{
"MetricExpr": "cha_0@event\\=0x0@",
"BriefDescription": "Socket actual clocks when any core is active on that socket",
{ "CPU-M-CF", "cpum_cf" },
{ "CPU-M-SF", "cpum_sf" },
{ "UPI LL", "uncore_upi" },
+ { "hisi_sccl,ddrc", "hisi_sccl,ddrc" },
+ { "hisi_sccl,hha", "hisi_sccl,hha" },
+ { "hisi_sccl,l3c", "hisi_sccl,l3c" },
{}
};
_Exit(1);
}
- fprintf(outfp, "#include \"../../pmu-events/pmu-events.h\"\n");
+ fprintf(outfp, "#include \"pmu-events/pmu-events.h\"\n");
print_mapping_table_prefix(outfp);
print_mapping_table_suffix(outfp);
fclose(outfp);
}
/* Include pmu-events.h first */
- fprintf(eventsfp, "#include \"../../pmu-events/pmu-events.h\"\n");
+ fprintf(eventsfp, "#include \"pmu-events/pmu-events.h\"\n");
/*
* The mapfile allows multiple CPUids to point to the same JSON file,
#
# fedora:
#
-# $ sudo yum install postgresql postgresql-server python-pyside qt-postgresql
+# $ sudo yum install postgresql postgresql-server qt-postgresql
# $ sudo su - postgres -c initdb
# $ sudo service postgresql start
# $ sudo su - postgres
-# $ createuser <your user id here>
+# $ createuser -s <your user id here> # Older versions may not support -s, in which case answer the prompt below:
# Shall the new role be a superuser? (y/n) y
+# $ sudo yum install python-pyside
+#
+# Alternately, to use Python3 and/or pyside 2, one of the following:
+# $ sudo yum install python3-pyside
+# $ pip install --user PySide2
+# $ pip3 install --user PySide2
#
# ubuntu:
#
-# $ sudo apt-get install postgresql python-pyside.qtsql libqt4-sql-psql
+# $ sudo apt-get install postgresql
# $ sudo su - postgres
# $ createuser -s <your user id here>
+# $ sudo apt-get install python-pyside.qtsql libqt4-sql-psql
+#
+# Alternately, to use Python3 and/or pyside 2, one of the following:
+#
+# $ sudo apt-get install python3-pyside.qtsql libqt4-sql-psql
+# $ sudo apt-get install python-pyside2.qtsql libqt5sql5-psql
+# $ sudo apt-get install python3-pyside2.qtsql libqt5sql5-psql
#
# An example of using this script with Intel PT:
#
# print "{0:>6} {1:>10} {2:>9} {3:<30} {4:>6} {5:<30}".format(query.value(0), query.value(1), query.value(2), query.value(3), query.value(4), query.value(5))
# call_path_id = query.value(6)
-from PySide.QtSql import *
+pyside_version_1 = True
+if not "pyside-version-1" in sys.argv:
+ try:
+ from PySide2.QtSql import *
+ pyside_version_1 = False
+ except:
+ pass
+
+if pyside_version_1:
+ from PySide.QtSql import *
if sys.version_info < (3, 0):
def toserverstr(str):
print(datetime.datetime.today(), *args, sep=' ', **kw_args)
def usage():
- printerr("Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>]")
- printerr("where: columns 'all' or 'branches'")
- printerr(" calls 'calls' => create calls and call_paths table")
- printerr(" callchains 'callchains' => create call_paths table")
- raise Exception("Too few arguments")
+ printerr("Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>] [<pyside-version-1>]");
+ printerr("where: columns 'all' or 'branches'");
+ printerr(" calls 'calls' => create calls and call_paths table");
+ printerr(" callchains 'callchains' => create call_paths table");
+ printerr(" pyside-version-1 'pyside-version-1' => use pyside version 1");
+ raise Exception("Too few or bad arguments")
if (len(sys.argv) < 2):
usage()
perf_db_export_calls = True
elif (sys.argv[i] == "callchains"):
perf_db_export_callchains = True
+ elif (sys.argv[i] == "pyside-version-1"):
+ pass
else:
usage()
'to_ip bigint,'
'branch_type integer,'
'in_tx boolean,'
- 'call_path_id bigint)')
+ 'call_path_id bigint,'
+ 'insn_count bigint,'
+ 'cyc_count bigint)')
else:
do_query(query, 'CREATE TABLE samples ('
'id bigint NOT NULL,'
'data_src bigint,'
'branch_type integer,'
'in_tx boolean,'
- 'call_path_id bigint)')
+ 'call_path_id bigint,'
+ 'insn_count bigint,'
+ 'cyc_count bigint)')
if perf_db_export_calls or perf_db_export_callchains:
do_query(query, 'CREATE TABLE call_paths ('
'return_id bigint,'
'parent_call_path_id bigint,'
'flags integer,'
- 'parent_id bigint)')
+ 'parent_id bigint,'
+ 'insn_count bigint,'
+ 'cyc_count bigint)')
+
+do_query(query, 'CREATE TABLE ptwrite ('
+ 'id bigint NOT NULL,'
+ 'payload bigint,'
+ 'exact_ip boolean)')
+
+do_query(query, 'CREATE TABLE cbr ('
+ 'id bigint NOT NULL,'
+ 'cbr integer,'
+ 'mhz integer,'
+ 'percent integer)')
+
+do_query(query, 'CREATE TABLE mwait ('
+ 'id bigint NOT NULL,'
+ 'hints integer,'
+ 'extensions integer)')
+
+do_query(query, 'CREATE TABLE pwre ('
+ 'id bigint NOT NULL,'
+ 'cstate integer,'
+ 'subcstate integer,'
+ 'hw boolean)')
+
+do_query(query, 'CREATE TABLE exstop ('
+ 'id bigint NOT NULL,'
+ 'exact_ip boolean)')
+
+do_query(query, 'CREATE TABLE pwrx ('
+ 'id bigint NOT NULL,'
+ 'deepest_cstate integer,'
+ 'last_cstate integer,'
+ 'wake_reason integer)')
do_query(query, 'CREATE VIEW machines_view AS '
'SELECT '
'return_time,'
'return_time - call_time AS elapsed_time,'
'branch_count,'
+ 'insn_count,'
+ 'cyc_count,'
+ 'CASE WHEN cyc_count=0 THEN CAST(0 AS NUMERIC(20, 2)) ELSE CAST((CAST(insn_count AS FLOAT) / cyc_count) AS NUMERIC(20, 2)) END AS IPC,'
'call_id,'
'return_id,'
'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE CAST ( flags AS VARCHAR(6) ) END AS flags,'
'to_sym_offset,'
'(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,'
'(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,'
- 'in_tx'
+ 'in_tx,'
+ 'insn_count,'
+ 'cyc_count,'
+ 'CASE WHEN cyc_count=0 THEN CAST(0 AS NUMERIC(20, 2)) ELSE CAST((CAST(insn_count AS FLOAT) / cyc_count) AS NUMERIC(20, 2)) END AS IPC'
' FROM samples')
+do_query(query, 'CREATE VIEW ptwrite_view AS '
+ 'SELECT '
+ 'ptwrite.id,'
+ 'time,'
+ 'cpu,'
+ 'to_hex(payload) AS payload_hex,'
+ 'CASE WHEN exact_ip=FALSE THEN \'False\' ELSE \'True\' END AS exact_ip'
+ ' FROM ptwrite'
+ ' INNER JOIN samples ON samples.id = ptwrite.id')
+
+do_query(query, 'CREATE VIEW cbr_view AS '
+ 'SELECT '
+ 'cbr.id,'
+ 'time,'
+ 'cpu,'
+ 'cbr,'
+ 'mhz,'
+ 'percent'
+ ' FROM cbr'
+ ' INNER JOIN samples ON samples.id = cbr.id')
+
+do_query(query, 'CREATE VIEW mwait_view AS '
+ 'SELECT '
+ 'mwait.id,'
+ 'time,'
+ 'cpu,'
+ 'to_hex(hints) AS hints_hex,'
+ 'to_hex(extensions) AS extensions_hex'
+ ' FROM mwait'
+ ' INNER JOIN samples ON samples.id = mwait.id')
+
+do_query(query, 'CREATE VIEW pwre_view AS '
+ 'SELECT '
+ 'pwre.id,'
+ 'time,'
+ 'cpu,'
+ 'cstate,'
+ 'subcstate,'
+ 'CASE WHEN hw=FALSE THEN \'False\' ELSE \'True\' END AS hw'
+ ' FROM pwre'
+ ' INNER JOIN samples ON samples.id = pwre.id')
+
+do_query(query, 'CREATE VIEW exstop_view AS '
+ 'SELECT '
+ 'exstop.id,'
+ 'time,'
+ 'cpu,'
+ 'CASE WHEN exact_ip=FALSE THEN \'False\' ELSE \'True\' END AS exact_ip'
+ ' FROM exstop'
+ ' INNER JOIN samples ON samples.id = exstop.id')
+
+do_query(query, 'CREATE VIEW pwrx_view AS '
+ 'SELECT '
+ 'pwrx.id,'
+ 'time,'
+ 'cpu,'
+ 'deepest_cstate,'
+ 'last_cstate,'
+ 'CASE WHEN wake_reason=1 THEN \'Interrupt\''
+ ' WHEN wake_reason=2 THEN \'Timer Deadline\''
+ ' WHEN wake_reason=4 THEN \'Monitored Address\''
+ ' WHEN wake_reason=8 THEN \'HW\''
+ ' ELSE CAST ( wake_reason AS VARCHAR(2) )'
+ 'END AS wake_reason'
+ ' FROM pwrx'
+ ' INNER JOIN samples ON samples.id = pwrx.id')
+
+do_query(query, 'CREATE VIEW power_events_view AS '
+ 'SELECT '
+ 'samples.id,'
+ 'samples.time,'
+ 'samples.cpu,'
+ 'selected_events.name AS event,'
+ 'FORMAT(\'%6s\', cbr.cbr) AS cbr,'
+ 'FORMAT(\'%6s\', cbr.mhz) AS MHz,'
+ 'FORMAT(\'%5s\', cbr.percent) AS percent,'
+ 'to_hex(mwait.hints) AS hints_hex,'
+ 'to_hex(mwait.extensions) AS extensions_hex,'
+ 'FORMAT(\'%3s\', pwre.cstate) AS cstate,'
+ 'FORMAT(\'%3s\', pwre.subcstate) AS subcstate,'
+ 'CASE WHEN pwre.hw=FALSE THEN \'False\' WHEN pwre.hw=TRUE THEN \'True\' ELSE NULL END AS hw,'
+ 'CASE WHEN exstop.exact_ip=FALSE THEN \'False\' WHEN exstop.exact_ip=TRUE THEN \'True\' ELSE NULL END AS exact_ip,'
+ 'FORMAT(\'%3s\', pwrx.deepest_cstate) AS deepest_cstate,'
+ 'FORMAT(\'%3s\', pwrx.last_cstate) AS last_cstate,'
+ 'CASE WHEN pwrx.wake_reason=1 THEN \'Interrupt\''
+ ' WHEN pwrx.wake_reason=2 THEN \'Timer Deadline\''
+ ' WHEN pwrx.wake_reason=4 THEN \'Monitored Address\''
+ ' WHEN pwrx.wake_reason=8 THEN \'HW\''
+ ' ELSE FORMAT(\'%2s\', pwrx.wake_reason)'
+ 'END AS wake_reason'
+ ' FROM cbr'
+ ' FULL JOIN mwait ON mwait.id = cbr.id'
+ ' FULL JOIN pwre ON pwre.id = cbr.id'
+ ' FULL JOIN exstop ON exstop.id = cbr.id'
+ ' FULL JOIN pwrx ON pwrx.id = cbr.id'
+ ' INNER JOIN samples ON samples.id = coalesce(cbr.id, mwait.id, pwre.id, exstop.id, pwrx.id)'
+ ' INNER JOIN selected_events ON selected_events.id = samples.evsel_id'
+ ' ORDER BY samples.id')
file_header = struct.pack("!11sii", b"PGCOPY\n\377\r\n\0", 0, 0)
file_trailer = b"\377\377"
call_path_file = open_output_file("call_path_table.bin")
if perf_db_export_calls:
call_file = open_output_file("call_table.bin")
+ptwrite_file = open_output_file("ptwrite_table.bin")
+cbr_file = open_output_file("cbr_table.bin")
+mwait_file = open_output_file("mwait_table.bin")
+pwre_file = open_output_file("pwre_table.bin")
+exstop_file = open_output_file("exstop_table.bin")
+pwrx_file = open_output_file("pwrx_table.bin")
def trace_begin():
printdate("Writing to intermediate files...")
comm_table(0, "unknown")
dso_table(0, 0, "unknown", "unknown", "")
symbol_table(0, 0, 0, 0, 0, "unknown")
- sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+ sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
if perf_db_export_calls or perf_db_export_callchains:
call_path_table(0, 0, 0, 0)
- call_return_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+ call_return_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
unhandled_count = 0
+def is_table_empty(table_name):
+ do_query(query, 'SELECT * FROM ' + table_name + ' LIMIT 1');
+ if query.next():
+ return False
+ return True
+
+def drop(table_name):
+ do_query(query, 'DROP VIEW ' + table_name + '_view');
+ do_query(query, 'DROP TABLE ' + table_name);
+
def trace_end():
printdate("Copying to database...")
copy_output_file(evsel_file, "selected_events")
copy_output_file(call_path_file, "call_paths")
if perf_db_export_calls:
copy_output_file(call_file, "calls")
+ copy_output_file(ptwrite_file, "ptwrite")
+ copy_output_file(cbr_file, "cbr")
+ copy_output_file(mwait_file, "mwait")
+ copy_output_file(pwre_file, "pwre")
+ copy_output_file(exstop_file, "exstop")
+ copy_output_file(pwrx_file, "pwrx")
printdate("Removing intermediate files...")
remove_output_file(evsel_file)
remove_output_file(call_path_file)
if perf_db_export_calls:
remove_output_file(call_file)
+ remove_output_file(ptwrite_file)
+ remove_output_file(cbr_file)
+ remove_output_file(mwait_file)
+ remove_output_file(pwre_file)
+ remove_output_file(exstop_file)
+ remove_output_file(pwrx_file)
os.rmdir(output_dir_name)
printdate("Adding primary keys")
do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE call_paths ADD PRIMARY KEY (id)')
if perf_db_export_calls:
do_query(query, 'ALTER TABLE calls ADD PRIMARY KEY (id)')
+ do_query(query, 'ALTER TABLE ptwrite ADD PRIMARY KEY (id)')
+ do_query(query, 'ALTER TABLE cbr ADD PRIMARY KEY (id)')
+ do_query(query, 'ALTER TABLE mwait ADD PRIMARY KEY (id)')
+ do_query(query, 'ALTER TABLE pwre ADD PRIMARY KEY (id)')
+ do_query(query, 'ALTER TABLE exstop ADD PRIMARY KEY (id)')
+ do_query(query, 'ALTER TABLE pwrx ADD PRIMARY KEY (id)')
printdate("Adding foreign keys")
do_query(query, 'ALTER TABLE threads '
'ADD CONSTRAINT parent_call_pathfk FOREIGN KEY (parent_call_path_id) REFERENCES call_paths (id)')
do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)')
+ do_query(query, 'ALTER TABLE ptwrite '
+ 'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)')
+ do_query(query, 'ALTER TABLE cbr '
+ 'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)')
+ do_query(query, 'ALTER TABLE mwait '
+ 'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)')
+ do_query(query, 'ALTER TABLE pwre '
+ 'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)')
+ do_query(query, 'ALTER TABLE exstop '
+ 'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)')
+ do_query(query, 'ALTER TABLE pwrx '
+ 'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)')
+
+ printdate("Dropping unused tables")
+ if is_table_empty("ptwrite"):
+ drop("ptwrite")
+ if is_table_empty("mwait") and is_table_empty("pwre") and is_table_empty("exstop") and is_table_empty("pwrx"):
+ drop("mwait")
+ drop("pwre")
+ drop("exstop")
+ drop("pwrx")
+ do_query(query, 'DROP VIEW power_events_view');
+ if is_table_empty("cbr"):
+ drop("cbr")
if (unhandled_count):
printdate("Warning: ", unhandled_count, " unhandled events")
value = struct.pack(fmt, 2, 4, branch_type, n, name)
branch_type_file.write(value)
-def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, call_path_id, *x):
+def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, call_path_id, insn_cnt, cyc_cnt, *x):
if branches:
- value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiBiq", 18, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx, 8, call_path_id)
+ value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiBiqiqiq", 20, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx, 8, call_path_id, 8, insn_cnt, 8, cyc_cnt)
else:
- value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiBiq", 22, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx, 8, call_path_id)
+ value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiBiqiqiq", 24, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx, 8, call_path_id, 8, insn_cnt, 8, cyc_cnt)
sample_file.write(value)
def call_path_table(cp_id, parent_id, symbol_id, ip, *x):
value = struct.pack(fmt, 4, 8, cp_id, 8, parent_id, 8, symbol_id, 8, ip)
call_path_file.write(value)
-def call_return_table(cr_id, thread_id, comm_id, call_path_id, call_time, return_time, branch_count, call_id, return_id, parent_call_path_id, flags, parent_id, *x):
- fmt = "!hiqiqiqiqiqiqiqiqiqiqiiiq"
- value = struct.pack(fmt, 12, 8, cr_id, 8, thread_id, 8, comm_id, 8, call_path_id, 8, call_time, 8, return_time, 8, branch_count, 8, call_id, 8, return_id, 8, parent_call_path_id, 4, flags, 8, parent_id)
+def call_return_table(cr_id, thread_id, comm_id, call_path_id, call_time, return_time, branch_count, call_id, return_id, parent_call_path_id, flags, parent_id, insn_cnt, cyc_cnt, *x):
+ fmt = "!hiqiqiqiqiqiqiqiqiqiqiiiqiqiq"
+ value = struct.pack(fmt, 14, 8, cr_id, 8, thread_id, 8, comm_id, 8, call_path_id, 8, call_time, 8, return_time, 8, branch_count, 8, call_id, 8, return_id, 8, parent_call_path_id, 4, flags, 8, parent_id, 8, insn_cnt, 8, cyc_cnt)
call_file.write(value)
+
+def ptwrite(id, raw_buf):
+ data = struct.unpack_from("<IQ", raw_buf)
+ flags = data[0]
+ payload = data[1]
+ exact_ip = flags & 1
+ value = struct.pack("!hiqiqiB", 3, 8, id, 8, payload, 1, exact_ip)
+ ptwrite_file.write(value)
+
+def cbr(id, raw_buf):
+ data = struct.unpack_from("<BBBBII", raw_buf)
+ cbr = data[0]
+ MHz = (data[4] + 500) / 1000
+ percent = ((cbr * 1000 / data[2]) + 5) / 10
+ value = struct.pack("!hiqiiiiii", 4, 8, id, 4, cbr, 4, MHz, 4, percent)
+ cbr_file.write(value)
+
+def mwait(id, raw_buf):
+ data = struct.unpack_from("<IQ", raw_buf)
+ payload = data[1]
+ hints = payload & 0xff
+ extensions = (payload >> 32) & 0x3
+ value = struct.pack("!hiqiiii", 3, 8, id, 4, hints, 4, extensions)
+ mwait_file.write(value)
+
+def pwre(id, raw_buf):
+ data = struct.unpack_from("<IQ", raw_buf)
+ payload = data[1]
+ hw = (payload >> 7) & 1
+ cstate = (payload >> 12) & 0xf
+ subcstate = (payload >> 8) & 0xf
+ value = struct.pack("!hiqiiiiiB", 4, 8, id, 4, cstate, 4, subcstate, 1, hw)
+ pwre_file.write(value)
+
+def exstop(id, raw_buf):
+ data = struct.unpack_from("<I", raw_buf)
+ flags = data[0]
+ exact_ip = flags & 1
+ value = struct.pack("!hiqiB", 2, 8, id, 1, exact_ip)
+ exstop_file.write(value)
+
+def pwrx(id, raw_buf):
+ data = struct.unpack_from("<IQ", raw_buf)
+ payload = data[1]
+ deepest_cstate = payload & 0xf
+ last_cstate = (payload >> 4) & 0xf
+ wake_reason = (payload >> 8) & 0xf
+ value = struct.pack("!hiqiiiiii", 4, 8, id, 4, deepest_cstate, 4, last_cstate, 4, wake_reason)
+ pwrx_file.write(value)
+
+def synth_data(id, config, raw_buf, *x):
+ if config == 0:
+ ptwrite(id, raw_buf)
+ elif config == 1:
+ mwait(id, raw_buf)
+ elif config == 2:
+ pwre(id, raw_buf)
+ elif config == 3:
+ exstop(id, raw_buf)
+ elif config == 4:
+ pwrx(id, raw_buf)
+ elif config == 5:
+ cbr(id, raw_buf)
# provides LGPL-licensed Python bindings for Qt. You will also need the package
# libqt4-sql-sqlite for Qt sqlite3 support.
#
+# Examples of installing pyside:
+#
+# ubuntu:
+#
+# $ sudo apt-get install python-pyside.qtsql libqt4-sql-psql
+#
+# Alternately, to use Python3 and/or pyside 2, one of the following:
+#
+# $ sudo apt-get install python3-pyside.qtsql libqt4-sql-psql
+# $ sudo apt-get install python-pyside2.qtsql libqt5sql5-psql
+# $ sudo apt-get install python3-pyside2.qtsql libqt5sql5-psql
+# fedora:
+#
+# $ sudo yum install python-pyside
+#
+# Alternately, to use Python3 and/or pyside 2, one of the following:
+# $ sudo yum install python3-pyside
+# $ pip install --user PySide2
+# $ pip3 install --user PySide2
+#
# An example of using this script with Intel PT:
#
# $ perf record -e intel_pt//u ls
# difference is the 'transaction' column of the 'samples' table which is
# renamed 'transaction_' in sqlite because 'transaction' is a reserved word.
-from PySide.QtSql import *
+pyside_version_1 = True
+if not "pyside-version-1" in sys.argv:
+ try:
+ from PySide2.QtSql import *
+ pyside_version_1 = False
+ except:
+ pass
+
+if pyside_version_1:
+ from PySide.QtSql import *
sys.path.append(os.environ['PERF_EXEC_PATH'] + \
'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
print(datetime.datetime.today(), *args, sep=' ', **kw_args)
def usage():
- printerr("Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>]");
- printerr("where: columns 'all' or 'branches'");
- printerr(" calls 'calls' => create calls and call_paths table");
- printerr(" callchains 'callchains' => create call_paths table");
- raise Exception("Too few arguments")
+ printerr("Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>] [<pyside-version-1>]");
+ printerr("where: columns 'all' or 'branches'");
+ printerr(" calls 'calls' => create calls and call_paths table");
+ printerr(" callchains 'callchains' => create call_paths table");
+ printerr(" pyside-version-1 'pyside-version-1' => use pyside version 1");
+ raise Exception("Too few or bad arguments")
if (len(sys.argv) < 2):
usage()
perf_db_export_calls = True
elif (sys.argv[i] == "callchains"):
perf_db_export_callchains = True
+ elif (sys.argv[i] == "pyside-version-1"):
+ pass
else:
usage()
'to_ip bigint,'
'branch_type integer,'
'in_tx boolean,'
- 'call_path_id bigint)')
+ 'call_path_id bigint,'
+ 'insn_count bigint,'
+ 'cyc_count bigint)')
else:
do_query(query, 'CREATE TABLE samples ('
'id integer NOT NULL PRIMARY KEY,'
'data_src bigint,'
'branch_type integer,'
'in_tx boolean,'
- 'call_path_id bigint)')
+ 'call_path_id bigint,'
+ 'insn_count bigint,'
+ 'cyc_count bigint)')
if perf_db_export_calls or perf_db_export_callchains:
do_query(query, 'CREATE TABLE call_paths ('
'return_id bigint,'
'parent_call_path_id bigint,'
'flags integer,'
- 'parent_id bigint)')
+ 'parent_id bigint,'
+ 'insn_count bigint,'
+ 'cyc_count bigint)')
+
+do_query(query, 'CREATE TABLE ptwrite ('
+ 'id integer NOT NULL PRIMARY KEY,'
+ 'payload bigint,'
+ 'exact_ip integer)')
+
+do_query(query, 'CREATE TABLE cbr ('
+ 'id integer NOT NULL PRIMARY KEY,'
+ 'cbr integer,'
+ 'mhz integer,'
+ 'percent integer)')
+
+do_query(query, 'CREATE TABLE mwait ('
+ 'id integer NOT NULL PRIMARY KEY,'
+ 'hints integer,'
+ 'extensions integer)')
+
+do_query(query, 'CREATE TABLE pwre ('
+ 'id integer NOT NULL PRIMARY KEY,'
+ 'cstate integer,'
+ 'subcstate integer,'
+ 'hw integer)')
+
+do_query(query, 'CREATE TABLE exstop ('
+ 'id integer NOT NULL PRIMARY KEY,'
+ 'exact_ip integer)')
+
+do_query(query, 'CREATE TABLE pwrx ('
+ 'id integer NOT NULL PRIMARY KEY,'
+ 'deepest_cstate integer,'
+ 'last_cstate integer,'
+ 'wake_reason integer)')
# printf was added to sqlite in version 3.8.3
sqlite_has_printf = False
'return_time,'
'return_time - call_time AS elapsed_time,'
'branch_count,'
+ 'insn_count,'
+ 'cyc_count,'
+ 'CASE WHEN cyc_count=0 THEN CAST(0 AS FLOAT) ELSE ROUND(CAST(insn_count AS FLOAT) / cyc_count, 2) END AS IPC,'
'call_id,'
'return_id,'
'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,'
'to_sym_offset,'
'(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,'
'(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,'
- 'in_tx'
+ 'in_tx,'
+ 'insn_count,'
+ 'cyc_count,'
+ 'CASE WHEN cyc_count=0 THEN CAST(0 AS FLOAT) ELSE ROUND(CAST(insn_count AS FLOAT) / cyc_count, 2) END AS IPC'
' FROM samples')
+do_query(query, 'CREATE VIEW ptwrite_view AS '
+ 'SELECT '
+ 'ptwrite.id,'
+ 'time,'
+ 'cpu,'
+ + emit_to_hex('payload') + ' AS payload_hex,'
+ 'CASE WHEN exact_ip=0 THEN \'False\' ELSE \'True\' END AS exact_ip'
+ ' FROM ptwrite'
+ ' INNER JOIN samples ON samples.id = ptwrite.id')
+
+do_query(query, 'CREATE VIEW cbr_view AS '
+ 'SELECT '
+ 'cbr.id,'
+ 'time,'
+ 'cpu,'
+ 'cbr,'
+ 'mhz,'
+ 'percent'
+ ' FROM cbr'
+ ' INNER JOIN samples ON samples.id = cbr.id')
+
+do_query(query, 'CREATE VIEW mwait_view AS '
+ 'SELECT '
+ 'mwait.id,'
+ 'time,'
+ 'cpu,'
+ + emit_to_hex('hints') + ' AS hints_hex,'
+ + emit_to_hex('extensions') + ' AS extensions_hex'
+ ' FROM mwait'
+ ' INNER JOIN samples ON samples.id = mwait.id')
+
+do_query(query, 'CREATE VIEW pwre_view AS '
+ 'SELECT '
+ 'pwre.id,'
+ 'time,'
+ 'cpu,'
+ 'cstate,'
+ 'subcstate,'
+ 'CASE WHEN hw=0 THEN \'False\' ELSE \'True\' END AS hw'
+ ' FROM pwre'
+ ' INNER JOIN samples ON samples.id = pwre.id')
+
+do_query(query, 'CREATE VIEW exstop_view AS '
+ 'SELECT '
+ 'exstop.id,'
+ 'time,'
+ 'cpu,'
+ 'CASE WHEN exact_ip=0 THEN \'False\' ELSE \'True\' END AS exact_ip'
+ ' FROM exstop'
+ ' INNER JOIN samples ON samples.id = exstop.id')
+
+do_query(query, 'CREATE VIEW pwrx_view AS '
+ 'SELECT '
+ 'pwrx.id,'
+ 'time,'
+ 'cpu,'
+ 'deepest_cstate,'
+ 'last_cstate,'
+ 'CASE WHEN wake_reason=1 THEN \'Interrupt\''
+ ' WHEN wake_reason=2 THEN \'Timer Deadline\''
+ ' WHEN wake_reason=4 THEN \'Monitored Address\''
+ ' WHEN wake_reason=8 THEN \'HW\''
+ ' ELSE wake_reason '
+ 'END AS wake_reason'
+ ' FROM pwrx'
+ ' INNER JOIN samples ON samples.id = pwrx.id')
+
+do_query(query, 'CREATE VIEW power_events_view AS '
+ 'SELECT '
+ 'samples.id,'
+ 'time,'
+ 'cpu,'
+ 'selected_events.name AS event,'
+ 'CASE WHEN selected_events.name=\'cbr\' THEN (SELECT cbr FROM cbr WHERE cbr.id = samples.id) ELSE "" END AS cbr,'
+ 'CASE WHEN selected_events.name=\'cbr\' THEN (SELECT mhz FROM cbr WHERE cbr.id = samples.id) ELSE "" END AS mhz,'
+ 'CASE WHEN selected_events.name=\'cbr\' THEN (SELECT percent FROM cbr WHERE cbr.id = samples.id) ELSE "" END AS percent,'
+ 'CASE WHEN selected_events.name=\'mwait\' THEN (SELECT ' + emit_to_hex('hints') + ' FROM mwait WHERE mwait.id = samples.id) ELSE "" END AS hints_hex,'
+ 'CASE WHEN selected_events.name=\'mwait\' THEN (SELECT ' + emit_to_hex('extensions') + ' FROM mwait WHERE mwait.id = samples.id) ELSE "" END AS extensions_hex,'
+ 'CASE WHEN selected_events.name=\'pwre\' THEN (SELECT cstate FROM pwre WHERE pwre.id = samples.id) ELSE "" END AS cstate,'
+ 'CASE WHEN selected_events.name=\'pwre\' THEN (SELECT subcstate FROM pwre WHERE pwre.id = samples.id) ELSE "" END AS subcstate,'
+ 'CASE WHEN selected_events.name=\'pwre\' THEN (SELECT hw FROM pwre WHERE pwre.id = samples.id) ELSE "" END AS hw,'
+ 'CASE WHEN selected_events.name=\'exstop\' THEN (SELECT exact_ip FROM exstop WHERE exstop.id = samples.id) ELSE "" END AS exact_ip,'
+ 'CASE WHEN selected_events.name=\'pwrx\' THEN (SELECT deepest_cstate FROM pwrx WHERE pwrx.id = samples.id) ELSE "" END AS deepest_cstate,'
+ 'CASE WHEN selected_events.name=\'pwrx\' THEN (SELECT last_cstate FROM pwrx WHERE pwrx.id = samples.id) ELSE "" END AS last_cstate,'
+ 'CASE WHEN selected_events.name=\'pwrx\' THEN (SELECT '
+ 'CASE WHEN wake_reason=1 THEN \'Interrupt\''
+ ' WHEN wake_reason=2 THEN \'Timer Deadline\''
+ ' WHEN wake_reason=4 THEN \'Monitored Address\''
+ ' WHEN wake_reason=8 THEN \'HW\''
+ ' ELSE wake_reason '
+ 'END'
+ ' FROM pwrx WHERE pwrx.id = samples.id) ELSE "" END AS wake_reason'
+ ' FROM samples'
+ ' INNER JOIN selected_events ON selected_events.id = evsel_id'
+ ' WHERE selected_events.name IN (\'cbr\',\'mwait\',\'exstop\',\'pwre\',\'pwrx\')')
+
do_query(query, 'END TRANSACTION')
evsel_query = QSqlQuery(db)
branch_type_query.prepare("INSERT INTO branch_types VALUES (?, ?)")
sample_query = QSqlQuery(db)
if branches:
- sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
+ sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
else:
- sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
+ sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
if perf_db_export_calls or perf_db_export_callchains:
call_path_query = QSqlQuery(db)
call_path_query.prepare("INSERT INTO call_paths VALUES (?, ?, ?, ?)")
if perf_db_export_calls:
call_query = QSqlQuery(db)
- call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
+ call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
+ptwrite_query = QSqlQuery(db)
+ptwrite_query.prepare("INSERT INTO ptwrite VALUES (?, ?, ?)")
+cbr_query = QSqlQuery(db)
+cbr_query.prepare("INSERT INTO cbr VALUES (?, ?, ?, ?)")
+mwait_query = QSqlQuery(db)
+mwait_query.prepare("INSERT INTO mwait VALUES (?, ?, ?)")
+pwre_query = QSqlQuery(db)
+pwre_query.prepare("INSERT INTO pwre VALUES (?, ?, ?, ?)")
+exstop_query = QSqlQuery(db)
+exstop_query.prepare("INSERT INTO exstop VALUES (?, ?)")
+pwrx_query = QSqlQuery(db)
+pwrx_query.prepare("INSERT INTO pwrx VALUES (?, ?, ?, ?)")
def trace_begin():
printdate("Writing records...")
comm_table(0, "unknown")
dso_table(0, 0, "unknown", "unknown", "")
symbol_table(0, 0, 0, 0, 0, "unknown")
- sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+ sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
if perf_db_export_calls or perf_db_export_callchains:
call_path_table(0, 0, 0, 0)
- call_return_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+ call_return_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
unhandled_count = 0
+def is_table_empty(table_name):
+ do_query(query, 'SELECT * FROM ' + table_name + ' LIMIT 1');
+ if query.next():
+ return False
+ return True
+
+def drop(table_name):
+ do_query(query, 'DROP VIEW ' + table_name + '_view');
+ do_query(query, 'DROP TABLE ' + table_name);
+
def trace_end():
do_query(query, 'END TRANSACTION')
do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)')
+ printdate("Dropping unused tables")
+ if is_table_empty("ptwrite"):
+ drop("ptwrite")
+ if is_table_empty("mwait") and is_table_empty("pwre") and is_table_empty("exstop") and is_table_empty("pwrx"):
+ drop("mwait")
+ drop("pwre")
+ drop("exstop")
+ drop("pwrx")
+ do_query(query, 'DROP VIEW power_events_view');
+ if is_table_empty("cbr"):
+ drop("cbr")
+
if (unhandled_count):
printdate("Warning: ", unhandled_count, " unhandled events")
printdate("Done")
if branches:
for xx in x[0:15]:
sample_query.addBindValue(str(xx))
- for xx in x[19:22]:
+ for xx in x[19:24]:
sample_query.addBindValue(str(xx))
do_query_(sample_query)
else:
- bind_exec(sample_query, 22, x)
+ bind_exec(sample_query, 24, x)
def call_path_table(*x):
bind_exec(call_path_query, 4, x)
def call_return_table(*x):
- bind_exec(call_query, 12, x)
+ bind_exec(call_query, 14, x)
+
+def ptwrite(id, raw_buf):
+ data = struct.unpack_from("<IQ", raw_buf)
+ flags = data[0]
+ payload = data[1]
+ exact_ip = flags & 1
+ ptwrite_query.addBindValue(str(id))
+ ptwrite_query.addBindValue(str(payload))
+ ptwrite_query.addBindValue(str(exact_ip))
+ do_query_(ptwrite_query)
+
+def cbr(id, raw_buf):
+ data = struct.unpack_from("<BBBBII", raw_buf)
+ cbr = data[0]
+ MHz = (data[4] + 500) / 1000
+ percent = ((cbr * 1000 / data[2]) + 5) / 10
+ cbr_query.addBindValue(str(id))
+ cbr_query.addBindValue(str(cbr))
+ cbr_query.addBindValue(str(MHz))
+ cbr_query.addBindValue(str(percent))
+ do_query_(cbr_query)
+
+def mwait(id, raw_buf):
+ data = struct.unpack_from("<IQ", raw_buf)
+ payload = data[1]
+ hints = payload & 0xff
+ extensions = (payload >> 32) & 0x3
+ mwait_query.addBindValue(str(id))
+ mwait_query.addBindValue(str(hints))
+ mwait_query.addBindValue(str(extensions))
+ do_query_(mwait_query)
+
+def pwre(id, raw_buf):
+ data = struct.unpack_from("<IQ", raw_buf)
+ payload = data[1]
+ hw = (payload >> 7) & 1
+ cstate = (payload >> 12) & 0xf
+ subcstate = (payload >> 8) & 0xf
+ pwre_query.addBindValue(str(id))
+ pwre_query.addBindValue(str(cstate))
+ pwre_query.addBindValue(str(subcstate))
+ pwre_query.addBindValue(str(hw))
+ do_query_(pwre_query)
+
+def exstop(id, raw_buf):
+ data = struct.unpack_from("<I", raw_buf)
+ flags = data[0]
+ exact_ip = flags & 1
+ exstop_query.addBindValue(str(id))
+ exstop_query.addBindValue(str(exact_ip))
+ do_query_(exstop_query)
+
+def pwrx(id, raw_buf):
+ data = struct.unpack_from("<IQ", raw_buf)
+ payload = data[1]
+ deepest_cstate = payload & 0xf
+ last_cstate = (payload >> 4) & 0xf
+ wake_reason = (payload >> 8) & 0xf
+ pwrx_query.addBindValue(str(id))
+ pwrx_query.addBindValue(str(deepest_cstate))
+ pwrx_query.addBindValue(str(last_cstate))
+ pwrx_query.addBindValue(str(wake_reason))
+ do_query_(pwrx_query)
+
+def synth_data(id, config, raw_buf, *x):
+ if config == 0:
+ ptwrite(id, raw_buf)
+ elif config == 1:
+ mwait(id, raw_buf)
+ elif config == 2:
+ pwre(id, raw_buf)
+ elif config == 3:
+ exstop(id, raw_buf)
+ elif config == 4:
+ pwrx(id, raw_buf)
+ elif config == 5:
+ cbr(id, raw_buf)
-#!/usr/bin/env python2
+#!/usr/bin/env python
# SPDX-License-Identifier: GPL-2.0
# exported-sql-viewer.py: view data from sql database
# Copyright (c) 2014-2018, Intel Corporation.
from __future__ import print_function
import sys
+import argparse
import weakref
import threading
import string
glb_nsz = 16
import re
import os
-from PySide.QtCore import *
-from PySide.QtGui import *
-from PySide.QtSql import *
+
pyside_version_1 = True
+if not "--pyside-version-1" in sys.argv:
+ try:
+ from PySide2.QtCore import *
+ from PySide2.QtGui import *
+ from PySide2.QtSql import *
+ from PySide2.QtWidgets import *
+ pyside_version_1 = False
+ except:
+ pass
+
+if pyside_version_1:
+ from PySide.QtCore import *
+ from PySide.QtGui import *
+ from PySide.QtSql import *
+
from decimal import *
from ctypes import *
from multiprocessing import Process, Array, Value, Event
class TreeModel(QAbstractItemModel):
- def __init__(self, glb, parent=None):
+ def __init__(self, glb, params, parent=None):
super(TreeModel, self).__init__(parent)
self.glb = glb
+ self.params = params
self.root = self.GetRoot()
self.last_row_read = 0
def Activate(self):
self.bar.show()
+ self.textbox.lineEdit().selectAll()
self.textbox.setFocus()
def Deactivate(self):
class CallGraphLevelItemBase(object):
- def __init__(self, glb, row, parent_item):
+ def __init__(self, glb, params, row, parent_item):
self.glb = glb
+ self.params = params
self.row = row
self.parent_item = parent_item
self.query_done = False;
class CallGraphLevelTwoPlusItemBase(CallGraphLevelItemBase):
- def __init__(self, glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item):
- super(CallGraphLevelTwoPlusItemBase, self).__init__(glb, row, parent_item)
+ def __init__(self, glb, params, row, comm_id, thread_id, call_path_id, time, insn_cnt, cyc_cnt, branch_count, parent_item):
+ super(CallGraphLevelTwoPlusItemBase, self).__init__(glb, params, row, parent_item)
self.comm_id = comm_id
self.thread_id = thread_id
self.call_path_id = call_path_id
+ self.insn_cnt = insn_cnt
+ self.cyc_cnt = cyc_cnt
self.branch_count = branch_count
self.time = time
def Select(self):
self.query_done = True;
query = QSqlQuery(self.glb.db)
- QueryExec(query, "SELECT call_path_id, name, short_name, COUNT(calls.id), SUM(return_time - call_time), SUM(branch_count)"
+ if self.params.have_ipc:
+ ipc_str = ", SUM(insn_count), SUM(cyc_count)"
+ else:
+ ipc_str = ""
+ QueryExec(query, "SELECT call_path_id, name, short_name, COUNT(calls.id), SUM(return_time - call_time)" + ipc_str + ", SUM(branch_count)"
" FROM calls"
" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
" GROUP BY call_path_id, name, short_name"
" ORDER BY call_path_id")
while query.next():
- child_item = CallGraphLevelThreeItem(self.glb, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), int(query.value(5)), self)
+ if self.params.have_ipc:
+ insn_cnt = int(query.value(5))
+ cyc_cnt = int(query.value(6))
+ branch_count = int(query.value(7))
+ else:
+ insn_cnt = 0
+ cyc_cnt = 0
+ branch_count = int(query.value(5))
+ child_item = CallGraphLevelThreeItem(self.glb, self.params, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), insn_cnt, cyc_cnt, branch_count, self)
self.child_items.append(child_item)
self.child_count += 1
class CallGraphLevelThreeItem(CallGraphLevelTwoPlusItemBase):
- def __init__(self, glb, row, comm_id, thread_id, call_path_id, name, dso, count, time, branch_count, parent_item):
- super(CallGraphLevelThreeItem, self).__init__(glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item)
+ def __init__(self, glb, params, row, comm_id, thread_id, call_path_id, name, dso, count, time, insn_cnt, cyc_cnt, branch_count, parent_item):
+ super(CallGraphLevelThreeItem, self).__init__(glb, params, row, comm_id, thread_id, call_path_id, time, insn_cnt, cyc_cnt, branch_count, parent_item)
dso = dsoname(dso)
- self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
+ if self.params.have_ipc:
+ insn_pcnt = PercentToOneDP(insn_cnt, parent_item.insn_cnt)
+ cyc_pcnt = PercentToOneDP(cyc_cnt, parent_item.cyc_cnt)
+ br_pcnt = PercentToOneDP(branch_count, parent_item.branch_count)
+ ipc = CalcIPC(cyc_cnt, insn_cnt)
+ self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(insn_cnt), insn_pcnt, str(cyc_cnt), cyc_pcnt, ipc, str(branch_count), br_pcnt ]
+ else:
+ self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
self.dbid = call_path_id
# Context-sensitive call graph data model level two item
class CallGraphLevelTwoItem(CallGraphLevelTwoPlusItemBase):
- def __init__(self, glb, row, comm_id, thread_id, pid, tid, parent_item):
- super(CallGraphLevelTwoItem, self).__init__(glb, row, comm_id, thread_id, 1, 0, 0, parent_item)
- self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
+ def __init__(self, glb, params, row, comm_id, thread_id, pid, tid, parent_item):
+ super(CallGraphLevelTwoItem, self).__init__(glb, params, row, comm_id, thread_id, 1, 0, 0, 0, 0, parent_item)
+ if self.params.have_ipc:
+ self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", "", "", "", "", "", ""]
+ else:
+ self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
self.dbid = thread_id
def Select(self):
super(CallGraphLevelTwoItem, self).Select()
for child_item in self.child_items:
self.time += child_item.time
+ self.insn_cnt += child_item.insn_cnt
+ self.cyc_cnt += child_item.cyc_cnt
self.branch_count += child_item.branch_count
for child_item in self.child_items:
child_item.data[4] = PercentToOneDP(child_item.time, self.time)
- child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
+ if self.params.have_ipc:
+ child_item.data[6] = PercentToOneDP(child_item.insn_cnt, self.insn_cnt)
+ child_item.data[8] = PercentToOneDP(child_item.cyc_cnt, self.cyc_cnt)
+ child_item.data[11] = PercentToOneDP(child_item.branch_count, self.branch_count)
+ else:
+ child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
# Context-sensitive call graph data model level one item
class CallGraphLevelOneItem(CallGraphLevelItemBase):
- def __init__(self, glb, row, comm_id, comm, parent_item):
- super(CallGraphLevelOneItem, self).__init__(glb, row, parent_item)
- self.data = [comm, "", "", "", "", "", ""]
+ def __init__(self, glb, params, row, comm_id, comm, parent_item):
+ super(CallGraphLevelOneItem, self).__init__(glb, params, row, parent_item)
+ if self.params.have_ipc:
+ self.data = [comm, "", "", "", "", "", "", "", "", "", "", ""]
+ else:
+ self.data = [comm, "", "", "", "", "", ""]
self.dbid = comm_id
def Select(self):
" INNER JOIN threads ON thread_id = threads.id"
" WHERE comm_id = " + str(self.dbid))
while query.next():
- child_item = CallGraphLevelTwoItem(self.glb, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
+ child_item = CallGraphLevelTwoItem(self.glb, self.params, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
self.child_items.append(child_item)
self.child_count += 1
class CallGraphRootItem(CallGraphLevelItemBase):
- def __init__(self, glb):
- super(CallGraphRootItem, self).__init__(glb, 0, None)
+ def __init__(self, glb, params):
+ super(CallGraphRootItem, self).__init__(glb, params, 0, None)
self.dbid = 0
self.query_done = True;
query = QSqlQuery(glb.db)
while query.next():
if not query.value(0):
continue
- child_item = CallGraphLevelOneItem(glb, self.child_count, query.value(0), query.value(1), self)
+ child_item = CallGraphLevelOneItem(glb, params, self.child_count, query.value(0), query.value(1), self)
self.child_items.append(child_item)
self.child_count += 1
+# Call graph model parameters
+
+class CallGraphModelParams():
+
+ def __init__(self, glb, parent=None):
+ self.have_ipc = IsSelectable(glb.db, "calls", columns = "insn_count, cyc_count")
+
# Context-sensitive call graph data model base
class CallGraphModelBase(TreeModel):
def __init__(self, glb, parent=None):
- super(CallGraphModelBase, self).__init__(glb, parent)
+ super(CallGraphModelBase, self).__init__(glb, CallGraphModelParams(glb), parent)
def FindSelect(self, value, pattern, query):
if pattern:
super(CallGraphModel, self).__init__(glb, parent)
def GetRoot(self):
- return CallGraphRootItem(self.glb)
+ return CallGraphRootItem(self.glb, self.params)
def columnCount(self, parent=None):
- return 7
+ if self.params.have_ipc:
+ return 12
+ else:
+ return 7
def columnHeader(self, column):
- headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
+ if self.params.have_ipc:
+ headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Insn Cnt", "Insn Cnt (%)", "Cyc Cnt", "Cyc Cnt (%)", "IPC", "Branch Count ", "Branch Count (%) "]
+ else:
+ headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
return headers[column]
def columnAlignment(self, column):
- alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
+ if self.params.have_ipc:
+ alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
+ else:
+ alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
return alignment[column]
def DoFindSelect(self, query, match):
class CallTreeLevelTwoPlusItemBase(CallGraphLevelItemBase):
- def __init__(self, glb, row, comm_id, thread_id, calls_id, time, branch_count, parent_item):
- super(CallTreeLevelTwoPlusItemBase, self).__init__(glb, row, parent_item)
+ def __init__(self, glb, params, row, comm_id, thread_id, calls_id, time, insn_cnt, cyc_cnt, branch_count, parent_item):
+ super(CallTreeLevelTwoPlusItemBase, self).__init__(glb, params, row, parent_item)
self.comm_id = comm_id
self.thread_id = thread_id
self.calls_id = calls_id
+ self.insn_cnt = insn_cnt
+ self.cyc_cnt = cyc_cnt
self.branch_count = branch_count
self.time = time
comm_thread = " AND comm_id = " + str(self.comm_id) + " AND thread_id = " + str(self.thread_id)
else:
comm_thread = ""
+ if self.params.have_ipc:
+ ipc_str = ", insn_count, cyc_count"
+ else:
+ ipc_str = ""
query = QSqlQuery(self.glb.db)
- QueryExec(query, "SELECT calls.id, name, short_name, call_time, return_time - call_time, branch_count"
+ QueryExec(query, "SELECT calls.id, name, short_name, call_time, return_time - call_time" + ipc_str + ", branch_count"
" FROM calls"
" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
" WHERE calls.parent_id = " + str(self.calls_id) + comm_thread +
" ORDER BY call_time, calls.id")
while query.next():
- child_item = CallTreeLevelThreeItem(self.glb, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), int(query.value(5)), self)
+ if self.params.have_ipc:
+ insn_cnt = int(query.value(5))
+ cyc_cnt = int(query.value(6))
+ branch_count = int(query.value(7))
+ else:
+ insn_cnt = 0
+ cyc_cnt = 0
+ branch_count = int(query.value(5))
+ child_item = CallTreeLevelThreeItem(self.glb, self.params, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), insn_cnt, cyc_cnt, branch_count, self)
self.child_items.append(child_item)
self.child_count += 1
class CallTreeLevelThreeItem(CallTreeLevelTwoPlusItemBase):
- def __init__(self, glb, row, comm_id, thread_id, calls_id, name, dso, count, time, branch_count, parent_item):
- super(CallTreeLevelThreeItem, self).__init__(glb, row, comm_id, thread_id, calls_id, time, branch_count, parent_item)
+ def __init__(self, glb, params, row, comm_id, thread_id, calls_id, name, dso, count, time, insn_cnt, cyc_cnt, branch_count, parent_item):
+ super(CallTreeLevelThreeItem, self).__init__(glb, params, row, comm_id, thread_id, calls_id, time, insn_cnt, cyc_cnt, branch_count, parent_item)
dso = dsoname(dso)
- self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
+ if self.params.have_ipc:
+ insn_pcnt = PercentToOneDP(insn_cnt, parent_item.insn_cnt)
+ cyc_pcnt = PercentToOneDP(cyc_cnt, parent_item.cyc_cnt)
+ br_pcnt = PercentToOneDP(branch_count, parent_item.branch_count)
+ ipc = CalcIPC(cyc_cnt, insn_cnt)
+ self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(insn_cnt), insn_pcnt, str(cyc_cnt), cyc_pcnt, ipc, str(branch_count), br_pcnt ]
+ else:
+ self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
self.dbid = calls_id
# Call tree data model level two item
class CallTreeLevelTwoItem(CallTreeLevelTwoPlusItemBase):
- def __init__(self, glb, row, comm_id, thread_id, pid, tid, parent_item):
- super(CallTreeLevelTwoItem, self).__init__(glb, row, comm_id, thread_id, 0, 0, 0, parent_item)
- self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
+ def __init__(self, glb, params, row, comm_id, thread_id, pid, tid, parent_item):
+ super(CallTreeLevelTwoItem, self).__init__(glb, params, row, comm_id, thread_id, 0, 0, 0, 0, 0, parent_item)
+ if self.params.have_ipc:
+ self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", "", "", "", "", "", ""]
+ else:
+ self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
self.dbid = thread_id
def Select(self):
super(CallTreeLevelTwoItem, self).Select()
for child_item in self.child_items:
self.time += child_item.time
+ self.insn_cnt += child_item.insn_cnt
+ self.cyc_cnt += child_item.cyc_cnt
self.branch_count += child_item.branch_count
for child_item in self.child_items:
child_item.data[4] = PercentToOneDP(child_item.time, self.time)
- child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
+ if self.params.have_ipc:
+ child_item.data[6] = PercentToOneDP(child_item.insn_cnt, self.insn_cnt)
+ child_item.data[8] = PercentToOneDP(child_item.cyc_cnt, self.cyc_cnt)
+ child_item.data[11] = PercentToOneDP(child_item.branch_count, self.branch_count)
+ else:
+ child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
# Call tree data model level one item
class CallTreeLevelOneItem(CallGraphLevelItemBase):
- def __init__(self, glb, row, comm_id, comm, parent_item):
- super(CallTreeLevelOneItem, self).__init__(glb, row, parent_item)
- self.data = [comm, "", "", "", "", "", ""]
+ def __init__(self, glb, params, row, comm_id, comm, parent_item):
+ super(CallTreeLevelOneItem, self).__init__(glb, params, row, parent_item)
+ if self.params.have_ipc:
+ self.data = [comm, "", "", "", "", "", "", "", "", "", "", ""]
+ else:
+ self.data = [comm, "", "", "", "", "", ""]
self.dbid = comm_id
def Select(self):
" INNER JOIN threads ON thread_id = threads.id"
" WHERE comm_id = " + str(self.dbid))
while query.next():
- child_item = CallTreeLevelTwoItem(self.glb, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
+ child_item = CallTreeLevelTwoItem(self.glb, self.params, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
self.child_items.append(child_item)
self.child_count += 1
class CallTreeRootItem(CallGraphLevelItemBase):
- def __init__(self, glb):
- super(CallTreeRootItem, self).__init__(glb, 0, None)
+ def __init__(self, glb, params):
+ super(CallTreeRootItem, self).__init__(glb, params, 0, None)
self.dbid = 0
self.query_done = True;
query = QSqlQuery(glb.db)
while query.next():
if not query.value(0):
continue
- child_item = CallTreeLevelOneItem(glb, self.child_count, query.value(0), query.value(1), self)
+ child_item = CallTreeLevelOneItem(glb, params, self.child_count, query.value(0), query.value(1), self)
self.child_items.append(child_item)
self.child_count += 1
super(CallTreeModel, self).__init__(glb, parent)
def GetRoot(self):
- return CallTreeRootItem(self.glb)
+ return CallTreeRootItem(self.glb, self.params)
def columnCount(self, parent=None):
- return 7
+ if self.params.have_ipc:
+ return 12
+ else:
+ return 7
def columnHeader(self, column):
- headers = ["Call Path", "Object", "Call Time", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
+ if self.params.have_ipc:
+ headers = ["Call Path", "Object", "Call Time", "Time (ns) ", "Time (%) ", "Insn Cnt", "Insn Cnt (%)", "Cyc Cnt", "Cyc Cnt (%)", "IPC", "Branch Count ", "Branch Count (%) "]
+ else:
+ headers = ["Call Path", "Object", "Call Time", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
return headers[column]
def columnAlignment(self, column):
- alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
+ if self.params.have_ipc:
+ alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
+ else:
+ alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
return alignment[column]
def DoFindSelect(self, query, match):
class BranchLevelTwoItem():
- def __init__(self, row, text, parent_item):
+ def __init__(self, row, col, text, parent_item):
self.row = row
self.parent_item = parent_item
- self.data = [""] * 8
- self.data[7] = text
+ self.data = [""] * (col + 1)
+ self.data[col] = text
self.level = 2
def getParentItem(self):
self.dbid = data[0]
self.level = 1
self.query_done = False
+ self.br_col = len(self.data) - 1
def getChildItem(self, row):
return self.child_items[row]
while k < 15:
byte_str += " "
k += 1
- self.child_items.append(BranchLevelTwoItem(0, byte_str + " " + text, self))
+ self.child_items.append(BranchLevelTwoItem(0, self.br_col, byte_str + " " + text, self))
self.child_count += 1
else:
return
def getData(self, column):
return ""
+# Calculate instructions per cycle
+
+def CalcIPC(cyc_cnt, insn_cnt):
+ if cyc_cnt and insn_cnt:
+ ipc = Decimal(float(insn_cnt) / cyc_cnt)
+ ipc = str(ipc.quantize(Decimal(".01"), rounding=ROUND_HALF_UP))
+ else:
+ ipc = "0"
+ return ipc
+
# Branch data preparation
-def BranchDataPrep(query):
- data = []
- for i in xrange(0, 8):
- data.append(query.value(i))
+def BranchDataPrepBr(query, data):
data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) +
" (" + dsoname(query.value(11)) + ")" + " -> " +
tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) +
" (" + dsoname(query.value(15)) + ")")
+
+def BranchDataPrepIPC(query, data):
+ insn_cnt = query.value(16)
+ cyc_cnt = query.value(17)
+ ipc = CalcIPC(cyc_cnt, insn_cnt)
+ data.append(insn_cnt)
+ data.append(cyc_cnt)
+ data.append(ipc)
+
+def BranchDataPrep(query):
+ data = []
+ for i in xrange(0, 8):
+ data.append(query.value(i))
+ BranchDataPrepBr(query, data)
return data
def BranchDataPrepWA(query):
data.append("{:>19}".format(query.value(1)))
for i in xrange(2, 8):
data.append(query.value(i))
- data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) +
- " (" + dsoname(query.value(11)) + ")" + " -> " +
- tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) +
- " (" + dsoname(query.value(15)) + ")")
+ BranchDataPrepBr(query, data)
+ return data
+
+def BranchDataWithIPCPrep(query):
+ data = []
+ for i in xrange(0, 8):
+ data.append(query.value(i))
+ BranchDataPrepIPC(query, data)
+ BranchDataPrepBr(query, data)
+ return data
+
+def BranchDataWithIPCPrepWA(query):
+ data = []
+ data.append(query.value(0))
+ # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+ data.append("{:>19}".format(query.value(1)))
+ for i in xrange(2, 8):
+ data.append(query.value(i))
+ BranchDataPrepIPC(query, data)
+ BranchDataPrepBr(query, data)
return data
# Branch data model
progress = Signal(object)
def __init__(self, glb, event_id, where_clause, parent=None):
- super(BranchModel, self).__init__(glb, parent)
+ super(BranchModel, self).__init__(glb, None, parent)
self.event_id = event_id
self.more = True
self.populated = 0
+ self.have_ipc = IsSelectable(glb.db, "samples", columns = "insn_count, cyc_count")
+ if self.have_ipc:
+ select_ipc = ", insn_count, cyc_count"
+ prep_fn = BranchDataWithIPCPrep
+ prep_wa_fn = BranchDataWithIPCPrepWA
+ else:
+ select_ipc = ""
+ prep_fn = BranchDataPrep
+ prep_wa_fn = BranchDataPrepWA
sql = ("SELECT samples.id, time, cpu, comm, pid, tid, branch_types.name,"
" CASE WHEN in_tx = '0' THEN 'No' ELSE 'Yes' END,"
" ip, symbols.name, sym_offset, dsos.short_name,"
" to_ip, to_symbols.name, to_sym_offset, to_dsos.short_name"
+ + select_ipc +
" FROM samples"
" INNER JOIN comms ON comm_id = comms.id"
" INNER JOIN threads ON thread_id = threads.id"
" ORDER BY samples.id"
" LIMIT " + str(glb_chunk_sz))
if pyside_version_1 and sys.version_info[0] == 3:
- prep = BranchDataPrepWA
+ prep = prep_fn
else:
- prep = BranchDataPrep
+ prep = prep_wa_fn
self.fetcher = SQLFetcher(glb, sql, prep, self.AddSample)
self.fetcher.done.connect(self.Update)
self.fetcher.Fetch(glb_chunk_sz)
return BranchRootItem()
def columnCount(self, parent=None):
- return 8
+ if self.have_ipc:
+ return 11
+ else:
+ return 8
def columnHeader(self, column):
- return ("Time", "CPU", "Command", "PID", "TID", "Branch Type", "In Tx", "Branch")[column]
+ if self.have_ipc:
+ return ("Time", "CPU", "Command", "PID", "TID", "Branch Type", "In Tx", "Insn Cnt", "Cyc Cnt", "IPC", "Branch")[column]
+ else:
+ return ("Time", "CPU", "Command", "PID", "TID", "Branch Type", "In Tx", "Branch")[column]
def columnFont(self, column):
- if column != 7:
+ if self.have_ipc:
+ br_col = 10
+ else:
+ br_col = 7
+ if column != br_col:
return None
return QFont("Monospace")
# Is a table selectable
-def IsSelectable(db, table, sql = ""):
+def IsSelectable(db, table, sql = "", columns = "*"):
query = QSqlQuery(db)
try:
- QueryExec(query, "SELECT * FROM " + table + " " + sql + " LIMIT 1")
+ QueryExec(query, "SELECT " + columns + " FROM " + table + " " + sql + " LIMIT 1")
except:
return False
return True
action = self.window_menu.addAction(label)
action.setCheckable(True)
action.setChecked(sub_window == self.mdi_area.activeSubWindow())
- action.triggered.connect(lambda x=nr: self.setActiveSubWindow(x))
+ action.triggered.connect(lambda a=None,x=nr: self.setActiveSubWindow(x))
self.window_menu.addAction(action)
nr += 1
sudo ./mfile.py --prefix=/usr/local install
sudo ldconfig
</pre>
+<h3>Instructions per Cycle (IPC)</h3>
+If available, IPC information is displayed in columns 'insn_cnt', 'cyc_cnt' and 'IPC'.
+<p><b>Intel PT note:</b> The information applies to the blocks of code ending with, and including, that branch.
+Due to the granularity of timing information, the number of cycles for some code blocks will not be known.
+In that case, 'insn_cnt', 'cyc_cnt' and 'IPC' are zero, but when 'IPC' is displayed it covers the period
+since the previous displayed 'IPC'.
<h3>Find</h3>
Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match.
Refer to Python documentation for the regular expression syntax.
event = event.split(":")[0]
if event == "branches":
label = "All branches" if branches_events == 1 else "All branches " + "(id=" + dbid + ")"
- reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewBranchView(x), self))
+ reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda a=None,x=dbid: self.NewBranchView(x), self))
label = "Selected branches" if branches_events == 1 else "Selected branches " + "(id=" + dbid + ")"
- reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewSelectedBranchView(x), self))
+ reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda a=None,x=dbid: self.NewSelectedBranchView(x), self))
def TableMenu(self, tables, menu):
table_menu = menu.addMenu("&Tables")
for table in tables:
- table_menu.addAction(CreateAction(table, "Create a new window containing a table view", lambda t=table: self.NewTableView(t), self))
+ table_menu.addAction(CreateAction(table, "Create a new window containing a table view", lambda a=None,t=table: self.NewTableView(t), self))
def NewCallGraph(self):
CallGraphWindow(self.glb, self)
# Main
def Main():
- if (len(sys.argv) < 2):
- printerr("Usage is: exported-sql-viewer.py {<database name> | --help-only}");
- raise Exception("Too few arguments")
-
- dbname = sys.argv[1]
- if dbname == "--help-only":
+ usage_str = "exported-sql-viewer.py [--pyside-version-1] <database name>\n" \
+ " or: exported-sql-viewer.py --help-only"
+ ap = argparse.ArgumentParser(usage = usage_str, add_help = False)
+ ap.add_argument("--pyside-version-1", action='store_true')
+ ap.add_argument("dbname", nargs="?")
+ ap.add_argument("--help-only", action='store_true')
+ args = ap.parse_args()
+
+ if args.help_only:
app = QApplication(sys.argv)
mainwindow = HelpOnlyWindow()
mainwindow.show()
err = app.exec_()
sys.exit(err)
+ dbname = args.dbname
+ if dbname is None:
+ ap.print_usage()
+ print("Too few arguments")
+ sys.exit(1)
+
is_sqlite3 = False
try:
f = open(dbname, "rb")
+# SPDX-License-Identifier: GPL-2.0
+
perf-y += builtin-test.o
perf-y += parse-events.o
perf-y += dso-data.o
perf-y += clang.o
perf-y += unit_number__scnprintf.o
perf-y += mem2node.o
+perf-y += map_groups.o
+perf-y += time-utils-test.o
$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
$(call rule_mkdir)
+// SPDX-License-Identifier: GPL-2.0
/*
* Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select
* 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu.
+// SPDX-License-Identifier: GPL-2.0
/*
* bpf-script-example.c
* Test basic LLVM building
+// SPDX-License-Identifier: GPL-2.0
/*
* bpf-script-test-kbuild.c
* Test include from kernel header
+// SPDX-License-Identifier: GPL-2.0
/*
* bpf-script-test-prologue.c
* Test BPF prologue
+// SPDX-License-Identifier: GPL-2.0
/*
* bpf-script-test-relocation.c
* Test BPF loader checking relocation
+// SPDX-License-Identifier: GPL-2.0
#include <errno.h>
#include <stdio.h>
#include <sys/epoll.h>
#include "string2.h"
#include "symbol.h"
#include <linux/kernel.h>
+#include <linux/string.h>
#include <subcmd/exec-cmd.h>
static bool dont_fork;
.desc = "mem2node",
.func = test__mem2node,
},
+ {
+ .desc = "time utils",
+ .func = test__time_utils,
+ },
+ {
+ .desc = "map_groups__merge_in",
+ .func = test__map_groups__merge_in,
+ },
{
.func = NULL,
},
description = fgets(description, size, fp);
fclose(fp);
- return description ? trim(description + 1) : NULL;
+ return description ? strim(description + 1) : NULL;
}
#define for_each_shell_test(dir, base, ent) \
#include "tests.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
#define BUFSZ 1024
#define READLEN 128
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include "tests.h"
+#include "map.h"
+#include "map_groups.h"
+#include "dso.h"
+#include "debug.h"
+
+struct map_def {
+ const char *name;
+ u64 start;
+ u64 end;
+};
+
+static int check_maps(struct map_def *merged, unsigned int size, struct map_groups *mg)
+{
+ struct map *map;
+ unsigned int i = 0;
+
+ map = map_groups__first(mg);
+ while (map) {
+ TEST_ASSERT_VAL("wrong map start", map->start == merged[i].start);
+ TEST_ASSERT_VAL("wrong map end", map->end == merged[i].end);
+ TEST_ASSERT_VAL("wrong map name", !strcmp(map->dso->name, merged[i].name));
+ TEST_ASSERT_VAL("wrong map refcnt", refcount_read(&map->refcnt) == 2);
+
+ i++;
+ map = map_groups__next(map);
+
+ TEST_ASSERT_VAL("less maps expected", (map && i < size) || (!map && i == size));
+ }
+
+ return TEST_OK;
+}
+
+int test__map_groups__merge_in(struct test *t __maybe_unused, int subtest __maybe_unused)
+{
+ struct map_groups mg;
+ unsigned int i;
+ struct map_def bpf_progs[] = {
+ { "bpf_prog_1", 200, 300 },
+ { "bpf_prog_2", 500, 600 },
+ { "bpf_prog_3", 800, 900 },
+ };
+ struct map_def merged12[] = {
+ { "kcore1", 100, 200 },
+ { "bpf_prog_1", 200, 300 },
+ { "kcore1", 300, 500 },
+ { "bpf_prog_2", 500, 600 },
+ { "kcore1", 600, 800 },
+ { "bpf_prog_3", 800, 900 },
+ { "kcore1", 900, 1000 },
+ };
+ struct map_def merged3[] = {
+ { "kcore1", 100, 200 },
+ { "bpf_prog_1", 200, 300 },
+ { "kcore1", 300, 500 },
+ { "bpf_prog_2", 500, 600 },
+ { "kcore1", 600, 800 },
+ { "bpf_prog_3", 800, 900 },
+ { "kcore1", 900, 1000 },
+ { "kcore3", 1000, 1100 },
+ };
+ struct map *map_kcore1, *map_kcore2, *map_kcore3;
+ int ret;
+
+ map_groups__init(&mg, NULL);
+
+ for (i = 0; i < ARRAY_SIZE(bpf_progs); i++) {
+ struct map *map;
+
+ map = dso__new_map(bpf_progs[i].name);
+ TEST_ASSERT_VAL("failed to create map", map);
+
+ map->start = bpf_progs[i].start;
+ map->end = bpf_progs[i].end;
+ map_groups__insert(&mg, map);
+ map__put(map);
+ }
+
+ map_kcore1 = dso__new_map("kcore1");
+ TEST_ASSERT_VAL("failed to create map", map_kcore1);
+
+ map_kcore2 = dso__new_map("kcore2");
+ TEST_ASSERT_VAL("failed to create map", map_kcore2);
+
+ map_kcore3 = dso__new_map("kcore3");
+ TEST_ASSERT_VAL("failed to create map", map_kcore3);
+
+ /* kcore1 map overlaps over all bpf maps */
+ map_kcore1->start = 100;
+ map_kcore1->end = 1000;
+
+ /* kcore2 map hides behind bpf_prog_2 */
+ map_kcore2->start = 550;
+ map_kcore2->end = 570;
+
+ /* kcore3 map hides behind bpf_prog_3, kcore1 and adds new map */
+ map_kcore3->start = 880;
+ map_kcore3->end = 1100;
+
+ ret = map_groups__merge_in(&mg, map_kcore1);
+ TEST_ASSERT_VAL("failed to merge map", !ret);
+
+ ret = check_maps(merged12, ARRAY_SIZE(merged12), &mg);
+ TEST_ASSERT_VAL("merge check failed", !ret);
+
+ ret = map_groups__merge_in(&mg, map_kcore2);
+ TEST_ASSERT_VAL("failed to merge map", !ret);
+
+ ret = check_maps(merged12, ARRAY_SIZE(merged12), &mg);
+ TEST_ASSERT_VAL("merge check failed", !ret);
+
+ ret = map_groups__merge_in(&mg, map_kcore3);
+ TEST_ASSERT_VAL("failed to merge map", !ret);
+
+ ret = check_maps(merged3, ARRAY_SIZE(merged3), &mg);
+ TEST_ASSERT_VAL("merge check failed", !ret);
+ return TEST_OK;
+}
+// SPDX-License-Identifier: GPL-2.0
#include "util/mem-events.h"
#include "util/symbol.h"
#include "linux/perf_event.h"
+// SPDX-License-Identifier: GPL-2.0
#include <linux/compiler.h>
#include <linux/bitmap.h>
#include "cpumap.h"
#define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+#if defined(__s390x__)
+/* Return true if kvm module is available and loaded. Test this
+ * and retun success when trace point kvm_s390_create_vm
+ * exists. Otherwise this test always fails.
+ */
+static bool kvm_s390_create_vm_valid(void)
+{
+ char *eventfile;
+ bool rc = false;
+
+ eventfile = get_events_file("kvm-s390");
+
+ if (eventfile) {
+ DIR *mydir = opendir(eventfile);
+
+ if (mydir) {
+ rc = true;
+ closedir(mydir);
+ }
+ put_events_file(eventfile);
+ }
+
+ return rc;
+}
+#endif
+
static int test__checkevent_tracepoint(struct perf_evlist *evlist)
{
struct perf_evsel *evsel = perf_evlist__first(evlist);
{
.name = "kvm-s390:kvm_s390_create_vm",
.check = test__checkevent_tracepoint,
+ .valid = kvm_s390_create_vm_valid,
.id = 100,
},
#endif
+# SPDX-License-Identifier: GPL-2.0
# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
skip_if_no_perf_probe() {
#!/bin/sh
# Add vfs_getname probe to get syscall args filenames
-#
+
+# SPDX-License-Identifier: GPL-2.0
# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
. $(dirname $0)/lib/probe.sh
# This needs no debuginfo package, all is done using the libc ELF symtab
# and the CFI info in the binaries.
+# SPDX-License-Identifier: GPL-2.0
# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
. $(dirname $0)/lib/probe.sh
# checks that that was captured by the vfs_getname probe in the generated
# perf.data file, with the temp file name as the pathname argument.
+# SPDX-License-Identifier: GPL-2.0
# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
. $(dirname $0)/lib/probe.sh
#!/bin/sh
# Zstd perf.data compression/decompression
+# SPDX-License-Identifier: GPL-2.0
+
trace_file=$(mktemp /tmp/perf.data.XXX)
perf_tool=perf
# that already handles "probe:vfs_getname" if present, and used in the
# "open" syscall "filename" argument beautifier.
+# SPDX-License-Identifier: GPL-2.0
# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
. $(dirname $0)/lib/probe.sh
int test__clang_subtest_get_nr(void);
int test__unit_number__scnprint(struct test *test, int subtest);
int test__mem2node(struct test *t, int subtest);
+int test__map_groups__merge_in(struct test *t, int subtest);
+int test__time_utils(struct test *t, int subtest);
bool test__bp_signal_is_supported(void);
bool test__wp_is_supported(void);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+#include <linux/time64.h>
+#include <inttypes.h>
+#include <string.h>
+#include "time-utils.h"
+#include "evlist.h"
+#include "session.h"
+#include "debug.h"
+#include "tests.h"
+
+static bool test__parse_nsec_time(const char *str, u64 expected)
+{
+ u64 ptime;
+ int err;
+
+ pr_debug("\nparse_nsec_time(\"%s\")\n", str);
+
+ err = parse_nsec_time(str, &ptime);
+ if (err) {
+ pr_debug("error %d\n", err);
+ return false;
+ }
+
+ if (ptime != expected) {
+ pr_debug("Failed. ptime %" PRIu64 " expected %" PRIu64 "\n",
+ ptime, expected);
+ return false;
+ }
+
+ pr_debug("%" PRIu64 "\n", ptime);
+
+ return true;
+}
+
+static bool test__perf_time__parse_str(const char *ostr, u64 start, u64 end)
+{
+ struct perf_time_interval ptime;
+ int err;
+
+ pr_debug("\nperf_time__parse_str(\"%s\")\n", ostr);
+
+ err = perf_time__parse_str(&ptime, ostr);
+ if (err) {
+ pr_debug("Error %d\n", err);
+ return false;
+ }
+
+ if (ptime.start != start || ptime.end != end) {
+ pr_debug("Failed. Expected %" PRIu64 " to %" PRIu64 "\n",
+ start, end);
+ return false;
+ }
+
+ return true;
+}
+
+#define TEST_MAX 64
+
+struct test_data {
+ const char *str;
+ u64 first;
+ u64 last;
+ struct perf_time_interval ptime[TEST_MAX];
+ int num;
+ u64 skip[TEST_MAX];
+ u64 noskip[TEST_MAX];
+};
+
+static bool test__perf_time__parse_for_ranges(struct test_data *d)
+{
+ struct perf_evlist evlist = {
+ .first_sample_time = d->first,
+ .last_sample_time = d->last,
+ };
+ struct perf_session session = { .evlist = &evlist };
+ struct perf_time_interval *ptime = NULL;
+ int range_size, range_num;
+ bool pass = false;
+ int i, err;
+
+ pr_debug("\nperf_time__parse_for_ranges(\"%s\")\n", d->str);
+
+ if (strchr(d->str, '%'))
+ pr_debug("first_sample_time %" PRIu64 " last_sample_time %" PRIu64 "\n",
+ d->first, d->last);
+
+ err = perf_time__parse_for_ranges(d->str, &session, &ptime, &range_size,
+ &range_num);
+ if (err) {
+ pr_debug("error %d\n", err);
+ goto out;
+ }
+
+ if (range_size < d->num || range_num != d->num) {
+ pr_debug("bad size: range_size %d range_num %d expected num %d\n",
+ range_size, range_num, d->num);
+ goto out;
+ }
+
+ for (i = 0; i < d->num; i++) {
+ if (ptime[i].start != d->ptime[i].start ||
+ ptime[i].end != d->ptime[i].end) {
+ pr_debug("bad range %d expected %" PRIu64 " to %" PRIu64 "\n",
+ i, d->ptime[i].start, d->ptime[i].end);
+ goto out;
+ }
+ }
+
+ if (perf_time__ranges_skip_sample(ptime, d->num, 0)) {
+ pr_debug("failed to keep 0\n");
+ goto out;
+ }
+
+ for (i = 0; i < TEST_MAX; i++) {
+ if (d->skip[i] &&
+ !perf_time__ranges_skip_sample(ptime, d->num, d->skip[i])) {
+ pr_debug("failed to skip %" PRIu64 "\n", d->skip[i]);
+ goto out;
+ }
+ if (d->noskip[i] &&
+ perf_time__ranges_skip_sample(ptime, d->num, d->noskip[i])) {
+ pr_debug("failed to keep %" PRIu64 "\n", d->noskip[i]);
+ goto out;
+ }
+ }
+
+ pass = true;
+out:
+ free(ptime);
+ return pass;
+}
+
+int test__time_utils(struct test *t __maybe_unused, int subtest __maybe_unused)
+{
+ bool pass = true;
+
+ pass &= test__parse_nsec_time("0", 0);
+ pass &= test__parse_nsec_time("1", 1000000000ULL);
+ pass &= test__parse_nsec_time("0.000000001", 1);
+ pass &= test__parse_nsec_time("1.000000001", 1000000001ULL);
+ pass &= test__parse_nsec_time("123456.123456", 123456123456000ULL);
+ pass &= test__parse_nsec_time("1234567.123456789", 1234567123456789ULL);
+ pass &= test__parse_nsec_time("18446744073.709551615",
+ 0xFFFFFFFFFFFFFFFFULL);
+
+ pass &= test__perf_time__parse_str("1234567.123456789,1234567.123456789",
+ 1234567123456789ULL, 1234567123456789ULL);
+ pass &= test__perf_time__parse_str("1234567.123456789,1234567.123456790",
+ 1234567123456789ULL, 1234567123456790ULL);
+ pass &= test__perf_time__parse_str("1234567.123456789,",
+ 1234567123456789ULL, 0);
+ pass &= test__perf_time__parse_str(",1234567.123456789",
+ 0, 1234567123456789ULL);
+ pass &= test__perf_time__parse_str("0,1234567.123456789",
+ 0, 1234567123456789ULL);
+
+ {
+ u64 b = 1234567123456789ULL;
+ struct test_data d = {
+ .str = "1234567.123456789,1234567.123456790",
+ .ptime = { {b, b + 1}, },
+ .num = 1,
+ .skip = { b - 1, b + 2, },
+ .noskip = { b, b + 1, },
+ };
+
+ pass &= test__perf_time__parse_for_ranges(&d);
+ }
+
+ {
+ u64 b = 1234567123456789ULL;
+ u64 c = 7654321987654321ULL;
+ u64 e = 8000000000000000ULL;
+ struct test_data d = {
+ .str = "1234567.123456789,1234567.123456790 "
+ "7654321.987654321,7654321.987654444 "
+ "8000000,8000000.000000005",
+ .ptime = { {b, b + 1}, {c, c + 123}, {e, e + 5}, },
+ .num = 3,
+ .skip = { b - 1, b + 2, c - 1, c + 124, e - 1, e + 6 },
+ .noskip = { b, b + 1, c, c + 123, e, e + 5 },
+ };
+
+ pass &= test__perf_time__parse_for_ranges(&d);
+ }
+
+ {
+ u64 b = 7654321ULL * NSEC_PER_SEC;
+ struct test_data d = {
+ .str = "10%/1",
+ .first = b,
+ .last = b + 100,
+ .ptime = { {b, b + 9}, },
+ .num = 1,
+ .skip = { b - 1, b + 10, },
+ .noskip = { b, b + 9, },
+ };
+
+ pass &= test__perf_time__parse_for_ranges(&d);
+ }
+
+ {
+ u64 b = 7654321ULL * NSEC_PER_SEC;
+ struct test_data d = {
+ .str = "10%/2",
+ .first = b,
+ .last = b + 100,
+ .ptime = { {b + 10, b + 19}, },
+ .num = 1,
+ .skip = { b + 9, b + 20, },
+ .noskip = { b + 10, b + 19, },
+ };
+
+ pass &= test__perf_time__parse_for_ranges(&d);
+ }
+
+ {
+ u64 b = 11223344ULL * NSEC_PER_SEC;
+ struct test_data d = {
+ .str = "10%/1,10%/2",
+ .first = b,
+ .last = b + 100,
+ .ptime = { {b, b + 9}, {b + 10, b + 19}, },
+ .num = 2,
+ .skip = { b - 1, b + 20, },
+ .noskip = { b, b + 8, b + 9, b + 10, b + 11, b + 12, b + 19, },
+ };
+
+ pass &= test__perf_time__parse_for_ranges(&d);
+ }
+
+ {
+ u64 b = 11223344ULL * NSEC_PER_SEC;
+ struct test_data d = {
+ .str = "10%/1,10%/3,10%/10",
+ .first = b,
+ .last = b + 100,
+ .ptime = { {b, b + 9}, {b + 20, b + 29}, { b + 90, b + 100}, },
+ .num = 3,
+ .skip = { b - 1, b + 10, b + 19, b + 30, b + 89, b + 101 },
+ .noskip = { b, b + 9, b + 20, b + 29, b + 90, b + 100},
+ };
+
+ pass &= test__perf_time__parse_for_ranges(&d);
+ }
+
+ pr_debug("\n");
+
+ return pass ? 0 : TEST_FAIL;
+}
perf-y += clone.o
perf-y += fcntl.o
perf-y += flock.o
+perf-y += fsmount.o
+perf-y += fspick.o
ifeq ($(SRCARCH),$(filter $(SRCARCH),x86))
perf-y += ioctl.o
endif
perf-y += kcmp.o
perf-y += mount_flags.o
+perf-y += move_mount.o
perf-y += pkey_alloc.o
perf-y += arch_prctl.o
perf-y += prctl.o
perf-y += sockaddr.o
perf-y += socket.o
perf-y += statx.o
+perf-y += sync_file_range.o
unsigned long syscall_arg__val(struct syscall_arg *arg, u8 idx);
+size_t syscall_arg__scnprintf_strarray_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_STRARRAY_FLAGS syscall_arg__scnprintf_strarray_flags
+
size_t syscall_arg__scnprintf_strarrays(char *bf, size_t size, struct syscall_arg *arg);
#define SCA_STRARRAYS syscall_arg__scnprintf_strarrays
size_t syscall_arg__scnprintf_flock(char *bf, size_t size, struct syscall_arg *arg);
#define SCA_FLOCK syscall_arg__scnprintf_flock
+size_t syscall_arg__scnprintf_fsmount_attr_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_FSMOUNT_ATTR_FLAGS syscall_arg__scnprintf_fsmount_attr_flags
+
+size_t syscall_arg__scnprintf_fspick_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_FSPICK_FLAGS syscall_arg__scnprintf_fspick_flags
+
size_t syscall_arg__scnprintf_ioctl_cmd(char *bf, size_t size, struct syscall_arg *arg);
#define SCA_IOCTL_CMD syscall_arg__scnprintf_ioctl_cmd
size_t syscall_arg__scnprintf_mount_flags(char *bf, size_t size, struct syscall_arg *arg);
#define SCA_MOUNT_FLAGS syscall_arg__scnprintf_mount_flags
+size_t syscall_arg__scnprintf_move_mount_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_MOVE_MOUNT_FLAGS syscall_arg__scnprintf_move_mount_flags
+
size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg);
#define SCA_PKEY_ALLOC_ACCESS_RIGHTS syscall_arg__scnprintf_pkey_alloc_access_rights
size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg);
#define SCA_STATX_MASK syscall_arg__scnprintf_statx_mask
+size_t syscall_arg__scnprintf_sync_file_range_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_SYNC_FILE_RANGE_FLAGS syscall_arg__scnprintf_sync_file_range_flags
+
size_t open__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix);
void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg,
P_FLAG(FS);
P_FLAG(FILES);
P_FLAG(SIGHAND);
+ P_FLAG(PIDFD);
P_FLAG(PTRACE);
P_FLAG(VFORK);
P_FLAG(PARENT);
--- /dev/null
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+if [ $# -ne 1 ] ; then
+ linux_header_dir=tools/include/uapi/linux
+else
+ linux_header_dir=$1
+fi
+
+linux_mount=${linux_header_dir}/mount.h
+
+printf "static const char *fsconfig_cmds[] = {\n"
+regex='^[[:space:]]*+FSCONFIG_([[:alnum:]_]+)[[:space:]]*=[[:space:]]*([[:digit:]]+)[[:space:]]*,[[:space:]]*.*'
+egrep $regex ${linux_mount} | \
+ sed -r "s/$regex/\2 \1/g" | \
+ xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
--- /dev/null
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * trace/beauty/fsmount.c
+ *
+ * Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/log2.h>
+#include <uapi/linux/mount.h>
+
+static size_t fsmount__scnprintf_attr_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
+{
+#include "trace/beauty/generated/fsmount_arrays.c"
+ static DEFINE_STRARRAY(fsmount_attr_flags, "MOUNT_ATTR_");
+ size_t printed = 0;
+
+ if ((flags & ~MOUNT_ATTR__ATIME) != 0)
+ printed += strarray__scnprintf_flags(&strarray__fsmount_attr_flags, bf, size, show_prefix, flags);
+
+ if ((flags & MOUNT_ATTR__ATIME) == MOUNT_ATTR_RELATIME) {
+ printed += scnprintf(bf + printed, size - printed, "%s%s%s",
+ printed ? "|" : "", show_prefix ? "MOUNT_ATTR_" : "", "RELATIME");
+ }
+
+ return printed;
+}
+
+size_t syscall_arg__scnprintf_fsmount_attr_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+ unsigned long flags = arg->val;
+
+ return fsmount__scnprintf_attr_flags(flags, bf, size, arg->show_string_prefix);
+}
--- /dev/null
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+if [ $# -ne 1 ] ; then
+ linux_header_dir=tools/include/uapi/linux
+else
+ linux_header_dir=$1
+fi
+
+linux_mount=${linux_header_dir}/mount.h
+
+# Remove MOUNT_ATTR_RELATIME as it is zeros, handle it a special way in the beautifier
+# Only handle MOUNT_ATTR_ followed by a capital letter/num as __ is special case
+# for things like MOUNT_ATTR__ATIME that is a mask for the possible ATIME handling
+# bits. Special case it as well in the beautifier
+
+printf "static const char *fsmount_attr_flags[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MOUNT_ATTR_([[:alnum:]][[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
+egrep $regex ${linux_mount} | grep -v MOUNT_ATTR_RELATIME | \
+ sed -r "s/$regex/\2 \1/g" | \
+ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n"
+printf "};\n"
--- /dev/null
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * trace/beauty/fspick.c
+ *
+ * Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/log2.h>
+
+static size_t fspick__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
+{
+#include "trace/beauty/generated/fspick_arrays.c"
+ static DEFINE_STRARRAY(fspick_flags, "FSPICK_");
+
+ return strarray__scnprintf_flags(&strarray__fspick_flags, bf, size, show_prefix, flags);
+}
+
+size_t syscall_arg__scnprintf_fspick_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+ unsigned long flags = arg->val;
+
+ return fspick__scnprintf_flags(flags, bf, size, arg->show_string_prefix);
+}
--- /dev/null
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+if [ $# -ne 1 ] ; then
+ linux_header_dir=tools/include/uapi/linux
+else
+ linux_header_dir=$1
+fi
+
+linux_mount=${linux_header_dir}/mount.h
+
+printf "static const char *fspick_flags[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+FSPICK_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
+egrep $regex ${linux_mount} | \
+ sed -r "s/$regex/\2 \1/g" | \
+ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n"
+printf "};\n"
--- /dev/null
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * trace/beauty/move_mount.c
+ *
+ * Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/log2.h>
+
+static size_t move_mount__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
+{
+#include "trace/beauty/generated/move_mount_flags_array.c"
+ static DEFINE_STRARRAY(move_mount_flags, "MOVE_MOUNT_");
+
+ return strarray__scnprintf_flags(&strarray__move_mount_flags, bf, size, show_prefix, flags);
+}
+
+size_t syscall_arg__scnprintf_move_mount_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+ unsigned long flags = arg->val;
+
+ return move_mount__scnprintf_flags(flags, bf, size, arg->show_string_prefix);
+}
--- /dev/null
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+if [ $# -ne 1 ] ; then
+ linux_header_dir=tools/include/uapi/linux
+else
+ linux_header_dir=$1
+fi
+
+linux_mount=${linux_header_dir}/mount.h
+
+printf "static const char *move_mount_flags[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MOVE_MOUNT_([FT]_[[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
+egrep $regex ${linux_mount} | \
+ sed -r "s/$regex/\2 \1/g" | \
+ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n"
+printf "};\n"
--- /dev/null
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * trace/beauty/sync_file_range.c
+ *
+ * Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/log2.h>
+#include <uapi/linux/fs.h>
+
+static size_t sync_file_range__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
+{
+#include "trace/beauty/generated/sync_file_range_arrays.c"
+ static DEFINE_STRARRAY(sync_file_range_flags, "SYNC_FILE_RANGE_");
+ size_t printed = 0;
+
+ if ((flags & SYNC_FILE_RANGE_WRITE_AND_WAIT) == SYNC_FILE_RANGE_WRITE_AND_WAIT) {
+ printed += scnprintf(bf + printed, size - printed, "%s%s", show_prefix ? "SYNC_FILE_RANGE_" : "", "WRITE_AND_WAIT");
+ flags &= ~SYNC_FILE_RANGE_WRITE_AND_WAIT;
+ }
+
+ return printed + strarray__scnprintf_flags(&strarray__sync_file_range_flags, bf + printed, size - printed, show_prefix, flags);
+}
+
+size_t syscall_arg__scnprintf_sync_file_range_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+ unsigned long flags = arg->val;
+
+ return sync_file_range__scnprintf_flags(flags, bf, size, arg->show_string_prefix);
+}
--- /dev/null
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+if [ $# -ne 1 ] ; then
+ linux_header_dir=tools/include/uapi/linux
+else
+ linux_header_dir=$1
+fi
+
+linux_fs=${linux_header_dir}/fs.h
+
+printf "static const char *sync_file_range_flags[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+SYNC_FILE_RANGE_([[:alnum:]_]+)[[:space:]]+([[:xdigit:]]+)[[:space:]]*.*'
+egrep $regex ${linux_fs} | \
+ sed -r "s/$regex/\2 \1/g" | \
+ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n"
+printf "};\n"
#include "helpline.h"
#include "keysyms.h"
#include "../color.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
static int ui_browser__percent_color(struct ui_browser *browser,
double percent, bool current)
break;
*bg = '\0';
- bg = ltrim(++bg);
+ bg = skip_spaces(bg + 1);
ui_browser__colorsets[i].bg = bg;
ui_browser__colorsets[i].fg = fg;
return 0;
struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
struct annotation *notes = browser__annotation(browser);
struct annotation_line *al = list_entry(entry, struct annotation_line, node);
+ const bool is_current_entry = ui_browser__is_current_entry(browser, row);
struct annotation_write_ops ops = {
.first_line = row == 0,
- .current_entry = ui_browser__is_current_entry(browser, row),
+ .current_entry = is_current_entry,
.change_color = (!notes->options->hide_src_code &&
- (!ops.current_entry ||
+ (!is_current_entry ||
(browser->use_navkeypressed &&
!browser->navkeypressed))),
.width = browser->width,
#include <stdlib.h>
#include <string.h>
#include <linux/rbtree.h>
+#include <linux/string.h>
#include <sys/ttydefaults.h>
#include <linux/time64.h>
#include "units.h"
#include "time-utils.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
extern void hist_browser__init_hpp(void);
int i = 0;
width -= fmt->entry(fmt, &hpp, entry);
- ui_browser__printf(&browser->b, "%s", ltrim(s));
+ ui_browser__printf(&browser->b, "%s", skip_spaces(s));
while (isspace(s[i++]))
width++;
ret = fmt->header(fmt, &dummy_hpp, hists, 0, NULL);
dummy_hpp.buf[ret] = '\0';
- start = trim(dummy_hpp.buf);
+ start = strim(dummy_hpp.buf);
ret = strlen(start);
if (start != dummy_hpp.buf)
advance_hpp(&hpp, ret);
}
- printed += fprintf(fp, "%s\n", rtrim(s));
+ strim(s);
+ printed += fprintf(fp, "%s\n", s);
if (he->leaf && folded_sign == '-') {
printed += hist_browser__fprintf_callchain(browser, he, fp,
#include "../keysyms.h"
#include "map.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
struct map_browser {
struct ui_browser b;
#include "../string2.h"
#include "gtk.h"
#include <signal.h>
+#include <linux/string.h>
#define MAX_COLUMNS 32
advance_hpp(hpp, ret + 2);
}
- gtk_tree_store_set(store, &iter, col_idx, ltrim(rtrim(bf)), -1);
+ gtk_tree_store_set(store, &iter, col_idx, strim(bf), -1);
if (!he->leaf) {
hpp->buf = bf;
first_col = false;
fmt->header(fmt, &hpp, hists, 0, NULL);
- strcat(buf, ltrim(rtrim(hpp.buf)));
+ strcat(buf, strim(hpp.buf));
}
}
#ifndef HAVE_LONG_LONG
#define HAVE_LONG_LONG __GLIBC_HAVE_LONG_LONG
#endif
+
+#ifdef HAVE_SLANG_INCLUDE_SUBDIR
+#include <slang/slang.h>
+#else
#include <slang.h>
+#endif
#if SLANG_VERSION < 20104
#define slsmg_printf(msg, args...) \
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
-#include "../cache.h"
+#include "../util/cache.h"
#include "progress.h"
static void null_progress__update(struct ui_progress *p __maybe_unused)
#include "../../util/srcline.h"
#include "../../util/string2.h"
#include "../../util/thread.h"
-#include "../../util/sane_ctype.h"
+#include <linux/ctype.h>
static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
{
* dynamic entries are right-aligned but we want left-aligned
* in the hierarchy mode
*/
- printed += fprintf(fp, "%s%s", sep ?: " ", ltrim(buf));
+ printed += fprintf(fp, "%s%s", sep ?: " ", skip_spaces(buf));
}
printed += putc('\n', fp);
return printed;
}
+static int hist_entry__block_fprintf(struct hist_entry *he,
+ char *bf, size_t size,
+ FILE *fp)
+{
+ struct block_hist *bh = container_of(he, struct block_hist, he);
+ int ret = 0;
+
+ for (unsigned int i = 0; i < bh->block_hists.nr_entries; i++) {
+ struct perf_hpp hpp = {
+ .buf = bf,
+ .size = size,
+ .skip = false,
+ };
+
+ bh->block_idx = i;
+ hist_entry__snprintf(he, &hpp);
+
+ if (!hpp.skip)
+ ret += fprintf(fp, "%s\n", bf);
+ }
+
+ return ret;
+}
+
static int hist_entry__fprintf(struct hist_entry *he, size_t size,
char *bf, size_t bfsz, FILE *fp,
bool ignore_callchains)
if (symbol_conf.report_hierarchy)
return hist_entry__hierarchy_fprintf(he, &hpp, hists, fp);
+ if (symbol_conf.report_block)
+ return hist_entry__block_fprintf(he, bf, size, fp);
+
hist_entry__snprintf(he, &hpp);
ret = fprintf(fp, "%s\n", bf);
static int print_hierarchy_indent(const char *sep, int indent,
const char *line, FILE *fp)
{
+ int width;
+
if (sep != NULL || indent < 2)
return 0;
- return fprintf(fp, "%-.*s", (indent - 2) * HIERARCHY_INDENT, line);
+ width = (indent - 2) * HIERARCHY_INDENT;
+
+ return fprintf(fp, "%-*.*s", width, width, line);
}
static int hists__fprintf_hierarchy_headers(struct hists *hists,
indent = hists->nr_hpp_node;
/* preserve max indent depth for column headers */
- print_hierarchy_indent(sep, indent, spaces, fp);
+ print_hierarchy_indent(sep, indent, " ", fp);
/* the first hpp_list_node is for overhead columns */
fmt_node = list_first_entry(&hists->hpp_formats,
fmt->header(fmt, hpp, hists, 0, NULL);
- header_width += fprintf(fp, "%s", trim(hpp->buf));
+ header_width += fprintf(fp, "%s", strim(hpp->buf));
}
}
if (!h->leaf && !hist_entry__has_hierarchy_children(h, min_pcnt)) {
int depth = hists->nr_hpp_node + h->depth + 1;
- print_hierarchy_indent(sep, depth, spaces, fp);
+ print_hierarchy_indent(sep, depth, " ", fp);
fprintf(fp, "%*sno entry >= %.2f%%\n", indent, "", min_pcnt);
if (max_rows && ++nr_rows >= max_rows)
perf-y += perf_regs.o
perf-y += path.o
perf-y += print_binary.o
+perf-y += argv_split.o
perf-y += rbtree.o
perf-y += libstring.o
perf-y += bitmap.o
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
+$(OUTPUT)util/argv_split.o: ../lib/argv_split.c FORCE
+ $(call rule_mkdir)
+ $(call if_changed_dep,cc_o_c)
+
$(OUTPUT)util/bitmap.o: ../lib/bitmap.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
+$(OUTPUT)util/ctype.o: ../lib/ctype.c FORCE
+ $(call rule_mkdir)
+ $(call if_changed_dep,cc_o_c)
+
$(OUTPUT)util/find_bit.o: ../lib/find_bit.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
if test -d ../../.git -o -f ../../.git
then
TAG=$(git describe --abbrev=0 --match "v[0-9].[0-9]*" 2>/dev/null )
- CID=$(git log -1 --abbrev=4 --pretty=format:"%h" 2>/dev/null) && CID="-g$CID"
+ CID=$(git log -1 --abbrev=12 --pretty=format:"%h" 2>/dev/null) && CID="-g$CID"
elif test -f ../../PERF-VERSION-FILE
then
TAG=$(cut -d' ' -f3 ../../PERF-VERSION-FILE | sed -e 's/\"//g')
#include <pthread.h>
#include <linux/bitops.h>
#include <linux/kernel.h>
+#include <linux/string.h>
#include <bpf/libbpf.h>
/* FIXME: For the HE_COLORSET */
#define DARROW_CHAR ((unsigned char)'.')
#define UARROW_CHAR ((unsigned char)'-')
-#include "sane_ctype.h"
+#include <linux/ctype.h>
struct annotation_options annotation__default_options = {
.use_offset = true,
#include "arch/arc/annotate/instructions.c"
#include "arch/arm/annotate/instructions.c"
#include "arch/arm64/annotate/instructions.c"
+#include "arch/csky/annotate/instructions.c"
#include "arch/x86/annotate/instructions.c"
#include "arch/powerpc/annotate/instructions.c"
#include "arch/s390/annotate/instructions.c"
.name = "arm64",
.init = arm64__annotate_init,
},
+ {
+ .name = "csky",
+ .init = csky__annotate_init,
+ },
{
.name = "x86",
.init = x86__annotate_init,
if (comment == NULL)
return 0;
- comment = ltrim(comment);
+ comment = skip_spaces(comment);
comment__symbol(ops->source.raw, comment + 1, &ops->source.addr, &ops->source.name);
comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
if (comment == NULL)
return 0;
- comment = ltrim(comment);
+ comment = skip_spaces(comment);
comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
return 0;
if (sym == NULL)
return 0;
src = symbol__hists(sym, evsel->evlist->nr_entries);
- if (src == NULL)
- return -ENOMEM;
- return __symbol__inc_addr_samples(sym, map, src, evsel->idx, addr, sample);
+ return (src) ? __symbol__inc_addr_samples(sym, map, src, evsel->idx,
+ addr, sample) : 0;
}
static int symbol__account_cycles(u64 addr, u64 start,
static int disasm_line__parse(char *line, const char **namep, char **rawp)
{
- char tmp, *name = ltrim(line);
+ char tmp, *name = skip_spaces(line);
if (name[0] == '\0')
return -1;
goto out_free_name;
(*rawp)[0] = tmp;
- *rawp = ltrim(*rawp);
+ *rawp = skip_spaces(*rawp);
return 0;
return -1;
line_ip = -1;
- parsed_line = rtrim(line);
+ parsed_line = strim(line);
/* /filename:linenr ? Save line number and ignore. */
if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) {
return 0;
}
- tmp = ltrim(parsed_line);
+ tmp = skip_spaces(parsed_line);
if (*tmp) {
/*
* Parse hexa addresses followed by ':'
#include "arm-spe.h"
#include "s390-cpumsf.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
#include "symbol/kallsyms.h"
static bool auxtrace__dont_decode(struct perf_session *session)
}
if (!str) {
- itrace_synth_opts__set_default(synth_opts, false);
+ itrace_synth_opts__set_default(synth_opts,
+ synth_opts->default_no_sample);
return 0;
}
* @period_type: 'instructions' events period type
* @initial_skip: skip N events at the beginning.
* @cpu_bitmap: CPUs for which to synthesize events, or NULL for all
+ * @ptime_range: time intervals to trace or NULL
+ * @range_num: number of time intervals to trace
*/
struct itrace_synth_opts {
bool set;
enum itrace_period_type period_type;
unsigned long initial_skip;
unsigned long *cpu_bitmap;
+ struct perf_time_interval *ptime_range;
+ int range_num;
};
/**
" PERIOD[ns|us|ms|i|t]: specify period to sample stream\n" \
" concatenate multiple options. Default is ibxwpe or cewp\n"
+static inline
+void itrace_synth_opts__set_time_range(struct itrace_synth_opts *opts,
+ struct perf_time_interval *ptime_range,
+ int range_num)
+{
+ opts->ptime_range = ptime_range;
+ opts->range_num = range_num;
+}
+
+static inline
+void itrace_synth_opts__clear_time_range(struct itrace_synth_opts *opts)
+{
+ opts->ptime_range = NULL;
+ opts->range_num = 0;
+}
#else
#define ITRACE_HELP ""
+static inline
+void itrace_synth_opts__set_time_range(struct itrace_synth_opts *opts
+ __maybe_unused,
+ struct perf_time_interval *ptime_range
+ __maybe_unused,
+ int range_num __maybe_unused)
+{
+}
+
+static inline
+void itrace_synth_opts__clear_time_range(struct itrace_synth_opts *opts
+ __maybe_unused)
+{
+}
+
#endif
#endif
#include "probe-file.h"
#include "strlist.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
static bool no_buildid_cache;
#include <unistd.h>
#include <linux/string.h>
-#include "sane_ctype.h"
+#include <linux/ctype.h>
#define MAXNAME (256)
if (ret < 0) {
pr_err("Error: wrong config key-value pair %s=%s\n",
key, value);
- break;
+ /*
+ * Can't be just a 'break', as perf_config_set__for_each_entry()
+ * expands to two nested for() loops.
+ */
+ goto out;
}
}
}
-
+out:
return ret;
}
#include <linux/bitmap.h>
#include "asm/bug.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
static int max_cpu_num;
static int max_present_cpu_num;
return 0;
}
+int cpu_map__get_die_id(int cpu)
+{
+ int value, ret = cpu__get_topology_int(cpu, "die_id", &value);
+
+ return ret ?: value;
+}
+
+int cpu_map__get_die(struct cpu_map *map, int idx, void *data)
+{
+ int cpu, die_id, s;
+
+ if (idx > map->nr)
+ return -1;
+
+ cpu = map->map[idx];
+
+ die_id = cpu_map__get_die_id(cpu);
+ /* There is no die_id on legacy system. */
+ if (die_id == -1)
+ die_id = 0;
+
+ s = cpu_map__get_socket(map, idx, data);
+ if (s == -1)
+ return -1;
+
+ /*
+ * Encode socket in bit range 15:8
+ * die_id is relative to socket, and
+ * we need a global id. So we combine
+ * socket + die id
+ */
+ if (WARN_ONCE(die_id >> 8, "The die id number is too big.\n"))
+ return -1;
+
+ if (WARN_ONCE(s >> 8, "The socket id number is too big.\n"))
+ return -1;
+
+ return (s << 8) | (die_id & 0xff);
+}
+
int cpu_map__get_core_id(int cpu)
{
int value, ret = cpu__get_topology_int(cpu, "core_id", &value);
int cpu_map__get_core(struct cpu_map *map, int idx, void *data)
{
- int cpu, s;
+ int cpu, s_die;
if (idx > map->nr)
return -1;
cpu = cpu_map__get_core_id(cpu);
- s = cpu_map__get_socket(map, idx, data);
- if (s == -1)
+ /* s_die is the combination of socket + die id */
+ s_die = cpu_map__get_die(map, idx, data);
+ if (s_die == -1)
return -1;
/*
- * encode socket in upper 16 bits
- * core_id is relative to socket, and
+ * encode socket in bit range 31:24
+ * encode die id in bit range 23:16
+ * core_id is relative to socket and die,
* we need a global id. So we combine
- * socket+ core id
+ * socket + die id + core id
*/
- return (s << 16) | (cpu & 0xffff);
+ if (WARN_ONCE(cpu >> 16, "The core id number is too big.\n"))
+ return -1;
+
+ return (s_die << 16) | (cpu & 0xffff);
}
int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp)
return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL);
}
+int cpu_map__build_die_map(struct cpu_map *cpus, struct cpu_map **diep)
+{
+ return cpu_map__build_map(cpus, diep, cpu_map__get_die, NULL);
+}
+
int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep)
{
return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL);
size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
int cpu_map__get_socket_id(int cpu);
int cpu_map__get_socket(struct cpu_map *map, int idx, void *data);
+int cpu_map__get_die_id(int cpu);
+int cpu_map__get_die(struct cpu_map *map, int idx, void *data);
int cpu_map__get_core_id(int cpu);
int cpu_map__get_core(struct cpu_map *map, int idx, void *data);
int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp);
+int cpu_map__build_die_map(struct cpu_map *cpus, struct cpu_map **diep);
int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep);
const struct cpu_map *cpu_map__online(void); /* thread unsafe */
static inline int cpu_map__id_to_socket(int id)
{
- return id >> 16;
+ return id >> 24;
+}
+
+static inline int cpu_map__id_to_die(int id)
+{
+ return (id >> 16) & 0xff;
}
static inline int cpu_map__id_to_cpu(int id)
// SPDX-License-Identifier: GPL-2.0
#include <sys/param.h>
+#include <sys/utsname.h>
#include <inttypes.h>
#include <api/fs/fs.h>
#include "util.h"
#include "env.h"
-
#define CORE_SIB_FMT \
"%s/devices/system/cpu/cpu%d/topology/core_siblings_list"
+#define DIE_SIB_FMT \
+ "%s/devices/system/cpu/cpu%d/topology/die_cpus_list"
#define THRD_SIB_FMT \
"%s/devices/system/cpu/cpu%d/topology/thread_siblings_list"
+#define THRD_SIB_FMT_NEW \
+ "%s/devices/system/cpu/cpu%d/topology/core_cpus_list"
#define NODE_ONLINE_FMT \
"%s/devices/system/node/online"
#define NODE_MEMINFO_FMT \
sysfs__mountpoint(), cpu);
fp = fopen(filename, "r");
if (!fp)
- goto try_threads;
+ goto try_dies;
sret = getline(&buf, &len, fp);
fclose(fp);
if (sret <= 0)
- goto try_threads;
+ goto try_dies;
p = strchr(buf, '\n');
if (p)
}
ret = 0;
+try_dies:
+ if (!tp->die_siblings)
+ goto try_threads;
+
+ scnprintf(filename, MAXPATHLEN, DIE_SIB_FMT,
+ sysfs__mountpoint(), cpu);
+ fp = fopen(filename, "r");
+ if (!fp)
+ goto try_threads;
+
+ sret = getline(&buf, &len, fp);
+ fclose(fp);
+ if (sret <= 0)
+ goto try_threads;
+
+ p = strchr(buf, '\n');
+ if (p)
+ *p = '\0';
+
+ for (i = 0; i < tp->die_sib; i++) {
+ if (!strcmp(buf, tp->die_siblings[i]))
+ break;
+ }
+ if (i == tp->die_sib) {
+ tp->die_siblings[i] = buf;
+ tp->die_sib++;
+ buf = NULL;
+ len = 0;
+ }
+ ret = 0;
+
try_threads:
- scnprintf(filename, MAXPATHLEN, THRD_SIB_FMT,
+ scnprintf(filename, MAXPATHLEN, THRD_SIB_FMT_NEW,
sysfs__mountpoint(), cpu);
+ if (access(filename, F_OK) == -1) {
+ scnprintf(filename, MAXPATHLEN, THRD_SIB_FMT,
+ sysfs__mountpoint(), cpu);
+ }
fp = fopen(filename, "r");
if (!fp)
goto done;
for (i = 0 ; i < tp->core_sib; i++)
zfree(&tp->core_siblings[i]);
+ if (tp->die_sib) {
+ for (i = 0 ; i < tp->die_sib; i++)
+ zfree(&tp->die_siblings[i]);
+ }
+
for (i = 0 ; i < tp->thread_sib; i++)
zfree(&tp->thread_siblings[i]);
free(tp);
}
+static bool has_die_topology(void)
+{
+ char filename[MAXPATHLEN];
+ struct utsname uts;
+
+ if (uname(&uts) < 0)
+ return false;
+
+ if (strncmp(uts.machine, "x86_64", 6))
+ return false;
+
+ scnprintf(filename, MAXPATHLEN, DIE_SIB_FMT,
+ sysfs__mountpoint(), 0);
+ if (access(filename, F_OK) == -1)
+ return false;
+
+ return true;
+}
+
struct cpu_topology *cpu_topology__new(void)
{
struct cpu_topology *tp = NULL;
void *addr;
- u32 nr, i;
+ u32 nr, i, nr_addr;
size_t sz;
long ncpus;
int ret = -1;
struct cpu_map *map;
+ bool has_die = has_die_topology();
ncpus = cpu__max_present_cpu();
nr = (u32)(ncpus & UINT_MAX);
sz = nr * sizeof(char *);
- addr = calloc(1, sizeof(*tp) + 2 * sz);
+ if (has_die)
+ nr_addr = 3;
+ else
+ nr_addr = 2;
+ addr = calloc(1, sizeof(*tp) + nr_addr * sz);
if (!addr)
goto out_free;
addr += sizeof(*tp);
tp->core_siblings = addr;
addr += sz;
+ if (has_die) {
+ tp->die_siblings = addr;
+ addr += sz;
+ }
tp->thread_siblings = addr;
for (i = 0; i < nr; i++) {
struct cpu_topology {
u32 core_sib;
+ u32 die_sib;
u32 thread_sib;
char **core_siblings;
+ char **die_siblings;
char **thread_siblings;
};
#include "intlist.h"
#include "util.h"
-#define MAX_BUFFER 1024
-
/* use raw logging */
#ifdef CS_DEBUG_RAW
#define CS_LOG_RAW_FRAMES
#endif
#endif
-#define CS_ETM_INVAL_ADDR 0xdeadbeefdeadbeefUL
-
struct cs_etm_decoder {
void *data;
void (*packet_printer)(const char *msg);
dcd_tree_handle_t dcd_tree;
cs_etm_mem_cb_type mem_access;
ocsd_datapath_resp_t prev_return;
- u32 packet_count;
- u32 head;
- u32 tail;
- struct cs_etm_packet packet_buffer[MAX_BUFFER];
};
static u32
cs_etm_decoder__mem_access(const void *context,
const ocsd_vaddr_t address,
const ocsd_mem_space_acc_t mem_space __maybe_unused,
+ const u8 trace_chan_id,
const u32 req_size,
u8 *buffer)
{
struct cs_etm_decoder *decoder = (struct cs_etm_decoder *) context;
- return decoder->mem_access(decoder->data,
- address,
- req_size,
- buffer);
+ return decoder->mem_access(decoder->data, trace_chan_id,
+ address, req_size, buffer);
}
int cs_etm_decoder__add_mem_access_cb(struct cs_etm_decoder *decoder,
{
decoder->mem_access = cb_func;
- if (ocsd_dt_add_callback_mem_acc(decoder->dcd_tree, start, end,
- OCSD_MEM_SPACE_ANY,
- cs_etm_decoder__mem_access, decoder))
+ if (ocsd_dt_add_callback_trcid_mem_acc(decoder->dcd_tree, start, end,
+ OCSD_MEM_SPACE_ANY,
+ cs_etm_decoder__mem_access,
+ decoder))
return -1;
return 0;
return 0;
}
-int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder,
+int cs_etm_decoder__get_packet(struct cs_etm_packet_queue *packet_queue,
struct cs_etm_packet *packet)
{
- if (!decoder || !packet)
+ if (!packet_queue || !packet)
return -EINVAL;
/* Nothing to do, might as well just return */
- if (decoder->packet_count == 0)
+ if (packet_queue->packet_count == 0)
return 0;
/*
* The queueing process in function cs_etm_decoder__buffer_packet()
* value. Otherwise the first element of the packet queue is not
* used.
*/
- decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1);
+ packet_queue->head = (packet_queue->head + 1) &
+ (CS_ETM_PACKET_MAX_BUFFER - 1);
- *packet = decoder->packet_buffer[decoder->head];
+ *packet = packet_queue->packet_buffer[packet_queue->head];
- decoder->packet_count--;
+ packet_queue->packet_count--;
return 1;
}
trace_config);
}
-static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
+static ocsd_datapath_resp_t
+cs_etm_decoder__do_soft_timestamp(struct cs_etm_queue *etmq,
+ struct cs_etm_packet_queue *packet_queue,
+ const uint8_t trace_chan_id)
{
- int i;
-
- decoder->head = 0;
- decoder->tail = 0;
- decoder->packet_count = 0;
- for (i = 0; i < MAX_BUFFER; i++) {
- decoder->packet_buffer[i].isa = CS_ETM_ISA_UNKNOWN;
- decoder->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR;
- decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR;
- decoder->packet_buffer[i].instr_count = 0;
- decoder->packet_buffer[i].last_instr_taken_branch = false;
- decoder->packet_buffer[i].last_instr_size = 0;
- decoder->packet_buffer[i].last_instr_type = 0;
- decoder->packet_buffer[i].last_instr_subtype = 0;
- decoder->packet_buffer[i].last_instr_cond = 0;
- decoder->packet_buffer[i].flags = 0;
- decoder->packet_buffer[i].exception_number = UINT32_MAX;
- decoder->packet_buffer[i].trace_chan_id = UINT8_MAX;
- decoder->packet_buffer[i].cpu = INT_MIN;
+ /* No timestamp packet has been received, nothing to do */
+ if (!packet_queue->timestamp)
+ return OCSD_RESP_CONT;
+
+ packet_queue->timestamp = packet_queue->next_timestamp;
+
+ /* Estimate the timestamp for the next range packet */
+ packet_queue->next_timestamp += packet_queue->instr_count;
+ packet_queue->instr_count = 0;
+
+ /* Tell the front end which traceid_queue needs attention */
+ cs_etm__etmq_set_traceid_queue_timestamp(etmq, trace_chan_id);
+
+ return OCSD_RESP_WAIT;
+}
+
+static ocsd_datapath_resp_t
+cs_etm_decoder__do_hard_timestamp(struct cs_etm_queue *etmq,
+ const ocsd_generic_trace_elem *elem,
+ const uint8_t trace_chan_id)
+{
+ struct cs_etm_packet_queue *packet_queue;
+
+ /* First get the packet queue for this traceID */
+ packet_queue = cs_etm__etmq_get_packet_queue(etmq, trace_chan_id);
+ if (!packet_queue)
+ return OCSD_RESP_FATAL_SYS_ERR;
+
+ /*
+ * We've seen a timestamp packet before - simply record the new value.
+ * Function do_soft_timestamp() will report the value to the front end,
+ * hence asking the decoder to keep decoding rather than stopping.
+ */
+ if (packet_queue->timestamp) {
+ packet_queue->next_timestamp = elem->timestamp;
+ return OCSD_RESP_CONT;
}
+
+ /*
+ * This is the first timestamp we've seen since the beginning of traces
+ * or a discontinuity. Since timestamps packets are generated *after*
+ * range packets have been generated, we need to estimate the time at
+ * which instructions started by substracting the number of instructions
+ * executed to the timestamp.
+ */
+ packet_queue->timestamp = elem->timestamp - packet_queue->instr_count;
+ packet_queue->next_timestamp = elem->timestamp;
+ packet_queue->instr_count = 0;
+
+ /* Tell the front end which traceid_queue needs attention */
+ cs_etm__etmq_set_traceid_queue_timestamp(etmq, trace_chan_id);
+
+ /* Halt processing until we are being told to proceed */
+ return OCSD_RESP_WAIT;
+}
+
+static void
+cs_etm_decoder__reset_timestamp(struct cs_etm_packet_queue *packet_queue)
+{
+ packet_queue->timestamp = 0;
+ packet_queue->next_timestamp = 0;
+ packet_queue->instr_count = 0;
}
static ocsd_datapath_resp_t
-cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
+cs_etm_decoder__buffer_packet(struct cs_etm_packet_queue *packet_queue,
const u8 trace_chan_id,
enum cs_etm_sample_type sample_type)
{
u32 et = 0;
int cpu;
- if (decoder->packet_count >= MAX_BUFFER - 1)
+ if (packet_queue->packet_count >= CS_ETM_PACKET_MAX_BUFFER - 1)
return OCSD_RESP_FATAL_SYS_ERR;
if (cs_etm__get_cpu(trace_chan_id, &cpu) < 0)
return OCSD_RESP_FATAL_SYS_ERR;
- et = decoder->tail;
- et = (et + 1) & (MAX_BUFFER - 1);
- decoder->tail = et;
- decoder->packet_count++;
-
- decoder->packet_buffer[et].sample_type = sample_type;
- decoder->packet_buffer[et].isa = CS_ETM_ISA_UNKNOWN;
- decoder->packet_buffer[et].cpu = cpu;
- decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR;
- decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR;
- decoder->packet_buffer[et].instr_count = 0;
- decoder->packet_buffer[et].last_instr_taken_branch = false;
- decoder->packet_buffer[et].last_instr_size = 0;
- decoder->packet_buffer[et].last_instr_type = 0;
- decoder->packet_buffer[et].last_instr_subtype = 0;
- decoder->packet_buffer[et].last_instr_cond = 0;
- decoder->packet_buffer[et].flags = 0;
- decoder->packet_buffer[et].exception_number = UINT32_MAX;
- decoder->packet_buffer[et].trace_chan_id = trace_chan_id;
-
- if (decoder->packet_count == MAX_BUFFER - 1)
+ et = packet_queue->tail;
+ et = (et + 1) & (CS_ETM_PACKET_MAX_BUFFER - 1);
+ packet_queue->tail = et;
+ packet_queue->packet_count++;
+
+ packet_queue->packet_buffer[et].sample_type = sample_type;
+ packet_queue->packet_buffer[et].isa = CS_ETM_ISA_UNKNOWN;
+ packet_queue->packet_buffer[et].cpu = cpu;
+ packet_queue->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR;
+ packet_queue->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR;
+ packet_queue->packet_buffer[et].instr_count = 0;
+ packet_queue->packet_buffer[et].last_instr_taken_branch = false;
+ packet_queue->packet_buffer[et].last_instr_size = 0;
+ packet_queue->packet_buffer[et].last_instr_type = 0;
+ packet_queue->packet_buffer[et].last_instr_subtype = 0;
+ packet_queue->packet_buffer[et].last_instr_cond = 0;
+ packet_queue->packet_buffer[et].flags = 0;
+ packet_queue->packet_buffer[et].exception_number = UINT32_MAX;
+ packet_queue->packet_buffer[et].trace_chan_id = trace_chan_id;
+
+ if (packet_queue->packet_count == CS_ETM_PACKET_MAX_BUFFER - 1)
return OCSD_RESP_WAIT;
return OCSD_RESP_CONT;
}
static ocsd_datapath_resp_t
-cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder,
+cs_etm_decoder__buffer_range(struct cs_etm_queue *etmq,
+ struct cs_etm_packet_queue *packet_queue,
const ocsd_generic_trace_elem *elem,
const uint8_t trace_chan_id)
{
int ret = 0;
struct cs_etm_packet *packet;
- ret = cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+ ret = cs_etm_decoder__buffer_packet(packet_queue, trace_chan_id,
CS_ETM_RANGE);
if (ret != OCSD_RESP_CONT && ret != OCSD_RESP_WAIT)
return ret;
- packet = &decoder->packet_buffer[decoder->tail];
+ packet = &packet_queue->packet_buffer[packet_queue->tail];
switch (elem->isa) {
case ocsd_isa_aarch64:
packet->last_instr_size = elem->last_instr_sz;
+ /* per-thread scenario, no need to generate a timestamp */
+ if (cs_etm__etmq_is_timeless(etmq))
+ goto out;
+
+ /*
+ * The packet queue is full and we haven't seen a timestamp (had we
+ * seen one the packet queue wouldn't be full). Let the front end
+ * deal with it.
+ */
+ if (ret == OCSD_RESP_WAIT)
+ goto out;
+
+ packet_queue->instr_count += elem->num_instr_range;
+ /* Tell the front end we have a new timestamp to process */
+ ret = cs_etm_decoder__do_soft_timestamp(etmq, packet_queue,
+ trace_chan_id);
+out:
return ret;
}
static ocsd_datapath_resp_t
-cs_etm_decoder__buffer_discontinuity(struct cs_etm_decoder *decoder,
- const uint8_t trace_chan_id)
+cs_etm_decoder__buffer_discontinuity(struct cs_etm_packet_queue *queue,
+ const uint8_t trace_chan_id)
{
- return cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+ /*
+ * Something happened and who knows when we'll get new traces so
+ * reset time statistics.
+ */
+ cs_etm_decoder__reset_timestamp(queue);
+ return cs_etm_decoder__buffer_packet(queue, trace_chan_id,
CS_ETM_DISCONTINUITY);
}
static ocsd_datapath_resp_t
-cs_etm_decoder__buffer_exception(struct cs_etm_decoder *decoder,
+cs_etm_decoder__buffer_exception(struct cs_etm_packet_queue *queue,
const ocsd_generic_trace_elem *elem,
const uint8_t trace_chan_id)
{ int ret = 0;
struct cs_etm_packet *packet;
- ret = cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+ ret = cs_etm_decoder__buffer_packet(queue, trace_chan_id,
CS_ETM_EXCEPTION);
if (ret != OCSD_RESP_CONT && ret != OCSD_RESP_WAIT)
return ret;
- packet = &decoder->packet_buffer[decoder->tail];
+ packet = &queue->packet_buffer[queue->tail];
packet->exception_number = elem->exception_number;
return ret;
}
static ocsd_datapath_resp_t
-cs_etm_decoder__buffer_exception_ret(struct cs_etm_decoder *decoder,
+cs_etm_decoder__buffer_exception_ret(struct cs_etm_packet_queue *queue,
const uint8_t trace_chan_id)
{
- return cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+ return cs_etm_decoder__buffer_packet(queue, trace_chan_id,
CS_ETM_EXCEPTION_RET);
}
+static ocsd_datapath_resp_t
+cs_etm_decoder__set_tid(struct cs_etm_queue *etmq,
+ struct cs_etm_packet_queue *packet_queue,
+ const ocsd_generic_trace_elem *elem,
+ const uint8_t trace_chan_id)
+{
+ pid_t tid;
+
+ /* Ignore PE_CONTEXT packets that don't have a valid contextID */
+ if (!elem->context.ctxt_id_valid)
+ return OCSD_RESP_CONT;
+
+ tid = elem->context.context_id;
+ if (cs_etm__etmq_set_tid(etmq, tid, trace_chan_id))
+ return OCSD_RESP_FATAL_SYS_ERR;
+
+ /*
+ * A timestamp is generated after a PE_CONTEXT element so make sure
+ * to rely on that coming one.
+ */
+ cs_etm_decoder__reset_timestamp(packet_queue);
+
+ return OCSD_RESP_CONT;
+}
+
static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
const void *context,
const ocsd_trc_index_t indx __maybe_unused,
{
ocsd_datapath_resp_t resp = OCSD_RESP_CONT;
struct cs_etm_decoder *decoder = (struct cs_etm_decoder *) context;
+ struct cs_etm_queue *etmq = decoder->data;
+ struct cs_etm_packet_queue *packet_queue;
+
+ /* First get the packet queue for this traceID */
+ packet_queue = cs_etm__etmq_get_packet_queue(etmq, trace_chan_id);
+ if (!packet_queue)
+ return OCSD_RESP_FATAL_SYS_ERR;
switch (elem->elem_type) {
case OCSD_GEN_TRC_ELEM_UNKNOWN:
case OCSD_GEN_TRC_ELEM_EO_TRACE:
case OCSD_GEN_TRC_ELEM_NO_SYNC:
case OCSD_GEN_TRC_ELEM_TRACE_ON:
- resp = cs_etm_decoder__buffer_discontinuity(decoder,
+ resp = cs_etm_decoder__buffer_discontinuity(packet_queue,
trace_chan_id);
break;
case OCSD_GEN_TRC_ELEM_INSTR_RANGE:
- resp = cs_etm_decoder__buffer_range(decoder, elem,
+ resp = cs_etm_decoder__buffer_range(etmq, packet_queue, elem,
trace_chan_id);
break;
case OCSD_GEN_TRC_ELEM_EXCEPTION:
- resp = cs_etm_decoder__buffer_exception(decoder, elem,
+ resp = cs_etm_decoder__buffer_exception(packet_queue, elem,
trace_chan_id);
break;
case OCSD_GEN_TRC_ELEM_EXCEPTION_RET:
- resp = cs_etm_decoder__buffer_exception_ret(decoder,
+ resp = cs_etm_decoder__buffer_exception_ret(packet_queue,
trace_chan_id);
break;
+ case OCSD_GEN_TRC_ELEM_TIMESTAMP:
+ resp = cs_etm_decoder__do_hard_timestamp(etmq, elem,
+ trace_chan_id);
+ break;
case OCSD_GEN_TRC_ELEM_PE_CONTEXT:
+ resp = cs_etm_decoder__set_tid(etmq, packet_queue,
+ elem, trace_chan_id);
+ break;
case OCSD_GEN_TRC_ELEM_ADDR_NACC:
- case OCSD_GEN_TRC_ELEM_TIMESTAMP:
case OCSD_GEN_TRC_ELEM_CYCLE_COUNT:
case OCSD_GEN_TRC_ELEM_ADDR_UNKNOWN:
case OCSD_GEN_TRC_ELEM_EVENT:
decoder->data = d_params->data;
decoder->prev_return = OCSD_RESP_CONT;
- cs_etm_decoder__clear_buffer(decoder);
format = (d_params->formatted ? OCSD_TRC_SRC_FRAME_FORMATTED :
OCSD_TRC_SRC_SINGLE);
flags = 0;
/* init library print logging support */
ret = cs_etm_decoder__init_def_logger_printing(d_params, decoder);
if (ret != 0)
- goto err_free_decoder_tree;
+ goto err_free_decoder;
/* init raw frame logging if required */
cs_etm_decoder__init_raw_frame_logging(d_params, decoder);
&t_params[i],
decoder);
if (ret != 0)
- goto err_free_decoder_tree;
+ goto err_free_decoder;
}
return decoder;
-err_free_decoder_tree:
- ocsd_destroy_dcd_tree(decoder->dcd_tree);
err_free_decoder:
- free(decoder);
+ cs_etm_decoder__free(decoder);
return NULL;
}
#include <stdio.h>
struct cs_etm_decoder;
-
-enum cs_etm_sample_type {
- CS_ETM_EMPTY,
- CS_ETM_RANGE,
- CS_ETM_DISCONTINUITY,
- CS_ETM_EXCEPTION,
- CS_ETM_EXCEPTION_RET,
-};
-
-enum cs_etm_isa {
- CS_ETM_ISA_UNKNOWN,
- CS_ETM_ISA_A64,
- CS_ETM_ISA_A32,
- CS_ETM_ISA_T32,
-};
-
-struct cs_etm_packet {
- enum cs_etm_sample_type sample_type;
- enum cs_etm_isa isa;
- u64 start_addr;
- u64 end_addr;
- u32 instr_count;
- u32 last_instr_type;
- u32 last_instr_subtype;
- u32 flags;
- u32 exception_number;
- u8 last_instr_cond;
- u8 last_instr_taken_branch;
- u8 last_instr_size;
- u8 trace_chan_id;
- int cpu;
-};
+struct cs_etm_packet;
+struct cs_etm_packet_queue;
struct cs_etm_queue;
-typedef u32 (*cs_etm_mem_cb_type)(struct cs_etm_queue *, u64,
- size_t, u8 *);
+typedef u32 (*cs_etm_mem_cb_type)(struct cs_etm_queue *, u8, u64, size_t, u8 *);
struct cs_etmv3_trace_params {
u32 reg_ctrl;
u64 start, u64 end,
cs_etm_mem_cb_type cb_func);
-int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder,
+int cs_etm_decoder__get_packet(struct cs_etm_packet_queue *packet_queue,
struct cs_etm_packet *packet);
int cs_etm_decoder__reset(struct cs_etm_decoder *decoder);
#include "thread.h"
#include "thread_map.h"
#include "thread-stack.h"
+#include <tools/libc_compat.h>
#include "util.h"
#define MAX_TIMESTAMP (~0ULL)
unsigned int pmu_type;
};
-struct cs_etm_queue {
- struct cs_etm_auxtrace *etm;
- struct thread *thread;
- struct cs_etm_decoder *decoder;
- struct auxtrace_buffer *buffer;
- union perf_event *event_buf;
- unsigned int queue_nr;
+struct cs_etm_traceid_queue {
+ u8 trace_chan_id;
pid_t pid, tid;
- int cpu;
- u64 offset;
u64 period_instructions;
+ size_t last_branch_pos;
+ union perf_event *event_buf;
+ struct thread *thread;
struct branch_stack *last_branch;
struct branch_stack *last_branch_rb;
- size_t last_branch_pos;
struct cs_etm_packet *prev_packet;
struct cs_etm_packet *packet;
+ struct cs_etm_packet_queue packet_queue;
+};
+
+struct cs_etm_queue {
+ struct cs_etm_auxtrace *etm;
+ struct cs_etm_decoder *decoder;
+ struct auxtrace_buffer *buffer;
+ unsigned int queue_nr;
+ u8 pending_timestamp;
+ u64 offset;
const unsigned char *buf;
size_t buf_len, buf_used;
+ /* Conversion between traceID and index in traceid_queues array */
+ struct intlist *traceid_queues_list;
+ struct cs_etm_traceid_queue **traceid_queues;
};
static int cs_etm__update_queues(struct cs_etm_auxtrace *etm);
+static int cs_etm__process_queues(struct cs_etm_auxtrace *etm);
static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
pid_t tid);
+static int cs_etm__get_data_block(struct cs_etm_queue *etmq);
+static int cs_etm__decode_data_block(struct cs_etm_queue *etmq);
/* PTMs ETMIDR [11:8] set to b0011 */
#define ETMIDR_PTM_VERSION 0x00000300
+/*
+ * A struct auxtrace_heap_item only has a queue_nr and a timestamp to
+ * work with. One option is to modify to auxtrace_heap_XYZ() API or simply
+ * encode the etm queue number as the upper 16 bit and the channel as
+ * the lower 16 bit.
+ */
+#define TO_CS_QUEUE_NR(queue_nr, trace_id_chan) \
+ (queue_nr << 16 | trace_chan_id)
+#define TO_QUEUE_NR(cs_queue_nr) (cs_queue_nr >> 16)
+#define TO_TRACE_CHAN_ID(cs_queue_nr) (cs_queue_nr & 0x0000ffff)
+
static u32 cs_etm__get_v7_protocol_version(u32 etmidr)
{
etmidr &= ETMIDR_PTM_VERSION;
return 0;
}
+void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq,
+ u8 trace_chan_id)
+{
+ /*
+ * Wnen a timestamp packet is encountered the backend code
+ * is stopped so that the front end has time to process packets
+ * that were accumulated in the traceID queue. Since there can
+ * be more than one channel per cs_etm_queue, we need to specify
+ * what traceID queue needs servicing.
+ */
+ etmq->pending_timestamp = trace_chan_id;
+}
+
+static u64 cs_etm__etmq_get_timestamp(struct cs_etm_queue *etmq,
+ u8 *trace_chan_id)
+{
+ struct cs_etm_packet_queue *packet_queue;
+
+ if (!etmq->pending_timestamp)
+ return 0;
+
+ if (trace_chan_id)
+ *trace_chan_id = etmq->pending_timestamp;
+
+ packet_queue = cs_etm__etmq_get_packet_queue(etmq,
+ etmq->pending_timestamp);
+ if (!packet_queue)
+ return 0;
+
+ /* Acknowledge pending status */
+ etmq->pending_timestamp = 0;
+
+ /* See function cs_etm_decoder__do_{hard|soft}_timestamp() */
+ return packet_queue->timestamp;
+}
+
+static void cs_etm__clear_packet_queue(struct cs_etm_packet_queue *queue)
+{
+ int i;
+
+ queue->head = 0;
+ queue->tail = 0;
+ queue->packet_count = 0;
+ for (i = 0; i < CS_ETM_PACKET_MAX_BUFFER; i++) {
+ queue->packet_buffer[i].isa = CS_ETM_ISA_UNKNOWN;
+ queue->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR;
+ queue->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR;
+ queue->packet_buffer[i].instr_count = 0;
+ queue->packet_buffer[i].last_instr_taken_branch = false;
+ queue->packet_buffer[i].last_instr_size = 0;
+ queue->packet_buffer[i].last_instr_type = 0;
+ queue->packet_buffer[i].last_instr_subtype = 0;
+ queue->packet_buffer[i].last_instr_cond = 0;
+ queue->packet_buffer[i].flags = 0;
+ queue->packet_buffer[i].exception_number = UINT32_MAX;
+ queue->packet_buffer[i].trace_chan_id = UINT8_MAX;
+ queue->packet_buffer[i].cpu = INT_MIN;
+ }
+}
+
+static void cs_etm__clear_all_packet_queues(struct cs_etm_queue *etmq)
+{
+ int idx;
+ struct int_node *inode;
+ struct cs_etm_traceid_queue *tidq;
+ struct intlist *traceid_queues_list = etmq->traceid_queues_list;
+
+ intlist__for_each_entry(inode, traceid_queues_list) {
+ idx = (int)(intptr_t)inode->priv;
+ tidq = etmq->traceid_queues[idx];
+ cs_etm__clear_packet_queue(&tidq->packet_queue);
+ }
+}
+
+static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq,
+ struct cs_etm_traceid_queue *tidq,
+ u8 trace_chan_id)
+{
+ int rc = -ENOMEM;
+ struct auxtrace_queue *queue;
+ struct cs_etm_auxtrace *etm = etmq->etm;
+
+ cs_etm__clear_packet_queue(&tidq->packet_queue);
+
+ queue = &etmq->etm->queues.queue_array[etmq->queue_nr];
+ tidq->tid = queue->tid;
+ tidq->pid = -1;
+ tidq->trace_chan_id = trace_chan_id;
+
+ tidq->packet = zalloc(sizeof(struct cs_etm_packet));
+ if (!tidq->packet)
+ goto out;
+
+ tidq->prev_packet = zalloc(sizeof(struct cs_etm_packet));
+ if (!tidq->prev_packet)
+ goto out_free;
+
+ if (etm->synth_opts.last_branch) {
+ size_t sz = sizeof(struct branch_stack);
+
+ sz += etm->synth_opts.last_branch_sz *
+ sizeof(struct branch_entry);
+ tidq->last_branch = zalloc(sz);
+ if (!tidq->last_branch)
+ goto out_free;
+ tidq->last_branch_rb = zalloc(sz);
+ if (!tidq->last_branch_rb)
+ goto out_free;
+ }
+
+ tidq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
+ if (!tidq->event_buf)
+ goto out_free;
+
+ return 0;
+
+out_free:
+ zfree(&tidq->last_branch_rb);
+ zfree(&tidq->last_branch);
+ zfree(&tidq->prev_packet);
+ zfree(&tidq->packet);
+out:
+ return rc;
+}
+
+static struct cs_etm_traceid_queue
+*cs_etm__etmq_get_traceid_queue(struct cs_etm_queue *etmq, u8 trace_chan_id)
+{
+ int idx;
+ struct int_node *inode;
+ struct intlist *traceid_queues_list;
+ struct cs_etm_traceid_queue *tidq, **traceid_queues;
+ struct cs_etm_auxtrace *etm = etmq->etm;
+
+ if (etm->timeless_decoding)
+ trace_chan_id = CS_ETM_PER_THREAD_TRACEID;
+
+ traceid_queues_list = etmq->traceid_queues_list;
+
+ /*
+ * Check if the traceid_queue exist for this traceID by looking
+ * in the queue list.
+ */
+ inode = intlist__find(traceid_queues_list, trace_chan_id);
+ if (inode) {
+ idx = (int)(intptr_t)inode->priv;
+ return etmq->traceid_queues[idx];
+ }
+
+ /* We couldn't find a traceid_queue for this traceID, allocate one */
+ tidq = malloc(sizeof(*tidq));
+ if (!tidq)
+ return NULL;
+
+ memset(tidq, 0, sizeof(*tidq));
+
+ /* Get a valid index for the new traceid_queue */
+ idx = intlist__nr_entries(traceid_queues_list);
+ /* Memory for the inode is free'ed in cs_etm_free_traceid_queues () */
+ inode = intlist__findnew(traceid_queues_list, trace_chan_id);
+ if (!inode)
+ goto out_free;
+
+ /* Associate this traceID with this index */
+ inode->priv = (void *)(intptr_t)idx;
+
+ if (cs_etm__init_traceid_queue(etmq, tidq, trace_chan_id))
+ goto out_free;
+
+ /* Grow the traceid_queues array by one unit */
+ traceid_queues = etmq->traceid_queues;
+ traceid_queues = reallocarray(traceid_queues,
+ idx + 1,
+ sizeof(*traceid_queues));
+
+ /*
+ * On failure reallocarray() returns NULL and the original block of
+ * memory is left untouched.
+ */
+ if (!traceid_queues)
+ goto out_free;
+
+ traceid_queues[idx] = tidq;
+ etmq->traceid_queues = traceid_queues;
+
+ return etmq->traceid_queues[idx];
+
+out_free:
+ /*
+ * Function intlist__remove() removes the inode from the list
+ * and delete the memory associated to it.
+ */
+ intlist__remove(traceid_queues_list, inode);
+ free(tidq);
+
+ return NULL;
+}
+
+struct cs_etm_packet_queue
+*cs_etm__etmq_get_packet_queue(struct cs_etm_queue *etmq, u8 trace_chan_id)
+{
+ struct cs_etm_traceid_queue *tidq;
+
+ tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
+ if (tidq)
+ return &tidq->packet_queue;
+
+ return NULL;
+}
+
static void cs_etm__packet_dump(const char *pkt_string)
{
const char *color = PERF_COLOR_BLUE;
if (!tool->ordered_events)
return -EINVAL;
- if (!etm->timeless_decoding)
- return -EINVAL;
-
ret = cs_etm__update_queues(etm);
if (ret < 0)
return ret;
- return cs_etm__process_timeless_queues(etm, -1);
+ if (etm->timeless_decoding)
+ return cs_etm__process_timeless_queues(etm, -1);
+
+ return cs_etm__process_queues(etm);
+}
+
+static void cs_etm__free_traceid_queues(struct cs_etm_queue *etmq)
+{
+ int idx;
+ uintptr_t priv;
+ struct int_node *inode, *tmp;
+ struct cs_etm_traceid_queue *tidq;
+ struct intlist *traceid_queues_list = etmq->traceid_queues_list;
+
+ intlist__for_each_entry_safe(inode, tmp, traceid_queues_list) {
+ priv = (uintptr_t)inode->priv;
+ idx = priv;
+
+ /* Free this traceid_queue from the array */
+ tidq = etmq->traceid_queues[idx];
+ thread__zput(tidq->thread);
+ zfree(&tidq->event_buf);
+ zfree(&tidq->last_branch);
+ zfree(&tidq->last_branch_rb);
+ zfree(&tidq->prev_packet);
+ zfree(&tidq->packet);
+ zfree(&tidq);
+
+ /*
+ * Function intlist__remove() removes the inode from the list
+ * and delete the memory associated to it.
+ */
+ intlist__remove(traceid_queues_list, inode);
+ }
+
+ /* Then the RB tree itself */
+ intlist__delete(traceid_queues_list);
+ etmq->traceid_queues_list = NULL;
+
+ /* finally free the traceid_queues array */
+ free(etmq->traceid_queues);
+ etmq->traceid_queues = NULL;
}
static void cs_etm__free_queue(void *priv)
if (!etmq)
return;
- thread__zput(etmq->thread);
cs_etm_decoder__free(etmq->decoder);
- zfree(&etmq->event_buf);
- zfree(&etmq->last_branch);
- zfree(&etmq->last_branch_rb);
- zfree(&etmq->prev_packet);
- zfree(&etmq->packet);
+ cs_etm__free_traceid_queues(etmq);
free(etmq);
}
}
}
-static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
- size_t size, u8 *buffer)
+static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id,
+ u64 address, size_t size, u8 *buffer)
{
u8 cpumode;
u64 offset;
int len;
- struct thread *thread;
- struct machine *machine;
- struct addr_location al;
+ struct thread *thread;
+ struct machine *machine;
+ struct addr_location al;
+ struct cs_etm_traceid_queue *tidq;
if (!etmq)
return 0;
machine = etmq->etm->machine;
cpumode = cs_etm__cpu_mode(etmq, address);
+ tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
+ if (!tidq)
+ return 0;
- thread = etmq->thread;
+ thread = tidq->thread;
if (!thread) {
if (cpumode != PERF_RECORD_MISC_KERNEL)
return 0;
struct cs_etm_decoder_params d_params;
struct cs_etm_trace_params *t_params = NULL;
struct cs_etm_queue *etmq;
- size_t szp = sizeof(struct cs_etm_packet);
etmq = zalloc(sizeof(*etmq));
if (!etmq)
return NULL;
- etmq->packet = zalloc(szp);
- if (!etmq->packet)
- goto out_free;
-
- etmq->prev_packet = zalloc(szp);
- if (!etmq->prev_packet)
- goto out_free;
-
- if (etm->synth_opts.last_branch) {
- size_t sz = sizeof(struct branch_stack);
-
- sz += etm->synth_opts.last_branch_sz *
- sizeof(struct branch_entry);
- etmq->last_branch = zalloc(sz);
- if (!etmq->last_branch)
- goto out_free;
- etmq->last_branch_rb = zalloc(sz);
- if (!etmq->last_branch_rb)
- goto out_free;
- }
-
- etmq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
- if (!etmq->event_buf)
+ etmq->traceid_queues_list = intlist__new(NULL);
+ if (!etmq->traceid_queues_list)
goto out_free;
/* Use metadata to fill in trace parameters for trace decoder */
out_free_decoder:
cs_etm_decoder__free(etmq->decoder);
out_free:
- zfree(&t_params);
- zfree(&etmq->event_buf);
- zfree(&etmq->last_branch);
- zfree(&etmq->last_branch_rb);
- zfree(&etmq->prev_packet);
- zfree(&etmq->packet);
+ intlist__delete(etmq->traceid_queues_list);
free(etmq);
return NULL;
unsigned int queue_nr)
{
int ret = 0;
+ unsigned int cs_queue_nr;
+ u8 trace_chan_id;
+ u64 timestamp;
struct cs_etm_queue *etmq = queue->priv;
if (list_empty(&queue->head) || etmq)
queue->priv = etmq;
etmq->etm = etm;
etmq->queue_nr = queue_nr;
- etmq->cpu = queue->cpu;
- etmq->tid = queue->tid;
- etmq->pid = -1;
etmq->offset = 0;
- etmq->period_instructions = 0;
+ if (etm->timeless_decoding)
+ goto out;
+
+ /*
+ * We are under a CPU-wide trace scenario. As such we need to know
+ * when the code that generated the traces started to execute so that
+ * it can be correlated with execution on other CPUs. So we get a
+ * handle on the beginning of traces and decode until we find a
+ * timestamp. The timestamp is then added to the auxtrace min heap
+ * in order to know what nibble (of all the etmqs) to decode first.
+ */
+ while (1) {
+ /*
+ * Fetch an aux_buffer from this etmq. Bail if no more
+ * blocks or an error has been encountered.
+ */
+ ret = cs_etm__get_data_block(etmq);
+ if (ret <= 0)
+ goto out;
+
+ /*
+ * Run decoder on the trace block. The decoder will stop when
+ * encountering a timestamp, a full packet queue or the end of
+ * trace for that block.
+ */
+ ret = cs_etm__decode_data_block(etmq);
+ if (ret)
+ goto out;
+
+ /*
+ * Function cs_etm_decoder__do_{hard|soft}_timestamp() does all
+ * the timestamp calculation for us.
+ */
+ timestamp = cs_etm__etmq_get_timestamp(etmq, &trace_chan_id);
+
+ /* We found a timestamp, no need to continue. */
+ if (timestamp)
+ break;
+
+ /*
+ * We didn't find a timestamp so empty all the traceid packet
+ * queues before looking for another timestamp packet, either
+ * in the current data block or a new one. Packets that were
+ * just decoded are useless since no timestamp has been
+ * associated with them. As such simply discard them.
+ */
+ cs_etm__clear_all_packet_queues(etmq);
+ }
+
+ /*
+ * We have a timestamp. Add it to the min heap to reflect when
+ * instructions conveyed by the range packets of this traceID queue
+ * started to execute. Once the same has been done for all the traceID
+ * queues of each etmq, redenring and decoding can start in
+ * chronological order.
+ *
+ * Note that packets decoded above are still in the traceID's packet
+ * queue and will be processed in cs_etm__process_queues().
+ */
+ cs_queue_nr = TO_CS_QUEUE_NR(queue_nr, trace_id_chan);
+ ret = auxtrace_heap__add(&etm->heap, cs_queue_nr, timestamp);
out:
return ret;
}
return 0;
}
-static inline void cs_etm__copy_last_branch_rb(struct cs_etm_queue *etmq)
+static inline
+void cs_etm__copy_last_branch_rb(struct cs_etm_queue *etmq,
+ struct cs_etm_traceid_queue *tidq)
{
- struct branch_stack *bs_src = etmq->last_branch_rb;
- struct branch_stack *bs_dst = etmq->last_branch;
+ struct branch_stack *bs_src = tidq->last_branch_rb;
+ struct branch_stack *bs_dst = tidq->last_branch;
size_t nr = 0;
/*
* two steps. First, copy the branches from the most recently inserted
* branch ->last_branch_pos until the end of bs_src->entries buffer.
*/
- nr = etmq->etm->synth_opts.last_branch_sz - etmq->last_branch_pos;
+ nr = etmq->etm->synth_opts.last_branch_sz - tidq->last_branch_pos;
memcpy(&bs_dst->entries[0],
- &bs_src->entries[etmq->last_branch_pos],
+ &bs_src->entries[tidq->last_branch_pos],
sizeof(struct branch_entry) * nr);
/*
if (bs_src->nr >= etmq->etm->synth_opts.last_branch_sz) {
memcpy(&bs_dst->entries[nr],
&bs_src->entries[0],
- sizeof(struct branch_entry) * etmq->last_branch_pos);
+ sizeof(struct branch_entry) * tidq->last_branch_pos);
}
}
-static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq)
+static inline
+void cs_etm__reset_last_branch_rb(struct cs_etm_traceid_queue *tidq)
{
- etmq->last_branch_pos = 0;
- etmq->last_branch_rb->nr = 0;
+ tidq->last_branch_pos = 0;
+ tidq->last_branch_rb->nr = 0;
}
static inline int cs_etm__t32_instr_size(struct cs_etm_queue *etmq,
- u64 addr) {
+ u8 trace_chan_id, u64 addr)
+{
u8 instrBytes[2];
- cs_etm__mem_access(etmq, addr, ARRAY_SIZE(instrBytes), instrBytes);
+ cs_etm__mem_access(etmq, trace_chan_id, addr,
+ ARRAY_SIZE(instrBytes), instrBytes);
/*
* T32 instruction size is indicated by bits[15:11] of the first
* 16-bit word of the instruction: 0b11101, 0b11110 and 0b11111
}
static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq,
+ u64 trace_chan_id,
const struct cs_etm_packet *packet,
u64 offset)
{
u64 addr = packet->start_addr;
while (offset > 0) {
- addr += cs_etm__t32_instr_size(etmq, addr);
+ addr += cs_etm__t32_instr_size(etmq,
+ trace_chan_id, addr);
offset--;
}
return addr;
return packet->start_addr + offset * 4;
}
-static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq)
+static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq,
+ struct cs_etm_traceid_queue *tidq)
{
- struct branch_stack *bs = etmq->last_branch_rb;
+ struct branch_stack *bs = tidq->last_branch_rb;
struct branch_entry *be;
/*
* buffer down. After writing the first element of the stack, move the
* insert position back to the end of the buffer.
*/
- if (!etmq->last_branch_pos)
- etmq->last_branch_pos = etmq->etm->synth_opts.last_branch_sz;
+ if (!tidq->last_branch_pos)
+ tidq->last_branch_pos = etmq->etm->synth_opts.last_branch_sz;
- etmq->last_branch_pos -= 1;
+ tidq->last_branch_pos -= 1;
- be = &bs->entries[etmq->last_branch_pos];
- be->from = cs_etm__last_executed_instr(etmq->prev_packet);
- be->to = cs_etm__first_executed_instr(etmq->packet);
+ be = &bs->entries[tidq->last_branch_pos];
+ be->from = cs_etm__last_executed_instr(tidq->prev_packet);
+ be->to = cs_etm__first_executed_instr(tidq->packet);
/* No support for mispredict */
be->flags.mispred = 0;
be->flags.predicted = 1;
}
static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
- struct auxtrace_queue *queue)
+ struct cs_etm_traceid_queue *tidq)
{
- struct cs_etm_queue *etmq = queue->priv;
+ if ((!tidq->thread) && (tidq->tid != -1))
+ tidq->thread = machine__find_thread(etm->machine, -1,
+ tidq->tid);
- /* CPU-wide tracing isn't supported yet */
- if (queue->tid == -1)
- return;
+ if (tidq->thread)
+ tidq->pid = tidq->thread->pid_;
+}
- if ((!etmq->thread) && (etmq->tid != -1))
- etmq->thread = machine__find_thread(etm->machine, -1,
- etmq->tid);
+int cs_etm__etmq_set_tid(struct cs_etm_queue *etmq,
+ pid_t tid, u8 trace_chan_id)
+{
+ int cpu, err = -EINVAL;
+ struct cs_etm_auxtrace *etm = etmq->etm;
+ struct cs_etm_traceid_queue *tidq;
- if (etmq->thread) {
- etmq->pid = etmq->thread->pid_;
- if (queue->cpu == -1)
- etmq->cpu = etmq->thread->cpu;
- }
+ tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
+ if (!tidq)
+ return err;
+
+ if (cs_etm__get_cpu(trace_chan_id, &cpu) < 0)
+ return err;
+
+ err = machine__set_current_tid(etm->machine, cpu, tid, tid);
+ if (err)
+ return err;
+
+ tidq->tid = tid;
+ thread__zput(tidq->thread);
+
+ cs_etm__set_pid_tid_cpu(etm, tidq);
+ return 0;
+}
+
+bool cs_etm__etmq_is_timeless(struct cs_etm_queue *etmq)
+{
+ return !!etmq->etm->timeless_decoding;
}
static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
+ struct cs_etm_traceid_queue *tidq,
u64 addr, u64 period)
{
int ret = 0;
struct cs_etm_auxtrace *etm = etmq->etm;
- union perf_event *event = etmq->event_buf;
+ union perf_event *event = tidq->event_buf;
struct perf_sample sample = {.ip = 0,};
event->sample.header.type = PERF_RECORD_SAMPLE;
event->sample.header.size = sizeof(struct perf_event_header);
sample.ip = addr;
- sample.pid = etmq->pid;
- sample.tid = etmq->tid;
+ sample.pid = tidq->pid;
+ sample.tid = tidq->tid;
sample.id = etmq->etm->instructions_id;
sample.stream_id = etmq->etm->instructions_id;
sample.period = period;
- sample.cpu = etmq->packet->cpu;
- sample.flags = etmq->prev_packet->flags;
+ sample.cpu = tidq->packet->cpu;
+ sample.flags = tidq->prev_packet->flags;
sample.insn_len = 1;
sample.cpumode = event->sample.header.misc;
if (etm->synth_opts.last_branch) {
- cs_etm__copy_last_branch_rb(etmq);
- sample.branch_stack = etmq->last_branch;
+ cs_etm__copy_last_branch_rb(etmq, tidq);
+ sample.branch_stack = tidq->last_branch;
}
if (etm->synth_opts.inject) {
ret);
if (etm->synth_opts.last_branch)
- cs_etm__reset_last_branch_rb(etmq);
+ cs_etm__reset_last_branch_rb(tidq);
return ret;
}
* The cs etm packet encodes an instruction range between a branch target
* and the next taken branch. Generate sample accordingly.
*/
-static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
+static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
+ struct cs_etm_traceid_queue *tidq)
{
int ret = 0;
struct cs_etm_auxtrace *etm = etmq->etm;
struct perf_sample sample = {.ip = 0,};
- union perf_event *event = etmq->event_buf;
+ union perf_event *event = tidq->event_buf;
struct dummy_branch_stack {
u64 nr;
struct branch_entry entries;
} dummy_bs;
u64 ip;
- ip = cs_etm__last_executed_instr(etmq->prev_packet);
+ ip = cs_etm__last_executed_instr(tidq->prev_packet);
event->sample.header.type = PERF_RECORD_SAMPLE;
event->sample.header.misc = cs_etm__cpu_mode(etmq, ip);
event->sample.header.size = sizeof(struct perf_event_header);
sample.ip = ip;
- sample.pid = etmq->pid;
- sample.tid = etmq->tid;
- sample.addr = cs_etm__first_executed_instr(etmq->packet);
+ sample.pid = tidq->pid;
+ sample.tid = tidq->tid;
+ sample.addr = cs_etm__first_executed_instr(tidq->packet);
sample.id = etmq->etm->branches_id;
sample.stream_id = etmq->etm->branches_id;
sample.period = 1;
- sample.cpu = etmq->packet->cpu;
- sample.flags = etmq->prev_packet->flags;
+ sample.cpu = tidq->packet->cpu;
+ sample.flags = tidq->prev_packet->flags;
sample.cpumode = event->sample.header.misc;
/*
return 0;
}
-static int cs_etm__sample(struct cs_etm_queue *etmq)
+static int cs_etm__sample(struct cs_etm_queue *etmq,
+ struct cs_etm_traceid_queue *tidq)
{
struct cs_etm_auxtrace *etm = etmq->etm;
struct cs_etm_packet *tmp;
int ret;
- u64 instrs_executed = etmq->packet->instr_count;
+ u8 trace_chan_id = tidq->trace_chan_id;
+ u64 instrs_executed = tidq->packet->instr_count;
- etmq->period_instructions += instrs_executed;
+ tidq->period_instructions += instrs_executed;
/*
* Record a branch when the last instruction in
* PREV_PACKET is a branch.
*/
if (etm->synth_opts.last_branch &&
- etmq->prev_packet->sample_type == CS_ETM_RANGE &&
- etmq->prev_packet->last_instr_taken_branch)
- cs_etm__update_last_branch_rb(etmq);
+ tidq->prev_packet->sample_type == CS_ETM_RANGE &&
+ tidq->prev_packet->last_instr_taken_branch)
+ cs_etm__update_last_branch_rb(etmq, tidq);
if (etm->sample_instructions &&
- etmq->period_instructions >= etm->instructions_sample_period) {
+ tidq->period_instructions >= etm->instructions_sample_period) {
/*
* Emit instruction sample periodically
* TODO: allow period to be defined in cycles and clock time
*/
/* Get number of instructions executed after the sample point */
- u64 instrs_over = etmq->period_instructions -
+ u64 instrs_over = tidq->period_instructions -
etm->instructions_sample_period;
/*
* executed, but PC has not advanced to next instruction)
*/
u64 offset = (instrs_executed - instrs_over - 1);
- u64 addr = cs_etm__instr_addr(etmq, etmq->packet, offset);
+ u64 addr = cs_etm__instr_addr(etmq, trace_chan_id,
+ tidq->packet, offset);
ret = cs_etm__synth_instruction_sample(
- etmq, addr, etm->instructions_sample_period);
+ etmq, tidq, addr, etm->instructions_sample_period);
if (ret)
return ret;
/* Carry remaining instructions into next sample period */
- etmq->period_instructions = instrs_over;
+ tidq->period_instructions = instrs_over;
}
if (etm->sample_branches) {
bool generate_sample = false;
/* Generate sample for tracing on packet */
- if (etmq->prev_packet->sample_type == CS_ETM_DISCONTINUITY)
+ if (tidq->prev_packet->sample_type == CS_ETM_DISCONTINUITY)
generate_sample = true;
/* Generate sample for branch taken packet */
- if (etmq->prev_packet->sample_type == CS_ETM_RANGE &&
- etmq->prev_packet->last_instr_taken_branch)
+ if (tidq->prev_packet->sample_type == CS_ETM_RANGE &&
+ tidq->prev_packet->last_instr_taken_branch)
generate_sample = true;
if (generate_sample) {
- ret = cs_etm__synth_branch_sample(etmq);
+ ret = cs_etm__synth_branch_sample(etmq, tidq);
if (ret)
return ret;
}
* Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
* the next incoming packet.
*/
- tmp = etmq->packet;
- etmq->packet = etmq->prev_packet;
- etmq->prev_packet = tmp;
+ tmp = tidq->packet;
+ tidq->packet = tidq->prev_packet;
+ tidq->prev_packet = tmp;
}
return 0;
}
-static int cs_etm__exception(struct cs_etm_queue *etmq)
+static int cs_etm__exception(struct cs_etm_traceid_queue *tidq)
{
/*
* When the exception packet is inserted, whether the last instruction
* swap PACKET with PREV_PACKET. This keeps PREV_PACKET to be useful
* for generating instruction and branch samples.
*/
- if (etmq->prev_packet->sample_type == CS_ETM_RANGE)
- etmq->prev_packet->last_instr_taken_branch = true;
+ if (tidq->prev_packet->sample_type == CS_ETM_RANGE)
+ tidq->prev_packet->last_instr_taken_branch = true;
return 0;
}
-static int cs_etm__flush(struct cs_etm_queue *etmq)
+static int cs_etm__flush(struct cs_etm_queue *etmq,
+ struct cs_etm_traceid_queue *tidq)
{
int err = 0;
struct cs_etm_auxtrace *etm = etmq->etm;
struct cs_etm_packet *tmp;
/* Handle start tracing packet */
- if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
+ if (tidq->prev_packet->sample_type == CS_ETM_EMPTY)
goto swap_packet;
if (etmq->etm->synth_opts.last_branch &&
- etmq->prev_packet->sample_type == CS_ETM_RANGE) {
+ tidq->prev_packet->sample_type == CS_ETM_RANGE) {
/*
* Generate a last branch event for the branches left in the
* circular buffer at the end of the trace.
* Use the address of the end of the last reported execution
* range
*/
- u64 addr = cs_etm__last_executed_instr(etmq->prev_packet);
+ u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
err = cs_etm__synth_instruction_sample(
- etmq, addr,
- etmq->period_instructions);
+ etmq, tidq, addr,
+ tidq->period_instructions);
if (err)
return err;
- etmq->period_instructions = 0;
+ tidq->period_instructions = 0;
}
if (etm->sample_branches &&
- etmq->prev_packet->sample_type == CS_ETM_RANGE) {
- err = cs_etm__synth_branch_sample(etmq);
+ tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+ err = cs_etm__synth_branch_sample(etmq, tidq);
if (err)
return err;
}
* Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
* the next incoming packet.
*/
- tmp = etmq->packet;
- etmq->packet = etmq->prev_packet;
- etmq->prev_packet = tmp;
+ tmp = tidq->packet;
+ tidq->packet = tidq->prev_packet;
+ tidq->prev_packet = tmp;
}
return err;
}
-static int cs_etm__end_block(struct cs_etm_queue *etmq)
+static int cs_etm__end_block(struct cs_etm_queue *etmq,
+ struct cs_etm_traceid_queue *tidq)
{
int err;
* the trace.
*/
if (etmq->etm->synth_opts.last_branch &&
- etmq->prev_packet->sample_type == CS_ETM_RANGE) {
+ tidq->prev_packet->sample_type == CS_ETM_RANGE) {
/*
* Use the address of the end of the last reported execution
* range.
*/
- u64 addr = cs_etm__last_executed_instr(etmq->prev_packet);
+ u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
err = cs_etm__synth_instruction_sample(
- etmq, addr,
- etmq->period_instructions);
+ etmq, tidq, addr,
+ tidq->period_instructions);
if (err)
return err;
- etmq->period_instructions = 0;
+ tidq->period_instructions = 0;
}
return 0;
return etmq->buf_len;
}
-static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq,
+static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq, u8 trace_chan_id,
struct cs_etm_packet *packet,
u64 end_addr)
{
- u16 instr16;
- u32 instr32;
+ /* Initialise to keep compiler happy */
+ u16 instr16 = 0;
+ u32 instr32 = 0;
u64 addr;
switch (packet->isa) {
* so below only read 2 bytes as instruction size for T32.
*/
addr = end_addr - 2;
- cs_etm__mem_access(etmq, addr, sizeof(instr16), (u8 *)&instr16);
+ cs_etm__mem_access(etmq, trace_chan_id, addr,
+ sizeof(instr16), (u8 *)&instr16);
if ((instr16 & 0xFF00) == 0xDF00)
return true;
* +---------+---------+-------------------------+
*/
addr = end_addr - 4;
- cs_etm__mem_access(etmq, addr, sizeof(instr32), (u8 *)&instr32);
+ cs_etm__mem_access(etmq, trace_chan_id, addr,
+ sizeof(instr32), (u8 *)&instr32);
if ((instr32 & 0x0F000000) == 0x0F000000 &&
(instr32 & 0xF0000000) != 0xF0000000)
return true;
* +-----------------------+---------+-----------+
*/
addr = end_addr - 4;
- cs_etm__mem_access(etmq, addr, sizeof(instr32), (u8 *)&instr32);
+ cs_etm__mem_access(etmq, trace_chan_id, addr,
+ sizeof(instr32), (u8 *)&instr32);
if ((instr32 & 0xFFE0001F) == 0xd4000001)
return true;
return false;
}
-static bool cs_etm__is_syscall(struct cs_etm_queue *etmq, u64 magic)
+static bool cs_etm__is_syscall(struct cs_etm_queue *etmq,
+ struct cs_etm_traceid_queue *tidq, u64 magic)
{
- struct cs_etm_packet *packet = etmq->packet;
- struct cs_etm_packet *prev_packet = etmq->prev_packet;
+ u8 trace_chan_id = tidq->trace_chan_id;
+ struct cs_etm_packet *packet = tidq->packet;
+ struct cs_etm_packet *prev_packet = tidq->prev_packet;
if (magic == __perf_cs_etmv3_magic)
if (packet->exception_number == CS_ETMV3_EXC_SVC)
*/
if (magic == __perf_cs_etmv4_magic) {
if (packet->exception_number == CS_ETMV4_EXC_CALL &&
- cs_etm__is_svc_instr(etmq, prev_packet,
+ cs_etm__is_svc_instr(etmq, trace_chan_id, prev_packet,
prev_packet->end_addr))
return true;
}
return false;
}
-static bool cs_etm__is_async_exception(struct cs_etm_queue *etmq, u64 magic)
+static bool cs_etm__is_async_exception(struct cs_etm_traceid_queue *tidq,
+ u64 magic)
{
- struct cs_etm_packet *packet = etmq->packet;
+ struct cs_etm_packet *packet = tidq->packet;
if (magic == __perf_cs_etmv3_magic)
if (packet->exception_number == CS_ETMV3_EXC_DEBUG_HALT ||
return false;
}
-static bool cs_etm__is_sync_exception(struct cs_etm_queue *etmq, u64 magic)
+static bool cs_etm__is_sync_exception(struct cs_etm_queue *etmq,
+ struct cs_etm_traceid_queue *tidq,
+ u64 magic)
{
- struct cs_etm_packet *packet = etmq->packet;
- struct cs_etm_packet *prev_packet = etmq->prev_packet;
+ u8 trace_chan_id = tidq->trace_chan_id;
+ struct cs_etm_packet *packet = tidq->packet;
+ struct cs_etm_packet *prev_packet = tidq->prev_packet;
if (magic == __perf_cs_etmv3_magic)
if (packet->exception_number == CS_ETMV3_EXC_SMC ||
* (SMC, HVC) are taken as sync exceptions.
*/
if (packet->exception_number == CS_ETMV4_EXC_CALL &&
- !cs_etm__is_svc_instr(etmq, prev_packet,
+ !cs_etm__is_svc_instr(etmq, trace_chan_id, prev_packet,
prev_packet->end_addr))
return true;
return false;
}
-static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq)
+static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq,
+ struct cs_etm_traceid_queue *tidq)
{
- struct cs_etm_packet *packet = etmq->packet;
- struct cs_etm_packet *prev_packet = etmq->prev_packet;
+ struct cs_etm_packet *packet = tidq->packet;
+ struct cs_etm_packet *prev_packet = tidq->prev_packet;
+ u8 trace_chan_id = tidq->trace_chan_id;
u64 magic;
int ret;
if (prev_packet->flags == (PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_RETURN |
PERF_IP_FLAG_INTERRUPT) &&
- cs_etm__is_svc_instr(etmq, packet, packet->start_addr))
+ cs_etm__is_svc_instr(etmq, trace_chan_id,
+ packet, packet->start_addr))
prev_packet->flags = PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_RETURN |
PERF_IP_FLAG_SYSCALLRET;
return ret;
/* The exception is for system call. */
- if (cs_etm__is_syscall(etmq, magic))
+ if (cs_etm__is_syscall(etmq, tidq, magic))
packet->flags = PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_CALL |
PERF_IP_FLAG_SYSCALLRET;
* The exceptions are triggered by external signals from bus,
* interrupt controller, debug module, PE reset or halt.
*/
- else if (cs_etm__is_async_exception(etmq, magic))
+ else if (cs_etm__is_async_exception(tidq, magic))
packet->flags = PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_CALL |
PERF_IP_FLAG_ASYNC |
* Otherwise, exception is caused by trap, instruction &
* data fault, or alignment errors.
*/
- else if (cs_etm__is_sync_exception(etmq, magic))
+ else if (cs_etm__is_sync_exception(etmq, tidq, magic))
packet->flags = PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_CALL |
PERF_IP_FLAG_INTERRUPT;
return ret;
}
-static int cs_etm__process_decoder_queue(struct cs_etm_queue *etmq)
+static int cs_etm__process_traceid_queue(struct cs_etm_queue *etmq,
+ struct cs_etm_traceid_queue *tidq)
{
int ret;
+ struct cs_etm_packet_queue *packet_queue;
- /* Process each packet in this chunk */
- while (1) {
- ret = cs_etm_decoder__get_packet(etmq->decoder,
- etmq->packet);
- if (ret <= 0)
- /*
- * Stop processing this chunk on
- * end of data or error
- */
- break;
+ packet_queue = &tidq->packet_queue;
+ /* Process each packet in this chunk */
+ while (1) {
+ ret = cs_etm_decoder__get_packet(packet_queue,
+ tidq->packet);
+ if (ret <= 0)
/*
- * Since packet addresses are swapped in packet
- * handling within below switch() statements,
- * thus setting sample flags must be called
- * prior to switch() statement to use address
- * information before packets swapping.
+ * Stop processing this chunk on
+ * end of data or error
*/
- ret = cs_etm__set_sample_flags(etmq);
- if (ret < 0)
- break;
-
- switch (etmq->packet->sample_type) {
- case CS_ETM_RANGE:
- /*
- * If the packet contains an instruction
- * range, generate instruction sequence
- * events.
- */
- cs_etm__sample(etmq);
- break;
- case CS_ETM_EXCEPTION:
- case CS_ETM_EXCEPTION_RET:
- /*
- * If the exception packet is coming,
- * make sure the previous instruction
- * range packet to be handled properly.
- */
- cs_etm__exception(etmq);
- break;
- case CS_ETM_DISCONTINUITY:
- /*
- * Discontinuity in trace, flush
- * previous branch stack
- */
- cs_etm__flush(etmq);
- break;
- case CS_ETM_EMPTY:
- /*
- * Should not receive empty packet,
- * report error.
- */
- pr_err("CS ETM Trace: empty packet\n");
- return -EINVAL;
- default:
- break;
- }
+ break;
+
+ /*
+ * Since packet addresses are swapped in packet
+ * handling within below switch() statements,
+ * thus setting sample flags must be called
+ * prior to switch() statement to use address
+ * information before packets swapping.
+ */
+ ret = cs_etm__set_sample_flags(etmq, tidq);
+ if (ret < 0)
+ break;
+
+ switch (tidq->packet->sample_type) {
+ case CS_ETM_RANGE:
+ /*
+ * If the packet contains an instruction
+ * range, generate instruction sequence
+ * events.
+ */
+ cs_etm__sample(etmq, tidq);
+ break;
+ case CS_ETM_EXCEPTION:
+ case CS_ETM_EXCEPTION_RET:
+ /*
+ * If the exception packet is coming,
+ * make sure the previous instruction
+ * range packet to be handled properly.
+ */
+ cs_etm__exception(tidq);
+ break;
+ case CS_ETM_DISCONTINUITY:
+ /*
+ * Discontinuity in trace, flush
+ * previous branch stack
+ */
+ cs_etm__flush(etmq, tidq);
+ break;
+ case CS_ETM_EMPTY:
+ /*
+ * Should not receive empty packet,
+ * report error.
+ */
+ pr_err("CS ETM Trace: empty packet\n");
+ return -EINVAL;
+ default:
+ break;
}
+ }
return ret;
}
+static void cs_etm__clear_all_traceid_queues(struct cs_etm_queue *etmq)
+{
+ int idx;
+ struct int_node *inode;
+ struct cs_etm_traceid_queue *tidq;
+ struct intlist *traceid_queues_list = etmq->traceid_queues_list;
+
+ intlist__for_each_entry(inode, traceid_queues_list) {
+ idx = (int)(intptr_t)inode->priv;
+ tidq = etmq->traceid_queues[idx];
+
+ /* Ignore return value */
+ cs_etm__process_traceid_queue(etmq, tidq);
+
+ /*
+ * Generate an instruction sample with the remaining
+ * branchstack entries.
+ */
+ cs_etm__flush(etmq, tidq);
+ }
+}
+
static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
{
int err = 0;
+ struct cs_etm_traceid_queue *tidq;
+
+ tidq = cs_etm__etmq_get_traceid_queue(etmq, CS_ETM_PER_THREAD_TRACEID);
+ if (!tidq)
+ return -EINVAL;
/* Go through each buffer in the queue and decode them one by one */
while (1) {
* an error occurs other than hoping the next one will
* be better.
*/
- err = cs_etm__process_decoder_queue(etmq);
+ err = cs_etm__process_traceid_queue(etmq, tidq);
} while (etmq->buf_len);
if (err == 0)
/* Flush any remaining branch stack entries */
- err = cs_etm__end_block(etmq);
+ err = cs_etm__end_block(etmq, tidq);
}
return err;
for (i = 0; i < queues->nr_queues; i++) {
struct auxtrace_queue *queue = &etm->queues.queue_array[i];
struct cs_etm_queue *etmq = queue->priv;
+ struct cs_etm_traceid_queue *tidq;
+
+ if (!etmq)
+ continue;
+
+ tidq = cs_etm__etmq_get_traceid_queue(etmq,
+ CS_ETM_PER_THREAD_TRACEID);
+
+ if (!tidq)
+ continue;
- if (etmq && ((tid == -1) || (etmq->tid == tid))) {
- cs_etm__set_pid_tid_cpu(etm, queue);
+ if ((tid == -1) || (tidq->tid == tid)) {
+ cs_etm__set_pid_tid_cpu(etm, tidq);
cs_etm__run_decoder(etmq);
}
}
return 0;
}
+static int cs_etm__process_queues(struct cs_etm_auxtrace *etm)
+{
+ int ret = 0;
+ unsigned int cs_queue_nr, queue_nr;
+ u8 trace_chan_id;
+ u64 timestamp;
+ struct auxtrace_queue *queue;
+ struct cs_etm_queue *etmq;
+ struct cs_etm_traceid_queue *tidq;
+
+ while (1) {
+ if (!etm->heap.heap_cnt)
+ goto out;
+
+ /* Take the entry at the top of the min heap */
+ cs_queue_nr = etm->heap.heap_array[0].queue_nr;
+ queue_nr = TO_QUEUE_NR(cs_queue_nr);
+ trace_chan_id = TO_TRACE_CHAN_ID(cs_queue_nr);
+ queue = &etm->queues.queue_array[queue_nr];
+ etmq = queue->priv;
+
+ /*
+ * Remove the top entry from the heap since we are about
+ * to process it.
+ */
+ auxtrace_heap__pop(&etm->heap);
+
+ tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
+ if (!tidq) {
+ /*
+ * No traceID queue has been allocated for this traceID,
+ * which means something somewhere went very wrong. No
+ * other choice than simply exit.
+ */
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * Packets associated with this timestamp are already in
+ * the etmq's traceID queue, so process them.
+ */
+ ret = cs_etm__process_traceid_queue(etmq, tidq);
+ if (ret < 0)
+ goto out;
+
+ /*
+ * Packets for this timestamp have been processed, time to
+ * move on to the next timestamp, fetching a new auxtrace_buffer
+ * if need be.
+ */
+refetch:
+ ret = cs_etm__get_data_block(etmq);
+ if (ret < 0)
+ goto out;
+
+ /*
+ * No more auxtrace_buffers to process in this etmq, simply
+ * move on to another entry in the auxtrace_heap.
+ */
+ if (!ret)
+ continue;
+
+ ret = cs_etm__decode_data_block(etmq);
+ if (ret)
+ goto out;
+
+ timestamp = cs_etm__etmq_get_timestamp(etmq, &trace_chan_id);
+
+ if (!timestamp) {
+ /*
+ * Function cs_etm__decode_data_block() returns when
+ * there is no more traces to decode in the current
+ * auxtrace_buffer OR when a timestamp has been
+ * encountered on any of the traceID queues. Since we
+ * did not get a timestamp, there is no more traces to
+ * process in this auxtrace_buffer. As such empty and
+ * flush all traceID queues.
+ */
+ cs_etm__clear_all_traceid_queues(etmq);
+
+ /* Fetch another auxtrace_buffer for this etmq */
+ goto refetch;
+ }
+
+ /*
+ * Add to the min heap the timestamp for packets that have
+ * just been decoded. They will be processed and synthesized
+ * during the next call to cs_etm__process_traceid_queue() for
+ * this queue/traceID.
+ */
+ cs_queue_nr = TO_CS_QUEUE_NR(queue_nr, trace_chan_id);
+ ret = auxtrace_heap__add(&etm->heap, cs_queue_nr, timestamp);
+ }
+
+out:
+ return ret;
+}
+
+static int cs_etm__process_itrace_start(struct cs_etm_auxtrace *etm,
+ union perf_event *event)
+{
+ struct thread *th;
+
+ if (etm->timeless_decoding)
+ return 0;
+
+ /*
+ * Add the tid/pid to the log so that we can get a match when
+ * we get a contextID from the decoder.
+ */
+ th = machine__findnew_thread(etm->machine,
+ event->itrace_start.pid,
+ event->itrace_start.tid);
+ if (!th)
+ return -ENOMEM;
+
+ thread__put(th);
+
+ return 0;
+}
+
+static int cs_etm__process_switch_cpu_wide(struct cs_etm_auxtrace *etm,
+ union perf_event *event)
+{
+ struct thread *th;
+ bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
+
+ /*
+ * Context switch in per-thread mode are irrelevant since perf
+ * will start/stop tracing as the process is scheduled.
+ */
+ if (etm->timeless_decoding)
+ return 0;
+
+ /*
+ * SWITCH_IN events carry the next process to be switched out while
+ * SWITCH_OUT events carry the process to be switched in. As such
+ * we don't care about IN events.
+ */
+ if (!out)
+ return 0;
+
+ /*
+ * Add the tid/pid to the log so that we can get a match when
+ * we get a contextID from the decoder.
+ */
+ th = machine__findnew_thread(etm->machine,
+ event->context_switch.next_prev_pid,
+ event->context_switch.next_prev_tid);
+ if (!th)
+ return -ENOMEM;
+
+ thread__put(th);
+
+ return 0;
+}
+
static int cs_etm__process_event(struct perf_session *session,
union perf_event *event,
struct perf_sample *sample,
return -EINVAL;
}
- if (!etm->timeless_decoding)
- return -EINVAL;
-
if (sample->time && (sample->time != (u64) -1))
timestamp = sample->time;
else
return err;
}
- if (event->header.type == PERF_RECORD_EXIT)
+ if (etm->timeless_decoding &&
+ event->header.type == PERF_RECORD_EXIT)
return cs_etm__process_timeless_queues(etm,
event->fork.tid);
+ if (event->header.type == PERF_RECORD_ITRACE_START)
+ return cs_etm__process_itrace_start(etm, event);
+ else if (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)
+ return cs_etm__process_switch_cpu_wide(etm, event);
+
+ if (!etm->timeless_decoding &&
+ event->header.type == PERF_RECORD_AUX)
+ return cs_etm__process_queues(etm);
+
return 0;
}
#include "util/event.h"
#include "util/session.h"
+#include <linux/bits.h>
/* Versionning header in case things need tro change in the future. That way
* decoding of old snapshot is still possible.
CS_ETMV4_EXC_END = 31,
};
+enum cs_etm_sample_type {
+ CS_ETM_EMPTY,
+ CS_ETM_RANGE,
+ CS_ETM_DISCONTINUITY,
+ CS_ETM_EXCEPTION,
+ CS_ETM_EXCEPTION_RET,
+};
+
+enum cs_etm_isa {
+ CS_ETM_ISA_UNKNOWN,
+ CS_ETM_ISA_A64,
+ CS_ETM_ISA_A32,
+ CS_ETM_ISA_T32,
+};
+
/* RB tree for quick conversion between traceID and metadata pointers */
struct intlist *traceid_list;
+struct cs_etm_queue;
+
+struct cs_etm_packet {
+ enum cs_etm_sample_type sample_type;
+ enum cs_etm_isa isa;
+ u64 start_addr;
+ u64 end_addr;
+ u32 instr_count;
+ u32 last_instr_type;
+ u32 last_instr_subtype;
+ u32 flags;
+ u32 exception_number;
+ u8 last_instr_cond;
+ u8 last_instr_taken_branch;
+ u8 last_instr_size;
+ u8 trace_chan_id;
+ int cpu;
+};
+
+#define CS_ETM_PACKET_MAX_BUFFER 1024
+
+/*
+ * When working with per-thread scenarios the process under trace can
+ * be scheduled on any CPU and as such, more than one traceID may be
+ * associated with the same process. Since a traceID of '0' is illegal
+ * as per the CoreSight architecture, use that specific value to
+ * identify the queue where all packets (with any traceID) are
+ * aggregated.
+ */
+#define CS_ETM_PER_THREAD_TRACEID 0
+
+struct cs_etm_packet_queue {
+ u32 packet_count;
+ u32 head;
+ u32 tail;
+ u32 instr_count;
+ u64 timestamp;
+ u64 next_timestamp;
+ struct cs_etm_packet packet_buffer[CS_ETM_PACKET_MAX_BUFFER];
+};
+
#define KiB(x) ((x) * 1024)
#define MiB(x) ((x) * 1024 * 1024)
+#define CS_ETM_INVAL_ADDR 0xdeadbeefdeadbeefUL
+
+#define BMVAL(val, lsb, msb) ((val & GENMASK(msb, lsb)) >> lsb)
+
#define CS_ETM_HEADER_SIZE (CS_HEADER_VERSION_0_MAX * sizeof(u64))
#define __perf_cs_etmv3_magic 0x3030303030303030ULL
int cs_etm__process_auxtrace_info(union perf_event *event,
struct perf_session *session);
int cs_etm__get_cpu(u8 trace_chan_id, int *cpu);
+int cs_etm__etmq_set_tid(struct cs_etm_queue *etmq,
+ pid_t tid, u8 trace_chan_id);
+bool cs_etm__etmq_is_timeless(struct cs_etm_queue *etmq);
+void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq,
+ u8 trace_chan_id);
+struct cs_etm_packet_queue
+*cs_etm__etmq_get_packet_queue(struct cs_etm_queue *etmq, u8 trace_chan_id);
#else
static inline int
cs_etm__process_auxtrace_info(union perf_event *event __maybe_unused,
{
return -1;
}
+
+static inline int cs_etm__etmq_set_tid(
+ struct cs_etm_queue *etmq __maybe_unused,
+ pid_t tid __maybe_unused,
+ u8 trace_chan_id __maybe_unused)
+{
+ return -1;
+}
+
+static inline bool cs_etm__etmq_is_timeless(
+ struct cs_etm_queue *etmq __maybe_unused)
+{
+ /* What else to return? */
+ return true;
+}
+
+static inline void cs_etm__etmq_set_traceid_queue_timestamp(
+ struct cs_etm_queue *etmq __maybe_unused,
+ u8 trace_chan_id __maybe_unused) {}
+
+static inline struct cs_etm_packet_queue *cs_etm__etmq_get_packet_queue(
+ struct cs_etm_queue *etmq __maybe_unused,
+ u8 trace_chan_id __maybe_unused)
+{
+ return NULL;
+}
#endif
#endif
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Sane locale-independent, ASCII ctype.
- *
- * No surprises, and works with signed and unsigned chars.
- */
-#include "sane_ctype.h"
-
-enum {
- S = GIT_SPACE,
- A = GIT_ALPHA,
- D = GIT_DIGIT,
- G = GIT_GLOB_SPECIAL, /* *, ?, [, \\ */
- R = GIT_REGEX_SPECIAL, /* $, (, ), +, ., ^, {, | * */
- P = GIT_PRINT_EXTRA, /* printable - alpha - digit - glob - regex */
-
- PS = GIT_SPACE | GIT_PRINT_EXTRA,
-};
-
-unsigned char sane_ctype[256] = {
-/* 0 1 2 3 4 5 6 7 8 9 A B C D E F */
-
- 0, 0, 0, 0, 0, 0, 0, 0, 0, S, S, 0, 0, S, 0, 0, /* 0.. 15 */
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 16.. 31 */
- PS,P, P, P, R, P, P, P, R, R, G, R, P, P, R, P, /* 32.. 47 */
- D, D, D, D, D, D, D, D, D, D, P, P, P, P, P, G, /* 48.. 63 */
- P, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A, /* 64.. 79 */
- A, A, A, A, A, A, A, A, A, A, A, G, G, P, R, P, /* 80.. 95 */
- P, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A, /* 96..111 */
- A, A, A, A, A, A, A, A, A, A, A, R, R, P, P, 0, /* 112..127 */
- /* Nothing in the 128.. range */
-};
-
-const char *graph_line =
- "_____________________________________________________________________"
- "_____________________________________________________________________"
- "_____________________________________________________________________";
-const char *graph_dotted_line =
- "---------------------------------------------------------------------"
- "---------------------------------------------------------------------"
- "---------------------------------------------------------------------";
-const char *spaces =
- " "
- " "
- " ";
-const char *dots =
- "....................................................................."
- "....................................................................."
- ".....................................................................";
#include "evsel.h"
#include "machine.h"
#include "config.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
#define pr_N(n, fmt, ...) \
eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__)
#include "util.h"
#include "target.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
int verbose;
bool dump_trace = false, quiet = false;
#include "demangle-java.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
enum {
MODE_PREFIX = 0,
// SPDX-License-Identifier: GPL-2.0
#include <asm/bug.h>
#include <linux/kernel.h>
+#include <linux/string.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/types.h>
#include <errno.h>
#include <fcntl.h>
#include <libgen.h>
+#include <bpf/libbpf.h>
+#include "bpf-event.h"
#include "compress.h"
#include "namespaces.h"
#include "path.h"
return -ENOMEM;
}
- strxfrchar(m->name, '-', '_');
+ strreplace(m->name, '-', '_');
}
return 0;
return false;
}
+static ssize_t bpf_read(struct dso *dso, u64 offset, char *data)
+{
+ struct bpf_prog_info_node *node;
+ ssize_t size = DSO__DATA_CACHE_SIZE;
+ u64 len;
+ u8 *buf;
+
+ node = perf_env__find_bpf_prog_info(dso->bpf_prog.env, dso->bpf_prog.id);
+ if (!node || !node->info_linear) {
+ dso->data.status = DSO_DATA_STATUS_ERROR;
+ return -1;
+ }
+
+ len = node->info_linear->info.jited_prog_len;
+ buf = (u8 *)(uintptr_t)node->info_linear->info.jited_prog_insns;
+
+ if (offset >= len)
+ return -1;
+
+ size = (ssize_t)min(len - offset, (u64)size);
+ memcpy(data, buf + offset, size);
+ return size;
+}
+
+static int bpf_size(struct dso *dso)
+{
+ struct bpf_prog_info_node *node;
+
+ node = perf_env__find_bpf_prog_info(dso->bpf_prog.env, dso->bpf_prog.id);
+ if (!node || !node->info_linear) {
+ dso->data.status = DSO_DATA_STATUS_ERROR;
+ return -1;
+ }
+
+ dso->data.file_size = node->info_linear->info.jited_prog_len;
+ return 0;
+}
+
static void
dso_cache__free(struct dso *dso)
{
return cache_size;
}
-static ssize_t
-dso_cache__read(struct dso *dso, struct machine *machine,
- u64 offset, u8 *data, ssize_t size)
+static ssize_t file_read(struct dso *dso, struct machine *machine,
+ u64 offset, char *data)
{
- struct dso_cache *cache;
- struct dso_cache *old;
ssize_t ret;
- do {
- u64 cache_offset;
+ pthread_mutex_lock(&dso__data_open_lock);
- cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
- if (!cache)
- return -ENOMEM;
+ /*
+ * dso->data.fd might be closed if other thread opened another
+ * file (dso) due to open file limit (RLIMIT_NOFILE).
+ */
+ try_to_open_dso(dso, machine);
- pthread_mutex_lock(&dso__data_open_lock);
+ if (dso->data.fd < 0) {
+ dso->data.status = DSO_DATA_STATUS_ERROR;
+ ret = -errno;
+ goto out;
+ }
- /*
- * dso->data.fd might be closed if other thread opened another
- * file (dso) due to open file limit (RLIMIT_NOFILE).
- */
- try_to_open_dso(dso, machine);
+ ret = pread(dso->data.fd, data, DSO__DATA_CACHE_SIZE, offset);
+out:
+ pthread_mutex_unlock(&dso__data_open_lock);
+ return ret;
+}
- if (dso->data.fd < 0) {
- ret = -errno;
- dso->data.status = DSO_DATA_STATUS_ERROR;
- break;
- }
+static ssize_t
+dso_cache__read(struct dso *dso, struct machine *machine,
+ u64 offset, u8 *data, ssize_t size)
+{
+ u64 cache_offset = offset & DSO__DATA_CACHE_MASK;
+ struct dso_cache *cache;
+ struct dso_cache *old;
+ ssize_t ret;
- cache_offset = offset & DSO__DATA_CACHE_MASK;
+ cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
+ if (!cache)
+ return -ENOMEM;
- ret = pread(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE, cache_offset);
- if (ret <= 0)
- break;
+ if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
+ ret = bpf_read(dso, cache_offset, cache->data);
+ else
+ ret = file_read(dso, machine, cache_offset, cache->data);
+ if (ret > 0) {
cache->offset = cache_offset;
cache->size = ret;
- } while (0);
-
- pthread_mutex_unlock(&dso__data_open_lock);
- if (ret > 0) {
old = dso_cache__insert(dso, cache);
if (old) {
/* we lose the race */
return r;
}
-int dso__data_file_size(struct dso *dso, struct machine *machine)
+static int file_size(struct dso *dso, struct machine *machine)
{
int ret = 0;
struct stat st;
char sbuf[STRERR_BUFSIZE];
- if (dso->data.file_size)
- return 0;
-
- if (dso->data.status == DSO_DATA_STATUS_ERROR)
- return -1;
-
pthread_mutex_lock(&dso__data_open_lock);
/*
return ret;
}
+int dso__data_file_size(struct dso *dso, struct machine *machine)
+{
+ if (dso->data.file_size)
+ return 0;
+
+ if (dso->data.status == DSO_DATA_STATUS_ERROR)
+ return -1;
+
+ if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
+ return bpf_size(dso);
+
+ return file_size(dso, machine);
+}
+
/**
* dso__data_size - Return dso data size
* @dso: dso object
// SPDX-License-Identifier: GPL-2.0
#include "cpumap.h"
#include "env.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
#include "util.h"
#include "bpf-event.h"
#include <errno.h>
for (cpu = 0; cpu < nr_cpus; ++cpu) {
env->cpu[cpu].core_id = cpu_map__get_core_id(cpu);
env->cpu[cpu].socket_id = cpu_map__get_socket_id(cpu);
+ env->cpu[cpu].die_id = cpu_map__get_die_id(cpu);
}
env->nr_cpus_avail = nr_cpus;
struct cpu_topology_map {
int socket_id;
+ int die_id;
int core_id;
};
int nr_cmdline;
int nr_sibling_cores;
+ int nr_sibling_dies;
int nr_sibling_threads;
int nr_numa_nodes;
int nr_memory_nodes;
char *cmdline;
const char **cmdline_argv;
char *sibling_cores;
+ char *sibling_dies;
char *sibling_threads;
char *pmu_mappings;
struct cpu_topology_map *cpu;
#include "strlist.h"
#include "thread.h"
#include "thread_map.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
#include "map.h"
#include "symbol.h"
#include "symbol/kallsyms.h"
if (name) {
char *nl;
- name += 5; /* strlen("Name:") */
- name = ltrim(name);
-
+ name = skip_spaces(name + 5); /* strlen("Name:") */
nl = strchr(name, '\n');
if (nl)
*nl = '\0';
size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp)
{
- return fprintf(fp, " ksymbol event with addr %" PRIx64 " len %u type %u flags 0x%x name %s\n",
+ return fprintf(fp, " addr %" PRIx64 " len %u type %u flags 0x%x name %s\n",
event->ksymbol_event.addr, event->ksymbol_event.len,
event->ksymbol_event.ksym_type,
event->ksymbol_event.flags, event->ksymbol_event.name);
size_t perf_event__fprintf_bpf_event(union perf_event *event, FILE *fp)
{
- return fprintf(fp, " bpf event with type %u, flags %u, id %u\n",
+ return fprintf(fp, " type %u, flags %u, id %u\n",
event->bpf_event.type, event->bpf_event.flags,
event->bpf_event.id);
}
u64 period;
u64 weight;
u64 transaction;
+ u64 insn_cnt;
+ u64 cyc_cnt;
u32 cpu;
u32 raw_size;
u64 data_src;
#include "debug.h"
#include "trace-event.h"
#include "stat.h"
+#include "string2.h"
#include "memswap.h"
#include "util/parse-branch-options.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
struct perf_missing_features perf_missing_features;
{
char bf[128];
+ if (!evsel)
+ goto out_unknown;
+
if (evsel->name)
return evsel->name;
evsel->name = strdup(bf);
- return evsel->name ?: "unknown";
+ if (evsel->name)
+ return evsel->name;
+out_unknown:
+ return "unknown";
}
const char *perf_evsel__group_name(struct perf_evsel *evsel)
attr->sample_max_stack = param->max_stack;
+ if (opts->kernel_callchains)
+ attr->exclude_callchain_user = 1;
+ if (opts->user_callchains)
+ attr->exclude_callchain_kernel = 1;
if (param->record_mode == CALLCHAIN_LBR) {
if (!opts->branch_stack) {
if (attr->exclude_user) {
if (!function) {
perf_evsel__set_sample_bit(evsel, REGS_USER);
perf_evsel__set_sample_bit(evsel, STACK_USER);
- attr->sample_regs_user |= PERF_REGS_MASK;
+ if (opts->sample_user_regs && DWARF_MINIMAL_REGS != PERF_REGS_MASK) {
+ attr->sample_regs_user |= DWARF_MINIMAL_REGS;
+ pr_warning("WARNING: The use of --call-graph=dwarf may require all the user registers, "
+ "specifying a subset with --user-regs may render DWARF unwinding unreliable, "
+ "so the minimal registers set (IP, SP) is explicitly forced.\n");
+ } else {
+ attr->sample_regs_user |= PERF_REGS_MASK;
+ }
attr->sample_stack_user = param->dump_size;
attr->exclude_callchain_user = 1;
} else {
static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
{
- if (evsel->system_wide)
- nthreads = 1;
-
evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
if (evsel->fd) {
#include <linux/list.h>
#include <linux/kernel.h>
#include <linux/bitops.h>
+#include <linux/string.h>
#include <linux/stringify.h>
#include <sys/stat.h>
#include <sys/utsname.h>
#include "cputopo.h"
#include "bpf-event.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
/*
* magic2 = "PERFILE2"
while (*p) {
if (isspace(*p)) {
char *r = p + 1;
- char *q = r;
+ char *q = skip_spaces(r);
*p = ' ';
- while (*q && isspace(*q))
- q++;
if (q != (p+1))
while ((*r++ = *q++));
}
if (ret < 0)
return ret;
}
+
+ if (!tp->die_sib)
+ goto done;
+
+ ret = do_write(ff, &tp->die_sib, sizeof(tp->die_sib));
+ if (ret < 0)
+ goto done;
+
+ for (i = 0; i < tp->die_sib; i++) {
+ ret = do_write_string(ff, tp->die_siblings[i]);
+ if (ret < 0)
+ goto done;
+ }
+
+ for (j = 0; j < perf_env.nr_cpus_avail; j++) {
+ ret = do_write(ff, &perf_env.cpu[j].die_id,
+ sizeof(perf_env.cpu[j].die_id));
+ if (ret < 0)
+ return ret;
+ }
+
done:
cpu_topology__delete(tp);
return ret;
return -1;
cache->type[len] = 0;
- cache->type = rtrim(cache->type);
+ cache->type = strim(cache->type);
scnprintf(file, PATH_MAX, "%s/size", path);
if (sysfs__read_str(file, &cache->size, &len)) {
}
cache->size[len] = 0;
- cache->size = rtrim(cache->size);
+ cache->size = strim(cache->size);
scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path);
if (sysfs__read_str(file, &cache->map, &len)) {
}
cache->map[len] = 0;
- cache->map = rtrim(cache->map);
+ cache->map = strim(cache->map);
return 0;
}
return 0;
}
-#define MAX_CACHES 2000
+#define MAX_CACHES (MAX_NR_CPUS * 4)
static int write_cache(struct feat_fd *ff,
struct perf_evlist *evlist __maybe_unused)
str = ph->env.sibling_cores;
for (i = 0; i < nr; i++) {
- fprintf(fp, "# sibling cores : %s\n", str);
+ fprintf(fp, "# sibling sockets : %s\n", str);
str += strlen(str) + 1;
}
+ if (ph->env.nr_sibling_dies) {
+ nr = ph->env.nr_sibling_dies;
+ str = ph->env.sibling_dies;
+
+ for (i = 0; i < nr; i++) {
+ fprintf(fp, "# sibling dies : %s\n", str);
+ str += strlen(str) + 1;
+ }
+ }
+
nr = ph->env.nr_sibling_threads;
str = ph->env.sibling_threads;
str += strlen(str) + 1;
}
- if (ph->env.cpu != NULL) {
- for (i = 0; i < cpu_nr; i++)
- fprintf(fp, "# CPU %d: Core ID %d, Socket ID %d\n", i,
- ph->env.cpu[i].core_id, ph->env.cpu[i].socket_id);
- } else
- fprintf(fp, "# Core ID and Socket ID information is not available\n");
+ if (ph->env.nr_sibling_dies) {
+ if (ph->env.cpu != NULL) {
+ for (i = 0; i < cpu_nr; i++)
+ fprintf(fp, "# CPU %d: Core ID %d, "
+ "Die ID %d, Socket ID %d\n",
+ i, ph->env.cpu[i].core_id,
+ ph->env.cpu[i].die_id,
+ ph->env.cpu[i].socket_id);
+ } else
+ fprintf(fp, "# Core ID, Die ID and Socket ID "
+ "information is not available\n");
+ } else {
+ if (ph->env.cpu != NULL) {
+ for (i = 0; i < cpu_nr; i++)
+ fprintf(fp, "# CPU %d: Core ID %d, "
+ "Socket ID %d\n",
+ i, ph->env.cpu[i].core_id,
+ ph->env.cpu[i].socket_id);
+ } else
+ fprintf(fp, "# Core ID and Socket ID "
+ "information is not available\n");
+ }
}
static void print_clockid(struct feat_fd *ff, FILE *fp)
goto free_cpu;
ph->env.cpu[i].core_id = nr;
+ size += sizeof(u32);
if (do_read_u32(ff, &nr))
goto free_cpu;
}
ph->env.cpu[i].socket_id = nr;
+ size += sizeof(u32);
+ }
+
+ /*
+ * The header may be from old perf,
+ * which doesn't include die information.
+ */
+ if (ff->size <= size)
+ return 0;
+
+ if (do_read_u32(ff, &nr))
+ return -1;
+
+ ph->env.nr_sibling_dies = nr;
+ size += sizeof(u32);
+
+ for (i = 0; i < nr; i++) {
+ str = do_read_string(ff);
+ if (!str)
+ goto error;
+
+ /* include a NULL character at the end */
+ if (strbuf_add(&sb, str, strlen(str) + 1) < 0)
+ goto error;
+ size += string_size(str);
+ free(str);
+ }
+ ph->env.sibling_dies = strbuf_detach(&sb, NULL);
+
+ for (i = 0; i < (u32)cpu_nr; i++) {
+ if (do_read_u32(ff, &nr))
+ goto free_cpu;
+
+ ph->env.cpu[i].die_id = nr;
}
return 0;
}
}
+struct hist_entry *hists__get_entry(struct hists *hists, int idx)
+{
+ struct rb_node *next = rb_first_cached(&hists->entries);
+ struct hist_entry *n;
+ int i = 0;
+
+ while (next) {
+ n = rb_entry(next, struct hist_entry, rb_node);
+ if (i == idx)
+ return n;
+
+ next = rb_next(&n->rb_node);
+ i++;
+ }
+
+ return NULL;
+}
+
/*
* histogram, sorted on item, collects periods
*/
*/
mem_info__zput(entry->mem_info);
+ block_info__zput(entry->block_info);
+
/* If the map of an existing hist_entry has
* become out-of-date due to an exec() or
* similar, update it. Otherwise we will
struct symbol *sym_parent,
struct branch_info *bi,
struct mem_info *mi,
+ struct block_info *block_info,
struct perf_sample *sample,
bool sample_self,
struct hist_entry_ops *ops)
.hists = hists,
.branch_info = bi,
.mem_info = mi,
+ .block_info = block_info,
.transaction = sample->transaction,
.raw_data = sample->raw_data,
.raw_size = sample->raw_size,
struct perf_sample *sample,
bool sample_self)
{
- return __hists__add_entry(hists, al, sym_parent, bi, mi,
+ return __hists__add_entry(hists, al, sym_parent, bi, mi, NULL,
sample, sample_self, NULL);
}
struct perf_sample *sample,
bool sample_self)
{
- return __hists__add_entry(hists, al, sym_parent, bi, mi,
+ return __hists__add_entry(hists, al, sym_parent, bi, mi, NULL,
sample, sample_self, ops);
}
+struct hist_entry *hists__add_entry_block(struct hists *hists,
+ struct addr_location *al,
+ struct block_info *block_info)
+{
+ struct hist_entry entry = {
+ .block_info = block_info,
+ .hists = hists,
+ }, *he = hists__findnew_entry(hists, &entry, al, false);
+
+ return he;
+}
+
static int
iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
struct addr_location *al __maybe_unused)
mem_info__zput(he->mem_info);
}
+ if (he->block_info)
+ block_info__zput(he->block_info);
+
zfree(&he->res_samples);
zfree(&he->stat_acc);
free_srcline(he->srcline);
char unit;
int printed;
const struct dso *dso = hists->dso_filter;
- const struct thread *thread = hists->thread_filter;
+ struct thread *thread = hists->thread_filter;
int socket_id = hists->socket_filter;
unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
u64 nr_events = hists->stats.total_period;
struct map_symbol;
struct mem_info;
struct branch_info;
+struct block_info;
struct symbol;
enum hist_filter {
struct perf_sample *sample,
bool sample_self);
+struct hist_entry *hists__add_entry_block(struct hists *hists,
+ struct addr_location *al,
+ struct block_info *bi);
+
int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
int max_stack_depth, void *arg);
void hists__delete_entries(struct hists *hists);
void hists__output_recalc_col_len(struct hists *hists, int max_rows);
+struct hist_entry *hists__get_entry(struct hists *hists, int idx);
+
u64 hists__total_period(struct hists *hists);
void hists__reset_stats(struct hists *hists);
void hists__inc_stats(struct hists *hists, struct hist_entry *h);
size_t size;
const char *sep;
void *ptr;
+ bool skip;
};
struct perf_hpp_fmt {
+++ /dev/null
-#include "../util.h"
uint64_t *insn_cnt_ptr, uint64_t *ip, uint64_t to_ip,
uint64_t max_insn_cnt, void *data);
bool (*pgd_ip)(uint64_t ip, void *data);
+ int (*lookahead)(void *data, intel_pt_lookahead_cb_t cb, void *cb_data);
void *data;
struct intel_pt_state state;
const unsigned char *buf;
bool have_cyc;
bool fixup_last_mtc;
bool have_last_ip;
+ bool in_psb;
enum intel_pt_param_flags flags;
uint64_t pos;
uint64_t last_ip;
uint64_t timestamp;
uint64_t tsc_timestamp;
uint64_t ref_timestamp;
+ uint64_t buf_timestamp;
uint64_t sample_timestamp;
uint64_t ret_addr;
uint64_t ctc_timestamp;
int mtc_shift;
struct intel_pt_stack stack;
enum intel_pt_pkt_state pkt_state;
+ enum intel_pt_pkt_ctx pkt_ctx;
+ enum intel_pt_pkt_ctx prev_pkt_ctx;
+ enum intel_pt_blk_type blk_type;
+ int blk_type_pos;
struct intel_pt_pkt packet;
struct intel_pt_pkt tnt;
int pkt_step;
uint64_t period_mask;
uint64_t period_ticks;
uint64_t last_masked_timestamp;
+ uint64_t tot_cyc_cnt;
+ uint64_t sample_tot_cyc_cnt;
+ uint64_t base_cyc_cnt;
+ uint64_t cyc_cnt_timestamp;
+ double tsc_to_cyc;
bool continuous_period;
bool overflow;
bool set_fup_tx_flags;
bool set_fup_mwait;
bool set_fup_pwre;
bool set_fup_exstop;
+ bool set_fup_bep;
+ bool sample_cyc;
unsigned int fup_tx_flags;
unsigned int tx_flags;
uint64_t fup_ptw_payload;
decoder->get_trace = params->get_trace;
decoder->walk_insn = params->walk_insn;
decoder->pgd_ip = params->pgd_ip;
+ decoder->lookahead = params->lookahead;
decoder->data = params->data;
decoder->return_compression = params->return_compression;
decoder->branch_enable = params->branch_enable;
return -EBADMSG;
}
-static int intel_pt_get_data(struct intel_pt_decoder *decoder)
+static inline void intel_pt_update_sample_time(struct intel_pt_decoder *decoder)
+{
+ decoder->sample_timestamp = decoder->timestamp;
+ decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
+}
+
+static void intel_pt_reposition(struct intel_pt_decoder *decoder)
+{
+ decoder->ip = 0;
+ decoder->pkt_state = INTEL_PT_STATE_NO_PSB;
+ decoder->timestamp = 0;
+ decoder->have_tma = false;
+}
+
+static int intel_pt_get_data(struct intel_pt_decoder *decoder, bool reposition)
{
struct intel_pt_buffer buffer = { .buf = 0, };
int ret;
intel_pt_log("No more data\n");
return -ENODATA;
}
- if (!buffer.consecutive) {
- decoder->ip = 0;
- decoder->pkt_state = INTEL_PT_STATE_NO_PSB;
+ decoder->buf_timestamp = buffer.ref_timestamp;
+ if (!buffer.consecutive || reposition) {
+ intel_pt_reposition(decoder);
decoder->ref_timestamp = buffer.ref_timestamp;
- decoder->timestamp = 0;
- decoder->have_tma = false;
decoder->state.trace_nr = buffer.trace_nr;
intel_pt_log("Reference timestamp 0x%" PRIx64 "\n",
decoder->ref_timestamp);
return 0;
}
-static int intel_pt_get_next_data(struct intel_pt_decoder *decoder)
+static int intel_pt_get_next_data(struct intel_pt_decoder *decoder,
+ bool reposition)
{
if (!decoder->next_buf)
- return intel_pt_get_data(decoder);
+ return intel_pt_get_data(decoder, reposition);
decoder->buf = decoder->next_buf;
decoder->len = decoder->next_len;
len = decoder->len;
memcpy(buf, decoder->buf, len);
- ret = intel_pt_get_data(decoder);
+ ret = intel_pt_get_data(decoder, false);
if (ret) {
decoder->pos += old_len;
return ret < 0 ? ret : -EINVAL;
memcpy(buf + len, decoder->buf, n);
len += n;
- ret = intel_pt_get_packet(buf, len, &decoder->packet);
+ decoder->prev_pkt_ctx = decoder->pkt_ctx;
+ ret = intel_pt_get_packet(buf, len, &decoder->packet, &decoder->pkt_ctx);
if (ret < (int)old_len) {
decoder->next_buf = decoder->buf;
decoder->next_len = decoder->len;
{
struct intel_pt_pkt_info pkt_info;
const unsigned char *buf = decoder->buf;
+ enum intel_pt_pkt_ctx pkt_ctx = decoder->pkt_ctx;
size_t len = decoder->len;
int ret;
if (!len)
return INTEL_PT_NEED_MORE_BYTES;
- ret = intel_pt_get_packet(buf, len, &pkt_info.packet);
+ ret = intel_pt_get_packet(buf, len, &pkt_info.packet,
+ &pkt_ctx);
if (!ret)
return INTEL_PT_NEED_MORE_BYTES;
if (ret < 0)
case INTEL_PT_MNT:
case INTEL_PT_PTWRITE:
case INTEL_PT_PTWRITE_IP:
+ case INTEL_PT_BBP:
+ case INTEL_PT_BIP:
+ case INTEL_PT_BEP:
+ case INTEL_PT_BEP_IP:
return 0;
case INTEL_PT_MTC:
decoder->len -= decoder->pkt_step;
if (!decoder->len) {
- ret = intel_pt_get_next_data(decoder);
+ ret = intel_pt_get_next_data(decoder, false);
if (ret)
return ret;
}
+ decoder->prev_pkt_ctx = decoder->pkt_ctx;
ret = intel_pt_get_packet(decoder->buf, decoder->len,
- &decoder->packet);
+ &decoder->packet, &decoder->pkt_ctx);
if (ret == INTEL_PT_NEED_MORE_BYTES && BITS_PER_LONG == 32 &&
decoder->len < INTEL_PT_PKT_MAX_SZ && !decoder->next_buf) {
ret = intel_pt_get_split_packet(decoder);
decoder->state.to_ip = 0;
ret = true;
}
+ if (decoder->set_fup_bep) {
+ decoder->set_fup_bep = false;
+ decoder->state.type |= INTEL_PT_BLK_ITEMS;
+ decoder->state.type &= ~INTEL_PT_BRANCH;
+ decoder->state.from_ip = decoder->ip;
+ decoder->state.to_ip = 0;
+ ret = true;
+ }
return ret;
}
decoder->ip += intel_pt_insn.length;
return 0;
}
+ decoder->sample_cyc = false;
decoder->ip += intel_pt_insn.length;
if (!decoder->tnt.count) {
- decoder->sample_timestamp = decoder->timestamp;
- decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
+ intel_pt_update_sample_time(decoder);
return -EAGAIN;
}
decoder->tnt.payload <<= 1;
return 0;
}
+static uint64_t intel_pt_8b_tsc(uint64_t timestamp, uint64_t ref_timestamp)
+{
+ timestamp |= (ref_timestamp & (0xffULL << 56));
+
+ if (timestamp < ref_timestamp) {
+ if (ref_timestamp - timestamp > (1ULL << 55))
+ timestamp += (1ULL << 56);
+ } else {
+ if (timestamp - ref_timestamp > (1ULL << 55))
+ timestamp -= (1ULL << 56);
+ }
+
+ return timestamp;
+}
+
static void intel_pt_calc_tsc_timestamp(struct intel_pt_decoder *decoder)
{
uint64_t timestamp;
decoder->have_tma = false;
if (decoder->ref_timestamp) {
- timestamp = decoder->packet.payload |
- (decoder->ref_timestamp & (0xffULL << 56));
- if (timestamp < decoder->ref_timestamp) {
- if (decoder->ref_timestamp - timestamp > (1ULL << 55))
- timestamp += (1ULL << 56);
- } else {
- if (timestamp - decoder->ref_timestamp > (1ULL << 55))
- timestamp -= (1ULL << 56);
- }
+ timestamp = intel_pt_8b_tsc(decoder->packet.payload,
+ decoder->ref_timestamp);
decoder->tsc_timestamp = timestamp;
decoder->timestamp = timestamp;
decoder->ref_timestamp = 0;
return -EOVERFLOW;
}
+static inline void intel_pt_mtc_cyc_cnt_pge(struct intel_pt_decoder *decoder)
+{
+ if (decoder->have_cyc)
+ return;
+
+ decoder->cyc_cnt_timestamp = decoder->timestamp;
+ decoder->base_cyc_cnt = decoder->tot_cyc_cnt;
+}
+
+static inline void intel_pt_mtc_cyc_cnt_cbr(struct intel_pt_decoder *decoder)
+{
+ decoder->tsc_to_cyc = decoder->cbr / decoder->max_non_turbo_ratio_fp;
+
+ if (decoder->pge)
+ intel_pt_mtc_cyc_cnt_pge(decoder);
+}
+
+static inline void intel_pt_mtc_cyc_cnt_upd(struct intel_pt_decoder *decoder)
+{
+ uint64_t tot_cyc_cnt, tsc_delta;
+
+ if (decoder->have_cyc)
+ return;
+
+ decoder->sample_cyc = true;
+
+ if (!decoder->pge || decoder->timestamp <= decoder->cyc_cnt_timestamp)
+ return;
+
+ tsc_delta = decoder->timestamp - decoder->cyc_cnt_timestamp;
+ tot_cyc_cnt = tsc_delta * decoder->tsc_to_cyc + decoder->base_cyc_cnt;
+
+ if (tot_cyc_cnt > decoder->tot_cyc_cnt)
+ decoder->tot_cyc_cnt = tot_cyc_cnt;
+}
+
static void intel_pt_calc_tma(struct intel_pt_decoder *decoder)
{
uint32_t ctc = decoder->packet.payload;
if (!decoder->tsc_ctc_ratio_d)
return;
+ if (decoder->pge && !decoder->in_psb)
+ intel_pt_mtc_cyc_cnt_pge(decoder);
+ else
+ intel_pt_mtc_cyc_cnt_upd(decoder);
+
decoder->last_mtc = (ctc >> decoder->mtc_shift) & 0xff;
decoder->ctc_timestamp = decoder->tsc_timestamp - fc;
if (decoder->tsc_ctc_mult) {
else
decoder->timestamp = timestamp;
+ intel_pt_mtc_cyc_cnt_upd(decoder);
+
decoder->timestamp_insn_cnt = 0;
decoder->last_mtc = mtc;
decoder->cbr = cbr;
decoder->cbr_cyc_to_tsc = decoder->max_non_turbo_ratio_fp / cbr;
+
+ intel_pt_mtc_cyc_cnt_cbr(decoder);
}
static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder)
decoder->have_cyc = true;
decoder->cycle_cnt += decoder->packet.payload;
+ if (decoder->pge)
+ decoder->tot_cyc_cnt += decoder->packet.payload;
+ decoder->sample_cyc = true;
if (!decoder->cyc_ref_timestamp)
return;
intel_pt_log_to("Setting timestamp", decoder->timestamp);
}
+static void intel_pt_bbp(struct intel_pt_decoder *decoder)
+{
+ if (decoder->prev_pkt_ctx == INTEL_PT_NO_CTX) {
+ memset(decoder->state.items.mask, 0, sizeof(decoder->state.items.mask));
+ decoder->state.items.is_32_bit = false;
+ }
+ decoder->blk_type = decoder->packet.payload;
+ decoder->blk_type_pos = intel_pt_blk_type_pos(decoder->blk_type);
+ if (decoder->blk_type == INTEL_PT_GP_REGS)
+ decoder->state.items.is_32_bit = decoder->packet.count;
+ if (decoder->blk_type_pos < 0) {
+ intel_pt_log("WARNING: Unknown block type %u\n",
+ decoder->blk_type);
+ } else if (decoder->state.items.mask[decoder->blk_type_pos]) {
+ intel_pt_log("WARNING: Duplicate block type %u\n",
+ decoder->blk_type);
+ }
+}
+
+static void intel_pt_bip(struct intel_pt_decoder *decoder)
+{
+ uint32_t id = decoder->packet.count;
+ uint32_t bit = 1 << id;
+ int pos = decoder->blk_type_pos;
+
+ if (pos < 0 || id >= INTEL_PT_BLK_ITEM_ID_CNT) {
+ intel_pt_log("WARNING: Unknown block item %u type %d\n",
+ id, decoder->blk_type);
+ return;
+ }
+
+ if (decoder->state.items.mask[pos] & bit) {
+ intel_pt_log("WARNING: Duplicate block item %u type %d\n",
+ id, decoder->blk_type);
+ }
+
+ decoder->state.items.mask[pos] |= bit;
+ decoder->state.items.val[pos][id] = decoder->packet.payload;
+}
+
/* Walk PSB+ packets when already in sync. */
static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder)
{
int err;
+ decoder->in_psb = true;
+
while (1) {
err = intel_pt_get_next_packet(decoder);
if (err)
- return err;
+ goto out;
switch (decoder->packet.type) {
case INTEL_PT_PSBEND:
- return 0;
+ err = 0;
+ goto out;
case INTEL_PT_TIP_PGD:
case INTEL_PT_TIP_PGE:
case INTEL_PT_MWAIT:
case INTEL_PT_PWRE:
case INTEL_PT_PWRX:
+ case INTEL_PT_BBP:
+ case INTEL_PT_BIP:
+ case INTEL_PT_BEP:
+ case INTEL_PT_BEP_IP:
decoder->have_tma = false;
intel_pt_log("ERROR: Unexpected packet\n");
- return -EAGAIN;
+ err = -EAGAIN;
+ goto out;
case INTEL_PT_OVF:
- return intel_pt_overflow(decoder);
+ err = intel_pt_overflow(decoder);
+ goto out;
case INTEL_PT_TSC:
intel_pt_calc_tsc_timestamp(decoder);
break;
}
}
+out:
+ decoder->in_psb = false;
+
+ return err;
}
static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
case INTEL_PT_MWAIT:
case INTEL_PT_PWRE:
case INTEL_PT_PWRX:
+ case INTEL_PT_BBP:
+ case INTEL_PT_BIP:
+ case INTEL_PT_BEP:
+ case INTEL_PT_BEP_IP:
intel_pt_log("ERROR: Missing TIP after FUP\n");
decoder->pkt_state = INTEL_PT_STATE_ERR3;
decoder->pkt_step = 0;
decoder->state.to_ip = decoder->ip;
}
decoder->state.type |= INTEL_PT_TRACE_BEGIN;
+ intel_pt_mtc_cyc_cnt_pge(decoder);
return 0;
case INTEL_PT_TIP:
case INTEL_PT_TIP_PGE: {
decoder->pge = true;
+ intel_pt_mtc_cyc_cnt_pge(decoder);
if (decoder->packet.count == 0) {
intel_pt_log_at("Skipping zero TIP.PGE",
decoder->pos);
goto next;
if (err)
return err;
+ /*
+ * PSB+ CBR will not have changed but cater for the
+ * possibility of another CBR change that gets caught up
+ * in the PSB+.
+ */
+ if (decoder->cbr != decoder->cbr_seen)
+ return 0;
break;
case INTEL_PT_PIP:
case INTEL_PT_CBR:
intel_pt_calc_cbr(decoder);
- if (!decoder->branch_enable &&
- decoder->cbr != decoder->cbr_seen) {
- decoder->cbr_seen = decoder->cbr;
- decoder->state.type = INTEL_PT_CBR_CHG;
- decoder->state.from_ip = decoder->ip;
- decoder->state.to_ip = 0;
- decoder->state.cbr_payload =
- decoder->packet.payload;
+ if (decoder->cbr != decoder->cbr_seen)
return 0;
- }
break;
case INTEL_PT_MODE_EXEC:
decoder->state.pwrx_payload = decoder->packet.payload;
return 0;
+ case INTEL_PT_BBP:
+ intel_pt_bbp(decoder);
+ break;
+
+ case INTEL_PT_BIP:
+ intel_pt_bip(decoder);
+ break;
+
+ case INTEL_PT_BEP:
+ decoder->state.type = INTEL_PT_BLK_ITEMS;
+ decoder->state.from_ip = decoder->ip;
+ decoder->state.to_ip = 0;
+ return 0;
+
+ case INTEL_PT_BEP_IP:
+ err = intel_pt_get_next_packet(decoder);
+ if (err)
+ return err;
+ if (decoder->packet.type == INTEL_PT_FUP) {
+ decoder->set_fup_bep = true;
+ no_tip = true;
+ } else {
+ intel_pt_log_at("ERROR: Missing FUP after BEP",
+ decoder->pos);
+ }
+ goto next;
+
default:
return intel_pt_bug(decoder);
}
{
int err;
+ decoder->in_psb = true;
+
while (1) {
err = intel_pt_get_next_packet(decoder);
if (err)
- return err;
+ goto out;
switch (decoder->packet.type) {
case INTEL_PT_TIP_PGD:
case INTEL_PT_MWAIT:
case INTEL_PT_PWRE:
case INTEL_PT_PWRX:
+ case INTEL_PT_BBP:
+ case INTEL_PT_BIP:
+ case INTEL_PT_BEP:
+ case INTEL_PT_BEP_IP:
intel_pt_log("ERROR: Unexpected packet\n");
- return -ENOENT;
+ err = -ENOENT;
+ goto out;
case INTEL_PT_FUP:
decoder->pge = true;
decoder->pkt_state = INTEL_PT_STATE_ERR4;
else
decoder->pkt_state = INTEL_PT_STATE_ERR3;
- return -ENOENT;
+ err = -ENOENT;
+ goto out;
case INTEL_PT_BAD: /* Does not happen */
- return intel_pt_bug(decoder);
+ err = intel_pt_bug(decoder);
+ goto out;
case INTEL_PT_OVF:
- return intel_pt_overflow(decoder);
+ err = intel_pt_overflow(decoder);
+ goto out;
case INTEL_PT_PSBEND:
- return 0;
+ err = 0;
+ goto out;
case INTEL_PT_PSB:
case INTEL_PT_VMCS:
break;
}
}
+out:
+ decoder->in_psb = false;
+
+ return err;
}
static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
switch (decoder->packet.type) {
case INTEL_PT_TIP_PGD:
decoder->continuous_period = false;
- __fallthrough;
+ decoder->pge = false;
+ if (intel_pt_have_ip(decoder))
+ intel_pt_set_ip(decoder);
+ if (!decoder->ip)
+ break;
+ decoder->state.type |= INTEL_PT_TRACE_END;
+ return 0;
+
case INTEL_PT_TIP_PGE:
+ decoder->pge = true;
+ intel_pt_mtc_cyc_cnt_pge(decoder);
+ if (intel_pt_have_ip(decoder))
+ intel_pt_set_ip(decoder);
+ if (!decoder->ip)
+ break;
+ decoder->state.type |= INTEL_PT_TRACE_BEGIN;
+ return 0;
+
case INTEL_PT_TIP:
- decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
+ decoder->pge = true;
if (intel_pt_have_ip(decoder))
intel_pt_set_ip(decoder);
if (!decoder->ip)
break;
- if (decoder->packet.type == INTEL_PT_TIP_PGE)
- decoder->state.type |= INTEL_PT_TRACE_BEGIN;
- if (decoder->packet.type == INTEL_PT_TIP_PGD)
- decoder->state.type |= INTEL_PT_TRACE_END;
return 0;
case INTEL_PT_FUP:
case INTEL_PT_MWAIT:
case INTEL_PT_PWRE:
case INTEL_PT_PWRX:
+ case INTEL_PT_BBP:
+ case INTEL_PT_BIP:
+ case INTEL_PT_BEP:
+ case INTEL_PT_BEP_IP:
default:
break;
}
decoder->set_fup_mwait = false;
decoder->set_fup_pwre = false;
decoder->set_fup_exstop = false;
+ decoder->set_fup_bep = false;
if (!decoder->branch_enable) {
decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
decoder->pos += decoder->len;
decoder->len = 0;
- ret = intel_pt_get_next_data(decoder);
+ ret = intel_pt_get_next_data(decoder, false);
if (ret)
return ret;
intel_pt_log("Scanning for PSB\n");
while (1) {
if (!decoder->len) {
- ret = intel_pt_get_next_data(decoder);
+ ret = intel_pt_get_next_data(decoder, false);
if (ret)
return ret;
}
if (err) {
decoder->state.err = intel_pt_ext_err(err);
decoder->state.from_ip = decoder->ip;
- decoder->sample_timestamp = decoder->timestamp;
- decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
+ intel_pt_update_sample_time(decoder);
+ decoder->sample_tot_cyc_cnt = decoder->tot_cyc_cnt;
} else {
decoder->state.err = 0;
- if (decoder->cbr != decoder->cbr_seen && decoder->state.type) {
+ if (decoder->cbr != decoder->cbr_seen) {
decoder->cbr_seen = decoder->cbr;
+ if (!decoder->state.type) {
+ decoder->state.from_ip = decoder->ip;
+ decoder->state.to_ip = 0;
+ }
decoder->state.type |= INTEL_PT_CBR_CHG;
decoder->state.cbr_payload = decoder->cbr_payload;
+ decoder->state.cbr = decoder->cbr;
}
if (intel_pt_sample_time(decoder->pkt_state)) {
- decoder->sample_timestamp = decoder->timestamp;
- decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
+ intel_pt_update_sample_time(decoder);
+ if (decoder->sample_cyc)
+ decoder->sample_tot_cyc_cnt = decoder->tot_cyc_cnt;
}
}
decoder->state.est_timestamp = intel_pt_est_timestamp(decoder);
decoder->state.cr3 = decoder->cr3;
decoder->state.tot_insn_cnt = decoder->tot_insn_cnt;
+ decoder->state.tot_cyc_cnt = decoder->sample_tot_cyc_cnt;
return &decoder->state;
}
static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc,
size_t *rem)
{
+ enum intel_pt_pkt_ctx ctx = INTEL_PT_NO_CTX;
struct intel_pt_pkt packet;
int ret;
while (len) {
- ret = intel_pt_get_packet(buf, len, &packet);
+ ret = intel_pt_get_packet(buf, len, &packet, &ctx);
if (ret <= 0)
return false;
if (packet.type == INTEL_PT_TSC) {
return buf_b; /* No overlap */
}
}
+
+/**
+ * struct fast_forward_data - data used by intel_pt_ff_cb().
+ * @timestamp: timestamp to fast forward towards
+ * @buf_timestamp: buffer timestamp of last buffer with trace data earlier than
+ * the fast forward timestamp.
+ */
+struct fast_forward_data {
+ uint64_t timestamp;
+ uint64_t buf_timestamp;
+};
+
+/**
+ * intel_pt_ff_cb - fast forward lookahead callback.
+ * @buffer: Intel PT trace buffer
+ * @data: opaque pointer to fast forward data (struct fast_forward_data)
+ *
+ * Determine if @buffer trace is past the fast forward timestamp.
+ *
+ * Return: 1 (stop lookahead) if @buffer trace is past the fast forward
+ * timestamp, and 0 otherwise.
+ */
+static int intel_pt_ff_cb(struct intel_pt_buffer *buffer, void *data)
+{
+ struct fast_forward_data *d = data;
+ unsigned char *buf;
+ uint64_t tsc;
+ size_t rem;
+ size_t len;
+
+ buf = (unsigned char *)buffer->buf;
+ len = buffer->len;
+
+ if (!intel_pt_next_psb(&buf, &len) ||
+ !intel_pt_next_tsc(buf, len, &tsc, &rem))
+ return 0;
+
+ tsc = intel_pt_8b_tsc(tsc, buffer->ref_timestamp);
+
+ intel_pt_log("Buffer 1st timestamp " x64_fmt " ref timestamp " x64_fmt "\n",
+ tsc, buffer->ref_timestamp);
+
+ /*
+ * If the buffer contains a timestamp earlier that the fast forward
+ * timestamp, then record it, else stop.
+ */
+ if (tsc < d->timestamp)
+ d->buf_timestamp = buffer->ref_timestamp;
+ else
+ return 1;
+
+ return 0;
+}
+
+/**
+ * intel_pt_fast_forward - reposition decoder forwards.
+ * @decoder: Intel PT decoder
+ * @timestamp: timestamp to fast forward towards
+ *
+ * Reposition decoder at the last PSB with a timestamp earlier than @timestamp.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int intel_pt_fast_forward(struct intel_pt_decoder *decoder, uint64_t timestamp)
+{
+ struct fast_forward_data d = { .timestamp = timestamp };
+ unsigned char *buf;
+ size_t len;
+ int err;
+
+ intel_pt_log("Fast forward towards timestamp " x64_fmt "\n", timestamp);
+
+ /* Find buffer timestamp of buffer to fast forward to */
+ err = decoder->lookahead(decoder->data, intel_pt_ff_cb, &d);
+ if (err < 0)
+ return err;
+
+ /* Walk to buffer with same buffer timestamp */
+ if (d.buf_timestamp) {
+ do {
+ decoder->pos += decoder->len;
+ decoder->len = 0;
+ err = intel_pt_get_next_data(decoder, true);
+ /* -ENOLINK means non-consecutive trace */
+ if (err && err != -ENOLINK)
+ return err;
+ } while (decoder->buf_timestamp != d.buf_timestamp);
+ }
+
+ if (!decoder->buf)
+ return 0;
+
+ buf = (unsigned char *)decoder->buf;
+ len = decoder->len;
+
+ if (!intel_pt_next_psb(&buf, &len))
+ return 0;
+
+ /*
+ * Walk PSBs while the PSB timestamp is less than the fast forward
+ * timestamp.
+ */
+ do {
+ uint64_t tsc;
+ size_t rem;
+
+ if (!intel_pt_next_tsc(buf, len, &tsc, &rem))
+ break;
+ tsc = intel_pt_8b_tsc(tsc, decoder->buf_timestamp);
+ /*
+ * A TSC packet can slip past MTC packets but, after fast
+ * forward, decoding starts at the TSC timestamp. That means
+ * the timestamps may not be exactly the same as the timestamps
+ * that would have been decoded without fast forward.
+ */
+ if (tsc < timestamp) {
+ intel_pt_log("Fast forward to next PSB timestamp " x64_fmt "\n", tsc);
+ decoder->pos += decoder->len - len;
+ decoder->buf = buf;
+ decoder->len = len;
+ intel_pt_reposition(decoder);
+ } else {
+ break;
+ }
+ } while (intel_pt_step_psb(&buf, &len));
+
+ return 0;
+}
INTEL_PT_CBR_CHG = 1 << 8,
INTEL_PT_TRACE_BEGIN = 1 << 9,
INTEL_PT_TRACE_END = 1 << 10,
+ INTEL_PT_BLK_ITEMS = 1 << 11,
};
enum intel_pt_period_type {
INTEL_PT_FUP_WITH_NLIP = 1 << 0,
};
+enum intel_pt_blk_type {
+ INTEL_PT_GP_REGS = 1,
+ INTEL_PT_PEBS_BASIC = 4,
+ INTEL_PT_PEBS_MEM = 5,
+ INTEL_PT_LBR_0 = 8,
+ INTEL_PT_LBR_1 = 9,
+ INTEL_PT_LBR_2 = 10,
+ INTEL_PT_XMM = 16,
+ INTEL_PT_BLK_TYPE_MAX
+};
+
+/*
+ * The block type numbers are not sequential but here they are given sequential
+ * positions to avoid wasting space for array placement.
+ */
+enum intel_pt_blk_type_pos {
+ INTEL_PT_GP_REGS_POS,
+ INTEL_PT_PEBS_BASIC_POS,
+ INTEL_PT_PEBS_MEM_POS,
+ INTEL_PT_LBR_0_POS,
+ INTEL_PT_LBR_1_POS,
+ INTEL_PT_LBR_2_POS,
+ INTEL_PT_XMM_POS,
+ INTEL_PT_BLK_TYPE_CNT
+};
+
+/* Get the array position for a block type */
+static inline int intel_pt_blk_type_pos(enum intel_pt_blk_type blk_type)
+{
+#define BLK_TYPE(bt) [INTEL_PT_##bt] = INTEL_PT_##bt##_POS + 1
+ const int map[INTEL_PT_BLK_TYPE_MAX] = {
+ BLK_TYPE(GP_REGS),
+ BLK_TYPE(PEBS_BASIC),
+ BLK_TYPE(PEBS_MEM),
+ BLK_TYPE(LBR_0),
+ BLK_TYPE(LBR_1),
+ BLK_TYPE(LBR_2),
+ BLK_TYPE(XMM),
+ };
+#undef BLK_TYPE
+
+ return blk_type < INTEL_PT_BLK_TYPE_MAX ? map[blk_type] - 1 : -1;
+}
+
+#define INTEL_PT_BLK_ITEM_ID_CNT 32
+
+/*
+ * Use unions so that the block items can be accessed by name or by array index.
+ * There is an array of 32-bit masks for each block type, which indicate which
+ * values are present. Then arrays of 32 64-bit values for each block type.
+ */
+struct intel_pt_blk_items {
+ union {
+ uint32_t mask[INTEL_PT_BLK_TYPE_CNT];
+ struct {
+ uint32_t has_rflags:1;
+ uint32_t has_rip:1;
+ uint32_t has_rax:1;
+ uint32_t has_rcx:1;
+ uint32_t has_rdx:1;
+ uint32_t has_rbx:1;
+ uint32_t has_rsp:1;
+ uint32_t has_rbp:1;
+ uint32_t has_rsi:1;
+ uint32_t has_rdi:1;
+ uint32_t has_r8:1;
+ uint32_t has_r9:1;
+ uint32_t has_r10:1;
+ uint32_t has_r11:1;
+ uint32_t has_r12:1;
+ uint32_t has_r13:1;
+ uint32_t has_r14:1;
+ uint32_t has_r15:1;
+ uint32_t has_unused_0:14;
+ uint32_t has_ip:1;
+ uint32_t has_applicable_counters:1;
+ uint32_t has_timestamp:1;
+ uint32_t has_unused_1:29;
+ uint32_t has_mem_access_address:1;
+ uint32_t has_mem_aux_info:1;
+ uint32_t has_mem_access_latency:1;
+ uint32_t has_tsx_aux_info:1;
+ uint32_t has_unused_2:28;
+ uint32_t has_lbr_0;
+ uint32_t has_lbr_1;
+ uint32_t has_lbr_2;
+ uint32_t has_xmm;
+ };
+ };
+ union {
+ uint64_t val[INTEL_PT_BLK_TYPE_CNT][INTEL_PT_BLK_ITEM_ID_CNT];
+ struct {
+ struct {
+ uint64_t rflags;
+ uint64_t rip;
+ uint64_t rax;
+ uint64_t rcx;
+ uint64_t rdx;
+ uint64_t rbx;
+ uint64_t rsp;
+ uint64_t rbp;
+ uint64_t rsi;
+ uint64_t rdi;
+ uint64_t r8;
+ uint64_t r9;
+ uint64_t r10;
+ uint64_t r11;
+ uint64_t r12;
+ uint64_t r13;
+ uint64_t r14;
+ uint64_t r15;
+ uint64_t unused_0[INTEL_PT_BLK_ITEM_ID_CNT - 18];
+ };
+ struct {
+ uint64_t ip;
+ uint64_t applicable_counters;
+ uint64_t timestamp;
+ uint64_t unused_1[INTEL_PT_BLK_ITEM_ID_CNT - 3];
+ };
+ struct {
+ uint64_t mem_access_address;
+ uint64_t mem_aux_info;
+ uint64_t mem_access_latency;
+ uint64_t tsx_aux_info;
+ uint64_t unused_2[INTEL_PT_BLK_ITEM_ID_CNT - 4];
+ };
+ uint64_t lbr_0[INTEL_PT_BLK_ITEM_ID_CNT];
+ uint64_t lbr_1[INTEL_PT_BLK_ITEM_ID_CNT];
+ uint64_t lbr_2[INTEL_PT_BLK_ITEM_ID_CNT];
+ uint64_t xmm[INTEL_PT_BLK_ITEM_ID_CNT];
+ };
+ };
+ bool is_32_bit;
+};
+
struct intel_pt_state {
enum intel_pt_sample_type type;
int err;
uint64_t to_ip;
uint64_t cr3;
uint64_t tot_insn_cnt;
+ uint64_t tot_cyc_cnt;
uint64_t timestamp;
uint64_t est_timestamp;
uint64_t trace_nr;
uint64_t pwre_payload;
uint64_t pwrx_payload;
uint64_t cbr_payload;
+ uint32_t cbr;
uint32_t flags;
enum intel_pt_insn_op insn_op;
int insn_len;
char insn[INTEL_PT_INSN_BUF_SZ];
+ struct intel_pt_blk_items items;
};
struct intel_pt_insn;
uint64_t trace_nr;
};
+typedef int (*intel_pt_lookahead_cb_t)(struct intel_pt_buffer *, void *);
+
struct intel_pt_params {
int (*get_trace)(struct intel_pt_buffer *buffer, void *data);
int (*walk_insn)(struct intel_pt_insn *intel_pt_insn,
uint64_t *insn_cnt_ptr, uint64_t *ip, uint64_t to_ip,
uint64_t max_insn_cnt, void *data);
bool (*pgd_ip)(uint64_t ip, void *data);
+ int (*lookahead)(void *data, intel_pt_lookahead_cb_t cb, void *cb_data);
void *data;
bool return_compression;
bool branch_enable;
const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder);
+int intel_pt_fast_forward(struct intel_pt_decoder *decoder, uint64_t timestamp);
+
unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
unsigned char *buf_b, size_t len_b,
bool have_tsc, bool *consecutive);
[INTEL_PT_MWAIT] = "MWAIT",
[INTEL_PT_PWRE] = "PWRE",
[INTEL_PT_PWRX] = "PWRX",
+ [INTEL_PT_BBP] = "BBP",
+ [INTEL_PT_BIP] = "BIP",
+ [INTEL_PT_BEP] = "BEP",
+ [INTEL_PT_BEP_IP] = "BEP",
};
const char *intel_pt_pkt_name(enum intel_pt_pkt_type type)
return 7;
}
+static int intel_pt_get_bbp(const unsigned char *buf, size_t len,
+ struct intel_pt_pkt *packet)
+{
+ if (len < 3)
+ return INTEL_PT_NEED_MORE_BYTES;
+ packet->type = INTEL_PT_BBP;
+ packet->count = buf[2] >> 7;
+ packet->payload = buf[2] & 0x1f;
+ return 3;
+}
+
+static int intel_pt_get_bip_4(const unsigned char *buf, size_t len,
+ struct intel_pt_pkt *packet)
+{
+ if (len < 5)
+ return INTEL_PT_NEED_MORE_BYTES;
+ packet->type = INTEL_PT_BIP;
+ packet->count = buf[0] >> 3;
+ memcpy_le64(&packet->payload, buf + 1, 4);
+ return 5;
+}
+
+static int intel_pt_get_bip_8(const unsigned char *buf, size_t len,
+ struct intel_pt_pkt *packet)
+{
+ if (len < 9)
+ return INTEL_PT_NEED_MORE_BYTES;
+ packet->type = INTEL_PT_BIP;
+ packet->count = buf[0] >> 3;
+ memcpy_le64(&packet->payload, buf + 1, 8);
+ return 9;
+}
+
+static int intel_pt_get_bep(size_t len, struct intel_pt_pkt *packet)
+{
+ if (len < 2)
+ return INTEL_PT_NEED_MORE_BYTES;
+ packet->type = INTEL_PT_BEP;
+ return 2;
+}
+
+static int intel_pt_get_bep_ip(size_t len, struct intel_pt_pkt *packet)
+{
+ if (len < 2)
+ return INTEL_PT_NEED_MORE_BYTES;
+ packet->type = INTEL_PT_BEP_IP;
+ return 2;
+}
+
static int intel_pt_get_ext(const unsigned char *buf, size_t len,
struct intel_pt_pkt *packet)
{
return intel_pt_get_pwre(buf, len, packet);
case 0xA2: /* PWRX */
return intel_pt_get_pwrx(buf, len, packet);
+ case 0x63: /* BBP */
+ return intel_pt_get_bbp(buf, len, packet);
+ case 0x33: /* BEP no IP */
+ return intel_pt_get_bep(len, packet);
+ case 0xb3: /* BEP with IP */
+ return intel_pt_get_bep_ip(len, packet);
default:
return INTEL_PT_BAD_PACKET;
}
}
static int intel_pt_do_get_packet(const unsigned char *buf, size_t len,
- struct intel_pt_pkt *packet)
+ struct intel_pt_pkt *packet,
+ enum intel_pt_pkt_ctx ctx)
{
unsigned int byte;
return INTEL_PT_NEED_MORE_BYTES;
byte = buf[0];
+
+ switch (ctx) {
+ case INTEL_PT_NO_CTX:
+ break;
+ case INTEL_PT_BLK_4_CTX:
+ if ((byte & 0x7) == 4)
+ return intel_pt_get_bip_4(buf, len, packet);
+ break;
+ case INTEL_PT_BLK_8_CTX:
+ if ((byte & 0x7) == 4)
+ return intel_pt_get_bip_8(buf, len, packet);
+ break;
+ default:
+ break;
+ };
+
if (!(byte & BIT(0))) {
if (byte == 0)
return intel_pt_get_pad(packet);
}
}
+void intel_pt_upd_pkt_ctx(const struct intel_pt_pkt *packet,
+ enum intel_pt_pkt_ctx *ctx)
+{
+ switch (packet->type) {
+ case INTEL_PT_BAD:
+ case INTEL_PT_PAD:
+ case INTEL_PT_TSC:
+ case INTEL_PT_TMA:
+ case INTEL_PT_MTC:
+ case INTEL_PT_FUP:
+ case INTEL_PT_CYC:
+ case INTEL_PT_CBR:
+ case INTEL_PT_MNT:
+ case INTEL_PT_EXSTOP:
+ case INTEL_PT_EXSTOP_IP:
+ case INTEL_PT_PWRE:
+ case INTEL_PT_PWRX:
+ case INTEL_PT_BIP:
+ break;
+ case INTEL_PT_TNT:
+ case INTEL_PT_TIP:
+ case INTEL_PT_TIP_PGD:
+ case INTEL_PT_TIP_PGE:
+ case INTEL_PT_MODE_EXEC:
+ case INTEL_PT_MODE_TSX:
+ case INTEL_PT_PIP:
+ case INTEL_PT_OVF:
+ case INTEL_PT_VMCS:
+ case INTEL_PT_TRACESTOP:
+ case INTEL_PT_PSB:
+ case INTEL_PT_PSBEND:
+ case INTEL_PT_PTWRITE:
+ case INTEL_PT_PTWRITE_IP:
+ case INTEL_PT_MWAIT:
+ case INTEL_PT_BEP:
+ case INTEL_PT_BEP_IP:
+ *ctx = INTEL_PT_NO_CTX;
+ break;
+ case INTEL_PT_BBP:
+ if (packet->count)
+ *ctx = INTEL_PT_BLK_4_CTX;
+ else
+ *ctx = INTEL_PT_BLK_8_CTX;
+ break;
+ default:
+ break;
+ }
+}
+
int intel_pt_get_packet(const unsigned char *buf, size_t len,
- struct intel_pt_pkt *packet)
+ struct intel_pt_pkt *packet, enum intel_pt_pkt_ctx *ctx)
{
int ret;
- ret = intel_pt_do_get_packet(buf, len, packet);
+ ret = intel_pt_do_get_packet(buf, len, packet, *ctx);
if (ret > 0) {
while (ret < 8 && len > (size_t)ret && !buf[ret])
ret += 1;
+ intel_pt_upd_pkt_ctx(packet, ctx);
}
return ret;
}
return snprintf(buf, buf_len, "%s 0x%llx IP:0", name, payload);
case INTEL_PT_PTWRITE_IP:
return snprintf(buf, buf_len, "%s 0x%llx IP:1", name, payload);
+ case INTEL_PT_BEP:
case INTEL_PT_EXSTOP:
return snprintf(buf, buf_len, "%s IP:0", name);
+ case INTEL_PT_BEP_IP:
case INTEL_PT_EXSTOP_IP:
return snprintf(buf, buf_len, "%s IP:1", name);
case INTEL_PT_MWAIT:
(unsigned int)((payload >> 4) & 0xf),
(unsigned int)(payload & 0xf),
(unsigned int)((payload >> 8) & 0xf));
+ case INTEL_PT_BBP:
+ return snprintf(buf, buf_len, "%s SZ %s-byte Type 0x%llx",
+ name, packet->count ? "4" : "8", payload);
+ case INTEL_PT_BIP:
+ return snprintf(buf, buf_len, "%s ID 0x%02x Value 0x%llx",
+ name, packet->count, payload);
default:
break;
}
INTEL_PT_MWAIT,
INTEL_PT_PWRE,
INTEL_PT_PWRX,
+ INTEL_PT_BBP,
+ INTEL_PT_BIP,
+ INTEL_PT_BEP,
+ INTEL_PT_BEP_IP,
};
struct intel_pt_pkt {
uint64_t payload;
};
+/*
+ * Decoding of BIP packets conflicts with single-byte TNT packets. Since BIP
+ * packets only occur in the context of a block (i.e. between BBP and BEP), that
+ * context must be recorded and passed to the packet decoder.
+ */
+enum intel_pt_pkt_ctx {
+ INTEL_PT_NO_CTX, /* BIP packets are invalid */
+ INTEL_PT_BLK_4_CTX, /* 4-byte BIP packets */
+ INTEL_PT_BLK_8_CTX, /* 8-byte BIP packets */
+};
+
const char *intel_pt_pkt_name(enum intel_pt_pkt_type);
int intel_pt_get_packet(const unsigned char *buf, size_t len,
- struct intel_pt_pkt *packet);
+ struct intel_pt_pkt *packet,
+ enum intel_pt_pkt_ctx *ctx);
+
+void intel_pt_upd_pkt_ctx(const struct intel_pt_pkt *packet,
+ enum intel_pt_pkt_ctx *ctx);
int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf, size_t len);
#include "tsc.h"
#include "intel-pt.h"
#include "config.h"
+#include "time-utils.h"
+
+#include "../arch/x86/include/uapi/asm/perf_regs.h"
#include "intel-pt-decoder/intel-pt-log.h"
#include "intel-pt-decoder/intel-pt-decoder.h"
#define MAX_TIMESTAMP (~0ULL)
+struct range {
+ u64 start;
+ u64 end;
+};
+
struct intel_pt {
struct auxtrace auxtrace;
struct auxtrace_queues queues;
u64 pwrx_id;
u64 cbr_id;
+ bool sample_pebs;
+ struct perf_evsel *pebs_evsel;
+
u64 tsc_bit;
u64 mtc_bit;
u64 mtc_freq_bits;
char *filter;
struct addr_filters filts;
+
+ struct range *time_ranges;
+ unsigned int range_cnt;
};
enum switch_state {
bool have_sample;
u64 time;
u64 timestamp;
+ u64 sel_timestamp;
+ bool sel_start;
+ unsigned int sel_idx;
u32 flags;
u16 insn_len;
u64 last_insn_cnt;
+ u64 ipc_insn_cnt;
+ u64 ipc_cyc_cnt;
+ u64 last_in_insn_cnt;
+ u64 last_in_cyc_cnt;
+ u64 last_br_insn_cnt;
+ u64 last_br_cyc_cnt;
+ unsigned int cbr_seen;
char insn[INTEL_PT_INSN_BUF_SZ];
};
int ret, pkt_len, i;
char desc[INTEL_PT_PKT_DESC_MAX];
const char *color = PERF_COLOR_BLUE;
+ enum intel_pt_pkt_ctx ctx = INTEL_PT_NO_CTX;
color_fprintf(stdout, color,
". ... Intel Processor Trace data: size %zu bytes\n",
len);
while (len) {
- ret = intel_pt_get_packet(buf, len, &packet);
+ ret = intel_pt_get_packet(buf, len, &packet, &ctx);
if (ret > 0)
pkt_len = ret;
else
return 0;
}
-/* This function assumes data is processed sequentially only */
-static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
+static int intel_pt_get_buffer(struct intel_pt_queue *ptq,
+ struct auxtrace_buffer *buffer,
+ struct auxtrace_buffer *old_buffer,
+ struct intel_pt_buffer *b)
{
- struct intel_pt_queue *ptq = data;
- struct auxtrace_buffer *buffer = ptq->buffer;
- struct auxtrace_buffer *old_buffer = ptq->old_buffer;
- struct auxtrace_queue *queue;
bool might_overlap;
- if (ptq->stop) {
- b->len = 0;
- return 0;
- }
-
- queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
-
- buffer = auxtrace_buffer__next(queue, buffer);
- if (!buffer) {
- if (old_buffer)
- auxtrace_buffer__drop_data(old_buffer);
- b->len = 0;
- return 0;
- }
-
- ptq->buffer = buffer;
-
if (!buffer->data) {
int fd = perf_data__fd(ptq->pt->session->data);
b->consecutive = true;
}
+ return 0;
+}
+
+/* Do not drop buffers with references - refer intel_pt_get_trace() */
+static void intel_pt_lookahead_drop_buffer(struct intel_pt_queue *ptq,
+ struct auxtrace_buffer *buffer)
+{
+ if (!buffer || buffer == ptq->buffer || buffer == ptq->old_buffer)
+ return;
+
+ auxtrace_buffer__drop_data(buffer);
+}
+
+/* Must be serialized with respect to intel_pt_get_trace() */
+static int intel_pt_lookahead(void *data, intel_pt_lookahead_cb_t cb,
+ void *cb_data)
+{
+ struct intel_pt_queue *ptq = data;
+ struct auxtrace_buffer *buffer = ptq->buffer;
+ struct auxtrace_buffer *old_buffer = ptq->old_buffer;
+ struct auxtrace_queue *queue;
+ int err = 0;
+
+ queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
+
+ while (1) {
+ struct intel_pt_buffer b = { .len = 0 };
+
+ buffer = auxtrace_buffer__next(queue, buffer);
+ if (!buffer)
+ break;
+
+ err = intel_pt_get_buffer(ptq, buffer, old_buffer, &b);
+ if (err)
+ break;
+
+ if (b.len) {
+ intel_pt_lookahead_drop_buffer(ptq, old_buffer);
+ old_buffer = buffer;
+ } else {
+ intel_pt_lookahead_drop_buffer(ptq, buffer);
+ continue;
+ }
+
+ err = cb(&b, cb_data);
+ if (err)
+ break;
+ }
+
+ if (buffer != old_buffer)
+ intel_pt_lookahead_drop_buffer(ptq, buffer);
+ intel_pt_lookahead_drop_buffer(ptq, old_buffer);
+
+ return err;
+}
+
+/*
+ * This function assumes data is processed sequentially only.
+ * Must be serialized with respect to intel_pt_lookahead()
+ */
+static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
+{
+ struct intel_pt_queue *ptq = data;
+ struct auxtrace_buffer *buffer = ptq->buffer;
+ struct auxtrace_buffer *old_buffer = ptq->old_buffer;
+ struct auxtrace_queue *queue;
+ int err;
+
+ if (ptq->stop) {
+ b->len = 0;
+ return 0;
+ }
+
+ queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
+
+ buffer = auxtrace_buffer__next(queue, buffer);
+ if (!buffer) {
+ if (old_buffer)
+ auxtrace_buffer__drop_data(old_buffer);
+ b->len = 0;
+ return 0;
+ }
+
+ ptq->buffer = buffer;
+
+ err = intel_pt_get_buffer(ptq, buffer, old_buffer, b);
+ if (err)
+ return err;
+
if (ptq->step_through_buffers)
ptq->stop = true;
params.get_trace = intel_pt_get_trace;
params.walk_insn = intel_pt_walk_next_insn;
+ params.lookahead = intel_pt_lookahead;
params.data = ptq;
params.return_compression = intel_pt_return_compression(pt);
params.branch_enable = intel_pt_branch_enable(pt);
ptq->flags |= PERF_IP_FLAG_TRACE_END;
}
+static void intel_pt_setup_time_range(struct intel_pt *pt,
+ struct intel_pt_queue *ptq)
+{
+ if (!pt->range_cnt)
+ return;
+
+ ptq->sel_timestamp = pt->time_ranges[0].start;
+ ptq->sel_idx = 0;
+
+ if (ptq->sel_timestamp) {
+ ptq->sel_start = true;
+ } else {
+ ptq->sel_timestamp = pt->time_ranges[0].end;
+ ptq->sel_start = false;
+ }
+}
+
static int intel_pt_setup_queue(struct intel_pt *pt,
struct auxtrace_queue *queue,
unsigned int queue_nr)
ptq->cpu = queue->cpu;
ptq->tid = queue->tid;
+ ptq->cbr_seen = UINT_MAX;
+
if (pt->sampling_mode && !pt->snapshot_mode &&
pt->timeless_decoding)
ptq->step_through_buffers = true;
ptq->sync_switch = pt->sync_switch;
+
+ intel_pt_setup_time_range(pt, ptq);
}
if (!ptq->on_heap &&
intel_pt_log("queue %u getting timestamp\n", queue_nr);
intel_pt_log("queue %u decoding cpu %d pid %d tid %d\n",
queue_nr, ptq->cpu, ptq->pid, ptq->tid);
+
+ if (ptq->sel_start && ptq->sel_timestamp) {
+ ret = intel_pt_fast_forward(ptq->decoder,
+ ptq->sel_timestamp);
+ if (ret)
+ return ret;
+ }
+
while (1) {
state = intel_pt_decode(ptq->decoder);
if (state->err) {
queue_nr, ptq->timestamp);
ptq->state = state;
ptq->have_sample = true;
+ if (ptq->sel_start && ptq->sel_timestamp &&
+ ptq->timestamp < ptq->sel_timestamp)
+ ptq->have_sample = false;
intel_pt_sample_flags(ptq);
ret = auxtrace_heap__add(&pt->heap, queue_nr, ptq->timestamp);
if (ret)
pt->num_events++ < pt->synth_opts.initial_skip;
}
+/*
+ * Cannot count CBR as skipped because it won't go away until cbr == cbr_seen.
+ * Also ensure CBR is first non-skipped event by allowing for 4 more samples
+ * from this decoder state.
+ */
+static inline bool intel_pt_skip_cbr_event(struct intel_pt *pt)
+{
+ return pt->synth_opts.initial_skip &&
+ pt->num_events + 4 < pt->synth_opts.initial_skip;
+}
+
+static void intel_pt_prep_a_sample(struct intel_pt_queue *ptq,
+ union perf_event *event,
+ struct perf_sample *sample)
+{
+ event->sample.header.type = PERF_RECORD_SAMPLE;
+ event->sample.header.size = sizeof(struct perf_event_header);
+
+ sample->pid = ptq->pid;
+ sample->tid = ptq->tid;
+ sample->cpu = ptq->cpu;
+ sample->insn_len = ptq->insn_len;
+ memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
+}
+
static void intel_pt_prep_b_sample(struct intel_pt *pt,
struct intel_pt_queue *ptq,
union perf_event *event,
struct perf_sample *sample)
{
+ intel_pt_prep_a_sample(ptq, event, sample);
+
if (!pt->timeless_decoding)
sample->time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
sample->ip = ptq->state->from_ip;
sample->cpumode = intel_pt_cpumode(pt, sample->ip);
- sample->pid = ptq->pid;
- sample->tid = ptq->tid;
sample->addr = ptq->state->to_ip;
sample->period = 1;
- sample->cpu = ptq->cpu;
sample->flags = ptq->flags;
- sample->insn_len = ptq->insn_len;
- memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
- event->sample.header.type = PERF_RECORD_SAMPLE;
event->sample.header.misc = sample->cpumode;
- event->sample.header.size = sizeof(struct perf_event_header);
}
static int intel_pt_inject_event(union perf_event *event,
sample.branch_stack = (struct branch_stack *)&dummy_bs;
}
+ sample.cyc_cnt = ptq->ipc_cyc_cnt - ptq->last_br_cyc_cnt;
+ if (sample.cyc_cnt) {
+ sample.insn_cnt = ptq->ipc_insn_cnt - ptq->last_br_insn_cnt;
+ ptq->last_br_insn_cnt = ptq->ipc_insn_cnt;
+ ptq->last_br_cyc_cnt = ptq->ipc_cyc_cnt;
+ }
+
return intel_pt_deliver_synth_b_event(pt, event, &sample,
pt->branches_sample_type);
}
sample.stream_id = ptq->pt->instructions_id;
sample.period = ptq->state->tot_insn_cnt - ptq->last_insn_cnt;
+ sample.cyc_cnt = ptq->ipc_cyc_cnt - ptq->last_in_cyc_cnt;
+ if (sample.cyc_cnt) {
+ sample.insn_cnt = ptq->ipc_insn_cnt - ptq->last_in_insn_cnt;
+ ptq->last_in_insn_cnt = ptq->ipc_insn_cnt;
+ ptq->last_in_cyc_cnt = ptq->ipc_cyc_cnt;
+ }
+
ptq->last_insn_cnt = ptq->state->tot_insn_cnt;
return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
struct perf_synth_intel_cbr raw;
u32 flags;
- if (intel_pt_skip_event(pt))
+ if (intel_pt_skip_cbr_event(pt))
return 0;
+ ptq->cbr_seen = ptq->state->cbr;
+
intel_pt_prep_p_sample(pt, ptq, event, &sample);
sample.id = ptq->pt->cbr_id;
pt->pwr_events_sample_type);
}
+/*
+ * PEBS gp_regs array indexes plus 1 so that 0 means not present. Refer
+ * intel_pt_add_gp_regs().
+ */
+static const int pebs_gp_regs[] = {
+ [PERF_REG_X86_FLAGS] = 1,
+ [PERF_REG_X86_IP] = 2,
+ [PERF_REG_X86_AX] = 3,
+ [PERF_REG_X86_CX] = 4,
+ [PERF_REG_X86_DX] = 5,
+ [PERF_REG_X86_BX] = 6,
+ [PERF_REG_X86_SP] = 7,
+ [PERF_REG_X86_BP] = 8,
+ [PERF_REG_X86_SI] = 9,
+ [PERF_REG_X86_DI] = 10,
+ [PERF_REG_X86_R8] = 11,
+ [PERF_REG_X86_R9] = 12,
+ [PERF_REG_X86_R10] = 13,
+ [PERF_REG_X86_R11] = 14,
+ [PERF_REG_X86_R12] = 15,
+ [PERF_REG_X86_R13] = 16,
+ [PERF_REG_X86_R14] = 17,
+ [PERF_REG_X86_R15] = 18,
+};
+
+static u64 *intel_pt_add_gp_regs(struct regs_dump *intr_regs, u64 *pos,
+ const struct intel_pt_blk_items *items,
+ u64 regs_mask)
+{
+ const u64 *gp_regs = items->val[INTEL_PT_GP_REGS_POS];
+ u32 mask = items->mask[INTEL_PT_GP_REGS_POS];
+ u32 bit;
+ int i;
+
+ for (i = 0, bit = 1; i < PERF_REG_X86_64_MAX; i++, bit <<= 1) {
+ /* Get the PEBS gp_regs array index */
+ int n = pebs_gp_regs[i] - 1;
+
+ if (n < 0)
+ continue;
+ /*
+ * Add only registers that were requested (i.e. 'regs_mask') and
+ * that were provided (i.e. 'mask'), and update the resulting
+ * mask (i.e. 'intr_regs->mask') accordingly.
+ */
+ if (mask & 1 << n && regs_mask & bit) {
+ intr_regs->mask |= bit;
+ *pos++ = gp_regs[n];
+ }
+ }
+
+ return pos;
+}
+
+#ifndef PERF_REG_X86_XMM0
+#define PERF_REG_X86_XMM0 32
+#endif
+
+static void intel_pt_add_xmm(struct regs_dump *intr_regs, u64 *pos,
+ const struct intel_pt_blk_items *items,
+ u64 regs_mask)
+{
+ u32 mask = items->has_xmm & (regs_mask >> PERF_REG_X86_XMM0);
+ const u64 *xmm = items->xmm;
+
+ /*
+ * If there are any XMM registers, then there should be all of them.
+ * Nevertheless, follow the logic to add only registers that were
+ * requested (i.e. 'regs_mask') and that were provided (i.e. 'mask'),
+ * and update the resulting mask (i.e. 'intr_regs->mask') accordingly.
+ */
+ intr_regs->mask |= (u64)mask << PERF_REG_X86_XMM0;
+
+ for (; mask; mask >>= 1, xmm++) {
+ if (mask & 1)
+ *pos++ = *xmm;
+ }
+}
+
+#define LBR_INFO_MISPRED (1ULL << 63)
+#define LBR_INFO_IN_TX (1ULL << 62)
+#define LBR_INFO_ABORT (1ULL << 61)
+#define LBR_INFO_CYCLES 0xffff
+
+/* Refer kernel's intel_pmu_store_pebs_lbrs() */
+static u64 intel_pt_lbr_flags(u64 info)
+{
+ union {
+ struct branch_flags flags;
+ u64 result;
+ } u = {
+ .flags = {
+ .mispred = !!(info & LBR_INFO_MISPRED),
+ .predicted = !(info & LBR_INFO_MISPRED),
+ .in_tx = !!(info & LBR_INFO_IN_TX),
+ .abort = !!(info & LBR_INFO_ABORT),
+ .cycles = info & LBR_INFO_CYCLES,
+ }
+ };
+
+ return u.result;
+}
+
+static void intel_pt_add_lbrs(struct branch_stack *br_stack,
+ const struct intel_pt_blk_items *items)
+{
+ u64 *to;
+ int i;
+
+ br_stack->nr = 0;
+
+ to = &br_stack->entries[0].from;
+
+ for (i = INTEL_PT_LBR_0_POS; i <= INTEL_PT_LBR_2_POS; i++) {
+ u32 mask = items->mask[i];
+ const u64 *from = items->val[i];
+
+ for (; mask; mask >>= 3, from += 3) {
+ if ((mask & 7) == 7) {
+ *to++ = from[0];
+ *to++ = from[1];
+ *to++ = intel_pt_lbr_flags(from[2]);
+ br_stack->nr += 1;
+ }
+ }
+ }
+}
+
+/* INTEL_PT_LBR_0, INTEL_PT_LBR_1 and INTEL_PT_LBR_2 */
+#define LBRS_MAX (INTEL_PT_BLK_ITEM_ID_CNT * 3)
+
+static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
+{
+ const struct intel_pt_blk_items *items = &ptq->state->items;
+ struct perf_sample sample = { .ip = 0, };
+ union perf_event *event = ptq->event_buf;
+ struct intel_pt *pt = ptq->pt;
+ struct perf_evsel *evsel = pt->pebs_evsel;
+ u64 sample_type = evsel->attr.sample_type;
+ u64 id = evsel->id[0];
+ u8 cpumode;
+
+ if (intel_pt_skip_event(pt))
+ return 0;
+
+ intel_pt_prep_a_sample(ptq, event, &sample);
+
+ sample.id = id;
+ sample.stream_id = id;
+
+ if (!evsel->attr.freq)
+ sample.period = evsel->attr.sample_period;
+
+ /* No support for non-zero CS base */
+ if (items->has_ip)
+ sample.ip = items->ip;
+ else if (items->has_rip)
+ sample.ip = items->rip;
+ else
+ sample.ip = ptq->state->from_ip;
+
+ /* No support for guest mode at this time */
+ cpumode = sample.ip < ptq->pt->kernel_start ?
+ PERF_RECORD_MISC_USER :
+ PERF_RECORD_MISC_KERNEL;
+
+ event->sample.header.misc = cpumode | PERF_RECORD_MISC_EXACT_IP;
+
+ sample.cpumode = cpumode;
+
+ if (sample_type & PERF_SAMPLE_TIME) {
+ u64 timestamp = 0;
+
+ if (items->has_timestamp)
+ timestamp = items->timestamp;
+ else if (!pt->timeless_decoding)
+ timestamp = ptq->timestamp;
+ if (timestamp)
+ sample.time = tsc_to_perf_time(timestamp, &pt->tc);
+ }
+
+ if (sample_type & PERF_SAMPLE_CALLCHAIN &&
+ pt->synth_opts.callchain) {
+ thread_stack__sample(ptq->thread, ptq->cpu, ptq->chain,
+ pt->synth_opts.callchain_sz, sample.ip,
+ pt->kernel_start);
+ sample.callchain = ptq->chain;
+ }
+
+ if (sample_type & PERF_SAMPLE_REGS_INTR &&
+ items->mask[INTEL_PT_GP_REGS_POS]) {
+ u64 regs[sizeof(sample.intr_regs.mask)];
+ u64 regs_mask = evsel->attr.sample_regs_intr;
+ u64 *pos;
+
+ sample.intr_regs.abi = items->is_32_bit ?
+ PERF_SAMPLE_REGS_ABI_32 :
+ PERF_SAMPLE_REGS_ABI_64;
+ sample.intr_regs.regs = regs;
+
+ pos = intel_pt_add_gp_regs(&sample.intr_regs, regs, items, regs_mask);
+
+ intel_pt_add_xmm(&sample.intr_regs, pos, items, regs_mask);
+ }
+
+ if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+ struct {
+ struct branch_stack br_stack;
+ struct branch_entry entries[LBRS_MAX];
+ } br;
+
+ if (items->mask[INTEL_PT_LBR_0_POS] ||
+ items->mask[INTEL_PT_LBR_1_POS] ||
+ items->mask[INTEL_PT_LBR_2_POS]) {
+ intel_pt_add_lbrs(&br.br_stack, items);
+ sample.branch_stack = &br.br_stack;
+ } else if (pt->synth_opts.last_branch) {
+ intel_pt_copy_last_branch_rb(ptq);
+ sample.branch_stack = ptq->last_branch;
+ } else {
+ br.br_stack.nr = 0;
+ sample.branch_stack = &br.br_stack;
+ }
+ }
+
+ if (sample_type & PERF_SAMPLE_ADDR && items->has_mem_access_address)
+ sample.addr = items->mem_access_address;
+
+ if (sample_type & PERF_SAMPLE_WEIGHT) {
+ /*
+ * Refer kernel's setup_pebs_adaptive_sample_data() and
+ * intel_hsw_weight().
+ */
+ if (items->has_mem_access_latency)
+ sample.weight = items->mem_access_latency;
+ if (!sample.weight && items->has_tsx_aux_info) {
+ /* Cycles last block */
+ sample.weight = (u32)items->tsx_aux_info;
+ }
+ }
+
+ if (sample_type & PERF_SAMPLE_TRANSACTION && items->has_tsx_aux_info) {
+ u64 ax = items->has_rax ? items->rax : 0;
+ /* Refer kernel's intel_hsw_transaction() */
+ u64 txn = (u8)(items->tsx_aux_info >> 32);
+
+ /* For RTM XABORTs also log the abort code from AX */
+ if (txn & PERF_TXN_TRANSACTION && ax & 1)
+ txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
+ sample.transaction = txn;
+ }
+
+ return intel_pt_deliver_synth_event(pt, ptq, event, &sample, sample_type);
+}
+
static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
pid_t pid, pid_t tid, u64 ip, u64 timestamp)
{
}
#define INTEL_PT_PWR_EVT (INTEL_PT_MWAIT_OP | INTEL_PT_PWR_ENTRY | \
- INTEL_PT_EX_STOP | INTEL_PT_PWR_EXIT | \
- INTEL_PT_CBR_CHG)
+ INTEL_PT_EX_STOP | INTEL_PT_PWR_EXIT)
static int intel_pt_sample(struct intel_pt_queue *ptq)
{
ptq->have_sample = false;
- if (pt->sample_pwr_events && (state->type & INTEL_PT_PWR_EVT)) {
- if (state->type & INTEL_PT_CBR_CHG) {
+ if (ptq->state->tot_cyc_cnt > ptq->ipc_cyc_cnt) {
+ /*
+ * Cycle count and instruction count only go together to create
+ * a valid IPC ratio when the cycle count changes.
+ */
+ ptq->ipc_insn_cnt = ptq->state->tot_insn_cnt;
+ ptq->ipc_cyc_cnt = ptq->state->tot_cyc_cnt;
+ }
+
+ /*
+ * Do PEBS first to allow for the possibility that the PEBS timestamp
+ * precedes the current timestamp.
+ */
+ if (pt->sample_pebs && state->type & INTEL_PT_BLK_ITEMS) {
+ err = intel_pt_synth_pebs_sample(ptq);
+ if (err)
+ return err;
+ }
+
+ if (pt->sample_pwr_events) {
+ if (ptq->state->cbr != ptq->cbr_seen) {
err = intel_pt_synth_cbr_sample(ptq);
if (err)
return err;
}
- if (state->type & INTEL_PT_MWAIT_OP) {
- err = intel_pt_synth_mwait_sample(ptq);
- if (err)
- return err;
- }
- if (state->type & INTEL_PT_PWR_ENTRY) {
- err = intel_pt_synth_pwre_sample(ptq);
- if (err)
- return err;
- }
- if (state->type & INTEL_PT_EX_STOP) {
- err = intel_pt_synth_exstop_sample(ptq);
- if (err)
- return err;
- }
- if (state->type & INTEL_PT_PWR_EXIT) {
- err = intel_pt_synth_pwrx_sample(ptq);
- if (err)
- return err;
+ if (state->type & INTEL_PT_PWR_EVT) {
+ if (state->type & INTEL_PT_MWAIT_OP) {
+ err = intel_pt_synth_mwait_sample(ptq);
+ if (err)
+ return err;
+ }
+ if (state->type & INTEL_PT_PWR_ENTRY) {
+ err = intel_pt_synth_pwre_sample(ptq);
+ if (err)
+ return err;
+ }
+ if (state->type & INTEL_PT_EX_STOP) {
+ err = intel_pt_synth_exstop_sample(ptq);
+ if (err)
+ return err;
+ }
+ if (state->type & INTEL_PT_PWR_EXIT) {
+ err = intel_pt_synth_pwrx_sample(ptq);
+ if (err)
+ return err;
+ }
}
}
}
}
+/*
+ * To filter against time ranges, it is only necessary to look at the next start
+ * or end time.
+ */
+static bool intel_pt_next_time(struct intel_pt_queue *ptq)
+{
+ struct intel_pt *pt = ptq->pt;
+
+ if (ptq->sel_start) {
+ /* Next time is an end time */
+ ptq->sel_start = false;
+ ptq->sel_timestamp = pt->time_ranges[ptq->sel_idx].end;
+ return true;
+ } else if (ptq->sel_idx + 1 < pt->range_cnt) {
+ /* Next time is a start time */
+ ptq->sel_start = true;
+ ptq->sel_idx += 1;
+ ptq->sel_timestamp = pt->time_ranges[ptq->sel_idx].start;
+ return true;
+ }
+
+ /* No next time */
+ return false;
+}
+
+static int intel_pt_time_filter(struct intel_pt_queue *ptq, u64 *ff_timestamp)
+{
+ int err;
+
+ while (1) {
+ if (ptq->sel_start) {
+ if (ptq->timestamp >= ptq->sel_timestamp) {
+ /* After start time, so consider next time */
+ intel_pt_next_time(ptq);
+ if (!ptq->sel_timestamp) {
+ /* No end time */
+ return 0;
+ }
+ /* Check against end time */
+ continue;
+ }
+ /* Before start time, so fast forward */
+ ptq->have_sample = false;
+ if (ptq->sel_timestamp > *ff_timestamp) {
+ if (ptq->sync_switch) {
+ intel_pt_next_tid(ptq->pt, ptq);
+ ptq->switch_state = INTEL_PT_SS_UNKNOWN;
+ }
+ *ff_timestamp = ptq->sel_timestamp;
+ err = intel_pt_fast_forward(ptq->decoder,
+ ptq->sel_timestamp);
+ if (err)
+ return err;
+ }
+ return 0;
+ } else if (ptq->timestamp > ptq->sel_timestamp) {
+ /* After end time, so consider next time */
+ if (!intel_pt_next_time(ptq)) {
+ /* No next time range, so stop decoding */
+ ptq->have_sample = false;
+ ptq->switch_state = INTEL_PT_SS_NOT_TRACING;
+ return 1;
+ }
+ /* Check against next start time */
+ continue;
+ } else {
+ /* Before end time */
+ return 0;
+ }
+ }
+}
+
static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
{
const struct intel_pt_state *state = ptq->state;
struct intel_pt *pt = ptq->pt;
+ u64 ff_timestamp = 0;
int err;
if (!pt->kernel_start) {
ptq->timestamp = state->timestamp;
}
+ if (ptq->sel_timestamp) {
+ err = intel_pt_time_filter(ptq, &ff_timestamp);
+ if (err)
+ return err;
+ }
+
if (!pt->timeless_decoding && ptq->timestamp >= *timestamp) {
*timestamp = ptq->timestamp;
return 0;
switch (ptq->switch_state) {
case INTEL_PT_SS_NOT_TRACING:
- ptq->next_tid = -1;
break;
case INTEL_PT_SS_UNKNOWN:
case INTEL_PT_SS_TRACING:
ptq->switch_state = INTEL_PT_SS_TRACING;
break;
case INTEL_PT_SS_EXPECTING_SWITCH_IP:
- ptq->next_tid = tid;
intel_pt_log("ERROR: cpu %d expecting switch ip\n", cpu);
break;
default:
break;
}
+ ptq->next_tid = -1;
+
return 1;
}
return machine__set_current_tid(pt->machine, cpu, -1, tid);
}
+static int intel_pt_context_switch_in(struct intel_pt *pt,
+ struct perf_sample *sample)
+{
+ pid_t pid = sample->pid;
+ pid_t tid = sample->tid;
+ int cpu = sample->cpu;
+
+ if (pt->sync_switch) {
+ struct intel_pt_queue *ptq;
+
+ ptq = intel_pt_cpu_to_ptq(pt, cpu);
+ if (ptq && ptq->sync_switch) {
+ ptq->next_tid = -1;
+ switch (ptq->switch_state) {
+ case INTEL_PT_SS_NOT_TRACING:
+ case INTEL_PT_SS_UNKNOWN:
+ case INTEL_PT_SS_TRACING:
+ break;
+ case INTEL_PT_SS_EXPECTING_SWITCH_EVENT:
+ case INTEL_PT_SS_EXPECTING_SWITCH_IP:
+ ptq->switch_state = INTEL_PT_SS_TRACING;
+ break;
+ default:
+ break;
+ }
+ }
+ }
+
+ /*
+ * If the current tid has not been updated yet, ensure it is now that
+ * a "switch in" event has occurred.
+ */
+ if (machine__get_current_tid(pt->machine, cpu) == tid)
+ return 0;
+
+ return machine__set_current_tid(pt->machine, cpu, pid, tid);
+}
+
static int intel_pt_context_switch(struct intel_pt *pt, union perf_event *event,
struct perf_sample *sample)
{
if (pt->have_sched_switch == 3) {
if (!out)
- return 0;
+ return intel_pt_context_switch_in(pt, sample);
if (event->header.type != PERF_RECORD_SWITCH_CPU_WIDE) {
pr_err("Expecting CPU-wide context switch event\n");
return -EINVAL;
thread__put(pt->unknown_thread);
addr_filters__exit(&pt->filts);
zfree(&pt->filter);
+ zfree(&pt->time_ranges);
free(pt);
}
return 0;
}
+/* Find least TSC which converts to ns or later */
+static u64 intel_pt_tsc_start(u64 ns, struct intel_pt *pt)
+{
+ u64 tsc, tm;
+
+ tsc = perf_time_to_tsc(ns, &pt->tc);
+
+ while (1) {
+ tm = tsc_to_perf_time(tsc, &pt->tc);
+ if (tm < ns)
+ break;
+ tsc -= 1;
+ }
+
+ while (tm < ns)
+ tm = tsc_to_perf_time(++tsc, &pt->tc);
+
+ return tsc;
+}
+
+/* Find greatest TSC which converts to ns or earlier */
+static u64 intel_pt_tsc_end(u64 ns, struct intel_pt *pt)
+{
+ u64 tsc, tm;
+
+ tsc = perf_time_to_tsc(ns, &pt->tc);
+
+ while (1) {
+ tm = tsc_to_perf_time(tsc, &pt->tc);
+ if (tm > ns)
+ break;
+ tsc += 1;
+ }
+
+ while (tm > ns)
+ tm = tsc_to_perf_time(--tsc, &pt->tc);
+
+ return tsc;
+}
+
+static int intel_pt_setup_time_ranges(struct intel_pt *pt,
+ struct itrace_synth_opts *opts)
+{
+ struct perf_time_interval *p = opts->ptime_range;
+ int n = opts->range_num;
+ int i;
+
+ if (!n || !p || pt->timeless_decoding)
+ return 0;
+
+ pt->time_ranges = calloc(n, sizeof(struct range));
+ if (!pt->time_ranges)
+ return -ENOMEM;
+
+ pt->range_cnt = n;
+
+ intel_pt_log("%s: %u range(s)\n", __func__, n);
+
+ for (i = 0; i < n; i++) {
+ struct range *r = &pt->time_ranges[i];
+ u64 ts = p[i].start;
+ u64 te = p[i].end;
+
+ /*
+ * Take care to ensure the TSC range matches the perf-time range
+ * when converted back to perf-time.
+ */
+ r->start = ts ? intel_pt_tsc_start(ts, pt) : 0;
+ r->end = te ? intel_pt_tsc_end(te, pt) : 0;
+
+ intel_pt_log("range %d: perf time interval: %"PRIu64" to %"PRIu64"\n",
+ i, ts, te);
+ intel_pt_log("range %d: TSC time interval: %#"PRIx64" to %#"PRIx64"\n",
+ i, r->start, r->end);
+ }
+
+ return 0;
+}
+
static const char * const intel_pt_info_fmts[] = {
[INTEL_PT_PMU_TYPE] = " PMU Type %"PRId64"\n",
[INTEL_PT_TIME_SHIFT] = " Time Shift %"PRIu64"\n",
} else {
itrace_synth_opts__set_default(&pt->synth_opts,
session->itrace_synth_opts->default_no_sample);
- if (use_browser != -1) {
+ if (!session->itrace_synth_opts->default_no_sample &&
+ !session->itrace_synth_opts->inject) {
pt->synth_opts.branches = false;
pt->synth_opts.callchain = true;
}
pt->cbr2khz = tsc_freq / pt->max_non_turbo_ratio / 1000;
}
+ if (session->itrace_synth_opts) {
+ err = intel_pt_setup_time_ranges(pt, session->itrace_synth_opts);
+ if (err)
+ goto err_delete_thread;
+ }
+
if (pt->synth_opts.calls)
pt->branches_filter |= PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
PERF_IP_FLAG_TRACE_END;
err_free:
addr_filters__exit(&pt->filts);
zfree(&pt->filter);
+ zfree(&pt->time_ranges);
free(pt);
return err;
}
#include "genelf.h"
#include "../builtin.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
struct jit_buf_desc {
struct perf_data *output;
#include "strlist.h"
#include "thread.h"
#include "vdso.h"
+#include "util.h"
#include <stdbool.h>
#include <sys/types.h>
#include <sys/stat.h>
#include "asm/bug.h"
#include "bpf-event.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
#include <symbol/kallsyms.h>
#include <linux/mman.h>
return -ENOMEM;
map->start = event->ksymbol_event.addr;
- map->pgoff = map->start;
map->end = map->start + event->ksymbol_event.len;
map_groups__insert(&machine->kmaps, map);
}
- sym = symbol__new(event->ksymbol_event.addr, event->ksymbol_event.len,
+ sym = symbol__new(map->map_ip(map, map->start),
+ event->ksymbol_event.len,
0, 0, event->ksymbol_event.name);
if (!sym)
return -ENOMEM;
return NULL;
tmp = fgets(version, sizeof(version), file);
- if (!tmp)
- *version = '\0';
fclose(file);
+ if (!tmp)
+ return NULL;
name = strstr(version, prefix);
if (!name)
size_t map__fprintf_dsoname(struct map *map, FILE *fp)
{
+ char buf[symbol_conf.pad_output_len_dso + 1];
const char *dsoname = "[unknown]";
if (map && map->dso) {
dsoname = map->dso->name;
}
+ if (symbol_conf.pad_output_len_dso) {
+ scnprintf_pad(buf, symbol_conf.pad_output_len_dso, "%s", dsoname);
+ dsoname = buf;
+ }
+
return fprintf(fp, "%s", dsoname);
}
struct map *map_groups__find_by_name(struct map_groups *mg, const char *name);
+int map_groups__merge_in(struct map_groups *kmaps, struct map *new_map);
+
#endif // __PERF_MAP_GROUPS_H
#include "pmu-events/pmu-events.h"
#include "strlist.h"
#include <assert.h>
-#include <ctype.h>
+#include <linux/ctype.h>
struct metric_event *metricgroup__lookup(struct rblist *metric_events,
struct perf_evsel *evsel,
const char *metric_expr;
};
-static struct perf_evsel *find_evsel(struct perf_evlist *perf_evlist,
- const char **ids,
- int idnum,
- struct perf_evsel **metric_events)
+static bool record_evsel(int *ind, struct perf_evsel **start,
+ int idnum,
+ struct perf_evsel **metric_events,
+ struct perf_evsel *ev)
+{
+ metric_events[*ind] = ev;
+ if (*ind == 0)
+ *start = ev;
+ if (++*ind == idnum) {
+ metric_events[*ind] = NULL;
+ return true;
+ }
+ return false;
+}
+
+static struct perf_evsel *find_evsel_group(struct perf_evlist *perf_evlist,
+ const char **ids,
+ int idnum,
+ struct perf_evsel **metric_events)
{
struct perf_evsel *ev, *start = NULL;
int ind = 0;
evlist__for_each_entry (perf_evlist, ev) {
+ if (ev->collect_stat)
+ continue;
if (!strcmp(ev->name, ids[ind])) {
- metric_events[ind] = ev;
- if (ind == 0)
- start = ev;
- if (++ind == idnum) {
- metric_events[ind] = NULL;
+ if (record_evsel(&ind, &start, idnum,
+ metric_events, ev))
return start;
- }
} else {
+ /*
+ * We saw some other event that is not
+ * in our list of events. Discard
+ * the whole match and start again.
+ */
ind = 0;
start = NULL;
+ if (!strcmp(ev->name, ids[ind])) {
+ if (record_evsel(&ind, &start, idnum,
+ metric_events, ev))
+ return start;
+ }
}
}
/*
ret = -ENOMEM;
break;
}
- evsel = find_evsel(perf_evlist, eg->ids, eg->idnum,
- metric_events);
+ evsel = find_evsel_group(perf_evlist, eg->ids, eg->idnum,
+ metric_events);
if (!evsel) {
pr_debug("Cannot resolve %s: %s\n",
eg->metric_name, eg->metric_expr);
struct mep *me;
char *s;
+ g = skip_spaces(g);
if (*g == 0)
g = "No_group";
- while (isspace(*g))
- g++;
if (filter && !strstr(g, filter))
continue;
if (raw)
struct mep *me = container_of(node, struct mep, nd);
if (metricgroups)
- printf("%s%s%s", me->name, metrics ? ":" : "", raw ? " " : "\n");
+ printf("%s%s%s", me->name, metrics && !raw ? ":" : "", raw ? " " : "\n");
if (metrics)
metricgroup__print_strlist(me->metrics, raw);
next = rb_next(node);
const char **ids;
int idnum;
struct egroup *eg;
+ bool no_group = false;
pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
strbuf_addf(events, ",");
for (j = 0; j < idnum; j++) {
pr_debug("found event %s\n", ids[j]);
+ /*
+ * Duration time maps to a software event and can make
+ * groups not count. Always use it outside a
+ * group.
+ */
+ if (!strcmp(ids[j], "duration_time")) {
+ if (j > 0)
+ strbuf_addf(events, "}:W,");
+ strbuf_addf(events, "duration_time");
+ no_group = true;
+ continue;
+ }
strbuf_addf(events, "%s%s",
- j == 0 ? "{" : ",",
+ j == 0 || no_group ? "{" : ",",
ids[j]);
+ no_group = false;
}
- strbuf_addf(events, "}:W");
+ if (!no_group)
+ strbuf_addf(events, "}:W");
eg = malloc(sizeof(struct egroup));
if (!eg) {
#ifdef HAVE_PERF_REGS_SUPPORT
#include <perf_regs.h>
+#define DWARF_MINIMAL_REGS ((1ULL << PERF_REG_IP) | (1ULL << PERF_REG_SP))
+
int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
#else
#define PERF_REGS_MASK 0
#define PERF_REGS_MAX 0
+#define DWARF_MINIMAL_REGS PERF_REGS_MASK
+
static inline const char *perf_reg_name(int id __maybe_unused)
{
return NULL;
// SPDX-License-Identifier: GPL-2.0
#include <linux/list.h>
#include <linux/compiler.h>
+#include <linux/string.h>
#include <sys/types.h>
#include <errno.h>
#include <fcntl.h>
buf[ret] = 0;
/* Remove trailing newline from sysfs file */
- rtrim(buf);
+ strim(buf);
return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
NULL, NULL, NULL);
return map;
}
+static bool pmu_uncore_alias_match(const char *pmu_name, const char *name)
+{
+ char *tmp = NULL, *tok, *str;
+ bool res;
+
+ str = strdup(pmu_name);
+ if (!str)
+ return false;
+
+ /*
+ * uncore alias may be from different PMU with common prefix
+ */
+ tok = strtok_r(str, ",", &tmp);
+ if (strncmp(pmu_name, tok, strlen(tok))) {
+ res = false;
+ goto out;
+ }
+
+ /*
+ * Match more complex aliases where the alias name is a comma-delimited
+ * list of tokens, orderly contained in the matching PMU name.
+ *
+ * Example: For alias "socket,pmuname" and PMU "socketX_pmunameY", we
+ * match "socket" in "socketX_pmunameY" and then "pmuname" in
+ * "pmunameY".
+ */
+ for (; tok; name += strlen(tok), tok = strtok_r(NULL, ",", &tmp)) {
+ name = strstr(name, tok);
+ if (!name) {
+ res = false;
+ goto out;
+ }
+ }
+
+ res = true;
+out:
+ free(str);
+ return res;
+}
+
/*
* From the pmu_events_map, find the table of PMU events that corresponds
* to the current running CPU. Then, add all PMU events from that table
{
int i;
struct pmu_events_map *map;
- struct pmu_event *pe;
const char *name = pmu->name;
- const char *pname;
map = perf_pmu__find_map(pmu);
if (!map)
*/
i = 0;
while (1) {
+ const char *cpu_name = is_arm_pmu_core(name) ? name : "cpu";
+ struct pmu_event *pe = &map->table[i++];
+ const char *pname = pe->pmu ? pe->pmu : cpu_name;
- pe = &map->table[i++];
if (!pe->name) {
if (pe->metric_group || pe->metric_name)
continue;
break;
}
- if (!is_arm_pmu_core(name)) {
- pname = pe->pmu ? pe->pmu : "cpu";
-
- /*
- * uncore alias may be from different PMU
- * with common prefix
- */
- if (pmu_is_uncore(name) &&
- !strncmp(pname, name, strlen(pname)))
- goto new_alias;
+ if (pmu_is_uncore(name) &&
+ pmu_uncore_alias_match(pname, name))
+ goto new_alias;
- if (strcmp(pname, name))
- continue;
- }
+ if (strcmp(pname, name))
+ continue;
new_alias:
/* need type casts to override 'const' */
break;
s += wlen;
column += n;
- s = ltrim(s);
+ s = skip_spaces(s);
}
}
// SPDX-License-Identifier: GPL-2.0
#include "print_binary.h"
#include <linux/log2.h>
-#include "sane_ctype.h"
+#include <linux/ctype.h>
int binary__fprintf(unsigned char *data, size_t len,
size_t bytes_per_line, binary__fprintf_t printer,
#include "session.h"
#include "string2.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
#define PERFPROBE_GROUP "probe"
#include <stdbool.h>
#include "intlist.h"
#include "probe-event.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
#define MAX_PROBE_BUFFER 1024
#define MAX_PROBES 128
#
util/python.c
-util/ctype.c
+../lib/ctype.c
util/evlist.c
util/evsel.c
util/cpumap.c
../lib/bitmap.c
../lib/find_bit.c
../lib/hweight.c
+../lib/string.c
../lib/vsprintf.c
util/thread_map.c
util/util.c
#include "print_binary.h"
#include "thread_map.h"
#include "mmap.h"
+#include "util.h"
#if PY_MAJOR_VERSION < 3
#define _PyUnicode_FromString(arg) \
* see Documentation/perf.data-file-format.txt.
* PERF_RECORD_AUXTRACE_INFO:
* Defines a table of contains for PERF_RECORD_AUXTRACE records. This
- * record is generated during 'perf record' command. Each record contains up
- * to 256 entries describing offset and size of the AUXTRACE data in the
+ * record is generated during 'perf record' command. Each record contains
+ * up to 256 entries describing offset and size of the AUXTRACE data in the
* perf.data file.
* PERF_RECORD_AUXTRACE_ERROR:
* Indicates an error during AUXTRACE collection such as buffer overflow.
return rc;
}
-/* Display s390 CPU measurement facility basic-sampling data entry */
+/* Display s390 CPU measurement facility basic-sampling data entry
+ * Data written on s390 in big endian byte order and contains bit
+ * fields across byte boundaries.
+ */
static bool s390_cpumsf_basic_show(const char *color, size_t pos,
- struct hws_basic_entry *basic)
+ struct hws_basic_entry *basicp)
{
+ struct hws_basic_entry *basic = basicp;
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ struct hws_basic_entry local;
+ unsigned long long word = be64toh(*(unsigned long long *)basicp);
+
+ memset(&local, 0, sizeof(local));
+ local.def = be16toh(basicp->def);
+ local.prim_asn = word & 0xffff;
+ local.CL = word >> 30 & 0x3;
+ local.I = word >> 32 & 0x1;
+ local.AS = word >> 33 & 0x3;
+ local.P = word >> 35 & 0x1;
+ local.W = word >> 36 & 0x1;
+ local.T = word >> 37 & 0x1;
+ local.U = word >> 40 & 0xf;
+ local.ia = be64toh(basicp->ia);
+ local.gpp = be64toh(basicp->gpp);
+ local.hpp = be64toh(basicp->hpp);
+ basic = &local;
+#endif
if (basic->def != 1) {
pr_err("Invalid AUX trace basic entry [%#08zx]\n", pos);
return false;
return true;
}
-/* Display s390 CPU measurement facility diagnostic-sampling data entry */
+/* Display s390 CPU measurement facility diagnostic-sampling data entry.
+ * Data written on s390 in big endian byte order and contains bit
+ * fields across byte boundaries.
+ */
static bool s390_cpumsf_diag_show(const char *color, size_t pos,
- struct hws_diag_entry *diag)
+ struct hws_diag_entry *diagp)
{
+ struct hws_diag_entry *diag = diagp;
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ struct hws_diag_entry local;
+ unsigned long long word = be64toh(*(unsigned long long *)diagp);
+
+ local.def = be16toh(diagp->def);
+ local.I = word >> 32 & 0x1;
+ diag = &local;
+#endif
if (diag->def < S390_CPUMSF_DIAG_DEF_FIRST) {
pr_err("Invalid AUX trace diagnostic entry [%#08zx]\n", pos);
return false;
}
/* Return TOD timestamp contained in an trailer entry */
-static unsigned long long trailer_timestamp(struct hws_trailer_entry *te)
+static unsigned long long trailer_timestamp(struct hws_trailer_entry *te,
+ int idx)
{
/* te->t set: TOD in STCKE format, bytes 8-15
* to->t not set: TOD in STCK format, bytes 0-7
*/
unsigned long long ts;
- memcpy(&ts, &te->timestamp[te->t], sizeof(ts));
- return ts;
+ memcpy(&ts, &te->timestamp[idx], sizeof(ts));
+ return be64toh(ts);
}
/* Display s390 CPU measurement facility trailer entry */
static bool s390_cpumsf_trailer_show(const char *color, size_t pos,
struct hws_trailer_entry *te)
{
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ struct hws_trailer_entry local;
+ const unsigned long long flags = be64toh(te->flags);
+
+ memset(&local, 0, sizeof(local));
+ local.f = flags >> 63 & 0x1;
+ local.a = flags >> 62 & 0x1;
+ local.t = flags >> 61 & 0x1;
+ local.bsdes = be16toh((flags >> 16 & 0xffff));
+ local.dsdes = be16toh((flags & 0xffff));
+ memcpy(&local.timestamp, te->timestamp, sizeof(te->timestamp));
+ local.overflow = be64toh(te->overflow);
+ local.clock_base = be64toh(te->progusage[0]) >> 63 & 1;
+ local.progusage2 = be64toh(te->progusage2);
+ te = &local;
+#endif
if (te->bsdes != sizeof(struct hws_basic_entry)) {
pr_err("Invalid AUX trace trailer entry [%#08zx]\n", pos);
return false;
}
color_fprintf(stdout, color, " [%#08zx] Trailer %c%c%c bsdes:%d"
" dsdes:%d Overflow:%lld Time:%#llx\n"
- "\t\tC:%d TOD:%#lx 1:%#llx 2:%#llx\n",
+ "\t\tC:%d TOD:%#lx\n",
pos,
te->f ? 'F' : ' ',
te->a ? 'A' : ' ',
te->t ? 'T' : ' ',
te->bsdes, te->dsdes, te->overflow,
- trailer_timestamp(te), te->clock_base, te->progusage2,
- te->progusage[0], te->progusage[1]);
+ trailer_timestamp(te, te->clock_base),
+ te->clock_base, te->progusage2);
return true;
}
*dsdes = *bsdes = 0;
if (len & (S390_CPUMSF_PAGESZ - 1)) /* Illegal size */
return false;
- if (basic->def != 1) /* No basic set entry, must be first */
+ if (be16toh(basic->def) != 1) /* No basic set entry, must be first */
return false;
/* Check for trailer entry at end of SDB */
te = (struct hws_trailer_entry *)(buf + S390_CPUMSF_PAGESZ
- sizeof(*te));
- *bsdes = te->bsdes;
- *dsdes = te->dsdes;
+ *bsdes = be16toh(te->bsdes);
+ *dsdes = be16toh(te->dsdes);
if (!te->bsdes && !te->dsdes) {
/* Very old hardware, use CPUID */
switch (machine_type) {
static unsigned long long get_trailer_time(const unsigned char *buf)
{
struct hws_trailer_entry *te;
- unsigned long long aux_time;
+ unsigned long long aux_time, progusage2;
+ bool clock_base;
te = (struct hws_trailer_entry *)(buf + S390_CPUMSF_PAGESZ
- sizeof(*te));
- if (!te->clock_base) /* TOD_CLOCK_BASE value missing */
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ clock_base = be64toh(te->progusage[0]) >> 63 & 0x1;
+ progusage2 = be64toh(te->progusage[1]);
+#else
+ clock_base = te->clock_base;
+ progusage2 = te->progusage2;
+#endif
+ if (!clock_base) /* TOD_CLOCK_BASE value missing */
return 0;
/* Correct calculation to convert time stamp in trailer entry to
* nano seconds (taken from arch/s390 function tod_to_ns()).
* TOD_CLOCK_BASE is stored in trailer entry member progusage2.
*/
- aux_time = trailer_timestamp(te) - te->progusage2;
+ aux_time = trailer_timestamp(te, clock_base) - progusage2;
aux_time = (aux_time >> 9) * 125 + (((aux_time & 0x1ff) * 125) >> 9);
return aux_time;
}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _PERF_SANE_CTYPE_H
-#define _PERF_SANE_CTYPE_H
-
-extern const char *graph_line;
-extern const char *graph_dotted_line;
-extern const char *spaces;
-extern const char *dots;
-
-/* Sane ctype - no locale, and works with signed chars */
-#undef isascii
-#undef isspace
-#undef isdigit
-#undef isxdigit
-#undef isalpha
-#undef isprint
-#undef isalnum
-#undef islower
-#undef isupper
-#undef tolower
-#undef toupper
-
-extern unsigned char sane_ctype[256];
-#define GIT_SPACE 0x01
-#define GIT_DIGIT 0x02
-#define GIT_ALPHA 0x04
-#define GIT_GLOB_SPECIAL 0x08
-#define GIT_REGEX_SPECIAL 0x10
-#define GIT_PRINT_EXTRA 0x20
-#define GIT_PRINT 0x3E
-#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0)
-#define isascii(x) (((x) & ~0x7f) == 0)
-#define isspace(x) sane_istest(x,GIT_SPACE)
-#define isdigit(x) sane_istest(x,GIT_DIGIT)
-#define isxdigit(x) \
- (sane_istest(toupper(x), GIT_ALPHA | GIT_DIGIT) && toupper(x) < 'G')
-#define isalpha(x) sane_istest(x,GIT_ALPHA)
-#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT)
-#define isprint(x) sane_istest(x,GIT_PRINT)
-#define islower(x) (sane_istest(x,GIT_ALPHA) && (x & 0x20))
-#define isupper(x) (sane_istest(x,GIT_ALPHA) && !(x & 0x20))
-#define tolower(x) sane_case((unsigned char)(x), 0x20)
-#define toupper(x) sane_case((unsigned char)(x), 0)
-
-static inline int sane_case(int x, int high)
-{
- if (sane_istest(x, GIT_ALPHA))
- x = (x & ~0x20) | high;
- return x;
-}
-
-#endif /* _PERF_SANE_CTYPE_H */
PyObject *sample_handler;
PyObject *call_path_handler;
PyObject *call_return_handler;
+ PyObject *synth_handler;
bool db_export_mode;
};
return PyTuple_SetItem(t, pos, _PyUnicode_FromString(s));
}
+static int tuple_set_bytes(PyObject *t, unsigned int pos, void *bytes,
+ unsigned int sz)
+{
+ return PyTuple_SetItem(t, pos, _PyBytes_FromStringAndSize(bytes, sz));
+}
+
static int python_export_evsel(struct db_export *dbe, struct perf_evsel *evsel)
{
struct tables *tables = container_of(dbe, struct tables, dbe);
return 0;
}
-static int python_export_sample(struct db_export *dbe,
- struct export_sample *es)
+static void python_export_sample_table(struct db_export *dbe,
+ struct export_sample *es)
{
struct tables *tables = container_of(dbe, struct tables, dbe);
PyObject *t;
- t = tuple_new(22);
+ t = tuple_new(24);
tuple_set_u64(t, 0, es->db_id);
tuple_set_u64(t, 1, es->evsel->db_id);
tuple_set_s32(t, 19, es->sample->flags & PERF_BRANCH_MASK);
tuple_set_s32(t, 20, !!(es->sample->flags & PERF_IP_FLAG_IN_TX));
tuple_set_u64(t, 21, es->call_path_id);
+ tuple_set_u64(t, 22, es->sample->insn_cnt);
+ tuple_set_u64(t, 23, es->sample->cyc_cnt);
call_object(tables->sample_handler, t, "sample_table");
Py_DECREF(t);
+}
+
+static void python_export_synth(struct db_export *dbe, struct export_sample *es)
+{
+ struct tables *tables = container_of(dbe, struct tables, dbe);
+ PyObject *t;
+
+ t = tuple_new(3);
+
+ tuple_set_u64(t, 0, es->db_id);
+ tuple_set_u64(t, 1, es->evsel->attr.config);
+ tuple_set_bytes(t, 2, es->sample->raw_data, es->sample->raw_size);
+
+ call_object(tables->synth_handler, t, "synth_data");
+
+ Py_DECREF(t);
+}
+
+static int python_export_sample(struct db_export *dbe,
+ struct export_sample *es)
+{
+ struct tables *tables = container_of(dbe, struct tables, dbe);
+
+ python_export_sample_table(dbe, es);
+
+ if (es->evsel->attr.type == PERF_TYPE_SYNTH && tables->synth_handler)
+ python_export_synth(dbe, es);
return 0;
}
u64 comm_db_id = cr->comm ? cr->comm->db_id : 0;
PyObject *t;
- t = tuple_new(12);
+ t = tuple_new(14);
tuple_set_u64(t, 0, cr->db_id);
tuple_set_u64(t, 1, cr->thread->db_id);
tuple_set_u64(t, 9, cr->cp->parent->db_id);
tuple_set_s32(t, 10, cr->flags);
tuple_set_u64(t, 11, cr->parent_db_id);
+ tuple_set_u64(t, 12, cr->insn_count);
+ tuple_set_u64(t, 13, cr->cyc_count);
call_object(tables->call_return_handler, t, "call_return_table");
SET_TABLE_HANDLER(sample);
SET_TABLE_HANDLER(call_path);
SET_TABLE_HANDLER(call_return);
+
+ /*
+ * Synthesized events are samples but with architecture-specific data
+ * stored in sample->raw_data. They are exported via
+ * python_export_sample() and consequently do not need a separate export
+ * callback.
+ */
+ tables->synth_handler = get_handler("synth_data");
}
#if PY_MAJOR_VERSION < 3
vars[var] = sub("-fcf-protection", "", vars[var])
if not clang_has_option("-fstack-clash-protection"):
vars[var] = sub("-fstack-clash-protection", "", vars[var])
+ if not clang_has_option("-fstack-protector-strong"):
+ vars[var] = sub("-fstack-protector-strong", "", vars[var])
from distutils.core import setup, Extension
char fn[256];
snprintf(fn, sizeof fn,
- "devices/system/cpu/cpu%d/topology/thread_siblings",
- cpu);
+ "devices/system/cpu/cpu%d/topology/core_cpus", cpu);
+ if (access(fn, F_OK) == -1) {
+ snprintf(fn, sizeof fn,
+ "devices/system/cpu/cpu%d/topology/thread_siblings",
+ cpu);
+ }
if (sysfs__read_str(fn, &str, &strlen) < 0)
continue;
/* Entry is hex, but does not have 0x, so need custom parser */
/* HISTC_WEIGHTED_DIFF */
s64 wdiff;
+
+ /* PERF_HPP_DIFF__CYCLES */
+ s64 cycles;
};
};
long time;
struct hists *hists;
struct mem_info *mem_info;
+ struct block_info *block_info;
void *raw_data;
u32 raw_size;
int num_res;
u8 se_width_idx;
};
+struct block_hist {
+ struct hists block_hists;
+ struct perf_hpp_list block_list;
+ struct perf_hpp_fmt block_fmt;
+ int block_idx;
+ bool valid;
+ struct hist_entry he;
+};
+
extern struct sort_entry sort_thread;
extern struct list_head hist_entry__sort_list;
#include <string.h>
#include <linux/kernel.h>
+#include <linux/string.h>
#include "util/dso.h"
#include "util/util.h"
#include "util/debug.h"
#include "util/callchain.h"
+#include "util/symbol_conf.h"
#include "srcline.h"
#include "string2.h"
#include "symbol.h"
}
if (a2l == NULL) {
- pr_warning("addr2line_init failed for %s\n", dso_name);
+ if (!symbol_conf.disable_add2line_warn)
+ pr_warning("addr2line_init failed for %s\n", dso_name);
return 0;
}
char *srcline;
struct symbol *inline_sym;
- rtrim(funcname);
+ strim(funcname);
if (getline(&filename, &filelen, fp) == -1)
goto out;
#include <stdio.h>
#include <inttypes.h>
+#include <linux/string.h>
#include <linux/time64.h>
#include <math.h>
#include "color.h"
#include "thread_map.h"
#include "cpumap.h"
#include "string2.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
#include "cgroup.h"
#include <math.h>
#include <api/fs/fs.h>
{
switch (config->aggr_mode) {
case AGGR_CORE:
- fprintf(config->output, "S%d-C%*d%s%*d%s",
+ fprintf(config->output, "S%d-D%d-C%*d%s%*d%s",
cpu_map__id_to_socket(id),
+ cpu_map__id_to_die(id),
config->csv_output ? 0 : -8,
cpu_map__id_to_cpu(id),
config->csv_sep,
nr,
config->csv_sep);
break;
+ case AGGR_DIE:
+ fprintf(config->output, "S%d-D%*d%s%*d%s",
+ cpu_map__id_to_socket(id << 16),
+ config->csv_output ? 0 : -8,
+ cpu_map__id_to_die(id << 16),
+ config->csv_sep,
+ config->csv_output ? 0 : 4,
+ nr,
+ config->csv_sep);
+ break;
case AGGR_SOCKET:
fprintf(config->output, "S%*d%s%*d%s",
config->csv_output ? 0 : -5,
break;
case AGGR_NONE:
if (evsel->percore) {
- fprintf(config->output, "S%d-C%*d%s",
+ fprintf(config->output, "S%d-D%d-C%*d%s",
cpu_map__id_to_socket(id),
+ cpu_map__id_to_die(id),
config->csv_output ? 0 : -5,
cpu_map__id_to_cpu(id), config->csv_sep);
} else {
return;
}
snprintf(buf, sizeof(buf), fmt, val);
- ends = vals = ltrim(buf);
+ ends = vals = skip_spaces(buf);
while (isdigit(*ends) || *ends == '.')
ends++;
*ends = 0;
- while (isspace(*unit))
- unit++;
- fprintf(out, "%s%s%s%s", config->csv_sep, vals, config->csv_sep, unit);
+ fprintf(out, "%s%s%s%s", config->csv_sep, vals, config->csv_sep, skip_spaces(unit));
}
/* Filter out some columns that don't work well in metrics only mode */
return;
unit = fixunit(tbuf, os->evsel, unit);
snprintf(buf, sizeof buf, fmt, val);
- ends = vals = ltrim(buf);
+ ends = vals = skip_spaces(buf);
while (isdigit(*ends) || *ends == '.')
ends++;
*ends = 0;
[AGGR_THREAD] = 1,
[AGGR_NONE] = 1,
[AGGR_SOCKET] = 2,
+ [AGGR_DIE] = 2,
[AGGR_CORE] = 2,
};
alias->scale != counter->scale ||
alias->cgrp != counter->cgrp ||
strcmp(alias->unit, counter->unit) ||
- perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
+ perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter) ||
+ !strcmp(alias->pmu_name, counter->pmu_name))
break;
alias->merged_stat = true;
cb(config, alias, data, false);
}
static int aggr_header_lens[] = {
- [AGGR_CORE] = 18,
+ [AGGR_CORE] = 24,
+ [AGGR_DIE] = 18,
[AGGR_SOCKET] = 12,
[AGGR_NONE] = 6,
[AGGR_THREAD] = 24,
static const char *aggr_header_csv[] = {
[AGGR_CORE] = "core,cpus,",
+ [AGGR_DIE] = "die,cpus",
[AGGR_SOCKET] = "socket,cpus",
[AGGR_NONE] = "cpu,",
[AGGR_THREAD] = "comm-pid,",
if (!metric_only)
fprintf(output, " counts %*s events\n", unit_width, "unit");
break;
+ case AGGR_DIE:
+ fprintf(output, "# time die cpus");
+ if (!metric_only)
+ fprintf(output, " counts %*s events\n", unit_width, "unit");
+ break;
case AGGR_CORE:
- fprintf(output, "# time core cpus");
+ fprintf(output, "# time core cpus");
if (!metric_only)
fprintf(output, " counts %*s events\n", unit_width, "unit");
break;
switch (config->aggr_mode) {
case AGGR_CORE:
+ case AGGR_DIE:
case AGGR_SOCKET:
print_aggr(config, evlist, prefix);
break;
/*
* AGGR_GLOBAL: Use CPU 0
* AGGR_SOCKET: Use first CPU of socket
+ * AGGR_DIE: Use first CPU of die
* AGGR_CORE: Use first CPU of core
* AGGR_NONE: Use matching CPU
* AGGR_THREAD: Not supported?
struct perf_evsel *c2;
evlist__for_each_entry (evsel_list, c2) {
- if (!strcasecmp(c2->name, name))
+ if (!strcasecmp(c2->name, name) && !c2->collect_stat)
return c2;
}
return NULL;
if (leader) {
/* Search in group */
for_each_group_member (oc, leader) {
- if (!strcasecmp(oc->name, metric_names[i])) {
+ if (!strcasecmp(oc->name, metric_names[i]) &&
+ !oc->collect_stat) {
found = true;
break;
}
double ratio;
int i;
void *ctxp = out->ctx;
+ char *n, *pn;
expr__ctx_init(&pctx);
expr__add_id(&pctx, name, avg);
stats = &v->stats;
scale = 1.0;
}
- expr__add_id(&pctx, metric_events[i]->name, avg_stats(stats)*scale);
+
+ n = strdup(metric_events[i]->name);
+ if (!n)
+ return;
+ /*
+ * This display code with --no-merge adds [cpu] postfixes.
+ * These are not supported by the parser. Remove everything
+ * after the space.
+ */
+ pn = strchr(n, ' ');
+ if (pn)
+ *pn = 0;
+ expr__add_id(&pctx, n, avg_stats(stats)*scale);
}
if (!metric_events[i]) {
const char *p = metric_expr;
(metric_name ? metric_name : name) : "", 0);
} else
print_metric(config, ctxp, NULL, NULL, "", 0);
+
+ for (i = 1; i < pctx.num_ids; i++)
+ free((void *)pctx.ids[i].name);
}
void perf_stat__print_shadow_stats(struct perf_stat_config *config,
switch (config->aggr_mode) {
case AGGR_THREAD:
case AGGR_CORE:
+ case AGGR_DIE:
case AGGR_SOCKET:
case AGGR_NONE:
if (!evsel->snapshot)
AGGR_NONE,
AGGR_GLOBAL,
AGGR_SOCKET,
+ AGGR_DIE,
AGGR_CORE,
AGGR_THREAD,
AGGR_UNSET,
#include "strfilter.h"
#include <errno.h>
-#include "sane_ctype.h"
+#include <linux/ctype.h>
+#include <linux/string.h>
/* Operators */
static const char *OP_and = "&"; /* Logical AND */
{
const char *p;
- while (isspace(*s)) /* Skip spaces */
- s++;
+ s = skip_spaces(s);
if (*s == '\0') {
p = s;
#include <linux/string.h>
#include <stdlib.h>
-#include "sane_ctype.h"
+#include <linux/ctype.h>
+
+const char *graph_dotted_line =
+ "---------------------------------------------------------------------"
+ "---------------------------------------------------------------------"
+ "---------------------------------------------------------------------";
+const char *dots =
+ "....................................................................."
+ "....................................................................."
+ ".....................................................................";
#define K 1024LL
/*
return -1;
}
-/*
- * Helper function for splitting a string into an argv-like array.
- * originally copied from lib/argv_split.c
- */
-static const char *skip_sep(const char *cp)
-{
- while (*cp && isspace(*cp))
- cp++;
-
- return cp;
-}
-
-static const char *skip_arg(const char *cp)
-{
- while (*cp && !isspace(*cp))
- cp++;
-
- return cp;
-}
-
-static int count_argc(const char *str)
-{
- int count = 0;
-
- while (*str) {
- str = skip_sep(str);
- if (*str) {
- count++;
- str = skip_arg(str);
- }
- }
-
- return count;
-}
-
-/**
- * argv_free - free an argv
- * @argv - the argument vector to be freed
- *
- * Frees an argv and the strings it points to.
- */
-void argv_free(char **argv)
-{
- char **p;
- for (p = argv; *p; p++) {
- free(*p);
- *p = NULL;
- }
-
- free(argv);
-}
-
-/**
- * argv_split - split a string at whitespace, returning an argv
- * @str: the string to be split
- * @argcp: returned argument count
- *
- * Returns an array of pointers to strings which are split out from
- * @str. This is performed by strictly splitting on white-space; no
- * quote processing is performed. Multiple whitespace characters are
- * considered to be a single argument separator. The returned array
- * is always NULL-terminated. Returns NULL on memory allocation
- * failure.
- */
-char **argv_split(const char *str, int *argcp)
-{
- int argc = count_argc(str);
- char **argv = calloc(argc + 1, sizeof(*argv));
- char **argvp;
-
- if (argv == NULL)
- goto out;
-
- if (argcp)
- *argcp = argc;
-
- argvp = argv;
-
- while (*str) {
- str = skip_sep(str);
-
- if (*str) {
- const char *p = str;
- char *t;
-
- str = skip_arg(str);
-
- t = strndup(p, str-p);
- if (t == NULL)
- goto fail;
- *argvp++ = t;
- }
- }
- *argvp = NULL;
-
-out:
- return argv;
-
-fail:
- argv_free(argv);
- return NULL;
-}
-
/* Character class matching */
static bool __match_charclass(const char *pat, char c, const char **npat)
{
return 0;
}
-/**
- * strxfrchar - Locate and replace character in @s
- * @s: The string to be searched/changed.
- * @from: Source character to be replaced.
- * @to: Destination character.
- *
- * Return pointer to the changed string.
- */
-char *strxfrchar(char *s, char from, char to)
-{
- char *p = s;
-
- while ((p = strchr(p, from)) != NULL)
- *p++ = to;
-
- return s;
-}
-
-/**
- * ltrim - Removes leading whitespace from @s.
- * @s: The string to be stripped.
- *
- * Return pointer to the first non-whitespace character in @s.
- */
-char *ltrim(char *s)
-{
- while (isspace(*s))
- s++;
-
- return s;
-}
-
-/**
- * rtrim - Removes trailing whitespace from @s.
- * @s: The string to be stripped.
- *
- * Note that the first trailing whitespace is replaced with a %NUL-terminator
- * in the given string @s. Returns @s.
- */
-char *rtrim(char *s)
-{
- size_t size = strlen(s);
- char *end;
-
- if (!size)
- return s;
-
- end = s + size - 1;
- while (end >= s && isspace(*end))
- end--;
- *(end + 1) = '\0';
-
- return s;
-}
-
char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints)
{
/*
#ifndef PERF_STRING_H
#define PERF_STRING_H
+#include <linux/string.h>
#include <linux/types.h>
#include <stddef.h>
#include <string.h>
+extern const char *graph_dotted_line;
+extern const char *dots;
+
s64 perf_atoll(const char *str);
-char **argv_split(const char *str, int *argcp);
-void argv_free(char **argv);
bool strglobmatch(const char *str, const char *pat);
bool strglobmatch_nocase(const char *str, const char *pat);
bool strlazymatch(const char *str, const char *pat);
return strpbrk(str, "*?[") != NULL;
}
int strtailcmp(const char *s1, const char *s2);
-char *strxfrchar(char *s, char from, char to);
-
-char *ltrim(char *s);
-char *rtrim(char *s);
-
-static inline char *trim(char *s)
-{
- return ltrim(rtrim(s));
-}
char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints);
#include "machine.h"
#include "vdso.h"
#include "debug.h"
-#include "sane_ctype.h"
+#include "util.h"
+#include <linux/ctype.h>
#include <symbol/kallsyms.h>
#ifndef EM_AARCH64
int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
enum dso_binary_type type)
{
- int err = -1;
GElf_Ehdr ehdr;
Elf *elf;
int fd;
elf_end(elf);
out_close:
close(fd);
- return err;
+ return -1;
}
/**
#include "namespaces.h"
#include "header.h"
#include "path.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
#include <elf.h>
#include <limits.h>
return 0;
}
+/*
+ * Merges map into map_groups by splitting the new map
+ * within the existing map regions.
+ */
+int map_groups__merge_in(struct map_groups *kmaps, struct map *new_map)
+{
+ struct map *old_map;
+ LIST_HEAD(merged);
+
+ for (old_map = map_groups__first(kmaps); old_map;
+ old_map = map_groups__next(old_map)) {
+
+ /* no overload with this one */
+ if (new_map->end < old_map->start ||
+ new_map->start >= old_map->end)
+ continue;
+
+ if (new_map->start < old_map->start) {
+ /*
+ * |new......
+ * |old....
+ */
+ if (new_map->end < old_map->end) {
+ /*
+ * |new......| -> |new..|
+ * |old....| -> |old....|
+ */
+ new_map->end = old_map->start;
+ } else {
+ /*
+ * |new.............| -> |new..| |new..|
+ * |old....| -> |old....|
+ */
+ struct map *m = map__clone(new_map);
+
+ if (!m)
+ return -ENOMEM;
+
+ m->end = old_map->start;
+ list_add_tail(&m->node, &merged);
+ new_map->start = old_map->end;
+ }
+ } else {
+ /*
+ * |new......
+ * |old....
+ */
+ if (new_map->end < old_map->end) {
+ /*
+ * |new..| -> x
+ * |old.........| -> |old.........|
+ */
+ map__put(new_map);
+ new_map = NULL;
+ break;
+ } else {
+ /*
+ * |new......| -> |new...|
+ * |old....| -> |old....|
+ */
+ new_map->start = old_map->end;
+ }
+ }
+ }
+
+ while (!list_empty(&merged)) {
+ old_map = list_entry(merged.next, struct map, node);
+ list_del_init(&old_map->node);
+ map_groups__insert(kmaps, old_map);
+ map__put(old_map);
+ }
+
+ if (new_map) {
+ map_groups__insert(kmaps, new_map);
+ map__put(new_map);
+ }
+ return 0;
+}
+
static int dso__load_kcore(struct dso *dso, struct map *map,
const char *kallsyms_filename)
{
while (old_map) {
struct map *next = map_groups__next(old_map);
- if (old_map != map)
+ /*
+ * We need to preserve eBPF maps even if they are
+ * covered by kcore, because we need to access
+ * eBPF dso for source data.
+ */
+ if (old_map != map && !__map__is_bpf_prog(old_map))
map_groups__remove(kmaps, old_map);
old_map = next;
}
map_groups__remove(kmaps, map);
map_groups__insert(kmaps, map);
map__put(map);
+ map__put(new_map);
} else {
- map_groups__insert(kmaps, new_map);
+ /*
+ * Merge kcore map into existing maps,
+ * and ensure that current maps (eBPF)
+ * stay intact.
+ */
+ if (map_groups__merge_in(kmaps, new_map))
+ goto out_err;
}
-
- map__put(new_map);
}
if (machine__is(machine, "x86_64")) {
refcount_set(&mi->refcnt, 1);
return mi;
}
+
+struct block_info *block_info__get(struct block_info *bi)
+{
+ if (bi)
+ refcount_inc(&bi->refcnt);
+ return bi;
+}
+
+void block_info__put(struct block_info *bi)
+{
+ if (bi && refcount_dec_and_test(&bi->refcnt))
+ free(bi);
+}
+
+struct block_info *block_info__new(void)
+{
+ struct block_info *bi = zalloc(sizeof(*bi));
+
+ if (bi)
+ refcount_set(&bi->refcnt, 1);
+ return bi;
+}
refcount_t refcnt;
};
+struct block_info {
+ struct symbol *sym;
+ u64 start;
+ u64 end;
+ u64 cycles;
+ u64 cycles_aggr;
+ int num;
+ int num_aggr;
+ refcount_t refcnt;
+};
+
struct addr_location {
struct machine *machine;
struct thread *thread;
#define mem_info__zput(mi) __mem_info__zput(&mi)
+struct block_info *block_info__new(void);
+struct block_info *block_info__get(struct block_info *bi);
+void block_info__put(struct block_info *bi);
+
+static inline void __block_info__zput(struct block_info **bi)
+{
+ block_info__put(*bi);
+ *bi = NULL;
+}
+
+#define block_info__zput(bi) __block_info__zput(&bi)
+
#endif /* __PERF_SYMBOL */
hide_unresolved,
raw_trace,
report_hierarchy,
- inline_name;
+ report_block,
+ inline_name,
+ disable_add2line_warn;
const char *vmlinux_name,
*kallsyms_name,
*source_prefix,
*tid_list;
const char *symfs;
int res_sample;
+ int pad_output_len_dso;
};
extern struct symbol_conf symbol_conf;
* @timestamp: timestamp (if known)
* @ref: external reference (e.g. db_id of sample)
* @branch_count: the branch count when the entry was created
+ * @insn_count: the instruction count when the entry was created
+ * @cyc_count the cycle count when the entry was created
* @db_id: id used for db-export
* @cp: call path
* @no_call: a 'call' was not seen
u64 timestamp;
u64 ref;
u64 branch_count;
+ u64 insn_count;
+ u64 cyc_count;
u64 db_id;
struct call_path *cp;
bool no_call;
* @sz: current maximum stack size
* @trace_nr: current trace number
* @branch_count: running branch count
+ * @insn_count: running instruction count
+ * @cyc_count running cycle count
* @kernel_start: kernel start address
* @last_time: last timestamp
* @crp: call/return processor
size_t sz;
u64 trace_nr;
u64 branch_count;
+ u64 insn_count;
+ u64 cyc_count;
u64 kernel_start;
u64 last_time;
struct call_return_processor *crp;
cr.call_time = tse->timestamp;
cr.return_time = timestamp;
cr.branch_count = ts->branch_count - tse->branch_count;
+ cr.insn_count = ts->insn_count - tse->insn_count;
+ cr.cyc_count = ts->cyc_count - tse->cyc_count;
cr.db_id = tse->db_id;
cr.call_ref = tse->ref;
cr.return_ref = ref;
tse->timestamp = timestamp;
tse->ref = ref;
tse->branch_count = ts->branch_count;
+ tse->insn_count = ts->insn_count;
+ tse->cyc_count = ts->cyc_count;
tse->cp = cp;
tse->no_call = no_call;
tse->trace_end = trace_end;
true, false);
}
+static int thread_stack__pop_ks(struct thread *thread, struct thread_stack *ts,
+ struct perf_sample *sample, u64 ref)
+{
+ u64 tm = sample->time;
+ int err;
+
+ /* Return to userspace, so pop all kernel addresses */
+ while (thread_stack__in_kernel(ts)) {
+ err = thread_stack__call_return(thread, ts, --ts->cnt,
+ tm, ref, true);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
static int thread_stack__no_call_return(struct thread *thread,
struct thread_stack *ts,
struct perf_sample *sample,
if (ip >= ks && addr < ks) {
/* Return to userspace, so pop all kernel addresses */
- while (thread_stack__in_kernel(ts)) {
- err = thread_stack__call_return(thread, ts, --ts->cnt,
- tm, ref, true);
- if (err)
- return err;
- }
+ err = thread_stack__pop_ks(thread, ts, sample, ref);
+ if (err)
+ return err;
/* If the stack is empty, push the userspace address */
if (!ts->cnt) {
}
} else if (thread_stack__in_kernel(ts) && ip < ks) {
/* Return to userspace, so pop all kernel addresses */
- while (thread_stack__in_kernel(ts)) {
- err = thread_stack__call_return(thread, ts, --ts->cnt,
- tm, ref, true);
- if (err)
- return err;
- }
+ err = thread_stack__pop_ks(thread, ts, sample, ref);
+ if (err)
+ return err;
}
if (ts->cnt)
}
ts->branch_count += 1;
+ ts->insn_count += sample->insn_cnt;
+ ts->cyc_count += sample->cyc_cnt;
ts->last_time = sample->time;
if (sample->flags & PERF_IP_FLAG_CALL) {
ts->rstate = X86_RETPOLINE_DETECTED;
} else if (sample->flags & PERF_IP_FLAG_RETURN) {
- if (!sample->ip || !sample->addr)
+ if (!sample->addr) {
+ u32 return_from_kernel = PERF_IP_FLAG_SYSCALLRET |
+ PERF_IP_FLAG_INTERRUPT;
+
+ if (!(sample->flags & return_from_kernel))
+ return 0;
+
+ /* Pop kernel stack */
+ return thread_stack__pop_ks(thread, ts, sample, ref);
+ }
+
+ if (!sample->ip)
return 0;
/* x86 retpoline 'return' doesn't match the stack */
* @call_time: timestamp of call (if known)
* @return_time: timestamp of return (if known)
* @branch_count: number of branches seen between call and return
+ * @insn_count: approx. number of instructions between call and return
+ * @cyc_count: approx. number of cycles between call and return
* @call_ref: external reference to 'call' sample (e.g. db_id)
* @return_ref: external reference to 'return' sample (e.g. db_id)
* @db_id: id used for db-export
u64 call_time;
u64 return_time;
u64 branch_count;
+ u64 insn_count;
+ u64 cyc_count;
u64 call_ref;
u64 return_ref;
u64 db_id;
return list_first_entry(&thread->namespaces_list, struct namespaces, list);
}
-struct namespaces *thread__namespaces(const struct thread *thread)
+struct namespaces *thread__namespaces(struct thread *thread)
{
struct namespaces *ns;
- down_read((struct rw_semaphore *)&thread->namespaces_lock);
+ down_read(&thread->namespaces_lock);
ns = __thread__namespaces(thread);
- up_read((struct rw_semaphore *)&thread->namespaces_lock);
+ up_read(&thread->namespaces_lock);
return ns;
}
return comm__str(comm);
}
-const char *thread__comm_str(const struct thread *thread)
+const char *thread__comm_str(struct thread *thread)
{
const char *str;
- down_read((struct rw_semaphore *)&thread->comm_lock);
+ down_read(&thread->comm_lock);
str = __thread__comm_str(thread);
- up_read((struct rw_semaphore *)&thread->comm_lock);
+ up_read(&thread->comm_lock);
return str;
}
thread->dead = true;
}
-struct namespaces *thread__namespaces(const struct thread *thread);
+struct namespaces *thread__namespaces(struct thread *thread);
int thread__set_namespaces(struct thread *thread, u64 timestamp,
struct namespaces_event *event);
int thread__comm_len(struct thread *thread);
struct comm *thread__comm(const struct thread *thread);
struct comm *thread__exec_comm(const struct thread *thread);
-const char *thread__comm_str(const struct thread *thread);
+const char *thread__comm_str(struct thread *thread);
int thread__insert_map(struct thread *thread, struct map *map);
int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone);
size_t thread__fprintf(struct thread *thread, FILE *fp);
#include "strlist.h"
#include <string.h>
#include <api/fs/fs.h>
+#include <linux/string.h>
#include "asm/bug.h"
#include "thread_map.h"
#include "util.h"
* mark the end of the string.
*/
(*comm)[size] = 0;
- rtrim(*comm);
+ strim(*comm);
}
free(path);
// SPDX-License-Identifier: GPL-2.0
#include <stdlib.h>
#include <string.h>
+#include <linux/string.h>
#include <sys/time.h>
#include <linux/time64.h>
#include <time.h>
#include <errno.h>
#include <inttypes.h>
#include <math.h>
+#include <linux/ctype.h>
#include "perf.h"
#include "debug.h"
return rc;
}
+static int perf_time__parse_strs(struct perf_time_interval *ptime,
+ const char *ostr, int size)
+{
+ const char *cp;
+ char *str, *arg, *p;
+ int i, num = 0, rc = 0;
+
+ /* Count the commas */
+ for (cp = ostr; *cp; cp++)
+ num += !!(*cp == ',');
+
+ if (!num)
+ return -EINVAL;
+
+ BUG_ON(num > size);
+
+ str = strdup(ostr);
+ if (!str)
+ return -ENOMEM;
+
+ /* Split the string and parse each piece, except the last */
+ for (i = 0, p = str; i < num - 1; i++) {
+ arg = p;
+ /* Find next comma, there must be one */
+ p = skip_spaces(strchr(p, ',') + 1);
+ /* Skip the value, must not contain space or comma */
+ while (*p && !isspace(*p)) {
+ if (*p++ == ',') {
+ rc = -EINVAL;
+ goto out;
+ }
+ }
+ /* Split and parse */
+ if (*p)
+ *p++ = 0;
+ rc = perf_time__parse_str(ptime + i, arg);
+ if (rc < 0)
+ goto out;
+ }
+
+ /* Parse the last piece */
+ rc = perf_time__parse_str(ptime + i, p);
+ if (rc < 0)
+ goto out;
+
+ /* Check there is no overlap */
+ for (i = 0; i < num - 1; i++) {
+ if (ptime[i].end >= ptime[i + 1].start) {
+ rc = -EINVAL;
+ goto out;
+ }
+ }
+
+ rc = num;
+out:
+ free(str);
+
+ return rc;
+}
+
static int parse_percent(double *pcnt, char *str)
{
char *c, *endptr;
return 0;
}
+static int set_percent_time(struct perf_time_interval *ptime, double start_pcnt,
+ double end_pcnt, u64 start, u64 end)
+{
+ u64 total = end - start;
+
+ if (start_pcnt < 0.0 || start_pcnt > 1.0 ||
+ end_pcnt < 0.0 || end_pcnt > 1.0) {
+ return -1;
+ }
+
+ ptime->start = start + round(start_pcnt * total);
+ ptime->end = start + round(end_pcnt * total);
+
+ if (ptime->end > ptime->start && ptime->end != end)
+ ptime->end -= 1;
+
+ return 0;
+}
+
static int percent_slash_split(char *str, struct perf_time_interval *ptime,
u64 start, u64 end)
{
char *p, *end_str;
double pcnt, start_pcnt, end_pcnt;
- u64 total = end - start;
int i;
/*
start_pcnt = pcnt * (i - 1);
end_pcnt = pcnt * i;
- if (start_pcnt < 0.0 || start_pcnt > 1.0 ||
- end_pcnt < 0.0 || end_pcnt > 1.0) {
- return -1;
- }
-
- ptime->start = start + round(start_pcnt * total);
- ptime->end = start + round(end_pcnt * total);
-
- return 0;
+ return set_percent_time(ptime, start_pcnt, end_pcnt, start, end);
}
static int percent_dash_split(char *str, struct perf_time_interval *ptime,
{
char *start_str = NULL, *end_str;
double start_pcnt, end_pcnt;
- u64 total = end - start;
int ret;
/*
free(start_str);
- if (start_pcnt < 0.0 || start_pcnt > 1.0 ||
- end_pcnt < 0.0 || end_pcnt > 1.0 ||
- start_pcnt > end_pcnt) {
- return -1;
- }
-
- ptime->start = start + round(start_pcnt * total);
- ptime->end = start + round(end_pcnt * total);
-
- return 0;
+ return set_percent_time(ptime, start_pcnt, end_pcnt, start, end);
}
typedef int (*time_pecent_split)(char *, struct perf_time_interval *,
ptime = &ptime_buf[i];
if (timestamp >= ptime->start &&
- ((timestamp < ptime->end && i < num - 1) ||
- (timestamp <= ptime->end && i == num - 1))) {
- break;
+ (timestamp <= ptime->end || !ptime->end)) {
+ return false;
}
}
- return (i == num) ? true : false;
+ return true;
}
int perf_time__parse_for_ranges(const char *time_str,
struct perf_time_interval **ranges,
int *range_size, int *range_num)
{
+ bool has_percent = strchr(time_str, '%');
struct perf_time_interval *ptime_range;
- int size, num, ret;
+ int size, num, ret = -EINVAL;
ptime_range = perf_time__range_alloc(time_str, &size);
if (!ptime_range)
return -ENOMEM;
- if (perf_time__parse_str(ptime_range, time_str) != 0) {
+ if (has_percent) {
if (session->evlist->first_sample_time == 0 &&
session->evlist->last_sample_time == 0) {
pr_err("HINT: no first/last sample time found in perf data.\n"
"Please use latest perf binary to execute 'perf record'\n"
"(if '--buildid-all' is enabled, please set '--timestamp-boundary').\n");
- ret = -EINVAL;
goto error;
}
time_str,
session->evlist->first_sample_time,
session->evlist->last_sample_time);
-
- if (num < 0) {
- pr_err("Invalid time string\n");
- ret = -EINVAL;
- goto error;
- }
} else {
- num = 1;
+ num = perf_time__parse_strs(ptime_range, time_str, size);
}
+ if (num < 0)
+ goto error_invalid;
+
*range_size = size;
*range_num = num;
*ranges = ptime_range;
return 0;
+error_invalid:
+ pr_err("Invalid time string\n");
error:
free(ptime_range);
return ret;
#include "debug.h"
#include "trace-event.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
static int get_common_field(struct scripting_context *context,
int *offset, int *size, const char *type)
return n;
}
-/*
- * While we find nice hex chars, build a long_val.
- * Return number of chars processed.
- */
-int hex2u64(const char *ptr, u64 *long_val)
-{
- char *p;
-
- *long_val = strtoull(ptr, &p, 16);
-
- return p - ptr;
-}
-
int perf_event_paranoid(void)
{
int value;
ssize_t writen(int fd, const void *buf, size_t n);
size_t hex_width(u64 v);
-int hex2u64(const char *ptr, u64 *val);
extern unsigned int page_size;
int __pure cacheline_size(void);
TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \
check_initial_reg_state sigreturn iopl mpx-mini-test ioperm \
- protection_keys test_vdso test_vsyscall mov_ss_trap
-TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
+ protection_keys test_vdso test_vsyscall mov_ss_trap \
+ syscall_arg_fault
+TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \
test_FCMOV test_FCOMI test_FISTTP \
vdso_restorer
TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip
#include <pthread.h>
#include <asm/ldt.h>
#include <sys/mman.h>
+#include <stddef.h>
+#include <sys/ptrace.h>
+#include <sys/wait.h>
+#include <setjmp.h>
#ifndef __x86_64__
# error This test is 64-bit only
static volatile sig_atomic_t want_segv;
static volatile unsigned long segv_addr;
+static unsigned short *shared_scratch;
+
static int nerrs;
static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
}
+static jmp_buf jmpbuf;
+
+static void sigill(int sig, siginfo_t *si, void *ctx_void)
+{
+ siglongjmp(jmpbuf, 1);
+}
+
+static bool have_fsgsbase;
+
+static inline unsigned long rdgsbase(void)
+{
+ unsigned long gsbase;
+
+ asm volatile("rdgsbase %0" : "=r" (gsbase) :: "memory");
+
+ return gsbase;
+}
+
+static inline unsigned long rdfsbase(void)
+{
+ unsigned long fsbase;
+
+ asm volatile("rdfsbase %0" : "=r" (fsbase) :: "memory");
+
+ return fsbase;
+}
+
+static inline void wrgsbase(unsigned long gsbase)
+{
+ asm volatile("wrgsbase %0" :: "r" (gsbase) : "memory");
+}
+
+static inline void wrfsbase(unsigned long fsbase)
+{
+ asm volatile("wrfsbase %0" :: "r" (fsbase) : "memory");
+}
+
enum which_base { FS, GS };
static unsigned long read_base(enum which_base which)
to_set, hard_zero ? " and clear gs" : "", sel);
}
-void do_unexpected_base(void)
+static __thread int set_thread_area_entry_number = -1;
+
+static unsigned short load_gs(void)
{
/*
- * The goal here is to try to arrange for GS == 0, GSBASE !=
- * 0, and for the the kernel the think that GSBASE == 0.
- *
- * To make the test as reliable as possible, this uses
- * explicit descriptorss. (This is not the only way. This
- * could use ARCH_SET_GS with a low, nonzero base, but the
- * relevant side effect of ARCH_SET_GS could change.)
+ * Sets GS != 0 and GSBASE != 0 but arranges for the kernel to think
+ * that GSBASE == 0 (i.e. thread.gsbase == 0).
*/
/* Step 1: tell the kernel that we have GSBASE == 0. */
.useable = 0
};
if (syscall(SYS_modify_ldt, 1, &desc, sizeof(desc)) == 0) {
- printf("\tother thread: using LDT slot 0\n");
+ printf("\tusing LDT slot 0\n");
asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0x7));
+ return 0x7;
} else {
/* No modify_ldt for us (configured out, perhaps) */
MAP_PRIVATE | MAP_ANONYMOUS | MAP_32BIT, -1, 0);
memcpy(low_desc, &desc, sizeof(desc));
- low_desc->entry_number = -1;
+ low_desc->entry_number = set_thread_area_entry_number;
/* 32-bit set_thread_area */
long ret;
if (ret != 0) {
printf("[NOTE]\tcould not create a segment -- test won't do anything\n");
- return;
+ return 0;
}
- printf("\tother thread: using GDT slot %d\n", desc.entry_number);
- asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)((desc.entry_number << 3) | 0x3)));
+ printf("\tusing GDT slot %d\n", desc.entry_number);
+ set_thread_area_entry_number = desc.entry_number;
+
+ unsigned short gs = (unsigned short)((desc.entry_number << 3) | 0x3);
+ asm volatile ("mov %0, %%gs" : : "rm" (gs));
+ return gs;
}
+}
- /*
- * Step 3: set the selector back to zero. On AMD chips, this will
- * preserve GSBASE.
- */
+void test_wrbase(unsigned short index, unsigned long base)
+{
+ unsigned short newindex;
+ unsigned long newbase;
- asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0));
+ printf("[RUN]\tGS = 0x%hx, GSBASE = 0x%lx\n", index, base);
+
+ asm volatile ("mov %0, %%gs" : : "rm" (index));
+ wrgsbase(base);
+
+ remote_base = 0;
+ ftx = 1;
+ syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0);
+ while (ftx != 0)
+ syscall(SYS_futex, &ftx, FUTEX_WAIT, 1, NULL, NULL, 0);
+
+ asm volatile ("mov %%gs, %0" : "=rm" (newindex));
+ newbase = rdgsbase();
+
+ if (newindex == index && newbase == base) {
+ printf("[OK]\tIndex and base were preserved\n");
+ } else {
+ printf("[FAIL]\tAfter switch, GS = 0x%hx and GSBASE = 0x%lx\n",
+ newindex, newbase);
+ nerrs++;
+ }
}
static void *threadproc(void *ctx)
if (ftx == 3)
return NULL;
- if (ftx == 1)
+ if (ftx == 1) {
do_remote_base();
- else if (ftx == 2)
- do_unexpected_base();
- else
+ } else if (ftx == 2) {
+ /*
+ * On AMD chips, this causes GSBASE != 0, GS == 0, and
+ * thread.gsbase == 0.
+ */
+
+ load_gs();
+ asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0));
+ } else {
errx(1, "helper thread got bad command");
+ }
ftx = 0;
syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0);
}
}
+#define USER_REGS_OFFSET(r) offsetof(struct user_regs_struct, r)
+
+static void test_ptrace_write_gsbase(void)
+{
+ int status;
+ pid_t child = fork();
+
+ if (child < 0)
+ err(1, "fork");
+
+ if (child == 0) {
+ printf("[RUN]\tPTRACE_POKE(), write GSBASE from ptracer\n");
+
+ *shared_scratch = load_gs();
+
+ if (ptrace(PTRACE_TRACEME, 0, NULL, NULL) != 0)
+ err(1, "PTRACE_TRACEME");
+
+ raise(SIGTRAP);
+ _exit(0);
+ }
+
+ wait(&status);
+
+ if (WSTOPSIG(status) == SIGTRAP) {
+ unsigned long gs, base;
+ unsigned long gs_offset = USER_REGS_OFFSET(gs);
+ unsigned long base_offset = USER_REGS_OFFSET(gs_base);
+
+ gs = ptrace(PTRACE_PEEKUSER, child, gs_offset, NULL);
+
+ if (gs != *shared_scratch) {
+ nerrs++;
+ printf("[FAIL]\tGS is not prepared with nonzero\n");
+ goto END;
+ }
+
+ if (ptrace(PTRACE_POKEUSER, child, base_offset, 0xFF) != 0)
+ err(1, "PTRACE_POKEUSER");
+
+ gs = ptrace(PTRACE_PEEKUSER, child, gs_offset, NULL);
+ base = ptrace(PTRACE_PEEKUSER, child, base_offset, NULL);
+
+ /*
+ * In a non-FSGSBASE system, the nonzero selector will load
+ * GSBASE (again). But what is tested here is whether the
+ * selector value is changed or not by the GSBASE write in
+ * a ptracer.
+ */
+ if (gs != *shared_scratch) {
+ nerrs++;
+ printf("[FAIL]\tGS changed to %lx\n", gs);
+
+ /*
+ * On older kernels, poking a nonzero value into the
+ * base would zero the selector. On newer kernels,
+ * this behavior has changed -- poking the base
+ * changes only the base and, if FSGSBASE is not
+ * available, this may have no effect.
+ */
+ if (gs == 0)
+ printf("\tNote: this is expected behavior on older kernels.\n");
+ } else if (have_fsgsbase && (base != 0xFF)) {
+ nerrs++;
+ printf("[FAIL]\tGSBASE changed to %lx\n", base);
+ } else {
+ printf("[OK]\tGS remained 0x%hx%s", *shared_scratch, have_fsgsbase ? " and GSBASE changed to 0xFF" : "");
+ printf("\n");
+ }
+ }
+
+END:
+ ptrace(PTRACE_CONT, child, NULL, NULL);
+}
+
int main()
{
pthread_t thread;
+ shared_scratch = mmap(NULL, 4096, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_SHARED, -1, 0);
+
+ /* Probe FSGSBASE */
+ sethandler(SIGILL, sigill, 0);
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ rdfsbase();
+ have_fsgsbase = true;
+ printf("\tFSGSBASE instructions are enabled\n");
+ } else {
+ printf("\tFSGSBASE instructions are disabled\n");
+ }
+ clearhandler(SIGILL);
+
sethandler(SIGSEGV, sigsegv, 0);
check_gs_value(0);
test_unexpected_base();
+ if (have_fsgsbase) {
+ unsigned short ss;
+
+ asm volatile ("mov %%ss, %0" : "=rm" (ss));
+
+ test_wrbase(0, 0);
+ test_wrbase(0, 1);
+ test_wrbase(0, 0x200000000);
+ test_wrbase(0, 0xffffffffffffffff);
+ test_wrbase(ss, 0);
+ test_wrbase(ss, 1);
+ test_wrbase(ss, 0x200000000);
+ test_wrbase(ss, 0xffffffffffffffff);
+ }
+
ftx = 3; /* Kill the thread. */
syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0);
if (pthread_join(thread, NULL) != 0)
err(1, "pthread_join");
+ test_ptrace_write_gsbase();
+
return nerrs == 0 ? 0 : 1;
}
#include <setjmp.h>
#include <errno.h>
+#ifdef __x86_64__
+# define WIDTH "q"
+#else
+# define WIDTH "l"
+#endif
+
/* Our sigaltstack scratch space. */
static unsigned char altstack_data[SIGSTKSZ];
+static unsigned long get_eflags(void)
+{
+ unsigned long eflags;
+ asm volatile ("pushf" WIDTH "\n\tpop" WIDTH " %0" : "=rm" (eflags));
+ return eflags;
+}
+
+static void set_eflags(unsigned long eflags)
+{
+ asm volatile ("push" WIDTH " %0\n\tpopf" WIDTH
+ : : "rm" (eflags) : "flags");
+}
+
+#define X86_EFLAGS_TF (1UL << 8)
+
static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
int flags)
{
static volatile sig_atomic_t n_errs;
+#ifdef __x86_64__
+#define REG_AX REG_RAX
+#define REG_IP REG_RIP
+#else
+#define REG_AX REG_EAX
+#define REG_IP REG_EIP
+#endif
+
static void sigsegv_or_sigbus(int sig, siginfo_t *info, void *ctx_void)
{
ucontext_t *ctx = (ucontext_t*)ctx_void;
+ long ax = (long)ctx->uc_mcontext.gregs[REG_AX];
- if (ctx->uc_mcontext.gregs[REG_EAX] != -EFAULT) {
- printf("[FAIL]\tAX had the wrong value: 0x%x\n",
- ctx->uc_mcontext.gregs[REG_EAX]);
+ if (ax != -EFAULT && ax != -ENOSYS) {
+ printf("[FAIL]\tAX had the wrong value: 0x%lx\n",
+ (unsigned long)ax);
n_errs++;
} else {
printf("[OK]\tSeems okay\n");
siglongjmp(jmpbuf, 1);
}
+static volatile sig_atomic_t sigtrap_consecutive_syscalls;
+
+static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
+{
+ /*
+ * KVM has some bugs that can cause us to stop making progress.
+ * detect them and complain, but don't infinite loop or fail the
+ * test.
+ */
+
+ ucontext_t *ctx = (ucontext_t*)ctx_void;
+ unsigned short *ip = (unsigned short *)ctx->uc_mcontext.gregs[REG_IP];
+
+ if (*ip == 0x340f || *ip == 0x050f) {
+ /* The trap was on SYSCALL or SYSENTER */
+ sigtrap_consecutive_syscalls++;
+ if (sigtrap_consecutive_syscalls > 3) {
+ printf("[WARN]\tGot stuck single-stepping -- you probably have a KVM bug\n");
+ siglongjmp(jmpbuf, 1);
+ }
+ } else {
+ sigtrap_consecutive_syscalls = 0;
+ }
+}
+
static void sigill(int sig, siginfo_t *info, void *ctx_void)
{
- printf("[SKIP]\tIllegal instruction\n");
+ ucontext_t *ctx = (ucontext_t*)ctx_void;
+ unsigned short *ip = (unsigned short *)ctx->uc_mcontext.gregs[REG_IP];
+
+ if (*ip == 0x0b0f) {
+ /* one of the ud2 instructions faulted */
+ printf("[OK]\tSYSCALL returned normally\n");
+ } else {
+ printf("[SKIP]\tIllegal instruction\n");
+ }
siglongjmp(jmpbuf, 1);
}
"movl $-1, %%ebp\n\t"
"movl $-1, %%esp\n\t"
"syscall\n\t"
- "pushl $0" /* make sure we segfault cleanly */
+ "ud2" /* make sure we recover cleanly */
+ : : : "memory", "flags");
+ }
+
+ printf("[RUN]\tSYSENTER with TF and invalid state\n");
+ sethandler(SIGTRAP, sigtrap, SA_ONSTACK);
+
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ sigtrap_consecutive_syscalls = 0;
+ set_eflags(get_eflags() | X86_EFLAGS_TF);
+ asm volatile (
+ "movl $-1, %%eax\n\t"
+ "movl $-1, %%ebx\n\t"
+ "movl $-1, %%ecx\n\t"
+ "movl $-1, %%edx\n\t"
+ "movl $-1, %%esi\n\t"
+ "movl $-1, %%edi\n\t"
+ "movl $-1, %%ebp\n\t"
+ "movl $-1, %%esp\n\t"
+ "sysenter"
+ : : : "memory", "flags");
+ }
+ set_eflags(get_eflags() & ~X86_EFLAGS_TF);
+
+ printf("[RUN]\tSYSCALL with TF and invalid state\n");
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ sigtrap_consecutive_syscalls = 0;
+ set_eflags(get_eflags() | X86_EFLAGS_TF);
+ asm volatile (
+ "movl $-1, %%eax\n\t"
+ "movl $-1, %%ebx\n\t"
+ "movl $-1, %%ecx\n\t"
+ "movl $-1, %%edx\n\t"
+ "movl $-1, %%esi\n\t"
+ "movl $-1, %%edi\n\t"
+ "movl $-1, %%ebp\n\t"
+ "movl $-1, %%esp\n\t"
+ "syscall\n\t"
+ "ud2" /* make sure we recover cleanly */
: : : "memory", "flags");
}
+ set_eflags(get_eflags() & ~X86_EFLAGS_TF);
return 0;
}