qiurui
/
Centos-kernel-stream-9
mirror of https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge: perf: sync with upstream v6.5 

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/3026

Bugzilla: https://bugzilla.redhat.com/2233483

Rebase of the perf codebase from v6.3-aligned to v6.5.

Signed-off-by: Michael Petlan <mpetlan@redhat.com>

Approved-by: Tony Camuso <tcamuso@redhat.com>
Approved-by: Artem Savkov <asavkov@redhat.com>
Approved-by: David Arcari <darcari@redhat.com>

Signed-off-by: Scott Weaver <scweaver@redhat.com>
This commit is contained in:
Scott Weaver 2023-09-21 09:45:23 -04:00
parent 9c73da1c3d e963e209dd
commit f3cff0333c
718 changed files with 197374 additions and 155362 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
arch/powerpc/include/asm/reg.h
View File

@ -1312,6 +1312,11 @@
#define PVR_VER_E500MC 0x8023
#define PVR_VER_E5500 0x8024
#define PVR_VER_E6500 0x8040
#define PVR_VER_7450 0x8000
#define PVR_VER_7455 0x8001
#define PVR_VER_7447 0x8002
#define PVR_VER_7447A 0x8003
#define PVR_VER_7448 0x8004
/*
* For the 8xx processors, all of them report the same PVR family for

6
arch/powerpc/perf/mpc7450-pmu.c
View File

@ -417,9 +417,9 @@ struct power_pmu mpc7450_pmu = {
static int __init init_mpc7450_pmu(void)
{
unsigned int pvr = mfspr(SPRN_PVR);
if (PVR_VER(pvr) != PVR_7450)
if (!pvr_version_is(PVR_VER_7450) && !pvr_version_is(PVR_VER_7455) &&
!pvr_version_is(PVR_VER_7447) && !pvr_version_is(PVR_VER_7447A) &&
!pvr_version_is(PVR_VER_7448))
return -ENODEV;
return register_power_pmu(&mpc7450_pmu);

2
arch/x86/events/amd/core.c
View File

@ -374,7 +374,7 @@ static int amd_pmu_hw_config(struct perf_event *event)
/* pass precise event sampling to ibs: */
if (event->attr.precise_ip && get_ibs_caps())
return -ENOENT;
return forward_event_to_ibs(event);
if (has_branch_stack(event) && !x86_pmu.lbr_nr)
return -EOPNOTSUPP;

53
arch/x86/events/amd/ibs.c
View File

@ -190,7 +190,7 @@ static struct perf_ibs *get_ibs_pmu(int type)
}
/*
* Use IBS for precise event sampling:
* core pmu config -> IBS config
*
* perf record -a -e cpu-cycles:p ... # use ibs op counting cycle count
* perf record -a -e r076:p ... # same as -e cpu-cycles:p
@ -199,25 +199,9 @@ static struct perf_ibs *get_ibs_pmu(int type)
* IbsOpCntCtl (bit 19) of IBS Execution Control Register (IbsOpCtl,
* MSRC001_1033) is used to select either cycle or micro-ops counting
* mode.
*
* The rip of IBS samples has skid 0. Thus, IBS supports precise
* levels 1 and 2 and the PERF_EFLAGS_EXACT is set. In rare cases the
* rip is invalid when IBS was not able to record the rip correctly.
* We clear PERF_EFLAGS_EXACT and take the rip from pt_regs then.
*
*/
static int perf_ibs_precise_event(struct perf_event *event, u64 *config)
static int core_pmu_ibs_config(struct perf_event *event, u64 *config)
{
switch (event->attr.precise_ip) {
case 0:
return -ENOENT;
case 1:
case 2:
break;
default:
return -EOPNOTSUPP;
}
switch (event->attr.type) {
case PERF_TYPE_HARDWARE:
switch (event->attr.config) {
@ -243,22 +227,37 @@ static int perf_ibs_precise_event(struct perf_event *event, u64 *config)
return -EOPNOTSUPP;
}
/*
* The rip of IBS samples has skid 0. Thus, IBS supports precise
* levels 1 and 2 and the PERF_EFLAGS_EXACT is set. In rare cases the
* rip is invalid when IBS was not able to record the rip correctly.
* We clear PERF_EFLAGS_EXACT and take the rip from pt_regs then.
*/
int forward_event_to_ibs(struct perf_event *event)
{
u64 config = 0;
if (!event->attr.precise_ip || event->attr.precise_ip > 2)
return -EOPNOTSUPP;
if (!core_pmu_ibs_config(event, &config)) {
event->attr.type = perf_ibs_op.pmu.type;
event->attr.config = config;
}
return -ENOENT;
}
static int perf_ibs_init(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
struct perf_ibs *perf_ibs;
u64 max_cnt, config;
int ret;
perf_ibs = get_ibs_pmu(event->attr.type);
if (perf_ibs) {
config = event->attr.config;
} else {
perf_ibs = &perf_ibs_op;
ret = perf_ibs_precise_event(event, &config);
if (ret)
return ret;
}
if (!perf_ibs)
return -ENOENT;
config = event->attr.config;
if (event->pmu != &perf_ibs->pmu)
return -ENOENT;

58
arch/x86/events/intel/core.c
View File

@ -349,6 +349,16 @@ static struct event_constraint intel_spr_event_constraints[] = {
EVENT_CONSTRAINT_END
};
static struct extra_reg intel_gnr_extra_regs[] __read_mostly = {
INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
INTEL_UEVENT_EXTRA_REG(0x02c6, MSR_PEBS_FRONTEND, 0x9, FE),
INTEL_UEVENT_EXTRA_REG(0x03c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE),
INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0x7, FE),
INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE),
EVENT_EXTRA_END
};
EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
@ -2451,7 +2461,7 @@ static void intel_pmu_disable_fixed(struct perf_event *event)
intel_clear_masks(event, idx);
mask = 0xfULL << ((idx - INTEL_PMC_IDX_FIXED) * 4);
mask = intel_fixed_bits_by_idx(idx - INTEL_PMC_IDX_FIXED, INTEL_FIXED_BITS_MASK);
cpuc->fixed_ctrl_val &= ~mask;
}
@ -2750,25 +2760,25 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
* if requested:
*/
if (!event->attr.precise_ip)
bits |= 0x8;
bits |= INTEL_FIXED_0_ENABLE_PMI;
if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
bits |= 0x2;
bits |= INTEL_FIXED_0_USER;
if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
bits |= 0x1;
bits |= INTEL_FIXED_0_KERNEL;
/*
* ANY bit is supported in v3 and up
*/
if (x86_pmu.version > 2 && hwc->config & ARCH_PERFMON_EVENTSEL_ANY)
bits |= 0x4;
bits |= INTEL_FIXED_0_ANYTHREAD;
idx -= INTEL_PMC_IDX_FIXED;
bits <<= (idx * 4);
mask = 0xfULL << (idx * 4);
bits = intel_fixed_bits_by_idx(idx, bits);
mask = intel_fixed_bits_by_idx(idx, INTEL_FIXED_BITS_MASK);
if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip) {
bits |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
mask |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
bits |= intel_fixed_bits_by_idx(idx, ICL_FIXED_0_ADAPTIVE);
mask |= intel_fixed_bits_by_idx(idx, ICL_FIXED_0_ADAPTIVE);
}
cpuc->fixed_ctrl_val &= ~mask;
@ -3983,6 +3993,13 @@ static int intel_pmu_hw_config(struct perf_event *event)
struct perf_event *leader = event->group_leader;
struct perf_event *sibling = NULL;
/*
* When this memload event is also the first event (no group
* exists yet), then there is no aux event before it.
*/
if (leader == event)
return -ENODATA;
if (!is_mem_loads_aux_event(leader)) {
for_each_sibling_event(sibling, leader) {
if (is_mem_loads_aux_event(sibling))
@ -4074,7 +4091,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
if (x86_pmu.intel_cap.pebs_baseline) {
arr[(*nr)++] = (struct perf_guest_switch_msr){
.msr = MSR_PEBS_DATA_CFG,
.host = cpuc->pebs_data_cfg,
.host = cpuc->active_pebs_data_cfg,
.guest = kvm_pmu->pebs_data_cfg,
};
}
@ -5469,6 +5486,15 @@ pebs_is_visible(struct kobject *kobj, struct attribute *attr, int i)
return x86_pmu.pebs ? attr->mode : 0;
}
static umode_t
mem_is_visible(struct kobject *kobj, struct attribute *attr, int i)
{
if (attr == &event_attr_mem_ld_aux.attr.attr)
return x86_pmu.flags & PMU_FL_MEM_LOADS_AUX ? attr->mode : 0;
return pebs_is_visible(kobj, attr, i);
}
static umode_t
lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
{
@ -5496,7 +5522,7 @@ static struct attribute_group group_events_td = {
static struct attribute_group group_events_mem = {
.name = "events",
.is_visible = pebs_is_visible,
.is_visible = mem_is_visible,
};
static struct attribute_group group_events_tsx = {
@ -6486,6 +6512,11 @@ __init int intel_pmu_init(void)
case INTEL_FAM6_SAPPHIRERAPIDS_X:
case INTEL_FAM6_EMERALDRAPIDS_X:
x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
x86_pmu.extra_regs = intel_spr_extra_regs;
fallthrough;
case INTEL_FAM6_GRANITERAPIDS_X:
case INTEL_FAM6_GRANITERAPIDS_D:
pmem = true;
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(hw_cache_event_ids));
@ -6493,7 +6524,8 @@ __init int intel_pmu_init(void)
x86_pmu.event_constraints = intel_spr_event_constraints;
x86_pmu.pebs_constraints = intel_spr_pebs_event_constraints;
x86_pmu.extra_regs = intel_spr_extra_regs;
if (!x86_pmu.extra_regs)
x86_pmu.extra_regs = intel_gnr_extra_regs;
x86_pmu.limit_period = spr_limit_period;
x86_pmu.pebs_ept = 1;
x86_pmu.pebs_aliases = NULL;
@ -6502,7 +6534,6 @@ __init int intel_pmu_init(void)
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = spr_get_event_constraints;
@ -6638,6 +6669,7 @@ __init int intel_pmu_init(void)
pmu->pebs_constraints = intel_grt_pebs_event_constraints;
pmu->extra_regs = intel_grt_extra_regs;
if (is_mtl(boot_cpu_data.x86_model)) {
x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].extra_regs = intel_gnr_extra_regs;
x86_pmu.pebs_latency_data = mtl_latency_data_small;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr;

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

@ -678,6 +678,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_cstates),
X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &icx_cstates),
X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &icx_cstates),
X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, &icx_cstates),
X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_D, &icx_cstates),
X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &icl_cstates),
X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &icl_cstates),

56
arch/x86/events/intel/ds.c
View File

@ -1229,12 +1229,14 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
struct perf_event *event, bool add)
{
struct pmu *pmu = event->pmu;
/*
* Make sure we get updated with the first PEBS
* event. It will trigger also during removal, but
* that does not hurt:
*/
bool update = cpuc->n_pebs == 1;
if (cpuc->n_pebs == 1)
cpuc->pebs_data_cfg = PEBS_UPDATE_DS_SW;
if (needed_cb != pebs_needs_sched_cb(cpuc)) {
if (!needed_cb)
@ -1242,7 +1244,7 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
else
perf_sched_cb_dec(pmu);
update = true;
cpuc->pebs_data_cfg |= PEBS_UPDATE_DS_SW;
}
/*
@ -1252,24 +1254,13 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
if (x86_pmu.intel_cap.pebs_baseline && add) {
u64 pebs_data_cfg;
/* Clear pebs_data_cfg and pebs_record_size for first PEBS. */
if (cpuc->n_pebs == 1) {
cpuc->pebs_data_cfg = 0;
cpuc->pebs_record_size = sizeof(struct pebs_basic);
}
pebs_data_cfg = pebs_update_adaptive_cfg(event);
/* Update pebs_record_size if new event requires more data. */
if (pebs_data_cfg & ~cpuc->pebs_data_cfg) {
cpuc->pebs_data_cfg |= pebs_data_cfg;
adaptive_pebs_record_size_update();
update = true;
}
/*
* Be sure to update the thresholds when we change the record.
*/
if (pebs_data_cfg & ~cpuc->pebs_data_cfg)
cpuc->pebs_data_cfg |= pebs_data_cfg | PEBS_UPDATE_DS_SW;
}
if (update)
pebs_update_threshold(cpuc);
}
void intel_pmu_pebs_add(struct perf_event *event)
@ -1326,9 +1317,17 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event)
wrmsrl(base + idx, value);
}
static inline void intel_pmu_drain_large_pebs(struct cpu_hw_events *cpuc)
{
if (cpuc->n_pebs == cpuc->n_large_pebs &&
cpuc->n_pebs != cpuc->n_pebs_via_pt)
intel_pmu_drain_pebs_buffer();
}
void intel_pmu_pebs_enable(struct perf_event *event)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
u64 pebs_data_cfg = cpuc->pebs_data_cfg & ~PEBS_UPDATE_DS_SW;
struct hw_perf_event *hwc = &event->hw;
struct debug_store *ds = cpuc->ds;
unsigned int idx = hwc->idx;
@ -1344,11 +1343,22 @@ void intel_pmu_pebs_enable(struct perf_event *event)
if (x86_pmu.intel_cap.pebs_baseline) {
hwc->config |= ICL_EVENTSEL_ADAPTIVE;
if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) {
wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg);
cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg;
if (pebs_data_cfg != cpuc->active_pebs_data_cfg) {
/*
* drain_pebs() assumes uniform record size;
* hence we need to drain when changing said
* size.
*/
intel_pmu_drain_large_pebs(cpuc);
adaptive_pebs_record_size_update();
wrmsrl(MSR_PEBS_DATA_CFG, pebs_data_cfg);
cpuc->active_pebs_data_cfg = pebs_data_cfg;
}
}
if (cpuc->pebs_data_cfg & PEBS_UPDATE_DS_SW) {
cpuc->pebs_data_cfg = pebs_data_cfg;
pebs_update_threshold(cpuc);
}
if (idx >= INTEL_PMC_IDX_FIXED) {
if (x86_pmu.intel_cap.pebs_format < 5)
@ -1391,9 +1401,7 @@ void intel_pmu_pebs_disable(struct perf_event *event)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
if (cpuc->n_pebs == cpuc->n_large_pebs &&
cpuc->n_pebs != cpuc->n_pebs_via_pt)
intel_pmu_drain_pebs_buffer();
intel_pmu_drain_large_pebs(cpuc);
cpuc->pebs_enabled &= ~(1ULL << hwc->idx);

33
arch/x86/events/intel/uncore_snbep.c
View File

@ -6068,6 +6068,17 @@ static struct intel_uncore_ops spr_uncore_mmio_ops = {
.read_counter = uncore_mmio_read_counter,
};
static struct uncore_event_desc spr_uncore_imc_events[] = {
INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x01,umask=0x00"),
INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x05,umask=0xcf"),
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=0x05,umask=0xf0"),
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 spr_uncore_imc = {
SPR_UNCORE_COMMON_FORMAT(),
.name = "imc",
@ -6075,6 +6086,7 @@ static struct intel_uncore_type spr_uncore_imc = {
.fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR,
.fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL,
.ops = &spr_uncore_mmio_ops,
.event_descs = spr_uncore_imc_events,
};
static void spr_uncore_pci_enable_event(struct intel_uncore_box *box,
@ -6138,6 +6150,7 @@ static struct intel_uncore_type spr_uncore_mdf = {
};
#define UNCORE_SPR_NUM_UNCORE_TYPES 12
#define UNCORE_SPR_CHA 0
#define UNCORE_SPR_IIO 1
#define UNCORE_SPR_IMC 6
#define UNCORE_SPR_UPI 8
@ -6448,12 +6461,32 @@ static int uncore_type_max_boxes(struct intel_uncore_type **types,
return max + 1;
}
#define SPR_MSR_UNC_CBO_CONFIG 0x2FFE
void spr_uncore_cpu_init(void)
{
struct intel_uncore_type *type;
u64 num_cbo;
uncore_msr_uncores = uncore_get_uncores(UNCORE_ACCESS_MSR,
UNCORE_SPR_MSR_EXTRA_UNCORES,
spr_msr_uncores);
type = uncore_find_type_by_id(uncore_msr_uncores, UNCORE_SPR_CHA);
if (type) {
/*
* The value from the discovery table (stored in the type->num_boxes
* of UNCORE_SPR_CHA) is incorrect on some SPR variants because of a
* firmware bug. Using the value from SPR_MSR_UNC_CBO_CONFIG to replace it.
*/
rdmsrl(SPR_MSR_UNC_CBO_CONFIG, num_cbo);
/*
* The MSR doesn't work on the EMR XCC, but the firmware bug doesn't impact
* the EMR XCC. Don't let the value from the MSR replace the existing value.
*/
if (num_cbo)
type->num_boxes = num_cbo;
}
spr_uncore_iio_free_running.num_boxes = uncore_type_max_boxes(uncore_msr_uncores, UNCORE_SPR_IIO);
}

2
arch/x86/events/msr.c
View File

@ -70,6 +70,8 @@ static bool test_intel(int idx, void *data)
case INTEL_FAM6_BROADWELL_X:
case INTEL_FAM6_SAPPHIRERAPIDS_X:
case INTEL_FAM6_EMERALDRAPIDS_X:
case INTEL_FAM6_GRANITERAPIDS_X:
case INTEL_FAM6_GRANITERAPIDS_D:
case INTEL_FAM6_ATOM_SILVERMONT:
case INTEL_FAM6_ATOM_SILVERMONT_D:

15
arch/x86/include/asm/perf_event.h
View File

@ -32,11 +32,21 @@
#define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23)
#define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL
#define INTEL_FIXED_BITS_MASK 0xFULL
#define INTEL_FIXED_BITS_STRIDE 4
#define INTEL_FIXED_0_KERNEL (1ULL << 0)
#define INTEL_FIXED_0_USER (1ULL << 1)
#define INTEL_FIXED_0_ANYTHREAD (1ULL << 2)
#define INTEL_FIXED_0_ENABLE_PMI (1ULL << 3)
#define HSW_IN_TX (1ULL << 32)
#define HSW_IN_TX_CHECKPOINTED (1ULL << 33)
#define ICL_EVENTSEL_ADAPTIVE (1ULL << 34)
#define ICL_FIXED_0_ADAPTIVE (1ULL << 32)
#define intel_fixed_bits_by_idx(_idx, _bits) \
((_bits) << ((_idx) * INTEL_FIXED_BITS_STRIDE))
#define AMD64_EVENTSEL_INT_CORE_ENABLE (1ULL << 36)
#define AMD64_EVENTSEL_GUESTONLY (1ULL << 40)
#define AMD64_EVENTSEL_HOSTONLY (1ULL << 41)
@ -121,6 +131,9 @@
#define PEBS_DATACFG_LBRS BIT_ULL(3)
#define PEBS_DATACFG_LBR_SHIFT 24
/* Steal the highest bit of pebs_data_cfg for SW usage */
#define PEBS_UPDATE_DS_SW BIT_ULL(63)
/*
* Intel "Architectural Performance Monitoring" CPUID
* detection/enumeration details:
@ -475,8 +488,10 @@ struct pebs_xmm {
#ifdef CONFIG_X86_LOCAL_APIC
extern u32 get_ibs_caps(void);
extern int forward_event_to_ibs(struct perf_event *event);
#else
static inline u32 get_ibs_caps(void) { return 0; }
static inline int forward_event_to_ibs(struct perf_event *event) { return -ENOENT; }
#endif
#ifdef CONFIG_PERF_EVENTS

2
include/linux/kernel.h
View File

@ -289,7 +289,7 @@ bool mac_pton(const char *s, u8 *mac);
*
* Use tracing_on/tracing_off when you want to quickly turn on or off
* tracing. It simply enables or disables the recording of the trace events.
* This also corresponds to the user space /sys/kernel/debug/tracing/tracing_on
* This also corresponds to the user space /sys/kernel/tracing/tracing_on
* file, which gives a means for the kernel and userspace to interact.
* Place a tracing_off() in the kernel where you want tracing to end.
* From user space, examine the trace, and then echo 1 > tracing_on

11
include/linux/perf_event.h
View File

@ -295,6 +295,8 @@ struct perf_event_pmu_context;
struct perf_output_handle;
#define PMU_NULL_DEV ((void *)(~0UL))
/**
* struct pmu - generic performance monitoring unit
*/
@ -303,6 +305,7 @@ struct pmu {
struct module *module;
struct device *dev;
struct device *parent;
const struct attribute_group **attr_groups;
const struct attribute_group **attr_update;
const char *name;
@ -827,6 +830,14 @@ struct perf_event {
void *security;
#endif
struct list_head sb_list;
/*
* Certain events gets forwarded to another pmu internally by over-
* writing kernel copy of event->attr.type without user being aware
* of it. event->orig_type contains original 'type' requested by
* user.
*/
__u32 orig_type;
#endif /* CONFIG_PERF_EVENTS */
};

4
include/linux/tracepoint.h
View File

@ -482,7 +482,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
* * This is how the trace record is structured and will
* * be saved into the ring buffer. These are the fields
* * that will be exposed to user-space in
* * /sys/kernel/debug/tracing/events/<*>/format.
* * /sys/kernel/tracing/events/<*>/format.
* *
* * The declared 'local variable' is called '__entry'
* *
@ -542,7 +542,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
* tracepoint callback (this is used by programmatic plugins and
* can also by used by generic instrumentation like SystemTap), and
* it is also used to expose a structured trace record in
* /sys/kernel/debug/tracing/events/.
* /sys/kernel/tracing/events/.
*
* A set of (un)registration functions can be passed to the variant
* TRACE_EVENT_FN to perform any (un)registration work.

3
include/uapi/linux/perf_event.h
View File

@ -1339,7 +1339,8 @@ union perf_mem_data_src {
#define PERF_MEM_LVLNUM_L2 0x02 /* L2 */
#define PERF_MEM_LVLNUM_L3 0x03 /* L3 */
#define PERF_MEM_LVLNUM_L4 0x04 /* L4 */
/* 5-0x8 available */
/* 5-0x7 available */
#define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */
#define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */
#define PERF_MEM_LVLNUM_IO 0x0a /* I/O */
#define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */

82
kernel/events/core.c
View File

@ -6647,7 +6647,7 @@ static void perf_sigtrap(struct perf_event *event)
return;
send_sig_perf((void __user *)event->pending_addr,
event->attr.type, event->attr.sig_data);
event->orig_type, event->attr.sig_data);
}
/*
@ -9433,8 +9433,8 @@ __perf_event_account_interrupt(struct perf_event *event, int throttle)
hwc->interrupts = 1;
} else {
hwc->interrupts++;
if (unlikely(throttle
&& hwc->interrupts >= max_samples_per_tick)) {
if (unlikely(throttle &&
hwc->interrupts > max_samples_per_tick)) {
__this_cpu_inc(perf_throttled_count);
tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS);
hwc->interrupts = MAX_INTERRUPTS;
@ -9951,6 +9951,9 @@ static void sw_perf_event_destroy(struct perf_event *event)
swevent_hlist_put();
}
static struct pmu perf_cpu_clock; /* fwd declaration */
static struct pmu perf_task_clock;
static int perf_swevent_init(struct perf_event *event)
{
u64 event_id = event->attr.config;
@ -9966,7 +9969,10 @@ static int perf_swevent_init(struct perf_event *event)
switch (event_id) {
case PERF_COUNT_SW_CPU_CLOCK:
event->attr.type = perf_cpu_clock.type;
return -ENOENT;
case PERF_COUNT_SW_TASK_CLOCK:
event->attr.type = perf_task_clock.type;
return -ENOENT;
default:
@ -11097,7 +11103,7 @@ static void cpu_clock_event_read(struct perf_event *event)
static int cpu_clock_event_init(struct perf_event *event)
{
if (event->attr.type != PERF_TYPE_SOFTWARE)
if (event->attr.type != perf_cpu_clock.type)
return -ENOENT;
if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK)
@ -11118,6 +11124,7 @@ static struct pmu perf_cpu_clock = {
.task_ctx_nr = perf_sw_context,
.capabilities = PERF_PMU_CAP_NO_NMI,
.dev = PMU_NULL_DEV,
.event_init = cpu_clock_event_init,
.add = cpu_clock_event_add,
@ -11178,7 +11185,7 @@ static void task_clock_event_read(struct perf_event *event)
static int task_clock_event_init(struct perf_event *event)
{
if (event->attr.type != PERF_TYPE_SOFTWARE)
if (event->attr.type != perf_task_clock.type)
return -ENOENT;
if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK)
@ -11199,6 +11206,7 @@ static struct pmu perf_task_clock = {
.task_ctx_nr = perf_sw_context,
.capabilities = PERF_PMU_CAP_NO_NMI,
.dev = PMU_NULL_DEV,
.event_init = task_clock_event_init,
.add = task_clock_event_add,
@ -11378,6 +11386,7 @@ static int pmu_dev_alloc(struct pmu *pmu)
dev_set_drvdata(pmu->dev, pmu);
pmu->dev->bus = &pmu_bus;
pmu->dev->parent = pmu->parent;
pmu->dev->release = pmu_dev_release;
ret = dev_set_name(pmu->dev, "%s", pmu->name);
@ -11426,31 +11435,31 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
goto unlock;
pmu->type = -1;
if (!name)
goto skip_type;
if (WARN_ONCE(!name, "Can not register anonymous pmu.\n")) {
ret = -EINVAL;
goto free_pdc;
}
pmu->name = name;
if (type != PERF_TYPE_SOFTWARE) {
if (type >= 0)
max = type;
if (type >= 0)
max = type;
ret = idr_alloc(&pmu_idr, pmu, max, 0, GFP_KERNEL);
if (ret < 0)
goto free_pdc;
ret = idr_alloc(&pmu_idr, pmu, max, 0, GFP_KERNEL);
if (ret < 0)
goto free_pdc;
WARN_ON(type >= 0 && ret != type);
WARN_ON(type >= 0 && ret != type);
type = ret;
}
type = ret;
pmu->type = type;
if (pmu_bus_running) {
if (pmu_bus_running && !pmu->dev) {
ret = pmu_dev_alloc(pmu);
if (ret)
goto free_idr;
}
skip_type:
ret = -ENOMEM;
pmu->cpu_pmu_context = alloc_percpu(struct perf_cpu_pmu_context);
if (!pmu->cpu_pmu_context)
@ -11492,16 +11501,7 @@ skip_type:
if (!pmu->event_idx)
pmu->event_idx = perf_event_idx_default;
/*
* Ensure the TYPE_SOFTWARE PMUs are at the head of the list,
* since these cannot be in the IDR. This way the linear search
* is fast, provided a valid software event is provided.
*/
if (type == PERF_TYPE_SOFTWARE || !name)
list_add_rcu(&pmu->entry, &pmus);
else
list_add_tail_rcu(&pmu->entry, &pmus);
list_add_rcu(&pmu->entry, &pmus);
atomic_set(&pmu->exclusive_cnt, 0);
ret = 0;
unlock:
@ -11510,12 +11510,13 @@ unlock:
return ret;
free_dev:
device_del(pmu->dev);
put_device(pmu->dev);
if (pmu->dev && pmu->dev != PMU_NULL_DEV) {
device_del(pmu->dev);
put_device(pmu->dev);
}
free_idr:
if (pmu->type != PERF_TYPE_SOFTWARE)
idr_remove(&pmu_idr, pmu->type);
idr_remove(&pmu_idr, pmu->type);
free_pdc:
free_percpu(pmu->pmu_disable_count);
@ -11536,9 +11537,8 @@ void perf_pmu_unregister(struct pmu *pmu)
synchronize_rcu();
free_percpu(pmu->pmu_disable_count);
if (pmu->type != PERF_TYPE_SOFTWARE)
idr_remove(&pmu_idr, pmu->type);
if (pmu_bus_running) {
idr_remove(&pmu_idr, pmu->type);
if (pmu_bus_running && pmu->dev && pmu->dev != PMU_NULL_DEV) {
if (pmu->nr_addr_filters)
device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
device_del(pmu->dev);
@ -11612,6 +11612,12 @@ static struct pmu *perf_init_event(struct perf_event *event)
idx = srcu_read_lock(&pmus_srcu);
/*
* Save original type before calling pmu->event_init() since certain
* pmus overwrites event->attr.type to forward event to another pmu.
*/
event->orig_type = event->attr.type;
/* Try parent's PMU first: */
if (event->parent && event->parent->pmu) {
pmu = event->parent->pmu;
@ -13651,8 +13657,8 @@ void __init perf_event_init(void)
perf_event_init_all_cpus();
init_srcu_struct(&pmus_srcu);
perf_pmu_register(&perf_swevent, "software", PERF_TYPE_SOFTWARE);
perf_pmu_register(&perf_cpu_clock, NULL, -1);
perf_pmu_register(&perf_task_clock, NULL, -1);
perf_pmu_register(&perf_cpu_clock, "cpu_clock", -1);
perf_pmu_register(&perf_task_clock, "task_clock", -1);
perf_tp_register();
perf_event_init_cpu(smp_processor_id());
register_reboot_notifier(&perf_reboot_notifier);
@ -13695,7 +13701,7 @@ static int __init perf_event_sysfs_init(void)
goto unlock;
list_for_each_entry(pmu, &pmus, entry) {
if (!pmu->name || pmu->type < 0)
if (pmu->dev)
continue;
ret = pmu_dev_alloc(pmu);

1
kernel/events/hw_breakpoint_test.c
View File

@ -329,5 +329,4 @@ static struct kunit_suite hw_breakpoint_test_suite = {
kunit_test_suites(&hw_breakpoint_test_suite);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Marco Elver <elver@google.com>");

20
kernel/trace/Kconfig
View File

@ -219,7 +219,7 @@ config DYNAMIC_FTRACE
enabled, and the functions not enabled will not affect
performance of the system.
See the files in /sys/kernel/debug/tracing:
See the files in /sys/kernel/tracing:
available_filter_functions
set_ftrace_filter
set_ftrace_notrace
@ -279,7 +279,7 @@ config STACK_TRACER
select KALLSYMS
help
This special tracer records the maximum stack footprint of the
kernel and displays it in /sys/kernel/debug/tracing/stack_trace.
kernel and displays it in /sys/kernel/tracing/stack_trace.
This tracer works by hooking into every function call that the
kernel executes, and keeping a maximum stack depth value and
@ -319,7 +319,7 @@ config IRQSOFF_TRACER
disabled by default and can be runtime (re-)started
via:
echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
echo 0 > /sys/kernel/tracing/tracing_max_latency
(Note that kernel size and overhead increase with this option
enabled. This option and the preempt-off timing option can be
@ -343,7 +343,7 @@ config PREEMPT_TRACER
disabled by default and can be runtime (re-)started
via:
echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
echo 0 > /sys/kernel/tracing/tracing_max_latency
(Note that kernel size and overhead increase with this option
enabled. This option and the irqs-off timing option can be
@ -493,7 +493,7 @@ config TRACER_SNAPSHOT
Allow tracing users to take snapshot of the current buffer using the
ftrace interface, e.g.:
echo 1 > /sys/kernel/debug/tracing/snapshot
echo 1 > /sys/kernel/tracing/snapshot
cat snapshot
config TRACER_SNAPSHOT_PER_CPU_SWAP
@ -505,7 +505,7 @@ config TRACER_SNAPSHOT_PER_CPU_SWAP
full swap (all buffers). If this is set, then the following is
allowed:
echo 1 > /sys/kernel/debug/tracing/per_cpu/cpu2/snapshot
echo 1 > /sys/kernel/tracing/per_cpu/cpu2/snapshot
After which, only the tracing buffer for CPU 2 was swapped with
the main tracing buffer, and the other CPU buffers remain the same.
@ -552,7 +552,7 @@ config PROFILE_ANNOTATED_BRANCHES
This tracer profiles all likely and unlikely macros
in the kernel. It will display the results in:
/sys/kernel/debug/tracing/trace_stat/branch_annotated
/sys/kernel/tracing/trace_stat/branch_annotated
Note: this will add a significant overhead; only turn this
on if you need to profile the system's use of these macros.
@ -565,7 +565,7 @@ config PROFILE_ALL_BRANCHES
taken in the kernel is recorded whether it hit or miss.
The results will be displayed in:
/sys/kernel/debug/tracing/trace_stat/branch_all
/sys/kernel/tracing/trace_stat/branch_all
This option also enables the likely/unlikely profiler.
@ -616,8 +616,8 @@ config BLK_DEV_IO_TRACE
Tracing also is possible using the ftrace interface, e.g.:
echo 1 > /sys/block/sda/sda1/trace/enable
echo blk > /sys/kernel/debug/tracing/current_tracer
cat /sys/kernel/debug/tracing/trace_pipe
echo blk > /sys/kernel/tracing/current_tracer
cat /sys/kernel/tracing/trace_pipe
If unsure, say N.

2
kernel/trace/kprobe_event_gen_test.c
View File

@ -21,7 +21,7 @@
* Then:
*
* # insmod kernel/trace/kprobe_event_gen_test.ko
* # cat /sys/kernel/debug/tracing/trace
* # cat /sys/kernel/tracing/trace
*
* You should see many instances of the "gen_kprobe_test" and
* "gen_kretprobe_test" events in the trace buffer.

2
kernel/trace/ring_buffer.c
View File

@ -2724,7 +2724,7 @@ rb_check_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
sched_clock_stable() ? "" :
"If you just came from a suspend/resume,\n"
"please switch to the trace global clock:\n"
" echo global > /sys/kernel/debug/tracing/trace_clock\n"
" echo global > /sys/kernel/tracing/trace_clock\n"
"or add trace_clock=global to the kernel command line\n");
}

2
kernel/trace/synth_event_gen_test.c
View File

@ -22,7 +22,7 @@
* Then:
*
* # insmod kernel/trace/synth_event_gen_test.ko
* # cat /sys/kernel/debug/tracing/trace
* # cat /sys/kernel/tracing/trace
*
* You should see several events in the trace buffer -
* "create_synth_test", "empty_synth_test", and several instances of

2
kernel/trace/trace.c
View File

@ -1154,7 +1154,7 @@ void tracing_snapshot_instance(struct trace_array *tr)
*
* Note, make sure to allocate the snapshot with either
* a tracing_snapshot_alloc(), or by doing it manually
* with: echo 1 > /sys/kernel/debug/tracing/snapshot
* with: echo 1 > /sys/kernel/tracing/snapshot
*
* If the snapshot buffer is not allocated, it will stop tracing.
* Basically making a permanent snapshot.

6
scripts/tracing/draw_functrace.py
View File

@ -12,9 +12,9 @@ calls. Only the functions's names and the the call time are provided.
Usage:
Be sure that you have CONFIG_FUNCTION_TRACER
# mount -t debugfs nodev /sys/kernel/debug
# echo function > /sys/kernel/debug/tracing/current_tracer
$ cat /sys/kernel/debug/tracing/trace_pipe > ~/raw_trace_func
# mount -t tracefs nodev /sys/kernel/tracing
# echo function > /sys/kernel/tracing/current_tracer
$ cat /sys/kernel/tracing/trace_pipe > ~/raw_trace_func
Wait some times but not too much, the script is a bit slow.
Break the pipe (Ctrl + Z)
$ scripts/tracing/draw_functrace.py < ~/raw_trace_func > draw_functrace

3
tools/arch/x86/include/uapi/asm/unistd_32.h
View File

@ -1,4 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __NR_fork
#define __NR_fork 2
#endif
#ifndef __NR_execve
#define __NR_execve 11
#endif

3
tools/arch/x86/include/uapi/asm/unistd_64.h
View File

@ -1,4 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __NR_fork
#define __NR_fork 57
#endif
#ifndef __NR_execve
#define __NR_execve 59
#endif

2
tools/build/Makefile.feature
View File

@ -64,6 +64,7 @@ FEATURE_TESTS_BASIC := \
lzma \
get_cpuid \
bpf \
scandirat \
sched_getcpu \
sdt \
setns \
@ -79,6 +80,7 @@ FEATURE_TESTS_EXTRA := \
compile-32 \
compile-x32 \
cplus-demangle \
cxa-demangle \
gtk2 \
gtk2-infobar \
hello \

17
tools/build/feature/Makefile
View File

@ -22,6 +22,7 @@ FILES= \
test-libbfd-liberty.bin \
test-libbfd-liberty-z.bin \
test-cplus-demangle.bin \
test-cxa-demangle.bin \
test-libcap.bin \
test-libelf.bin \
test-libelf-getphdrnum.bin \
@ -57,19 +58,13 @@ FILES= \
test-lzma.bin \
test-bpf.bin \
test-libbpf.bin \
test-libbpf-btf__load_from_kernel_by_id.bin \
test-libbpf-bpf_prog_load.bin \
test-libbpf-bpf_map_create.bin \
test-libbpf-bpf_object__next_program.bin \
test-libbpf-bpf_object__next_map.bin \
test-libbpf-bpf_program__set_insns.bin \
test-libbpf-btf__raw_data.bin \
test-get_cpuid.bin \
test-sdt.bin \
test-cxx.bin \
test-gettid.bin \
test-jvmti.bin \
test-jvmti-cmlr.bin \
test-scandirat.bin \
test-sched_getcpu.bin \
test-setns.bin \
test-libopencsd.bin \
@ -132,6 +127,9 @@ $(OUTPUT)test-get_current_dir_name.bin:
$(OUTPUT)test-glibc.bin:
$(BUILD)
$(OUTPUT)test-scandirat.bin:
$(BUILD)
$(OUTPUT)test-sched_getcpu.bin:
$(BUILD)
@ -207,7 +205,7 @@ $(OUTPUT)test-libtraceevent.bin:
$(BUILD) -ltraceevent
$(OUTPUT)test-libtracefs.bin:
$(BUILD) -ltracefs
$(BUILD) $(shell $(PKG_CONFIG) --cflags libtraceevent 2>/dev/null) -ltracefs
$(OUTPUT)test-libcrypto.bin:
$(BUILD) -lcrypto
@ -261,6 +259,9 @@ $(OUTPUT)test-libbfd-liberty-z.bin:
$(OUTPUT)test-cplus-demangle.bin:
$(BUILD) -liberty
$(OUTPUT)test-cxa-demangle.bin:
$(BUILDXX)
$(OUTPUT)test-backtrace.bin:
$(BUILD)

5
tools/build/feature/test-all.c
View File

@ -114,6 +114,10 @@
# include "test-pthread-barrier.c"
#undef main
#define main main_test_scandirat
# include "test-scandirat.c"
#undef main
#define main main_test_sched_getcpu
# include "test-sched_getcpu.c"
#undef main
@ -202,6 +206,7 @@ int main(int argc, char *argv[])
main_test_get_cpuid();
main_test_bpf();
main_test_libcrypto();
main_test_scandirat();
main_test_sched_getcpu();
main_test_sdt();
main_test_setns();

17
tools/build/feature/test-cxa-demangle.cpp Normal file
View File

@ -0,0 +1,17 @@
// SPDX-License-Identifier: GPL-2.0
#include <stdio.h>
#include <stdlib.h>
#include <cxxabi.h>
int main(void)
{
size_t len = 256;
char *output = (char*)malloc(len);
int status;
output = abi::__cxa_demangle("FieldName__9ClassNameFd", output, &len, &status);
printf("demangled symbol: {%s}\n", output);
return 0;
}

8
tools/build/feature/test-libbpf-bpf_map_create.c
View File

@ -1,8 +0,0 @@
// SPDX-License-Identifier: GPL-2.0
#include <bpf/bpf.h>
int main(void)
{
return bpf_map_create(0 /* map_type */, NULL /* map_name */, 0, /* key_size */,
0 /* value_size */, 0 /* max_entries */, NULL /* opts */);
}

8
tools/build/feature/test-libbpf-bpf_object__next_map.c
View File

@ -1,8 +0,0 @@
// SPDX-License-Identifier: GPL-2.0
#include <bpf/libbpf.h>
int main(void)
{
bpf_object__next_map(NULL /* obj */, NULL /* prev */);
return 0;
}

8
tools/build/feature/test-libbpf-bpf_object__next_program.c
View File

@ -1,8 +0,0 @@
// SPDX-License-Identifier: GPL-2.0
#include <bpf/libbpf.h>
int main(void)
{
bpf_object__next_program(NULL /* obj */, NULL /* prev */);
return 0;
}

9
tools/build/feature/test-libbpf-bpf_prog_load.c
View File

@ -1,9 +0,0 @@
// SPDX-License-Identifier: GPL-2.0
#include <bpf/bpf.h>
int main(void)
{
return bpf_prog_load(0 /* prog_type */, NULL /* prog_name */,
NULL /* license */, NULL /* insns */,
0 /* insn_cnt */, NULL /* opts */);
}

8
tools/build/feature/test-libbpf-bpf_program__set_insns.c
View File

@ -1,8 +0,0 @@
// SPDX-License-Identifier: GPL-2.0
#include <bpf/libbpf.h>
int main(void)
{
bpf_program__set_insns(NULL /* prog */, NULL /* new_insns */, 0 /* new_insn_cnt */);
return 0;
}

8
tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c
View File

@ -1,8 +0,0 @@
// SPDX-License-Identifier: GPL-2.0
#include <bpf/btf.h>
int main(void)
{
btf__load_from_kernel_by_id(20151128);
return 0;
}

8
tools/build/feature/test-libbpf-btf__raw_data.c
View File

@ -1,8 +0,0 @@
// SPDX-License-Identifier: GPL-2.0
#include <bpf/btf.h>
int main(void)
{
btf__raw_data(NULL /* btf_ro */, NULL /* size */);
return 0;
}

4
tools/build/feature/test-libbpf.c
View File

@ -1,6 +1,10 @@
// SPDX-License-Identifier: GPL-2.0
#include <bpf/libbpf.h>
#if !defined(LIBBPF_MAJOR_VERSION) || (LIBBPF_MAJOR_VERSION < 1)
#error At least libbpf 1.0 is required for Linux tools.
#endif
int main(void)
{
return bpf_object__open("test") ? 0 : -1;

13
tools/build/feature/test-scandirat.c Normal file
View File

@ -0,0 +1,13 @@
// SPDX-License-Identifier: GPL-2.0
#ifndef _GNU_SOURCE
#define _GNU_SOURCE
#endif
#include <dirent.h>
int main(void)
{
// expects non-NULL, arg3 is 'restrict' so "pointers" have to be different
return scandirat(/*dirfd=*/ 0, /*dirp=*/ (void *)1, /*namelist=*/ (void *)2, /*filter=*/ (void *)3, /*compar=*/ (void *)4);
}
#undef _GNU_SOURCE

6
tools/include/linux/compiler-gcc.h
View File

@ -12,8 +12,10 @@
+ __GNUC_PATCHLEVEL__)
#endif
#if GCC_VERSION >= 70000 && !defined(__CHECKER__)
# define __fallthrough __attribute__ ((fallthrough))
#if __has_attribute(__fallthrough__)
# define fallthrough __attribute__((__fallthrough__))
#else
# define fallthrough do {} while (0) /* fallthrough */
#endif
#if GCC_VERSION >= 40300

4
tools/include/linux/compiler.h
View File

@ -186,10 +186,6 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
})
#ifndef __fallthrough
# define __fallthrough
#endif
/* Indirect macros required for expanded argument pasting, eg. __LINE__. */
#define ___PASTE(a, b) a##b
#define __PASTE(a, b) ___PASTE(a, b)

34
tools/include/linux/coresight-pmu.h
View File

@ -7,8 +7,19 @@
#ifndef _LINUX_CORESIGHT_PMU_H
#define _LINUX_CORESIGHT_PMU_H
#include <linux/bits.h>
#define CORESIGHT_ETM_PMU_NAME "cs_etm"
#define CORESIGHT_ETM_PMU_SEED 0x10
/*
* The legacy Trace ID system based on fixed calculation from the cpu
* number. This has been replaced by drivers using a dynamic allocation
* system - but need to retain the legacy algorithm for backward comparibility
* in certain situations:-
* a) new perf running on older systems that generate the legacy mapping
* b) older tools that may not update at the same time as the kernel.
*/
#define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) (0x10 + (cpu * 2))
/*
* Below are the definition of bit offsets for perf option, and works as
@ -34,15 +45,16 @@
#define ETM4_CFG_BIT_RETSTK 12
#define ETM4_CFG_BIT_VMID_OPT 15
static inline int coresight_get_trace_id(int cpu)
{
/*
* A trace ID of value 0 is invalid, so let's start at some
* random value that fits in 7 bits and go from there. Since
* the common convention is to have data trace IDs be I(N) + 1,
* set instruction trace IDs as a function of the CPU number.
*/
return (CORESIGHT_ETM_PMU_SEED + (cpu * 2));
}
/*
* Interpretation of the PERF_RECORD_AUX_OUTPUT_HW_ID payload.
* Used to associate a CPU with the CoreSight Trace ID.
* [07:00] - Trace ID - uses 8 bits to make value easy to read in file.
* [59:08] - Unused (SBZ)
* [63:60] - Version
*/
#define CS_AUX_HW_ID_TRACE_ID_MASK GENMASK_ULL(7, 0)
#define CS_AUX_HW_ID_VERSION_MASK GENMASK_ULL(63, 60)
#define CS_AUX_HW_ID_CURR_VERSION 0
#endif

3
tools/include/uapi/linux/perf_event.h
View File

@ -1339,7 +1339,8 @@ union perf_mem_data_src {
#define PERF_MEM_LVLNUM_L2 0x02 /* L2 */
#define PERF_MEM_LVLNUM_L3 0x03 /* L3 */
#define PERF_MEM_LVLNUM_L4 0x04 /* L4 */
/* 5-0x8 available */
/* 5-0x7 available */
#define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */
#define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */
#define PERF_MEM_LVLNUM_IO 0x0a /* I/O */
#define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */

17
tools/lib/api/fs/cgroup.c
View File

@ -14,7 +14,7 @@ struct cgroupfs_cache_entry {
};
/* just cache last used one */
static struct cgroupfs_cache_entry cached;
static struct cgroupfs_cache_entry *cached;
int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys)
{
@ -24,9 +24,9 @@ int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys)
char *p, *path;
char mountpoint[PATH_MAX];
if (!strcmp(cached.subsys, subsys)) {
if (strlen(cached.mountpoint) < maxlen) {
strcpy(buf, cached.mountpoint);
if (cached && !strcmp(cached->subsys, subsys)) {
if (strlen(cached->mountpoint) < maxlen) {
strcpy(buf, cached->mountpoint);
return 0;
}
return -1;
@ -91,8 +91,13 @@ int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys)
free(line);
fclose(fp);
strncpy(cached.subsys, subsys, sizeof(cached.subsys) - 1);
strcpy(cached.mountpoint, mountpoint);
if (!cached)
cached = calloc(1, sizeof(*cached));
if (cached) {
strncpy(cached->subsys, subsys, sizeof(cached->subsys) - 1);
strcpy(cached->mountpoint, mountpoint);
}
if (mountpoint[0] && strlen(mountpoint) < maxlen) {
strcpy(buf, mountpoint);

226
tools/lib/api/fs/fs.c
View File

@ -1,4 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
#include <assert.h>
#include <ctype.h>
#include <errno.h>
#include <limits.h>
@ -10,6 +11,7 @@
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <pthread.h>
#include <unistd.h>
#include <sys/mount.h>
@ -43,7 +45,7 @@
#define BPF_FS_MAGIC 0xcafe4a11
#endif
static const char * const sysfs__fs_known_mountpoints[] = {
static const char * const sysfs__known_mountpoints[] = {
"/sys",
0,
};
@ -86,87 +88,89 @@ static const char * const bpf_fs__known_mountpoints[] = {
};
struct fs {
const char *name;
const char * const *mounts;
char path[PATH_MAX];
bool found;
bool checked;
long magic;
};
enum {
FS__SYSFS = 0,
FS__PROCFS = 1,
FS__DEBUGFS = 2,
FS__TRACEFS = 3,
FS__HUGETLBFS = 4,
FS__BPF_FS = 5,
const char * const name;
const char * const * const mounts;
char *path;
pthread_mutex_t mount_mutex;
const long magic;
};
#ifndef TRACEFS_MAGIC
#define TRACEFS_MAGIC 0x74726163
#endif
static struct fs fs__entries[] = {
[FS__SYSFS] = {
.name = "sysfs",
.mounts = sysfs__fs_known_mountpoints,
.magic = SYSFS_MAGIC,
.checked = false,
},
[FS__PROCFS] = {
.name = "proc",
.mounts = procfs__known_mountpoints,
.magic = PROC_SUPER_MAGIC,
.checked = false,
},
[FS__DEBUGFS] = {
.name = "debugfs",
.mounts = debugfs__known_mountpoints,
.magic = DEBUGFS_MAGIC,
.checked = false,
},
[FS__TRACEFS] = {
.name = "tracefs",
.mounts = tracefs__known_mountpoints,
.magic = TRACEFS_MAGIC,
.checked = false,
},
[FS__HUGETLBFS] = {
.name = "hugetlbfs",
.mounts = hugetlbfs__known_mountpoints,
.magic = HUGETLBFS_MAGIC,
.checked = false,
},
[FS__BPF_FS] = {
.name = "bpf",
.mounts = bpf_fs__known_mountpoints,
.magic = BPF_FS_MAGIC,
.checked = false,
},
};
static void fs__init_once(struct fs *fs);
static const char *fs__mountpoint(const struct fs *fs);
static const char *fs__mount(struct fs *fs);
#define FS(lower_name, fs_name, upper_name) \
static struct fs fs__##lower_name = { \
.name = #fs_name, \
.mounts = lower_name##__known_mountpoints, \
.magic = upper_name##_MAGIC, \
.mount_mutex = PTHREAD_MUTEX_INITIALIZER, \
}; \
\
static void lower_name##_init_once(void) \
{ \
struct fs *fs = &fs__##lower_name; \
\
fs__init_once(fs); \
} \
\
const char *lower_name##__mountpoint(void) \
{ \
static pthread_once_t init_once = PTHREAD_ONCE_INIT; \
struct fs *fs = &fs__##lower_name; \
\
pthread_once(&init_once, lower_name##_init_once); \
return fs__mountpoint(fs); \
} \
\
const char *lower_name##__mount(void) \
{ \
const char *mountpoint = lower_name##__mountpoint(); \
struct fs *fs = &fs__##lower_name; \
\
if (mountpoint) \
return mountpoint; \
\
return fs__mount(fs); \
} \
\
bool lower_name##__configured(void) \
{ \
return lower_name##__mountpoint() != NULL; \
}
FS(sysfs, sysfs, SYSFS);
FS(procfs, procfs, PROC_SUPER);
FS(debugfs, debugfs, DEBUGFS);
FS(tracefs, tracefs, TRACEFS);
FS(hugetlbfs, hugetlbfs, HUGETLBFS);
FS(bpf_fs, bpf, BPF_FS);
static bool fs__read_mounts(struct fs *fs)
{
bool found = false;
char type[100];
FILE *fp;
char path[PATH_MAX + 1];
fp = fopen("/proc/mounts", "r");
if (fp == NULL)
return NULL;
return false;
while (!found &&
fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n",
fs->path, type) == 2) {
while (fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n",
path, type) == 2) {
if (strcmp(type, fs->name) == 0)
found = true;
if (strcmp(type, fs->name) == 0) {
fs->path = strdup(path);
fclose(fp);
return fs->path != NULL;
}
}
fclose(fp);
fs->checked = true;
return fs->found = found;
return false;
}
static int fs__valid_mount(const char *fs, long magic)
@ -188,8 +192,9 @@ static bool fs__check_mounts(struct fs *fs)
ptr = fs->mounts;
while (*ptr) {
if (fs__valid_mount(*ptr, fs->magic) == 0) {
fs->found = true;
strcpy(fs->path, *ptr);
fs->path = strdup(*ptr);
if (!fs->path)
return false;
return true;
}
ptr++;
@ -227,43 +232,26 @@ static bool fs__env_override(struct fs *fs)
if (!override_path)
return false;
fs->found = true;
fs->checked = true;
strncpy(fs->path, override_path, sizeof(fs->path) - 1);
fs->path[sizeof(fs->path) - 1] = '\0';
fs->path = strdup(override_path);
if (!fs->path)
return false;
return true;
}
static const char *fs__get_mountpoint(struct fs *fs)
static void fs__init_once(struct fs *fs)
{
if (fs__env_override(fs))
return fs->path;
if (fs__check_mounts(fs))
return fs->path;
if (fs__read_mounts(fs))
return fs->path;
return NULL;
if (!fs__env_override(fs) &&
!fs__check_mounts(fs) &&
!fs__read_mounts(fs)) {
assert(!fs->path);
} else {
assert(fs->path);
}
}
static const char *fs__mountpoint(int idx)
static const char *fs__mountpoint(const struct fs *fs)
{
struct fs *fs = &fs__entries[idx];
if (fs->found)
return (const char *)fs->path;
/* the mount point was already checked for the mount point
* but and did not exist, so return NULL to avoid scanning again.
* This makes the found and not found paths cost equivalent
* in case of multiple calls.
*/
if (fs->checked)
return NULL;
return fs__get_mountpoint(fs);
return fs->path;
}
static const char *mount_overload(struct fs *fs)
@ -278,45 +266,29 @@ static const char *mount_overload(struct fs *fs)
return getenv(upper_name) ?: *fs->mounts;
}
static const char *fs__mount(int idx)
static const char *fs__mount(struct fs *fs)
{
struct fs *fs = &fs__entries[idx];
const char *mountpoint;
if (fs__mountpoint(idx))
return (const char *)fs->path;
pthread_mutex_lock(&fs->mount_mutex);
/* Check if path found inside the mutex to avoid races with other callers of mount. */
mountpoint = fs__mountpoint(fs);
if (mountpoint)
goto out;
mountpoint = mount_overload(fs);
if (mount(NULL, mountpoint, fs->name, 0, NULL) < 0)
return NULL;
return fs__check_mounts(fs) ? fs->path : NULL;
if (mount(NULL, mountpoint, fs->name, 0, NULL) == 0 &&
fs__valid_mount(mountpoint, fs->magic) == 0) {
fs->path = strdup(mountpoint);
mountpoint = fs->path;
}
out:
pthread_mutex_unlock(&fs->mount_mutex);
return mountpoint;
}
#define FS(name, idx) \
const char *name##__mountpoint(void) \
{ \
return fs__mountpoint(idx); \
} \
\
const char *name##__mount(void) \
{ \
return fs__mount(idx); \
} \
\
bool name##__configured(void) \
{ \
return name##__mountpoint() != NULL; \
}
FS(sysfs, FS__SYSFS);
FS(procfs, FS__PROCFS);
FS(debugfs, FS__DEBUGFS);
FS(tracefs, FS__TRACEFS);
FS(hugetlbfs, FS__HUGETLBFS);
FS(bpf_fs, FS__BPF_FS);
int filename__read_int(const char *filename, int *value)
{
char line[64];

19
tools/lib/api/fs/tracing_path.c
View File

@ -13,17 +13,12 @@
#include "tracing_path.h"
static char tracing_mnt[PATH_MAX] = "/sys/kernel/debug";
static char tracing_path[PATH_MAX] = "/sys/kernel/debug/tracing";
static char tracing_events_path[PATH_MAX] = "/sys/kernel/debug/tracing/events";
static char tracing_path[PATH_MAX] = "/sys/kernel/tracing";
static void __tracing_path_set(const char *tracing, const char *mountpoint)
{
snprintf(tracing_mnt, sizeof(tracing_mnt), "%s", mountpoint);
snprintf(tracing_path, sizeof(tracing_path), "%s/%s",
mountpoint, tracing);
snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s%s",
mountpoint, tracing, "events");
}
static const char *tracing_path_tracefs_mount(void)
@ -149,15 +144,15 @@ int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
/* sdt markers */
if (!strncmp(filename, "sdt_", 4)) {
snprintf(buf, size,
"Error:\tFile %s/%s not found.\n"
"Error:\tFile %s/events/%s not found.\n"
"Hint:\tSDT event cannot be directly recorded on.\n"
"\tPlease first use 'perf probe %s:%s' before recording it.\n",
tracing_events_path, filename, sys, name);
tracing_path, filename, sys, name);
} else {
snprintf(buf, size,
"Error:\tFile %s/%s not found.\n"
"Error:\tFile %s/events/%s not found.\n"
"Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n",
tracing_events_path, filename);
tracing_path, filename);
}
break;
}
@ -169,9 +164,9 @@ int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
break;
case EACCES: {
snprintf(buf, size,
"Error:\tNo permissions to read %s/%s\n"
"Error:\tNo permissions to read %s/events/%s\n"
"Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
tracing_events_path, filename, tracing_path_mount());
tracing_path, filename, tracing_path_mount());
}
break;
default:

73
tools/lib/api/io.h
View File

@ -7,7 +7,10 @@
#ifndef __API_IO__
#define __API_IO__
#include <errno.h>
#include <poll.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
struct io {
@ -21,6 +24,8 @@ struct io {
char *end;
/* Currently accessed data pointer. */
char *data;
/* Read timeout, 0 implies no timeout. */
int timeout_ms;
/* Set true on when the end of file on read error. */
bool eof;
};
@ -33,6 +38,7 @@ static inline void io__init(struct io *io, int fd,
io->buf = buf;
io->end = buf;
io->data = buf;
io->timeout_ms = 0;
io->eof = false;
}
@ -45,7 +51,29 @@ static inline int io__get_char(struct io *io)
return -1;
if (ptr == io->end) {
ssize_t n = read(io->fd, io->buf, io->buf_len);
ssize_t n;
if (io->timeout_ms != 0) {
struct pollfd pfds[] = {
{
.fd = io->fd,
.events = POLLIN,
},
};
n = poll(pfds, 1, io->timeout_ms);
if (n == 0)
errno = ETIMEDOUT;
if (n > 0 && !(pfds[0].revents & POLLIN)) {
errno = EIO;
n = -1;
}
if (n <= 0) {
io->eof = true;
return -1;
}
}
n = read(io->fd, io->buf, io->buf_len);
if (n <= 0) {
io->eof = true;
@ -112,4 +140,47 @@ static inline int io__get_dec(struct io *io, __u64 *dec)
}
}
/* Read up to and including the first newline following the pattern of getline. */
static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_len_out)
{
char buf[128];
int buf_pos = 0;
char *line = NULL, *temp;
size_t line_len = 0;
int ch = 0;
/* TODO: reuse previously allocated memory. */
free(*line_out);
while (ch != '\n') {
ch = io__get_char(io);
if (ch < 0)
break;
if (buf_pos == sizeof(buf)) {
temp = realloc(line, line_len + sizeof(buf));
if (!temp)
goto err_out;
line = temp;
memcpy(&line[line_len], buf, sizeof(buf));
line_len += sizeof(buf);
buf_pos = 0;
}
buf[buf_pos++] = (char)ch;
}
temp = realloc(line, line_len + buf_pos + 1);
if (!temp)
goto err_out;
line = temp;
memcpy(&line[line_len], buf, buf_pos);
line[line_len + buf_pos] = '\0';
line_len += buf_pos;
*line_out = line;
*line_len_out = line_len;
return line_len;
err_out:
free(line);
return -ENOMEM;
}
#endif /* __API_IO__ */

2
tools/lib/perf/Makefile
View File

@ -188,7 +188,7 @@ install_lib: libs
cp -fpR $(LIBPERF_ALL) $(DESTDIR)$(libdir_SQ)
HDRS := bpf_perf.h core.h cpumap.h threadmap.h evlist.h evsel.h event.h mmap.h
INTERNAL_HDRS := cpumap.h evlist.h evsel.h lib.h mmap.h threadmap.h xyarray.h
INTERNAL_HDRS := cpumap.h evlist.h evsel.h lib.h mmap.h rc_check.h threadmap.h xyarray.h
INSTALL_HDRS_PFX := $(DESTDIR)$(prefix)/include/perf
INSTALL_HDRS := $(addprefix $(INSTALL_HDRS_PFX)/, $(HDRS))

171
tools/lib/perf/cpumap.c
View File

@ -10,16 +10,21 @@
#include <ctype.h>
#include <limits.h>
static struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus)
{
struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);
RC_CHK_ACCESS(map)->nr = nr_cpus;
}
if (cpus != NULL) {
struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
{
RC_STRUCT(perf_cpu_map) *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);
struct perf_cpu_map *result;
if (ADD_RC_CHK(result, cpus)) {
cpus->nr = nr_cpus;
refcount_set(&cpus->refcnt, 1);
}
return cpus;
return result;
}
struct perf_cpu_map *perf_cpu_map__dummy_new(void)
@ -27,7 +32,7 @@ struct perf_cpu_map *perf_cpu_map__dummy_new(void)
struct perf_cpu_map *cpus = perf_cpu_map__alloc(1);
if (cpus)
cpus->map[0].cpu = -1;
RC_CHK_ACCESS(cpus)->map[0].cpu = -1;
return cpus;
}
@ -35,23 +40,30 @@ struct perf_cpu_map *perf_cpu_map__dummy_new(void)
static void cpu_map__delete(struct perf_cpu_map *map)
{
if (map) {
WARN_ONCE(refcount_read(&map->refcnt) != 0,
WARN_ONCE(refcount_read(perf_cpu_map__refcnt(map)) != 0,
"cpu_map refcnt unbalanced\n");
free(map);
RC_CHK_FREE(map);
}
}
struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map)
{
if (map)
refcount_inc(&map->refcnt);
return map;
struct perf_cpu_map *result;
if (RC_CHK_GET(result, map))
refcount_inc(perf_cpu_map__refcnt(map));
return result;
}
void perf_cpu_map__put(struct perf_cpu_map *map)
{
if (map && refcount_dec_and_test(&map->refcnt))
cpu_map__delete(map);
if (map) {
if (refcount_dec_and_test(perf_cpu_map__refcnt(map)))
cpu_map__delete(map);
else
RC_CHK_PUT(map);
}
}
static struct perf_cpu_map *cpu_map__default_new(void)
@ -68,7 +80,7 @@ static struct perf_cpu_map *cpu_map__default_new(void)
int i;
for (i = 0; i < nr_cpus; ++i)
cpus->map[i].cpu = i;
RC_CHK_ACCESS(cpus)->map[i].cpu = i;
}
return cpus;
@ -87,6 +99,11 @@ static int cmp_cpu(const void *a, const void *b)
return cpu_a->cpu - cpu_b->cpu;
}
static struct perf_cpu __perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
{
return RC_CHK_ACCESS(cpus)->map[idx];
}
static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu *tmp_cpus)
{
size_t payload_size = nr_cpus * sizeof(struct perf_cpu);
@ -94,15 +111,19 @@ static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu
int i, j;
if (cpus != NULL) {
memcpy(cpus->map, tmp_cpus, payload_size);
qsort(cpus->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu);
memcpy(RC_CHK_ACCESS(cpus)->map, tmp_cpus, payload_size);
qsort(RC_CHK_ACCESS(cpus)->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu);
/* Remove dups */
j = 0;
for (i = 0; i < nr_cpus; i++) {
if (i == 0 || cpus->map[i].cpu != cpus->map[i - 1].cpu)
cpus->map[j++].cpu = cpus->map[i].cpu;
if (i == 0 ||
__perf_cpu_map__cpu(cpus, i).cpu !=
__perf_cpu_map__cpu(cpus, i - 1).cpu) {
RC_CHK_ACCESS(cpus)->map[j++].cpu =
__perf_cpu_map__cpu(cpus, i).cpu;
}
}
cpus->nr = j;
perf_cpu_map__set_nr(cpus, j);
assert(j <= nr_cpus);
}
return cpus;
@ -257,26 +278,31 @@ out:
return cpus;
}
static int __perf_cpu_map__nr(const struct perf_cpu_map *cpus)
{
return RC_CHK_ACCESS(cpus)->nr;
}
struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
{
struct perf_cpu result = {
.cpu = -1
};
if (cpus && idx < cpus->nr)
return cpus->map[idx];
if (cpus && idx < __perf_cpu_map__nr(cpus))
return __perf_cpu_map__cpu(cpus, idx);
return result;
}
int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
{
return cpus ? cpus->nr : 1;
return cpus ? __perf_cpu_map__nr(cpus) : 1;
}
bool perf_cpu_map__empty(const struct perf_cpu_map *map)
{
return map ? map->map[0].cpu == -1 : true;
return map ? __perf_cpu_map__cpu(map, 0).cpu == -1 : true;
}
int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
@ -287,10 +313,10 @@ int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
return -1;
low = 0;
high = cpus->nr;
high = __perf_cpu_map__nr(cpus);
while (low < high) {
int idx = (low + high) / 2;
struct perf_cpu cpu_at_idx = cpus->map[idx];
struct perf_cpu cpu_at_idx = __perf_cpu_map__cpu(cpus, idx);
if (cpu_at_idx.cpu == cpu.cpu)
return idx;
@ -309,6 +335,32 @@ bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
return perf_cpu_map__idx(cpus, cpu) != -1;
}
bool perf_cpu_map__equal(const struct perf_cpu_map *lhs, const struct perf_cpu_map *rhs)
{
int nr;
if (lhs == rhs)
return true;
if (!lhs || !rhs)
return false;
nr = __perf_cpu_map__nr(lhs);
if (nr != __perf_cpu_map__nr(rhs))
return false;
for (int idx = 0; idx < nr; idx++) {
if (__perf_cpu_map__cpu(lhs, idx).cpu != __perf_cpu_map__cpu(rhs, idx).cpu)
return false;
}
return true;
}
bool perf_cpu_map__has_any_cpu(const struct perf_cpu_map *map)
{
return map && __perf_cpu_map__cpu(map, 0).cpu == -1;
}
struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map)
{
struct perf_cpu result = {
@ -316,7 +368,9 @@ struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map)
};
// cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well.
return map->nr > 0 ? map->map[map->nr - 1] : result;
return __perf_cpu_map__nr(map) > 0
? __perf_cpu_map__cpu(map, __perf_cpu_map__nr(map) - 1)
: result;
}
/** Is 'b' a subset of 'a'. */
@ -324,15 +378,15 @@ bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu
{
if (a == b || !b)
return true;
if (!a || b->nr > a->nr)
if (!a || __perf_cpu_map__nr(b) > __perf_cpu_map__nr(a))
return false;
for (int i = 0, j = 0; i < a->nr; i++) {
if (a->map[i].cpu > b->map[j].cpu)
for (int i = 0, j = 0; i < __perf_cpu_map__nr(a); i++) {
if (__perf_cpu_map__cpu(a, i).cpu > __perf_cpu_map__cpu(b, j).cpu)
return false;
if (a->map[i].cpu == b->map[j].cpu) {
if (__perf_cpu_map__cpu(a, i).cpu == __perf_cpu_map__cpu(b, j).cpu) {
j++;
if (j == b->nr)
if (j == __perf_cpu_map__nr(b))
return true;
}
}
@ -362,27 +416,27 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
return perf_cpu_map__get(other);
}
tmp_len = orig->nr + other->nr;
tmp_len = __perf_cpu_map__nr(orig) + __perf_cpu_map__nr(other);
tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
if (!tmp_cpus)
return NULL;
/* Standard merge algorithm from wikipedia */
i = j = k = 0;
while (i < orig->nr && j < other->nr) {
if (orig->map[i].cpu <= other->map[j].cpu) {
if (orig->map[i].cpu == other->map[j].cpu)
while (i < __perf_cpu_map__nr(orig) && j < __perf_cpu_map__nr(other)) {
if (__perf_cpu_map__cpu(orig, i).cpu <= __perf_cpu_map__cpu(other, j).cpu) {
if (__perf_cpu_map__cpu(orig, i).cpu == __perf_cpu_map__cpu(other, j).cpu)
j++;
tmp_cpus[k++] = orig->map[i++];
tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++);
} else
tmp_cpus[k++] = other->map[j++];
tmp_cpus[k++] = __perf_cpu_map__cpu(other, j++);
}
while (i < orig->nr)
tmp_cpus[k++] = orig->map[i++];
while (i < __perf_cpu_map__nr(orig))
tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++);
while (j < other->nr)
tmp_cpus[k++] = other->map[j++];
while (j < __perf_cpu_map__nr(other))
tmp_cpus[k++] = __perf_cpu_map__cpu(other, j++);
assert(k <= tmp_len);
merged = cpu_map__trim_new(k, tmp_cpus);
@ -390,3 +444,38 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
perf_cpu_map__put(orig);
return merged;
}
struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig,
struct perf_cpu_map *other)
{
struct perf_cpu *tmp_cpus;
int tmp_len;
int i, j, k;
struct perf_cpu_map *merged = NULL;
if (perf_cpu_map__is_subset(other, orig))
return perf_cpu_map__get(orig);
if (perf_cpu_map__is_subset(orig, other))
return perf_cpu_map__get(other);
tmp_len = max(__perf_cpu_map__nr(orig), __perf_cpu_map__nr(other));
tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
if (!tmp_cpus)
return NULL;
i = j = k = 0;
while (i < __perf_cpu_map__nr(orig) && j < __perf_cpu_map__nr(other)) {
if (__perf_cpu_map__cpu(orig, i).cpu < __perf_cpu_map__cpu(other, j).cpu)
i++;
else if (__perf_cpu_map__cpu(orig, i).cpu > __perf_cpu_map__cpu(other, j).cpu)
j++;
else {
j++;
tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++);
}
}
if (k)
merged = cpu_map__trim_new(k, tmp_cpus);
free(tmp_cpus);
return merged;
}

56
tools/lib/perf/evlist.c
View File

@ -36,18 +36,33 @@ void perf_evlist__init(struct perf_evlist *evlist)
static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
struct perf_evsel *evsel)
{
/*
* We already have cpus for evsel (via PMU sysfs) so
* keep it, if there's no target cpu list defined.
*/
if (evsel->system_wide) {
/* System wide: set the cpu map of the evsel to all online CPUs. */
perf_cpu_map__put(evsel->cpus);
evsel->cpus = perf_cpu_map__new(NULL);
} else if (evlist->has_user_cpus && evsel->is_pmu_core) {
/*
* User requested CPUs on a core PMU, ensure the requested CPUs
* are valid by intersecting with those of the PMU.
*/
perf_cpu_map__put(evsel->cpus);
evsel->cpus = perf_cpu_map__intersect(evlist->user_requested_cpus, evsel->own_cpus);
} else if (!evsel->own_cpus || evlist->has_user_cpus ||
(!evsel->requires_cpu && perf_cpu_map__empty(evlist->user_requested_cpus))) {
(!evsel->requires_cpu && perf_cpu_map__has_any_cpu(evlist->user_requested_cpus))) {
/*
* The PMU didn't specify a default cpu map, this isn't a core
* event and the user requested CPUs or the evlist user
* requested CPUs have the "any CPU" (aka dummy) CPU value. In
* which case use the user requested CPUs rather than the PMU
* ones.
*/
perf_cpu_map__put(evsel->cpus);
evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
} else if (evsel->cpus != evsel->own_cpus) {
/*
* No user requested cpu map but the PMU cpu map doesn't match
* the evsel's. Reset it back to the PMU cpu map.
*/
perf_cpu_map__put(evsel->cpus);
evsel->cpus = perf_cpu_map__get(evsel->own_cpus);
}
@ -687,15 +702,14 @@ perf_evlist__next_mmap(struct perf_evlist *evlist, struct perf_mmap *map,
void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader)
{
struct perf_evsel *first, *last, *evsel;
struct perf_evsel *evsel;
int n = 0;
first = list_first_entry(list, struct perf_evsel, node);
last = list_last_entry(list, struct perf_evsel, node);
leader->nr_members = last->idx - first->idx + 1;
__perf_evlist__for_each_entry(list, evsel)
__perf_evlist__for_each_entry(list, evsel) {
evsel->leader = leader;
n++;
}
leader->nr_members = n;
}
void perf_evlist__set_leader(struct perf_evlist *evlist)
@ -704,7 +718,23 @@ void perf_evlist__set_leader(struct perf_evlist *evlist)
struct perf_evsel *first = list_entry(evlist->entries.next,
struct perf_evsel, node);
evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0;
__perf_evlist__set_leader(&evlist->entries, first);
}
}
int perf_evlist__nr_groups(struct perf_evlist *evlist)
{
struct perf_evsel *evsel;
int nr_groups = 0;
perf_evlist__for_each_evsel(evlist, evsel) {
/*
* evsels by default have a nr_members of 1, and they are their
* own leader. If the nr_members is >1 then this is an
* indication of a group.
*/
if (evsel->leader == evsel && evsel->nr_members > 1)
nr_groups++;
}
return nr_groups;
}

10
tools/lib/perf/include/internal/cpumap.h
View File

@ -4,6 +4,7 @@
#include <linux/refcount.h>
#include <perf/cpumap.h>
#include <internal/rc_check.h>
/**
* A sized, reference counted, sorted array of integers representing CPU
@ -12,7 +13,7 @@
* gaps if CPU numbers were used. For events associated with a pid, rather than
* a CPU, a single dummy map with an entry of -1 is used.
*/
struct perf_cpu_map {
DECLARE_RC_STRUCT(perf_cpu_map) {
refcount_t refcnt;
/** Length of the map array. */
int nr;
@ -24,7 +25,14 @@ struct perf_cpu_map {
#define MAX_NR_CPUS 2048
#endif
struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus);
int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu);
bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b);
void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus);
static inline refcount_t *perf_cpu_map__refcnt(struct perf_cpu_map *map)
{
return &RC_CHK_ACCESS(map)->refcnt;
}
#endif /* __LIBPERF_INTERNAL_CPUMAP_H */

1
tools/lib/perf/include/internal/evlist.h
View File

@ -17,7 +17,6 @@ struct perf_mmap_param;
struct perf_evlist {
struct list_head entries;
int nr_entries;
int nr_groups;
bool has_user_cpus;
bool needs_map_propagation;
/**

15
tools/lib/perf/include/internal/evsel.h
View File

@ -41,7 +41,14 @@ struct perf_sample_id {
struct perf_evsel {
struct list_head node;
struct perf_event_attr attr;
/** The commonly used cpu map of CPUs the event should be opened upon, etc. */
struct perf_cpu_map *cpus;
/**
* The cpu map read from the PMU. For core PMUs this is the list of all
* CPUs the event can be opened upon. For other PMUs this is the default
* cpu map for opening the event on, for example, the first CPU on a
* socket for an uncore event.
*/
struct perf_cpu_map *own_cpus;
struct perf_thread_map *threads;
struct xyarray *fd;
@ -55,9 +62,9 @@ struct perf_evsel {
int nr_members;
/*
* system_wide is for events that need to be on every CPU, irrespective
* of user requested CPUs or threads. Map propagation will set cpus to
* this event's own_cpus, whereby they will contribute to evlist
* all_cpus.
* of user requested CPUs or threads. Tha main example of this is the
* dummy event. Map propagation will set cpus for this event to all CPUs
* as software PMU events like dummy, have a CPU map that is empty.
*/
bool system_wide;
/*
@ -65,6 +72,8 @@ struct perf_evsel {
* i.e. it cannot be the 'any CPU' value of -1.
*/
bool requires_cpu;
/** Is the PMU for the event a core one? Effects the handling of own_cpus. */
bool is_pmu_core;
int idx;
};

102
tools/lib/perf/include/internal/rc_check.h Normal file
View File

@ -0,0 +1,102 @@
/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
#ifndef __LIBPERF_INTERNAL_RC_CHECK_H
#define __LIBPERF_INTERNAL_RC_CHECK_H
#include <stdlib.h>
#include <linux/zalloc.h>
/*
* Enable reference count checking implicitly with leak checking, which is
* integrated into address sanitizer.
*/
#if defined(LEAK_SANITIZER) || defined(ADDRESS_SANITIZER)
#define REFCNT_CHECKING 1
#endif
/*
* Shared reference count checking macros.
*
* Reference count checking is an approach to sanitizing the use of reference
* counted structs. It leverages address and leak sanitizers to make sure gets
* are paired with a put. Reference count checking adds a malloc-ed layer of
* indirection on a get, and frees it on a put. A missed put will be reported as
* a memory leak. A double put will be reported as a double free. Accessing
* after a put will cause a use-after-free and/or a segfault.
*/
#ifndef REFCNT_CHECKING
/* Replaces "struct foo" so that the pointer may be interposed. */
#define DECLARE_RC_STRUCT(struct_name) \
struct struct_name
/* Declare a reference counted struct variable. */
#define RC_STRUCT(struct_name) struct struct_name
/*
* Interpose the indirection. Result will hold the indirection and object is the
* reference counted struct.
*/
#define ADD_RC_CHK(result, object) (result = object, object)
/* Strip the indirection layer. */
#define RC_CHK_ACCESS(object) object
/* Frees the object and the indirection layer. */
#define RC_CHK_FREE(object) free(object)
/* A get operation adding the indirection layer. */
#define RC_CHK_GET(result, object) ADD_RC_CHK(result, object)
/* A put operation removing the indirection layer. */
#define RC_CHK_PUT(object) {}
#else
/* Replaces "struct foo" so that the pointer may be interposed. */
#define DECLARE_RC_STRUCT(struct_name) \
struct original_##struct_name; \
struct struct_name { \
struct original_##struct_name *orig; \
}; \
struct original_##struct_name
/* Declare a reference counted struct variable. */
#define RC_STRUCT(struct_name) struct original_##struct_name
/*
* Interpose the indirection. Result will hold the indirection and object is the
* reference counted struct.
*/
#define ADD_RC_CHK(result, object) \
( \
object ? (result = malloc(sizeof(*result)), \
result ? (result->orig = object, result) \
: (result = NULL, NULL)) \
: (result = NULL, NULL) \
)
/* Strip the indirection layer. */
#define RC_CHK_ACCESS(object) object->orig
/* Frees the object and the indirection layer. */
#define RC_CHK_FREE(object) \
do { \
zfree(&object->orig); \
free(object); \
} while(0)
/* A get operation adding the indirection layer. */
#define RC_CHK_GET(result, object) ADD_RC_CHK(result, (object ? object->orig : NULL))
/* A put operation removing the indirection layer. */
#define RC_CHK_PUT(object) \
do { \
if (object) { \
object->orig = NULL; \
free(object); \
} \
} while(0)
#endif
#endif /* __LIBPERF_INTERNAL_RC_CHECK_H */

19
tools/lib/perf/include/perf/cpumap.h
View File

@ -11,8 +11,16 @@ struct perf_cpu {
int cpu;
};
struct perf_cache {
int cache_lvl;
int cache;
};
struct perf_cpu_map;
/**
* perf_cpu_map__dummy_new - a map with a singular "any CPU"/dummy -1 value.
*/
LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void);
LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
@ -20,12 +28,23 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file);
LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
struct perf_cpu_map *other);
LIBPERF_API struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig,
struct perf_cpu_map *other);
LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
/**
* perf_cpu_map__empty - is map either empty or the "any CPU"/dummy value.
*/
LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map);
LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
LIBPERF_API bool perf_cpu_map__equal(const struct perf_cpu_map *lhs,
const struct perf_cpu_map *rhs);
/**
* perf_cpu_map__any_cpu - Does the map contain the "any CPU"/dummy -1 value?
*/
LIBPERF_API bool perf_cpu_map__has_any_cpu(const struct perf_cpu_map *map);
#define perf_cpu_map__for_each_cpu(cpu, idx, cpus) \
for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx); \

5
tools/lib/perf/include/perf/event.h
View File

@ -70,6 +70,8 @@ struct perf_record_lost {
__u64 lost;
};
#define PERF_RECORD_MISC_LOST_SAMPLES_BPF (1 << 15)
struct perf_record_lost_samples {
struct perf_event_header header;
__u64 lost;
@ -378,7 +380,8 @@ enum {
PERF_STAT_CONFIG_TERM__AGGR_MODE = 0,
PERF_STAT_CONFIG_TERM__INTERVAL = 1,
PERF_STAT_CONFIG_TERM__SCALE = 2,
PERF_STAT_CONFIG_TERM__MAX = 3,
PERF_STAT_CONFIG_TERM__AGGR_LEVEL = 3,
PERF_STAT_CONFIG_TERM__MAX = 4,
};
struct perf_record_stat_config_entry {

1
tools/lib/perf/include/perf/evlist.h
View File

@ -47,4 +47,5 @@ LIBPERF_API struct perf_mmap *perf_evlist__next_mmap(struct perf_evlist *evlist,
(pos) = perf_evlist__next_mmap((evlist), (pos), overwrite))
LIBPERF_API void perf_evlist__set_leader(struct perf_evlist *evlist);
LIBPERF_API int perf_evlist__nr_groups(struct perf_evlist *evlist);
#endif /* __LIBPERF_EVLIST_H */

35
tools/lib/subcmd/exec-cmd.c
View File

@ -36,38 +36,40 @@ static int is_absolute_path(const char *path)
return path[0] == '/';
}
static const char *get_pwd_cwd(void)
static const char *get_pwd_cwd(char *buf, size_t sz)
{
static char cwd[PATH_MAX + 1];
char *pwd;
struct stat cwd_stat, pwd_stat;
if (getcwd(cwd, PATH_MAX) == NULL)
if (getcwd(buf, sz) == NULL)
return NULL;
pwd = getenv("PWD");
if (pwd && strcmp(pwd, cwd)) {
stat(cwd, &cwd_stat);
if (pwd && strcmp(pwd, buf)) {
stat(buf, &cwd_stat);
if (!stat(pwd, &pwd_stat) &&
pwd_stat.st_dev == cwd_stat.st_dev &&
pwd_stat.st_ino == cwd_stat.st_ino) {
strlcpy(cwd, pwd, PATH_MAX);
strlcpy(buf, pwd, sz);
}
}
return cwd;
return buf;
}
static const char *make_nonrelative_path(const char *path)
static const char *make_nonrelative_path(char *buf, size_t sz, const char *path)
{
static char buf[PATH_MAX + 1];
if (is_absolute_path(path)) {
if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX)
if (strlcpy(buf, path, sz) >= sz)
die("Too long path: %.*s", 60, path);
} else {
const char *cwd = get_pwd_cwd();
const char *cwd = get_pwd_cwd(buf, sz);
if (!cwd)
die("Cannot determine the current working directory");
if (snprintf(buf, PATH_MAX, "%s/%s", cwd, path) >= PATH_MAX)
if (strlen(cwd) + strlen(path) + 2 >= sz)
die("Too long path: %.*s", 60, path);
strcat(buf, "/");
strcat(buf, path);
}
return buf;
}
@ -133,8 +135,11 @@ static void add_path(char **out, const char *path)
if (path && *path) {
if (is_absolute_path(path))
astrcat(out, path);
else
astrcat(out, make_nonrelative_path(path));
else {
char buf[PATH_MAX];
astrcat(out, make_nonrelative_path(buf, sizeof(buf), path));
}
astrcat(out, ":");
}

22
tools/lib/subcmd/help.c
View File

@ -16,6 +16,8 @@
void add_cmdname(struct cmdnames *cmds, const char *name, size_t len)
{
struct cmdname *ent = malloc(sizeof(*ent) + len + 1);
if (!ent)
return;
ent->len = len;
memcpy(ent->name, name, len);
@ -66,7 +68,13 @@ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
while (ci < cmds->cnt && ei < excludes->cnt) {
cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name);
if (cmp < 0) {
cmds->names[cj++] = cmds->names[ci++];
if (ci == cj) {
ci++;
cj++;
} else {
zfree(&cmds->names[cj]);
cmds->names[cj++] = cmds->names[ci++];
}
} else if (cmp == 0) {
ci++;
ei++;
@ -74,10 +82,14 @@ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
ei++;
}
}
while (ci < cmds->cnt)
cmds->names[cj++] = cmds->names[ci++];
if (ci != cj) {
while (ci < cmds->cnt) {
zfree(&cmds->names[cj]);
cmds->names[cj++] = cmds->names[ci++];
}
}
for (ci = cj; ci < cmds->cnt; ci++)
zfree(&cmds->names[ci]);
cmds->cnt = cj;
}

15
tools/perf/Documentation/Makefile
View File

@ -250,11 +250,20 @@ $(MAN_HTML): $(OUTPUT)%.html : %.txt
$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
mv $@+ $@
# Generate date from either KBUILD_BUILD_TIMESTAMP or git log of
# the doc input file
PERF_DATE = $(strip \
$(if $(KBUILD_BUILD_TIMESTAMP), \
$(shell date -u -d '$(KBUILD_BUILD_TIMESTAMP)' +%Y-%m-%d), \
$(shell git log -1 --pretty="format:%cd" \
--date=short --no-show-signature $<)))
ifdef USE_ASCIIDOCTOR
$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : %.txt
$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
$(ASCIIDOC) -b manpage -d manpage \
$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) \
-adocdate=$(PERF_DATE) -o $@+ $< && \
mv $@+ $@
endif
@ -266,9 +275,7 @@ $(OUTPUT)%.xml : %.txt
$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
$(ASCIIDOC) -b docbook -d manpage \
$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) \
-aperf_date=$(shell git log -1 --pretty="format:%cd" \
--date=short --no-show-signature $<) \
-o $@+ $< && \
-aperf_date=$(PERF_DATE) -o $@+ $< && \
mv $@+ $@
XSLT = docbook.xsl

3
tools/perf/Documentation/perf-annotate.txt
View File

@ -116,6 +116,9 @@ include::itrace.txt[]
-M::
--disassembler-style=:: Set disassembler style for objdump.
--addr2line=<path>::
Path to addr2line binary.
--objdump=<path>::
Path to objdump binary.

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

@ -250,7 +250,13 @@ annotate.*::
These are in control of addresses, jump function, source code
in lines of assembly code from a specific program.
annotate.disassembler_style:
annotate.addr2line::
addr2line binary to use for file names and line numbers.
annotate.objdump::
objdump binary to use for disassembly and annotations.
annotate.disassembler_style::
Use this to change the default disassembler style to some other value
supported by binutils, such as "intel", see the '-M' option help in the
'objdump' man page.
@ -663,7 +669,7 @@ llvm.*::
"$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 - $LLVM_OPTIONS_PIPE"
"-c \"$CLANG_SOURCE\" --target=bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
llvm.clang-opt::
Options passed to clang.

22
tools/perf/Documentation/perf-dlfilter.txt
View File

@ -64,6 +64,12 @@ internal filtering.
If implemented, 'filter_description' should return a one-line description
of the filter, and optionally a longer description.
Do not assume the 'sample' argument is valid (dereferenceable)
after 'filter_event' and 'filter_event_early' return.
Do not assume data referenced by pointers in struct perf_dlfilter_sample
is valid (dereferenceable) after 'filter_event' and 'filter_event_early' return.
The perf_dlfilter_sample structure
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@ -150,7 +156,8 @@ struct perf_dlfilter_fns {
const char *(*srcline)(void *ctx, __u32 *line_number);
struct perf_event_attr *(*attr)(void *ctx);
__s32 (*object_code)(void *ctx, __u64 ip, void *buf, __u32 len);
void *(*reserved[120])(void *);
void (*al_cleanup)(void *ctx, struct perf_dlfilter_al *al);
void *(*reserved[119])(void *);
};
----
@ -161,7 +168,8 @@ struct perf_dlfilter_fns {
'args' returns arguments from --dlarg options.
'resolve_address' provides information about 'address'. al->size must be set
before calling. Returns 0 on success, -1 otherwise.
before calling. Returns 0 on success, -1 otherwise. Call al_cleanup() (if present,
see below) when 'al' data is no longer needed.
'insn' returns instruction bytes and length.
@ -171,6 +179,12 @@ before calling. Returns 0 on success, -1 otherwise.
'object_code' reads object code and returns the number of bytes read.
'al_cleanup' must be called (if present, so check perf_dlfilter_fns.al_cleanup != NULL)
after resolve_address() to free any associated resources.
Do not assume pointers obtained via perf_dlfilter_fns are valid (dereferenceable)
after 'filter_event' and 'filter_event_early' return.
The perf_dlfilter_al structure
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@ -197,9 +211,13 @@ struct perf_dlfilter_al {
/* Below members are only populated by resolve_ip() */
__u8 filtered; /* true if this sample event will be filtered out */
const char *comm;
void *priv; /* Private data. Do not change */
};
----
Do not assume data referenced by pointers in struct perf_dlfilter_al
is valid (dereferenceable) after 'filter_event' and 'filter_event_early' return.
perf_dlfilter_sample flags
~~~~~~~~~~~~~~~~~~~~~~~~~~

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

@ -58,7 +58,7 @@ There are a couple of variants of perf kvm:
events.
'perf kvm stat report' reports statistical data which includes events
handled time, samples, and so on.
handled sample, percent_sample, time, percent_time, max_t, min_t, mean_t.
'perf kvm stat live' reports statistical data in a live mode (similar to
record + report but with statistical data updated live at a given display
@ -82,6 +82,8 @@ OPTIONS
:GMEXAMPLESUBCMD: top
include::guest-files.txt[]
--stdio:: Use the stdio interface.
-v::
--verbose::
Be more verbose (show counter open errors, etc).
@ -97,7 +99,10 @@ STAT REPORT OPTIONS
-k::
--key=<value>::
Sorting key. Possible values: sample (default, sort by samples
number), time (sort by average time).
number), percent_sample (sort by sample percentage), time
(sort by average time), precent_time (sort by time percentage),
max_t (sort by maximum time), min_t (sort by minimum time), mean_t
(sort by mean time).
-p::
--pid=::
Analyze events only for given process ID(s) (comma separated list).

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

@ -36,6 +36,9 @@ COMMON OPTIONS
--input=<file>::
Input file name. (default: perf.data unless stdin is a fifo)
--output=<file>::
Output file name for perf lock contention and report.
-v::
--verbose::
Be more verbose (show symbol address, etc).
@ -155,8 +158,10 @@ CONTENTION OPTIONS
--tid=<value>::
Record events on existing thread ID (comma separated list).
-M::
--map-nr-entries=<value>::
Maximum number of BPF map entries (default: 10240).
Maximum number of BPF map entries (default: 16384).
This will be aligned to a power of 2.
--max-stack=<value>::
Maximum stack depth when collecting lock contention (default: 8).
@ -198,6 +203,11 @@ CONTENTION OPTIONS
Note that it matches the substring so 'rq' would match both 'raw_spin_rq_lock'
and 'irq_enter_rcu'.
-x::
--field-separator=<SEP>::
Show results using a CSV-style output to make it easy to import directly
into spreadsheets. Columns are separated by the string specified in SEP.
SEE ALSO
--------

60
tools/perf/Documentation/perf-record.txt
View File

@ -119,9 +119,12 @@ OPTIONS
"perf report" to view group events together.
--filter=<filter>::
Event filter. This option should follow an event selector (-e) which
selects either tracepoint event(s) or a hardware trace PMU
(e.g. Intel PT or CoreSight).
Event filter. This option should follow an event selector (-e).
If the event is a tracepoint, the filter string will be parsed by
the kernel. If the event is a hardware trace PMU (e.g. Intel PT
or CoreSight), it'll be processed as an address filter. Otherwise
it means a general filter using BPF which can be applied for any
kind of event.
- tracepoint filters
@ -176,6 +179,57 @@ OPTIONS
Multiple filters can be separated with space or comma.
- bpf filters
A BPF filter can access the sample data and make a decision based on the
data. Users need to set an appropriate sample type to use the BPF
filter. BPF filters need root privilege.
The sample data field can be specified in lower case letter. Multiple
filters can be separated with comma. For example,
--filter 'period > 1000, cpu == 1'
or
--filter 'mem_op == load || mem_op == store, mem_lvl > l1'
The former filter only accept samples with period greater than 1000 AND
CPU number is 1. The latter one accepts either load and store memory
operations but it should have memory level above the L1. Since the
mem_op and mem_lvl fields come from the (memory) data_source, it'd only
work with some events which set the data_source field.
Also user should request to collect that information (with -d option in
the above case). Otherwise, the following message will be shown.
$ sudo perf record -e cycles --filter 'mem_op == load'
Error: cycles event does not have PERF_SAMPLE_DATA_SRC
Hint: please add -d option to perf record.
failed to set filter "BPF" on event cycles with 22 (Invalid argument)
Essentially the BPF filter expression is:
<term> <operator> <value> (("," | "||") <term> <operator> <value>)*
The <term> can be one of:
ip, id, tid, pid, cpu, time, addr, period, txn, weight, phys_addr,
code_pgsz, data_pgsz, weight1, weight2, weight3, ins_lat, retire_lat,
p_stage_cyc, mem_op, mem_lvl, mem_snoop, mem_remote, mem_lock,
mem_dtlb, mem_blk, mem_hops
The <operator> can be one of:
==, !=, >, >=, <, <=, &
The <value> can be one of:
<number> (for any term)
na, load, store, pfetch, exec (for mem_op)
l1, l2, l3, l4, cxl, io, any_cache, lfb, ram, pmem (for mem_lvl)
na, none, hit, miss, hitm, fwd, peer (for mem_snoop)
remote (for mem_remote)
na, locked (for mem_locked)
na, l1_hit, l1_miss, l2_hit, l2_miss, any_hit, any_miss, walk, fault (for mem_dtlb)
na, by_data, by_addr (for mem_blk)
hops0, hops1, hops2, hops3 (for mem_hops)
--exclude-perf::
Don't record events issued by perf itself. This option should follow
an event selector (-e) which selects tracepoint event(s). It adds a

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

@ -117,6 +117,7 @@ OPTIONS
- addr: (Full) virtual address of the sampled instruction
- retire_lat: On X86, this reports pipeline stall of this instruction compared
to the previous instruction in cycles. And currently supported only on X86
- simd: Flags describing a SIMD operation. "e" for empty Arm SVE predicate. "p" for partial Arm SVE predicate
By default, comm, dso and symbol keys are used.
(i.e. --sort comm,dso,symbol)
@ -380,6 +381,9 @@ OPTIONS
This allows to examine the path the program took to each sample.
The data collection must have used -b (or -j) and -g.
--addr2line=<path>::
Path to addr2line binary.
--objdump=<path>::
Path to objdump binary.

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

@ -130,7 +130,7 @@ OPTIONS
-F::
--fields::
Comma separated list of fields to print. Options are:
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, dsoff, addr, symoff,
srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output,
brstackinsn, brstackinsnlen, brstackoff, callindent, insn, insnlen, synth,
phys_addr, metric, misc, srccode, ipc, data_page_size, code_page_size, ins_lat,

56
tools/perf/Documentation/perf-stat.txt
View File

@ -308,6 +308,14 @@ 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-cache::
Aggregate counts per cache instance for system-wide mode measurements. By
default, the aggregation happens for the cache level at the highest index
in the system. To specify a particular level, mention the cache level
alongside the option in the format [Ll][1-9][0-9]*. For example:
Using option "--per-cache=l3" or "--per-cache=L3" will aggregate the
information at the boundary of the level 3 cache in the system.
--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,
@ -353,6 +361,15 @@ small group that need not have multiplexing is lowered. This option
forbids the event merging logic from sharing events between groups and
may be used to increase accuracy in this case.
--metric-no-threshold::
Metric thresholds may increase the number of events necessary to
compute whether a metric has exceeded its threshold expression. This
may not be desirable, for example, as the events can introduce
multiplexing. This option disables the adding of threshold expression
events for a metric. However, if there are sufficient events to
compute the threshold then the threshold is still computed and used to
color the metric's computed value.
--quiet::
Don't print output, warnings or messages. This is useful with perf stat
record below to only write data to the perf.data file.
@ -379,6 +396,14 @@ Aggregate counts per processor socket for system-wide mode measurements.
--per-die::
Aggregate counts per processor die for system-wide mode measurements.
--per-cache::
Aggregate counts per cache instance for system-wide mode measurements. By
default, the aggregation happens for the cache level at the highest index
in the system. To specify a particular level, mention the cache level
alongside the option in the format [Ll][1-9][0-9]*. For example: Using
option "--per-cache=l3" or "--per-cache=L3" will aggregate the
information at the boundary of the level 3 cache in the system.
--per-core::
Aggregate counts per physical processor for system-wide mode measurements.
@ -389,15 +414,21 @@ For a group all metrics from the group are added.
The events from the metrics are automatically measured.
See perf list output for the possible metrics and metricgroups.
When threshold information is available for a metric, the
color red is used to signify a metric has exceeded a threshold
while green shows it hasn't. The default color means that
no threshold information was available or the threshold
couldn't be computed.
-A::
--no-aggr::
Do not aggregate counts across all monitored CPUs.
--topdown::
Print complete top-down metrics supported by the CPU. This allows to
determine bottle necks in the CPU pipeline for CPU bound workloads,
by breaking the cycles consumed down into frontend bound, backend bound,
bad speculation and retiring.
Print top-down metrics supported by the CPU. This allows to determine
bottle necks in the CPU pipeline for CPU bound workloads, by breaking
the cycles consumed down into frontend bound, backend bound, bad
speculation and retiring.
Frontend bound means that the CPU cannot fetch and decode instructions fast
enough. Backend bound means that computation or memory access is the bottle
@ -430,15 +461,18 @@ CPUs the workload runs on. If needed the CPUs can be forced using
taskset.
--td-level::
Print the top-down statistics that equal to or lower than the input level.
It allows users to print the interested top-down metrics level instead of
the complete top-down metrics.
Print the top-down statistics that equal the input level. It allows
users to print the interested top-down metrics level instead of the
level 1 top-down metrics.
The availability of the top-down metrics level depends on the hardware. For
example, Ice Lake only supports L1 top-down metrics. The Sapphire Rapids
supports both L1 and L2 top-down metrics.
As the higher levels gather more metrics and use more counters they
will be less accurate. By convention a metric can be examined by
appending '_group' to it and this will increase accuracy compared to
gathering all metrics for a level. For example, level 1 analysis may
highlight 'tma_frontend_bound'. This metric may be drilled into with
'tma_frontend_bound_group' with
'perf stat -M tma_frontend_bound_group...'.
Default: 0 means the max level that the current hardware support.
Error out if the input is higher than the supported max level.
--no-merge::

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

@ -161,6 +161,12 @@ Default is to monitor all CPUS.
-M::
--disassembler-style=:: Set disassembler style for objdump.
--addr2line=<path>::
Path to addr2line binary.
--objdump=<path>::
Path to objdump binary.
--prefix=PREFIX::
--prefix-strip=N::
Remove first N entries from source file path names in executables
@ -248,6 +254,10 @@ Default is to monitor all CPUS.
The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
Note that this feature may not be available on all processors.
--branch-history::
Add the addresses of sampled taken branches to the callstack.
This allows to examine the path the program took to each sample.
--raw-trace::
When displaying traceevent output, do not use print fmt or plugins.

70
tools/perf/Documentation/topdown.txt
View File

@ -1,46 +1,35 @@
Using TopDown metrics in user space
-----------------------------------
Using TopDown metrics
---------------------
Intel CPUs (since Sandy Bridge and Silvermont) support a TopDown
methodology to break down CPU pipeline execution into 4 bottlenecks:
frontend bound, backend bound, bad speculation, retiring.
TopDown metrics break apart performance bottlenecks. Starting at level
1 it is typical to get metrics on retiring, bad speculation, frontend
bound, and backend bound. Higher levels provide more detail in to the
level 1 bottlenecks, such as at level 2: core bound, memory bound,
heavy operations, light operations, branch mispredicts, machine
clears, fetch latency and fetch bandwidth. For more details see [1][2][3].
For more details on Topdown see [1][5]
perf stat --topdown implements this using available metrics that vary
per architecture.
Traditionally this was implemented by events in generic counters
and specific formulas to compute the bottlenecks.
% perf stat -a --topdown -I1000
# time % tma_retiring % tma_backend_bound % tma_frontend_bound % tma_bad_speculation
1.001141351 11.5 34.9 46.9 6.7
2.006141972 13.4 28.1 50.4 8.1
3.010162040 12.9 28.1 51.1 8.0
4.014009311 12.5 28.6 51.8 7.2
5.017838554 11.8 33.0 48.0 7.2
5.704818971 14.0 27.5 51.3 7.3
...
perf stat --topdown implements this.
Full Top Down includes more levels that can break down the
bottlenecks further. This is not directly implemented in perf,
but available in other tools that can run on top of perf,
such as toplev[2] or vtune[3]
New Topdown features in Ice Lake
===============================
New Topdown features in Intel Ice Lake
======================================
With Ice Lake CPUs the TopDown metrics are directly available as
fixed counters and do not require generic counters. This allows
to collect TopDown always in addition to other events.
% perf stat -a --topdown -I1000
# time retiring bad speculation frontend bound backend bound
1.001281330 23.0% 15.3% 29.6% 32.1%
2.003009005 5.0% 6.8% 46.6% 41.6%
3.004646182 6.7% 6.7% 46.0% 40.6%
4.006326375 5.0% 6.4% 47.6% 41.0%
5.007991804 5.1% 6.3% 46.3% 42.3%
6.009626773 6.2% 7.1% 47.3% 39.3%
7.011296356 4.7% 6.7% 46.2% 42.4%
8.012951831 4.7% 6.7% 47.5% 41.1%
...
This also enables measuring TopDown per thread/process instead
of only per core.
Using TopDown through RDPMC in applications on Ice Lake
======================================================
Using TopDown through RDPMC in applications on Intel Ice Lake
=============================================================
For more fine grained measurements it can be useful to
access the new directly from user space. This is more complicated,
@ -301,8 +290,8 @@ This "opens" a new measurement period.
A program using RDPMC for TopDown should schedule such a reset
regularly, as in every few seconds.
Limits on Ice Lake
==================
Limits on Intel Ice Lake
========================
Four pseudo TopDown metric events are exposed for the end-users,
topdown-retiring, topdown-bad-spec, topdown-fe-bound and topdown-be-bound.
@ -318,8 +307,8 @@ a sampling read group. Since the SLOTS event must be the leader of a TopDown
group, the second event of the group is the sampling event.
For example, perf record -e '{slots, $sampling_event, topdown-retiring}:S'
Extension on Sapphire Rapids Server
===================================
Extension on Intel Sapphire Rapids Server
=========================================
The metrics counter is extended to support TMA method level 2 metrics.
The lower half of the register is the TMA level 1 metrics (legacy).
The upper half is also divided into four 8-bit fields for the new level 2
@ -338,7 +327,6 @@ other four level 2 metrics by subtracting corresponding metrics as below.
[1] https://software.intel.com/en-us/top-down-microarchitecture-analysis-method-win
[2] https://github.com/andikleen/pmu-tools/wiki/toplev-manual
[3] https://software.intel.com/en-us/intel-vtune-amplifier-xe
[2] https://sites.google.com/site/analysismethods/yasin-pubs
[3] https://perf.wiki.kernel.org/index.php/Top-Down_Analysis
[4] https://github.com/andikleen/pmu-tools/tree/master/jevents
[5] https://sites.google.com/site/analysismethods/yasin-pubs

135
tools/perf/Makefile.config
View File

@ -149,9 +149,9 @@ FEATURE_CHECK_LDFLAGS-libcrypto = -lcrypto
ifdef CSINCLUDES
LIBOPENCSD_CFLAGS := -I$(CSINCLUDES)
endif
OPENCSDLIBS := -lopencsd_c_api
OPENCSDLIBS := -lopencsd_c_api -lopencsd
ifeq ($(findstring -static,${LDFLAGS}),-static)
OPENCSDLIBS += -lopencsd -lstdc++
OPENCSDLIBS += -lstdc++
endif
ifdef CSLIBS
LIBOPENCSD_LDFLAGS := -L$(CSLIBS)
@ -210,6 +210,12 @@ ifeq ($(call get-executable,$(BISON)),)
dummy := $(error Error: $(BISON) is missing on this system, please install it)
endif
ifeq ($(BUILD_BPF_SKEL),1)
ifeq ($(call get-executable,$(CLANG)),)
dummy := $(error $(CLANG) is missing on this system, please install it to be able to build with BUILD_BPF_SKEL=1)
endif
endif
ifneq ($(OUTPUT),)
ifeq ($(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \>\= 371), 1)
BISON_FILE_PREFIX_MAP := --file-prefix-map=$(OUTPUT)=
@ -228,6 +234,7 @@ ifndef DEBUG
endif
ifeq ($(DEBUG),0)
CORE_CFLAGS += -DNDEBUG=1
ifeq ($(CC_NO_CLANG), 0)
CORE_CFLAGS += -O3
else
@ -303,6 +310,7 @@ FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
FEATURE_CHECK_LDFLAGS-libaio = -lrt
FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl
FEATURE_CHECK_LDFLAGS-disassembler-init-styled = -lbfd -lopcodes -ldl
CORE_CFLAGS += -fno-omit-frame-pointer
CORE_CFLAGS += -ggdb3
@ -413,7 +421,6 @@ endif
ifdef NO_LIBELF
NO_DWARF := 1
NO_DEMANGLE := 1
NO_LIBUNWIND := 1
NO_LIBDW_DWARF_UNWIND := 1
NO_LIBBPF := 1
@ -427,15 +434,7 @@ else
LIBC_SUPPORT := 1
endif
ifeq ($(LIBC_SUPPORT),1)
msg := $(warning No libelf found. Disables 'probe' tool, jvmti and BPF support in 'perf record'. Please install libelf-dev, libelf-devel or elfutils-libelf-devel);
NO_LIBELF := 1
NO_DWARF := 1
NO_DEMANGLE := 1
NO_LIBUNWIND := 1
NO_LIBDW_DWARF_UNWIND := 1
NO_LIBBPF := 1
NO_JVMTI := 1
msg := $(error ERROR: No libelf found. Disables 'probe' tool, jvmti and BPF support. Please install libelf-dev, libelf-devel, elfutils-libelf-devel or build with NO_LIBELF=1.)
else
ifneq ($(filter s% -fsanitize=address%,$(EXTRA_CFLAGS),),)
ifneq ($(shell ldconfig -p | grep libasan >/dev/null 2>&1; echo $$?), 0)
@ -477,10 +476,6 @@ else
endif # libelf support
endif # NO_LIBELF
ifeq ($(feature-glibc), 1)
CFLAGS += -DHAVE_GLIBC_SUPPORT
endif
ifeq ($(feature-libaio), 1)
ifndef NO_AIO
CFLAGS += -DHAVE_AIO_SUPPORT
@ -491,6 +486,10 @@ ifdef NO_DWARF
NO_LIBDW_DWARF_UNWIND := 1
endif
ifeq ($(feature-scandirat), 1)
CFLAGS += -DHAVE_SCANDIRAT_SUPPORT
endif
ifeq ($(feature-sched_getcpu), 1)
CFLAGS += -DHAVE_SCHED_GETCPU_SUPPORT
endif
@ -567,54 +566,17 @@ ifndef NO_LIBELF
# detecting libbpf without LIBBPF_DYNAMIC, so make VF=1 shows libbpf detection status
$(call feature_check,libbpf)
ifdef LIBBPF_DYNAMIC
ifeq ($(feature-libbpf), 1)
EXTLIBS += -lbpf
$(call detected,CONFIG_LIBBPF_DYNAMIC)
$(call feature_check,libbpf-btf__load_from_kernel_by_id)
ifeq ($(feature-libbpf-btf__load_from_kernel_by_id), 1)
CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
endif
$(call feature_check,libbpf-bpf_prog_load)
ifeq ($(feature-libbpf-bpf_prog_load), 1)
CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD
endif
$(call feature_check,libbpf-bpf_object__next_program)
ifeq ($(feature-libbpf-bpf_object__next_program), 1)
CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM
endif
$(call feature_check,libbpf-bpf_object__next_map)
ifeq ($(feature-libbpf-bpf_object__next_map), 1)
CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_MAP
endif
$(call feature_check,libbpf-bpf_program__set_insns)
ifeq ($(feature-libbpf-bpf_program__set_insns), 1)
CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS
else
dummy := $(error Error: libbpf devel library needs to be >= 0.8.0 to build with LIBBPF_DYNAMIC, update or build statically with the version that comes with the kernel sources);
endif
$(call feature_check,libbpf-btf__raw_data)
ifeq ($(feature-libbpf-btf__raw_data), 1)
CFLAGS += -DHAVE_LIBBPF_BTF__RAW_DATA
endif
$(call feature_check,libbpf-bpf_map_create)
ifeq ($(feature-libbpf-bpf_map_create), 1)
CFLAGS += -DHAVE_LIBBPF_BPF_MAP_CREATE
endif
else
dummy := $(error Error: No libbpf devel library found, please install libbpf-devel);
dummy := $(error Error: No libbpf devel library found or older than v1.0, please install/update libbpf-devel);
endif
else
# Libbpf will be built as a static library from tools/lib/bpf.
LIBBPF_STATIC := 1
CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD
CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM
CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_MAP
CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS
CFLAGS += -DHAVE_LIBBPF_BTF__RAW_DATA
CFLAGS += -DHAVE_LIBBPF_BPF_MAP_CREATE
endif
endif
@ -715,6 +677,10 @@ ifdef BUILD_BPF_SKEL
CFLAGS += -DHAVE_BPF_SKEL
endif
ifndef GEN_VMLINUX_H
VMLINUX_H=$(src-perf)/util/bpf_skel/vmlinux/vmlinux.h
endif
dwarf-post-unwind := 1
dwarf-post-unwind-text := BUG
@ -798,10 +764,6 @@ ifndef NO_LIBCRYPTO
endif
endif
ifdef NO_NEWT
NO_SLANG=1
endif
ifndef NO_SLANG
ifneq ($(feature-libslang), 1)
ifneq ($(feature-libslang-include-subdir), 1)
@ -918,19 +880,17 @@ endif
ifneq ($(NO_JEVENTS),1)
NO_JEVENTS := 0
ifndef PYTHON
$(warning No python interpreter disabling jevent generation)
NO_JEVENTS := 1
$(error ERROR: No python interpreter needed for jevents generation. Install python or build with NO_JEVENTS=1.)
else
# jevents.py uses f-strings present in Python 3.6 released in Dec. 2016.
JEVENTS_PYTHON_GOOD := $(shell $(PYTHON) -c 'import sys;print("1" if(sys.version_info.major >= 3 and sys.version_info.minor >= 6) else "0")' 2> /dev/null)
ifneq ($(JEVENTS_PYTHON_GOOD), 1)
$(warning Python interpreter too old (older than 3.6) disabling jevent generation)
NO_JEVENTS := 1
$(error ERROR: Python interpreter needed for jevents generation too old (older than 3.6). Install a newer python or build with NO_JEVENTS=1.)
endif
endif
endif
ifndef NO_LIBBFD
ifdef BUILD_NONDISTRO
ifeq ($(feature-libbfd), 1)
EXTLIBS += -lbfd -lopcodes
else
@ -945,15 +905,19 @@ ifndef NO_LIBBFD
ifeq ($(feature-libbfd-liberty), 1)
EXTLIBS += -lbfd -lopcodes -liberty
FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -ldl
FEATURE_CHECK_LDFLAGS-disassembler-init-styled += -liberty -ldl
else
ifeq ($(feature-libbfd-liberty-z), 1)
EXTLIBS += -lbfd -lopcodes -liberty -lz
FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -lz -ldl
FEATURE_CHECK_LDFLAGS-disassembler-init-styled += -liberty -lz -ldl
endif
endif
$(call feature_check,disassembler-four-args)
endif
CFLAGS += -DHAVE_LIBBFD_SUPPORT
CXXFLAGS += -DHAVE_LIBBFD_SUPPORT
ifeq ($(feature-libbfd-buildid), 1)
CFLAGS += -DHAVE_LIBBFD_BUILDID_SUPPORT
else
@ -961,33 +925,26 @@ ifndef NO_LIBBFD
endif
endif
ifdef NO_DEMANGLE
CFLAGS += -DNO_DEMANGLE
else
ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
EXTLIBS += -liberty
else
ifndef NO_DEMANGLE
$(call feature_check,cxa-demangle)
ifeq ($(feature-cxa-demangle), 1)
EXTLIBS += -lstdc++
CFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT
CXXFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT
$(call detected,CONFIG_CXX_DEMANGLE)
endif
ifdef BUILD_NONDISTRO
ifeq ($(filter -liberty,$(EXTLIBS)),)
$(call feature_check,cplus-demangle)
# we dont have neither HAVE_CPLUS_DEMANGLE_SUPPORT
# or any of 'bfd iberty z' trinity
ifeq ($(feature-cplus-demangle), 1)
EXTLIBS += -liberty
else
msg := $(warning No bfd.h/libbfd found, please install binutils-dev[el]/zlib-static/libiberty-dev to gain symbol demangling)
CFLAGS += -DNO_DEMANGLE
endif
endif
ifneq ($(filter -liberty,$(EXTLIBS)),)
CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT
CXXFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT
endif
endif
ifneq ($(filter -liberty,$(EXTLIBS)),)
CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT
endif
endif
ifneq ($(filter -lbfd,$(EXTLIBS)),)
CFLAGS += -DHAVE_LIBBFD_SUPPORT
endif
ifndef NO_ZLIB
@ -1118,6 +1075,11 @@ ifndef NO_AUXTRACE
endif
endif
ifdef EXTRA_TESTS
$(call detected,CONFIG_EXTRA_TESTS)
CFLAGS += -DHAVE_EXTRA_TESTS
endif
ifndef NO_JVMTI
ifneq (,$(wildcard /usr/sbin/update-java-alternatives))
JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}')
@ -1181,7 +1143,7 @@ ifdef LIBCLANGLLVM
endif
endif
ifdef LIBPFM4
ifndef NO_LIBPFM4
$(call feature_check,libpfm4)
ifeq ($(feature-libpfm4), 1)
CFLAGS += -DHAVE_LIBPFM
@ -1190,7 +1152,6 @@ ifdef LIBPFM4
$(call detected,CONFIG_LIBPFM4)
else
msg := $(warning libpfm4 not found, disables libpfm4 support. Please install libpfm4-dev);
NO_LIBPFM4 := 1
endif
endif
@ -1208,7 +1169,7 @@ ifneq ($(NO_LIBTRACEEVENT),1)
CFLAGS += -DLIBTRACEEVENT_VERSION=$(LIBTRACEEVENT_VERSION_CPP)
$(call detected,CONFIG_LIBTRACEEVENT)
else
dummy := $(warning Warning: libtraceevent is missing limiting functionality, please install libtraceevent-dev/libtraceevent-devel)
dummy := $(error ERROR: libtraceevent is missing. Please install libtraceevent-dev/libtraceevent-devel or build with NO_LIBTRACEEVENT=1)
endif
$(call feature_check,libtracefs)

70
tools/perf/Makefile.perf
View File

@ -44,8 +44,6 @@ include ../scripts/utilities.mak
#
# Define WERROR=0 to disable treating any warnings as errors.
#
# Define NO_NEWT if you do not want TUI support. (deprecated)
#
# Define NO_SLANG if you do not want TUI support.
#
# Define GTK2 if you want GTK+ GUI support.
@ -122,12 +120,20 @@ include ../scripts/utilities.mak
# generated from the kernel .tbl or unistd.h files and use, if available, libaudit
# for doing the conversions to/from strings/id.
#
# Define LIBPFM4 to enable libpfm4 events extension.
# Define NO_LIBPFM4 to disable libpfm4 events extension.
#
# Define NO_LIBDEBUGINFOD if you do not want support debuginfod
#
# Define BUILD_BPF_SKEL to enable BPF skeletons
#
# Define BUILD_NONDISTRO to enable building an linking against libbfd and
# libiberty distribution license incompatible libraries.
#
# Define EXTRA_TESTS to enable building extra tests useful mainly to perf
# developers, such as:
# x86 instruction decoder - new instructions test
#
# Define GEN_VMLINUX_H to generate vmlinux.h from the BTF.
# As per kernel Makefile, avoid funny character set dependencies
unexport LC_ALL
@ -181,7 +187,6 @@ HOSTCC ?= gcc
HOSTLD ?= ld
HOSTAR ?= ar
CLANG ?= clang
LLVM_STRIP ?= llvm-strip
PKG_CONFIG = $(CROSS_COMPILE)pkg-config
@ -194,6 +199,7 @@ FLEX ?= flex
BISON ?= bison
STRIP = strip
AWK = awk
READELF ?= readelf
# include Makefile.config by default and rule out
# non-config cases
@ -375,7 +381,7 @@ ifndef NO_JVMTI
PROGRAMS += $(OUTPUT)$(LIBJVMTI)
endif
DLFILTERS := dlfilter-test-api-v0.so dlfilter-show-cycles.so
DLFILTERS := dlfilter-test-api-v0.so dlfilter-test-api-v2.so dlfilter-show-cycles.so
DLFILTERS := $(patsubst %,$(OUTPUT)dlfilters/%,$(DLFILTERS))
# what 'all' will build and 'install' will install, in perfexecdir
@ -1050,25 +1056,65 @@ SKELETONS := $(SKEL_OUT)/bpf_prog_profiler.skel.h
SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h
SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h
SKELETONS += $(SKEL_OUT)/off_cpu.skel.h $(SKEL_OUT)/lock_contention.skel.h
SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h
SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_OUT)/sample_filter.skel.h
$(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_OUTPUT) $(LIBSYMBOL_OUTPUT):
$(Q)$(MKDIR) -p $@
ifdef BUILD_BPF_SKEL
BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool
BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE)
# Get Clang's default includes on this system, as opposed to those seen by
# '--target=bpf'. This fixes "missing" files on some architectures/distros,
# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
#
# Use '-idirafter': Don't interfere with include mechanics except where the
# build would have failed anyways.
define get_sys_includes
$(shell $(1) $(2) -v -E - </dev/null 2>&1 \
| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}')
endef
ifneq ($(CROSS_COMPILE),)
CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%))
endif
CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES)
TOOLS_UAPI_INCLUDE := -I$(srctree)/tools/include/uapi
$(BPFTOOL): | $(SKEL_TMP_OUT)
$(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \
OUTPUT=$(SKEL_TMP_OUT)/ bootstrap
VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \
# Paths to search for a kernel to generate vmlinux.h from.
VMLINUX_BTF_ELF_PATHS ?= $(if $(O),$(O)/vmlinux) \
$(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \
../../vmlinux \
/sys/kernel/btf/vmlinux \
/boot/vmlinux-$(shell uname -r)
VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
# Paths to BTF information.
VMLINUX_BTF_BTF_PATHS ?= /sys/kernel/btf/vmlinux
# Filter out kernels that don't exist or without a BTF section.
VMLINUX_BTF_ELF_ABSPATHS ?= $(abspath $(wildcard $(VMLINUX_BTF_ELF_PATHS)))
VMLINUX_BTF_PATHS ?= $(shell for file in $(VMLINUX_BTF_ELF_ABSPATHS); \
do \
if [ -f $$file ] && ($(READELF) -S "$$file" | grep -q .BTF); \
then \
echo "$$file"; \
fi; \
done) \
$(wildcard $(VMLINUX_BTF_BTF_PATHS))
# Select the first as the source of vmlinux.h.
VMLINUX_BTF ?= $(firstword $(VMLINUX_BTF_PATHS))
ifeq ($(VMLINUX_H),)
ifeq ($(VMLINUX_BTF),)
$(error Missing bpftool input for generating vmlinux.h)
endif
endif
$(SKEL_OUT)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL)
ifeq ($(VMLINUX_H),)
@ -1078,8 +1124,8 @@ else
endif
$(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) $(SKEL_OUT)/vmlinux.h | $(SKEL_TMP_OUT)
$(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) \
-c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ && $(LLVM_STRIP) -g $@
$(QUIET_CLANG)$(CLANG) -g -O2 --target=bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \
-c $(filter util/bpf_skel/%.bpf.c,$^) -o $@
$(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL)
$(QUIET_GENSKEL)$(BPFTOOL) gen skeleton $< > $@

4
tools/perf/arch/arm/tests/dwarf-unwind.c
View File

@ -26,14 +26,14 @@ static int sample_ustack(struct perf_sample *sample,
sp = (unsigned long) regs[PERF_REG_ARM_SP];
map = maps__find(thread->maps, (u64)sp);
map = maps__find(thread__maps(thread), (u64)sp);
if (!map) {
pr_debug("failed to get stack map\n");
free(buf);
return -1;
}
stack_size = map->end - sp;
stack_size = map__end(map) - sp;
stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
memcpy(buf, (void *) sp, stack_size);

7
tools/perf/arch/arm/util/auxtrace.c
View File

@ -14,6 +14,7 @@
#include "../../../util/debug.h"
#include "../../../util/evlist.h"
#include "../../../util/pmu.h"
#include "../../../util/pmus.h"
#include "cs-etm.h"
#include "arm-spe.h"
#include "hisi-ptt.h"
@ -40,7 +41,7 @@ static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err)
return NULL;
}
arm_spe_pmus[*nr_spes] = perf_pmu__find(arm_spe_pmu_name);
arm_spe_pmus[*nr_spes] = perf_pmus__find(arm_spe_pmu_name);
if (arm_spe_pmus[*nr_spes]) {
pr_debug2("%s %d: arm_spe_pmu %d type %d name %s\n",
__func__, __LINE__, *nr_spes,
@ -87,7 +88,7 @@ static struct perf_pmu **find_all_hisi_ptt_pmus(int *nr_ptts, int *err)
rewinddir(dir);
while ((dent = readdir(dir))) {
if (strstr(dent->d_name, HISI_PTT_PMU_NAME) && idx < *nr_ptts) {
hisi_ptt_pmus[idx] = perf_pmu__find(dent->d_name);
hisi_ptt_pmus[idx] = perf_pmus__find(dent->d_name);
if (hisi_ptt_pmus[idx])
idx++;
}
@ -131,7 +132,7 @@ struct auxtrace_record
if (!evlist)
return NULL;
cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME);
cs_etm_pmu = perf_pmus__find(CORESIGHT_ETM_PMU_NAME);
arm_spe_pmus = find_all_arm_spe_pmus(&nr_spes, err);
hisi_ptt_pmus = find_all_hisi_ptt_pmus(&nr_ptts, err);

271
tools/perf/arch/arm/util/cs-etm.c
View File

@ -25,7 +25,7 @@
#include "../../../util/evsel.h"
#include "../../../util/perf_api_probe.h"
#include "../../../util/evsel_config.h"
#include "../../../util/pmu.h"
#include "../../../util/pmus.h"
#include "../../../util/cs-etm.h"
#include <internal/lib.h> // page_size
#include "../../../util/session.h"
@ -69,21 +69,29 @@ static const char * const metadata_ete_ro[] = {
static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu);
static bool cs_etm_is_ete(struct auxtrace_record *itr, int cpu);
static int cs_etm_set_context_id(struct auxtrace_record *itr,
struct evsel *evsel, int cpu)
static int cs_etm_validate_context_id(struct auxtrace_record *itr,
struct evsel *evsel, int cpu)
{
struct cs_etm_recording *ptr;
struct perf_pmu *cs_etm_pmu;
struct cs_etm_recording *ptr =
container_of(itr, struct cs_etm_recording, itr);
struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
char path[PATH_MAX];
int err = -EINVAL;
int err;
u32 val;
u64 contextid;
u64 contextid = evsel->core.attr.config &
(perf_pmu__format_bits(&cs_etm_pmu->format, "contextid") |
perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") |
perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2"));
ptr = container_of(itr, struct cs_etm_recording, itr);
cs_etm_pmu = ptr->cs_etm_pmu;
if (!contextid)
return 0;
if (!cs_etm_is_etmv4(itr, cpu))
goto out;
/* Not supported in etmv3 */
if (!cs_etm_is_etmv4(itr, cpu)) {
pr_err("%s: contextid not supported in ETMv3, disable with %s/contextid=0/\n",
CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME);
return -EINVAL;
}
/* Get a handle on TRCIDR2 */
snprintf(path, PATH_MAX, "cpu%d/%s",
@ -92,27 +100,13 @@ static int cs_etm_set_context_id(struct auxtrace_record *itr,
/* 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;
pr_err("%s: can't read file %s\n", CORESIGHT_ETM_PMU_NAME,
path);
return err;
}
/* User has configured for PID tracing, respects it. */
contextid = evsel->core.attr.config &
(BIT(ETM_OPT_CTXTID) | BIT(ETM_OPT_CTXTID2));
/*
* If user doesn't configure the contextid format, parse PMU format and
* enable PID tracing according to the "contextid" format bits:
*
* If bit ETM_OPT_CTXTID is set, trace CONTEXTIDR_EL1;
* If bit ETM_OPT_CTXTID2 is set, trace CONTEXTIDR_EL2.
*/
if (!contextid)
contextid = perf_pmu__format_bits(&cs_etm_pmu->format,
"contextid");
if (contextid & BIT(ETM_OPT_CTXTID)) {
if (contextid &
perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1")) {
/*
* TRCIDR2.CIDSIZE, bit [9-5], indicates whether contextID
* tracing is supported:
@ -120,16 +114,15 @@ static int cs_etm_set_context_id(struct auxtrace_record *itr,
* 0b00100 Maximum of 32-bit Context ID size.
* All other values are reserved.
*/
val = BMVAL(val, 5, 9);
if (!val || val != 0x4) {
pr_err("%s: CONTEXTIDR_EL1 isn't supported\n",
CORESIGHT_ETM_PMU_NAME);
err = -EINVAL;
goto out;
if (BMVAL(val, 5, 9) != 0x4) {
pr_err("%s: CONTEXTIDR_EL1 isn't supported, disable with %s/contextid1=0/\n",
CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME);
return -EINVAL;
}
}
if (contextid & BIT(ETM_OPT_CTXTID2)) {
if (contextid &
perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2")) {
/*
* TRCIDR2.VMIDOPT[30:29] != 0 and
* TRCIDR2.VMIDSIZE[14:10] == 0b00100 (32bit virtual contextid)
@ -138,35 +131,34 @@ static int cs_etm_set_context_id(struct auxtrace_record *itr,
* Any value of VMIDSIZE >= 4 (i.e, > 32bit) is fine for us.
*/
if (!BMVAL(val, 29, 30) || BMVAL(val, 10, 14) < 4) {
pr_err("%s: CONTEXTIDR_EL2 isn't supported\n",
CORESIGHT_ETM_PMU_NAME);
err = -EINVAL;
goto out;
pr_err("%s: CONTEXTIDR_EL2 isn't supported, disable with %s/contextid2=0/\n",
CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME);
return -EINVAL;
}
}
/* All good, let the kernel know */
evsel->core.attr.config |= contextid;
err = 0;
out:
return err;
return 0;
}
static int cs_etm_set_timestamp(struct auxtrace_record *itr,
struct evsel *evsel, int cpu)
static int cs_etm_validate_timestamp(struct auxtrace_record *itr,
struct evsel *evsel, int cpu)
{
struct cs_etm_recording *ptr;
struct perf_pmu *cs_etm_pmu;
struct cs_etm_recording *ptr =
container_of(itr, struct cs_etm_recording, itr);
struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
char path[PATH_MAX];
int err = -EINVAL;
int err;
u32 val;
ptr = container_of(itr, struct cs_etm_recording, itr);
cs_etm_pmu = ptr->cs_etm_pmu;
if (!(evsel->core.attr.config &
perf_pmu__format_bits(&cs_etm_pmu->format, "timestamp")))
return 0;
if (!cs_etm_is_etmv4(itr, cpu))
goto out;
if (!cs_etm_is_etmv4(itr, cpu)) {
pr_err("%s: timestamp not supported in ETMv3, disable with %s/timestamp=0/\n",
CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME);
return -EINVAL;
}
/* Get a handle on TRCIRD0 */
snprintf(path, PATH_MAX, "cpu%d/%s",
@ -177,7 +169,7 @@ static int cs_etm_set_timestamp(struct auxtrace_record *itr,
if (err != 1) {
pr_err("%s: can't read file %s\n",
CORESIGHT_ETM_PMU_NAME, path);
goto out;
return err;
}
/*
@ -189,24 +181,21 @@ static int cs_etm_set_timestamp(struct auxtrace_record *itr,
*/
val &= GENMASK(28, 24);
if (!val) {
err = -EINVAL;
goto out;
return -EINVAL;
}
/* All good, let the kernel know */
evsel->core.attr.config |= (1 << ETM_OPT_TS);
err = 0;
out:
return err;
return 0;
}
#define ETM_SET_OPT_CTXTID (1 << 0)
#define ETM_SET_OPT_TS (1 << 1)
#define ETM_SET_OPT_MASK (ETM_SET_OPT_CTXTID | ETM_SET_OPT_TS)
static int cs_etm_set_option(struct auxtrace_record *itr,
struct evsel *evsel, u32 option)
/*
* Check whether the requested timestamp and contextid options should be
* available on all requested CPUs and if not, tell the user how to override.
* The kernel will silently disable any unavailable options so a warning here
* first is better. In theory the kernel could still disable the option for
* some other reason so this is best effort only.
*/
static int cs_etm_validate_config(struct auxtrace_record *itr,
struct evsel *evsel)
{
int i, err = -EINVAL;
struct perf_cpu_map *event_cpus = evsel->evlist->core.user_requested_cpus;
@ -220,18 +209,11 @@ static int cs_etm_set_option(struct auxtrace_record *itr,
!perf_cpu_map__has(online_cpus, cpu))
continue;
if (option & BIT(ETM_OPT_CTXTID)) {
err = cs_etm_set_context_id(itr, evsel, i);
if (err)
goto out;
}
if (option & BIT(ETM_OPT_TS)) {
err = cs_etm_set_timestamp(itr, evsel, i);
if (err)
goto out;
}
if (option & ~(BIT(ETM_OPT_CTXTID) | BIT(ETM_OPT_TS)))
/* Nothing else is currently supported */
err = cs_etm_validate_context_id(itr, evsel, i);
if (err)
goto out;
err = cs_etm_validate_timestamp(itr, evsel, i);
if (err)
goto out;
}
@ -319,13 +301,6 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
bool privileged = perf_event_paranoid_check(-1);
int err = 0;
ptr->evlist = evlist;
ptr->snapshot_mode = opts->auxtrace_snapshot_mode;
if (!record_opts__no_switch_events(opts) &&
perf_can_record_switch_events())
opts->record_switch_events = true;
evlist__for_each_entry(evlist, evsel) {
if (evsel->core.attr.type == cs_etm_pmu->type) {
if (cs_etm_evsel) {
@ -333,11 +308,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
CORESIGHT_ETM_PMU_NAME);
return -EINVAL;
}
evsel->core.attr.freq = 0;
evsel->core.attr.sample_period = 1;
evsel->needs_auxtrace_mmap = true;
cs_etm_evsel = evsel;
opts->full_auxtrace = true;
}
}
@ -345,6 +316,16 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
if (!cs_etm_evsel)
return 0;
ptr->evlist = evlist;
ptr->snapshot_mode = opts->auxtrace_snapshot_mode;
if (!record_opts__no_switch_events(opts) &&
perf_can_record_switch_events())
opts->record_switch_events = true;
cs_etm_evsel->needs_auxtrace_mmap = true;
opts->full_auxtrace = true;
ret = cs_etm_set_sink_attr(cs_etm_pmu, cs_etm_evsel);
if (ret)
return ret;
@ -414,8 +395,8 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
}
}
/* We are in full trace mode but '-m,xyz' wasn't specified */
if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
/* Buffer sizes weren't specified with '-m,xyz' so give some defaults */
if (!opts->auxtrace_mmap_pages) {
if (privileged) {
opts->auxtrace_mmap_pages = MiB(4) / page_size;
} else {
@ -423,7 +404,6 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
if (opts->mmap_pages == UINT_MAX)
opts->mmap_pages = KiB(256) / page_size;
}
}
if (opts->auxtrace_snapshot_mode)
@ -437,38 +417,36 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
evlist__to_front(evlist, cs_etm_evsel);
/*
* In the case of per-cpu mmaps, we need the CPU on the
* AUX event. We also need the contextID in order to be notified
* get the CPU on the sample - need it to associate trace ID in the
* AUX_OUTPUT_HW_ID event, and the AUX event for per-cpu mmaps.
*/
evsel__set_sample_bit(cs_etm_evsel, CPU);
/*
* Also the case of per-cpu mmaps, need the contextID in order to be notified
* when a context switch happened.
*/
if (!perf_cpu_map__empty(cpus)) {
evsel__set_sample_bit(cs_etm_evsel, CPU);
err = cs_etm_set_option(itr, cs_etm_evsel,
BIT(ETM_OPT_CTXTID) | BIT(ETM_OPT_TS));
if (err)
goto out;
evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel,
"timestamp", 1);
evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel,
"contextid", 1);
}
/* Add dummy event to keep tracking */
if (opts->full_auxtrace) {
struct evsel *tracking_evsel;
err = parse_event(evlist, "dummy:u");
if (err)
goto out;
evsel = evlist__last(evlist);
evlist__set_tracking_event(evlist, evsel);
evsel->core.attr.freq = 0;
evsel->core.attr.sample_period = 1;
err = parse_event(evlist, "dummy:u");
if (err)
goto out;
tracking_evsel = evlist__last(evlist);
evlist__set_tracking_event(evlist, tracking_evsel);
tracking_evsel->core.attr.freq = 0;
tracking_evsel->core.attr.sample_period = 1;
/* In per-cpu case, always need the time of mmap events etc */
if (!perf_cpu_map__empty(cpus))
evsel__set_sample_bit(tracking_evsel, TIME);
}
/* In per-cpu case, always need the time of mmap events etc */
if (!perf_cpu_map__empty(cpus))
evsel__set_sample_bit(evsel, TIME);
err = cs_etm_validate_config(itr, cs_etm_evsel);
out:
return err;
}
@ -659,8 +637,12 @@ static bool cs_etm_is_ete(struct auxtrace_record *itr, int cpu)
{
struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr);
struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
int trcdevarch = cs_etm_get_ro(cs_etm_pmu, cpu, metadata_ete_ro[CS_ETE_TRCDEVARCH]);
int trcdevarch;
if (!cs_etm_pmu_path_exists(cs_etm_pmu, cpu, metadata_ete_ro[CS_ETE_TRCDEVARCH]))
return false;
trcdevarch = cs_etm_get_ro(cs_etm_pmu, cpu, metadata_ete_ro[CS_ETE_TRCDEVARCH]);
/*
* ETE if ARCHVER is 5 (ARCHVER is 4 for ETM) and ARCHPART is 0xA13.
* See ETM_DEVARCH_ETE_ARCH in coresight-etm4x.h
@ -675,8 +657,10 @@ static void cs_etm_save_etmv4_header(__u64 data[], struct auxtrace_record *itr,
/* Get trace configuration register */
data[CS_ETMV4_TRCCONFIGR] = cs_etmv4_get_config(itr);
/* Get traceID from the framework */
data[CS_ETMV4_TRCTRACEIDR] = coresight_get_trace_id(cpu);
/* traceID set to legacy version, in case new perf running on older system */
data[CS_ETMV4_TRCTRACEIDR] =
CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) | CORESIGHT_TRACE_ID_UNUSED_FLAG;
/* Get read-only information from sysFS */
data[CS_ETMV4_TRCIDR0] = cs_etm_get_ro(cs_etm_pmu, cpu,
metadata_etmv4_ro[CS_ETMV4_TRCIDR0]);
@ -694,8 +678,8 @@ static void cs_etm_save_etmv4_header(__u64 data[], struct auxtrace_record *itr,
data[CS_ETMV4_TS_SOURCE] = (__u64) cs_etm_get_ro_signed(cs_etm_pmu, cpu,
metadata_etmv4_ro[CS_ETMV4_TS_SOURCE]);
else {
pr_warning("[%03d] pmu file 'ts_source' not found. Fallback to safe value (-1)\n",
cpu);
pr_debug3("[%03d] pmu file 'ts_source' not found. Fallback to safe value (-1)\n",
cpu);
data[CS_ETMV4_TS_SOURCE] = (__u64) -1;
}
}
@ -707,8 +691,10 @@ static void cs_etm_save_ete_header(__u64 data[], struct auxtrace_record *itr, in
/* Get trace configuration register */
data[CS_ETE_TRCCONFIGR] = cs_etmv4_get_config(itr);
/* Get traceID from the framework */
data[CS_ETE_TRCTRACEIDR] = coresight_get_trace_id(cpu);
/* traceID set to legacy version, in case new perf running on older system */
data[CS_ETE_TRCTRACEIDR] =
CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) | CORESIGHT_TRACE_ID_UNUSED_FLAG;
/* Get read-only information from sysFS */
data[CS_ETE_TRCIDR0] = cs_etm_get_ro(cs_etm_pmu, cpu,
metadata_ete_ro[CS_ETE_TRCIDR0]);
@ -729,8 +715,8 @@ static void cs_etm_save_ete_header(__u64 data[], struct auxtrace_record *itr, in
data[CS_ETE_TS_SOURCE] = (__u64) cs_etm_get_ro_signed(cs_etm_pmu, cpu,
metadata_ete_ro[CS_ETE_TS_SOURCE]);
else {
pr_warning("[%03d] pmu file 'ts_source' not found. Fallback to safe value (-1)\n",
cpu);
pr_debug3("[%03d] pmu file 'ts_source' not found. Fallback to safe value (-1)\n",
cpu);
data[CS_ETE_TS_SOURCE] = (__u64) -1;
}
}
@ -764,9 +750,9 @@ static void cs_etm_get_metadata(int cpu, u32 *offset,
magic = __perf_cs_etmv3_magic;
/* Get configuration register */
info->priv[*offset + CS_ETM_ETMCR] = cs_etm_get_config(itr);
/* Get traceID from the framework */
/* traceID set to legacy value in case new perf running on old system */
info->priv[*offset + CS_ETM_ETMTRACEIDR] =
coresight_get_trace_id(cpu);
CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) | CORESIGHT_TRACE_ID_UNUSED_FLAG;
/* Get read-only information from sysFS */
info->priv[*offset + CS_ETM_ETMCCER] =
cs_etm_get_ro(cs_etm_pmu, cpu,
@ -895,7 +881,7 @@ struct auxtrace_record *cs_etm_record_init(int *err)
struct perf_pmu *cs_etm_pmu;
struct cs_etm_recording *ptr;
cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME);
cs_etm_pmu = perf_pmus__find(CORESIGHT_ETM_PMU_NAME);
if (!cs_etm_pmu) {
*err = -EINVAL;
@ -925,3 +911,22 @@ struct auxtrace_record *cs_etm_record_init(int *err)
out:
return NULL;
}
/*
* Set a default config to enable the user changed config tracking mechanism
* (CFG_CHG and evsel__set_config_if_unset()). If no default is set then user
* changes aren't tracked.
*/
struct perf_event_attr *
cs_etm_get_default_config(struct perf_pmu *pmu __maybe_unused)
{
struct perf_event_attr *attr;
attr = zalloc(sizeof(struct perf_event_attr));
if (!attr)
return NULL;
attr->sample_period = 1;
return attr;
}

2
tools/perf/arch/arm/util/pmu.c
View File

@ -12,6 +12,7 @@
#include "arm-spe.h"
#include "hisi-ptt.h"
#include "../../../util/pmu.h"
#include "../../../util/cs-etm.h"
struct perf_event_attr
*perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
@ -20,6 +21,7 @@ struct perf_event_attr
if (!strcmp(pmu->name, CORESIGHT_ETM_PMU_NAME)) {
/* add ETM default config here */
pmu->selectable = true;
return cs_etm_get_default_config(pmu);
#if defined(__aarch64__)
} else if (strstarts(pmu->name, ARM_SPE_PMU_NAME)) {
return arm_spe_pmu_default_config(pmu);

17
tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
View File

@ -19,27 +19,28 @@ if ! test -r $input; then
exit 1
fi
create_table_from_c()
create_sc_table()
{
local sc nr last_sc
local sc nr max_nr
while read sc nr; do
printf "%s\n" " [$nr] = \"$sc\","
last_sc=$sc
max_nr=$nr
done
printf "%s\n" "#define SYSCALLTBL_ARM64_MAX_ID __NR_$last_sc"
echo "#define SYSCALLTBL_ARM64_MAX_ID $max_nr"
}
create_table()
{
echo "#include \"$input\""
echo "static const char *syscalltbl_arm64[] = {"
create_table_from_c
echo "static const char *const syscalltbl_arm64[] = {"
create_sc_table
echo "};"
}
$gcc -E -dM -x c -I $incpath/include/uapi $input \
|sed -ne 's/^#define __NR_//p' \
|sort -t' ' -k2 -n \
|awk '$2 ~ "__NR" && $3 !~ "__NR3264_" {
sub("^#define __NR(3264)?_", "");
print | "sort -k2 -n"}' \
|create_table

4
tools/perf/arch/arm64/tests/dwarf-unwind.c
View File

@ -26,14 +26,14 @@ static int sample_ustack(struct perf_sample *sample,
sp = (unsigned long) regs[PERF_REG_ARM64_SP];
map = maps__find(thread->maps, (u64)sp);
map = maps__find(thread__maps(thread), (u64)sp);
if (!map) {
pr_debug("failed to get stack map\n");
free(buf);
return -1;
}
stack_size = map->end - sp;
stack_size = map__end(map) - sp;
stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
memcpy(buf, (void *) sp, stack_size);

28
tools/perf/arch/arm64/util/arm-spe.c
View File

@ -36,29 +36,6 @@ struct arm_spe_recording {
bool *wrapped;
};
static void arm_spe_set_timestamp(struct auxtrace_record *itr,
struct evsel *evsel)
{
struct arm_spe_recording *ptr;
struct perf_pmu *arm_spe_pmu;
struct evsel_config_term *term = evsel__get_config_term(evsel, CFG_CHG);
u64 user_bits = 0, bit;
ptr = container_of(itr, struct arm_spe_recording, itr);
arm_spe_pmu = ptr->arm_spe_pmu;
if (term)
user_bits = term->val.cfg_chg;
bit = perf_pmu__format_bits(&arm_spe_pmu->format, "ts_enable");
/* Skip if user has set it */
if (bit & user_bits)
return;
evsel->core.attr.config |= bit;
}
static size_t
arm_spe_info_priv_size(struct auxtrace_record *itr __maybe_unused,
struct evlist *evlist __maybe_unused)
@ -238,7 +215,8 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
*/
if (!perf_cpu_map__empty(cpus)) {
evsel__set_sample_bit(arm_spe_evsel, CPU);
arm_spe_set_timestamp(itr, arm_spe_evsel);
evsel__set_config_if_unset(arm_spe_pmu, arm_spe_evsel,
"ts_enable", 1);
}
/*
@ -479,7 +457,7 @@ static void arm_spe_recording_free(struct auxtrace_record *itr)
struct arm_spe_recording *sper =
container_of(itr, struct arm_spe_recording, itr);
free(sper->wrapped);
zfree(&sper->wrapped);
free(sper);
}

4
tools/perf/arch/arm64/util/header.c
View File

@ -29,8 +29,8 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
char path[PATH_MAX];
FILE *file;
scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR,
sysfs, cpus->map[cpu]);
scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR,
sysfs, RC_CHK_ACCESS(cpus)->map[cpu].cpu);
file = fopen(path, "r");
if (!file) {

5
tools/perf/arch/arm64/util/kvm-stat.c
View File

@ -11,7 +11,6 @@ define_exit_reasons_table(arm64_trap_exit_reasons, kvm_arm_exception_class);
const char *kvm_trap_exit_reason = "esr_ec";
const char *vcpu_id_str = "id";
const int decode_str_len = 20;
const char *kvm_exit_reason = "ret";
const char *kvm_entry_trace = "kvm:kvm_entry";
const char *kvm_exit_trace = "kvm:kvm_exit";
@ -45,14 +44,14 @@ static bool event_begin(struct evsel *evsel,
struct perf_sample *sample __maybe_unused,
struct event_key *key __maybe_unused)
{
return !strcmp(evsel->name, kvm_entry_trace);
return evsel__name_is(evsel, kvm_entry_trace);
}
static bool event_end(struct evsel *evsel,
struct perf_sample *sample,
struct event_key *key)
{
if (!strcmp(evsel->name, kvm_exit_trace)) {
if (evsel__name_is(evsel, kvm_exit_trace)) {
event_get_key(evsel, sample, key);
return true;
}

2
tools/perf/arch/arm64/util/mem-events.c
View File

@ -20,7 +20,7 @@ struct perf_mem_event *perf_mem_events__ptr(int i)
return &perf_mem_events[i];
}
char *perf_mem_events__name(int i, char *pmu_name __maybe_unused)
const char *perf_mem_events__name(int i, const char *pmu_name __maybe_unused)
{
struct perf_mem_event *e = perf_mem_events__ptr(i);

15
tools/perf/arch/arm64/util/pmu.c
View File

@ -3,6 +3,7 @@
#include <internal/cpumap.h>
#include "../../../util/cpumap.h"
#include "../../../util/pmu.h"
#include "../../../util/pmus.h"
#include <api/fs/fs.h>
#include <math.h>
@ -10,15 +11,12 @@ static struct perf_pmu *pmu__find_core_pmu(void)
{
struct perf_pmu *pmu = NULL;
while ((pmu = perf_pmu__scan(pmu))) {
if (!is_pmu_core(pmu->name))
continue;
while ((pmu = perf_pmus__scan_core(pmu))) {
/*
* The cpumap should cover all CPUs. Otherwise, some CPUs may
* not support some events or have different event IDs.
*/
if (pmu->cpus->nr != cpu__max_cpu().cpu)
if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu)
return NULL;
return pmu;
@ -56,10 +54,11 @@ double perf_pmu__cpu_slots_per_cycle(void)
perf_pmu__pathname_scnprintf(path, sizeof(path),
pmu->name, "caps/slots");
/*
* The value of slots is not greater than 32 bits, but sysfs__read_int
* can't read value with 0x prefix, so use sysfs__read_ull instead.
* The value of slots is not greater than 32 bits, but
* filename__read_int can't read value with 0x prefix,
* so use filename__read_ull instead.
*/
sysfs__read_ull(path, &slots);
filename__read_ull(path, &slots);
}
return slots ? (double)slots : NAN;

22
tools/perf/arch/common.c
View File

@ -43,6 +43,20 @@ const char *const powerpc_triplets[] = {
NULL
};
const char *const riscv32_triplets[] = {
"riscv32-unknown-linux-gnu-",
"riscv32-linux-android-",
"riscv32-linux-gnu-",
NULL
};
const char *const riscv64_triplets[] = {
"riscv64-unknown-linux-gnu-",
"riscv64-linux-android-",
"riscv64-linux-gnu-",
NULL
};
const char *const s390_triplets[] = {
"s390-ibm-linux-",
"s390x-linux-gnu-",
@ -130,7 +144,7 @@ static int lookup_triplets(const char *const *triplets, const char *name)
}
static int perf_env__lookup_binutils_path(struct perf_env *env,
const char *name, const char **path)
const char *name, char **path)
{
int idx;
const char *arch = perf_env__arch(env), *cross_env;
@ -166,6 +180,10 @@ static int perf_env__lookup_binutils_path(struct perf_env *env,
path_list = arm64_triplets;
else if (!strcmp(arch, "powerpc"))
path_list = powerpc_triplets;
else if (!strcmp(arch, "riscv32"))
path_list = riscv32_triplets;
else if (!strcmp(arch, "riscv64"))
path_list = riscv64_triplets;
else if (!strcmp(arch, "sh"))
path_list = sh_triplets;
else if (!strcmp(arch, "s390"))
@ -202,7 +220,7 @@ out_error:
return -1;
}
int perf_env__lookup_objdump(struct perf_env *env, const char **path)
int perf_env__lookup_objdump(struct perf_env *env, char **path)
{
/*
* For live mode, env->arch will be NULL and we can use

2
tools/perf/arch/common.h
View File

@ -6,7 +6,7 @@
struct perf_env;
int perf_env__lookup_objdump(struct perf_env *env, const char **path);
int perf_env__lookup_objdump(struct perf_env *env, char **path);
bool perf_env__single_address_space(struct perf_env *env);
#endif /* ARCH_PERF_COMMON_H */

2
tools/perf/arch/mips/entry/syscalls/mksyscalltbl
View File

@ -18,7 +18,7 @@ create_table()
{
local max_nr nr abi sc discard
echo 'static const char *syscalltbl_mips_n64[] = {'
echo 'static const char *const syscalltbl_mips_n64[] = {'
while read nr abi sc discard; do
printf '\t[%d] = "%s",\n' $nr $sc
max_nr=$nr

2
tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl
View File

@ -23,7 +23,7 @@ create_table()
max_nr=-1
nr=0
echo "static const char *syscalltbl_powerpc_${wordsize}[] = {"
echo "static const char *const syscalltbl_powerpc_${wordsize}[] = {"
while read nr abi sc discard; do
if [ "$max_nr" -lt "$nr" ]; then
printf '\t[%d] = "%s",\n' $nr $sc

4
tools/perf/arch/powerpc/tests/dwarf-unwind.c
View File

@ -26,14 +26,14 @@ static int sample_ustack(struct perf_sample *sample,
sp = (unsigned long) regs[PERF_REG_POWERPC_R1];
map = maps__find(thread->maps, (u64)sp);
map = maps__find(thread__maps(thread), (u64)sp);
if (!map) {
pr_debug("failed to get stack map\n");
free(buf);
return -1;
}
stack_size = map->end - sp;
stack_size = map__end(map) - sp;
stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
memcpy(buf, (void *) sp, stack_size);

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

@ -45,6 +45,6 @@ int arch_get_runtimeparam(const struct pmu_metric *pm)
int count;
char path[PATH_MAX] = "/devices/hv_24x7/interface/";
atoi(pm->aggr_mode) == PerChip ? strcat(path, "sockets") : strcat(path, "coresperchip");
strcat(path, pm->aggr_mode == PerChip ? "sockets" : "coresperchip");
return sysfs__read_int(path, &count) < 0 ? 1 : count;
}

11
tools/perf/arch/powerpc/util/kvm-stat.c
View File

@ -5,7 +5,7 @@
#include "util/debug.h"
#include "util/evsel.h"
#include "util/evlist.h"
#include "util/pmu.h"
#include "util/pmus.h"
#include "book3s_hv_exits.h"
#include "book3s_hcalls.h"
@ -14,7 +14,6 @@
#define NR_TPS 4
const char *vcpu_id_str = "vcpu_id";
const int decode_str_len = 40;
const char *kvm_entry_trace = "kvm_hv:kvm_guest_enter";
const char *kvm_exit_trace = "kvm_hv:kvm_guest_exit";
@ -61,13 +60,13 @@ static bool hcall_event_end(struct evsel *evsel,
struct perf_sample *sample __maybe_unused,
struct event_key *key __maybe_unused)
{
return (!strcmp(evsel->name, kvm_events_tp[3]));
return (evsel__name_is(evsel, kvm_events_tp[3]));
}
static bool hcall_event_begin(struct evsel *evsel,
struct perf_sample *sample, struct event_key *key)
{
if (!strcmp(evsel->name, kvm_events_tp[2])) {
if (evsel__name_is(evsel, kvm_events_tp[2])) {
hcall_event_get_key(evsel, sample, key);
return true;
}
@ -80,7 +79,7 @@ static void hcall_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
{
const char *hcall_reason = get_hcall_exit_reason(key->key);
scnprintf(decode, decode_str_len, "%s", hcall_reason);
scnprintf(decode, KVM_EVENT_NAME_LEN, "%s", hcall_reason);
}
static struct kvm_events_ops hcall_events = {
@ -205,7 +204,7 @@ int kvm_add_default_arch_event(int *argc, const char **argv)
parse_options(j, tmp, event_options, NULL, PARSE_OPT_KEEP_UNKNOWN);
if (!event) {
if (pmu_have_event("trace_imc", "trace_cycles")) {
if (perf_pmus__have_event("trace_imc", "trace_cycles")) {
argv[j++] = strdup("-e");
argv[j++] = strdup("trace_imc/trace_cycles/");
*argc += 2;

6
tools/perf/arch/powerpc/util/mem-events.c
View File

@ -3,10 +3,10 @@
#include "mem-events.h"
/* PowerPC does not support 'ldlat' parameter. */
char *perf_mem_events__name(int i, char *pmu_name __maybe_unused)
const char *perf_mem_events__name(int i, const char *pmu_name __maybe_unused)
{
if (i == PERF_MEM_EVENTS__LOAD)
return (char *) "cpu/mem-loads/";
return "cpu/mem-loads/";
return (char *) "cpu/mem-stores/";
return "cpu/mem-stores/";
}

8
tools/perf/arch/powerpc/util/skip-callchain-idx.c
View File

@ -250,19 +250,21 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
if (!chain || chain->nr < 3)
return skip_slot;
addr_location__init(&al);
ip = chain->ips[1];
thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
if (al.map)
dso = al.map->dso;
dso = map__dso(al.map);
if (!dso) {
pr_debug("%" PRIx64 " dso is NULL\n", ip);
addr_location__exit(&al);
return skip_slot;
}
rc = check_return_addr(dso, al.map->start, ip);
rc = check_return_addr(dso, map__start(al.map), ip);
pr_debug("[DSO %s, sym %s, ip 0x%" PRIx64 "] rc %d\n",
dso->long_name, al.sym->name, ip, rc);
@ -279,5 +281,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
*/
skip_slot = 3;
}
addr_location__exit(&al);
return skip_slot;
}

4
tools/perf/arch/powerpc/util/sym-handling.c
View File

@ -104,7 +104,7 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev,
lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym);
if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS)
if (map__dso(map)->symtab_type == DSO_BINARY_TYPE__KALLSYMS)
tev->point.offset += PPC64LE_LEP_OFFSET;
else if (lep_offset) {
if (pev->uprobes)
@ -131,7 +131,7 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
for (i = 0; i < ntevs; i++) {
tev = &pev->tevs[i];
map__for_each_symbol(map, sym, tmp) {
if (map->unmap_ip(map, sym->start) == tev->point.address) {
if (map__unmap_ip(map, sym->start) == tev->point.address) {
arch__fix_tev_from_maps(pev, tev, map, sym);
break;
}

2
tools/perf/arch/s390/annotate/instructions.c
View File

@ -39,7 +39,7 @@ static int s390_call__parse(struct arch *arch, struct ins_operands *ops,
target.addr = map__objdump_2mem(map, ops->target.addr);
if (maps__find_ams(ms->maps, &target) == 0 &&
map__rip_2objdump(target.ms.map, map->map_ip(target.ms.map, target.addr)) == ops->target.addr)
map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
ops->target.sym = target.ms.sym;
return 0;

2
tools/perf/arch/s390/entry/syscalls/mksyscalltbl
View File

@ -18,7 +18,7 @@ create_table()
{
local max_nr nr abi sc discard
echo 'static const char *syscalltbl_s390_64[] = {'
echo 'static const char *const syscalltbl_s390_64[] = {'
while read nr abi sc discard; do
printf '\t[%d] = "%s",\n' $nr $sc
max_nr=$nr

1
tools/perf/arch/s390/util/Build
View File

@ -6,5 +6,6 @@ perf-$(CONFIG_DWARF) += dwarf-regs.o
perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
perf-y += machine.o
perf-y += pmu.o
perf-$(CONFIG_AUXTRACE) += auxtrace.o

1
tools/perf/arch/s390/util/kvm-stat.c
View File

@ -19,7 +19,6 @@ define_exit_reasons_table(sie_diagnose_codes, diagnose_codes);
define_exit_reasons_table(sie_icpt_prog_codes, icpt_prog_codes);
const char *vcpu_id_str = "id";
const int decode_str_len = 40;
const char *kvm_exit_reason = "icptcode";
const char *kvm_entry_trace = "kvm:kvm_s390_sie_enter";
const char *kvm_exit_trace = "kvm:kvm_s390_sie_exit";

23
tools/perf/arch/s390/util/pmu.c Normal file
View File

@ -0,0 +1,23 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2023
* Author(s): Thomas Richter <tmricht@linux.ibm.com>
*/
#include <string.h>
#include "../../../util/pmu.h"
#define S390_PMUPAI_CRYPTO "pai_crypto"
#define S390_PMUPAI_EXT "pai_ext"
#define S390_PMUCPUM_CF "cpum_cf"
struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu)
{
if (!strcmp(pmu->name, S390_PMUPAI_CRYPTO) ||
!strcmp(pmu->name, S390_PMUPAI_EXT) ||
!strcmp(pmu->name, S390_PMUCPUM_CF))
pmu->selectable = true;
return NULL;
}

50
tools/perf/arch/x86/annotate/instructions.c
View File

@ -1,46 +1,37 @@
// SPDX-License-Identifier: GPL-2.0
/*
* x86 instruction nmemonic table to parse disasm lines for annotate.
* This table is searched twice - one for exact match and another for
* match without a size suffix (b, w, l, q) in case of AT&T syntax.
*
* So this table should not have entries with the suffix unless it's
* a complete different instruction than ones without the suffix.
*/
static struct ins x86__instructions[] = {
{ .name = "adc", .ops = &mov_ops, },
{ .name = "adcb", .ops = &mov_ops, },
{ .name = "adcl", .ops = &mov_ops, },
{ .name = "add", .ops = &mov_ops, },
{ .name = "addl", .ops = &mov_ops, },
{ .name = "addq", .ops = &mov_ops, },
{ .name = "addsd", .ops = &mov_ops, },
{ .name = "addw", .ops = &mov_ops, },
{ .name = "and", .ops = &mov_ops, },
{ .name = "andb", .ops = &mov_ops, },
{ .name = "andl", .ops = &mov_ops, },
{ .name = "andpd", .ops = &mov_ops, },
{ .name = "andps", .ops = &mov_ops, },
{ .name = "andq", .ops = &mov_ops, },
{ .name = "andw", .ops = &mov_ops, },
{ .name = "bsr", .ops = &mov_ops, },
{ .name = "bt", .ops = &mov_ops, },
{ .name = "btr", .ops = &mov_ops, },
{ .name = "bts", .ops = &mov_ops, },
{ .name = "btsq", .ops = &mov_ops, },
{ .name = "call", .ops = &call_ops, },
{ .name = "callq", .ops = &call_ops, },
{ .name = "cmovbe", .ops = &mov_ops, },
{ .name = "cmove", .ops = &mov_ops, },
{ .name = "cmovae", .ops = &mov_ops, },
{ .name = "cmp", .ops = &mov_ops, },
{ .name = "cmpb", .ops = &mov_ops, },
{ .name = "cmpl", .ops = &mov_ops, },
{ .name = "cmpq", .ops = &mov_ops, },
{ .name = "cmpw", .ops = &mov_ops, },
{ .name = "cmpxch", .ops = &mov_ops, },
{ .name = "cmpxchg", .ops = &mov_ops, },
{ .name = "cs", .ops = &mov_ops, },
{ .name = "dec", .ops = &dec_ops, },
{ .name = "decl", .ops = &dec_ops, },
{ .name = "divsd", .ops = &mov_ops, },
{ .name = "divss", .ops = &mov_ops, },
{ .name = "gs", .ops = &mov_ops, },
{ .name = "imul", .ops = &mov_ops, },
{ .name = "inc", .ops = &dec_ops, },
{ .name = "incl", .ops = &dec_ops, },
{ .name = "ja", .ops = &jump_ops, },
{ .name = "jae", .ops = &jump_ops, },
{ .name = "jb", .ops = &jump_ops, },
@ -54,7 +45,6 @@ static struct ins x86__instructions[] = {
{ .name = "jl", .ops = &jump_ops, },
{ .name = "jle", .ops = &jump_ops, },
{ .name = "jmp", .ops = &jump_ops, },
{ .name = "jmpq", .ops = &jump_ops, },
{ .name = "jna", .ops = &jump_ops, },
{ .name = "jnae", .ops = &jump_ops, },
{ .name = "jnb", .ops = &jump_ops, },
@ -81,48 +71,32 @@ static struct ins x86__instructions[] = {
{ .name = "mov", .ops = &mov_ops, },
{ .name = "movapd", .ops = &mov_ops, },
{ .name = "movaps", .ops = &mov_ops, },
{ .name = "movb", .ops = &mov_ops, },
{ .name = "movdqa", .ops = &mov_ops, },
{ .name = "movdqu", .ops = &mov_ops, },
{ .name = "movl", .ops = &mov_ops, },
{ .name = "movq", .ops = &mov_ops, },
{ .name = "movsd", .ops = &mov_ops, },
{ .name = "movslq", .ops = &mov_ops, },
{ .name = "movss", .ops = &mov_ops, },
{ .name = "movupd", .ops = &mov_ops, },
{ .name = "movups", .ops = &mov_ops, },
{ .name = "movw", .ops = &mov_ops, },
{ .name = "movzbl", .ops = &mov_ops, },
{ .name = "movzwl", .ops = &mov_ops, },
{ .name = "mulsd", .ops = &mov_ops, },
{ .name = "mulss", .ops = &mov_ops, },
{ .name = "nop", .ops = &nop_ops, },
{ .name = "nopl", .ops = &nop_ops, },
{ .name = "nopw", .ops = &nop_ops, },
{ .name = "or", .ops = &mov_ops, },
{ .name = "orb", .ops = &mov_ops, },
{ .name = "orl", .ops = &mov_ops, },
{ .name = "orps", .ops = &mov_ops, },
{ .name = "orq", .ops = &mov_ops, },
{ .name = "pand", .ops = &mov_ops, },
{ .name = "paddq", .ops = &mov_ops, },
{ .name = "pcmpeqb", .ops = &mov_ops, },
{ .name = "por", .ops = &mov_ops, },
{ .name = "rclb", .ops = &mov_ops, },
{ .name = "rcll", .ops = &mov_ops, },
{ .name = "rcl", .ops = &mov_ops, },
{ .name = "ret", .ops = &ret_ops, },
{ .name = "retq", .ops = &ret_ops, },
{ .name = "sbb", .ops = &mov_ops, },
{ .name = "sbbl", .ops = &mov_ops, },
{ .name = "sete", .ops = &mov_ops, },
{ .name = "sub", .ops = &mov_ops, },
{ .name = "subl", .ops = &mov_ops, },
{ .name = "subq", .ops = &mov_ops, },
{ .name = "subsd", .ops = &mov_ops, },
{ .name = "subw", .ops = &mov_ops, },
{ .name = "test", .ops = &mov_ops, },
{ .name = "testb", .ops = &mov_ops, },
{ .name = "testl", .ops = &mov_ops, },
{ .name = "tzcnt", .ops = &mov_ops, },
{ .name = "ucomisd", .ops = &mov_ops, },
{ .name = "ucomiss", .ops = &mov_ops, },
{ .name = "vaddsd", .ops = &mov_ops, },
@ -135,11 +109,9 @@ static struct ins x86__instructions[] = {
{ .name = "vsubsd", .ops = &mov_ops, },
{ .name = "vucomisd", .ops = &mov_ops, },
{ .name = "xadd", .ops = &mov_ops, },
{ .name = "xbeginl", .ops = &jump_ops, },
{ .name = "xbeginq", .ops = &jump_ops, },
{ .name = "xbegin", .ops = &jump_ops, },
{ .name = "xchg", .ops = &mov_ops, },
{ .name = "xor", .ops = &mov_ops, },
{ .name = "xorb", .ops = &mov_ops, },
{ .name = "xorpd", .ops = &mov_ops, },
{ .name = "xorps", .ops = &mov_ops, },
};

2
tools/perf/arch/x86/entry/syscalls/syscalltbl.sh
View File

@ -18,7 +18,7 @@ emit() {
syscall_macro "$nr" "$entry"
}
echo "static const char *syscalltbl_${arch}[] = {"
echo "static const char *const syscalltbl_${arch}[] = {"
sorted_table=$(mktemp /tmp/syscalltbl.XXXXXX)
grep '^[0-9]' "$in" | sort -n > $sorted_table

4
tools/perf/arch/x86/include/arch-tests.h
View File

@ -6,11 +6,15 @@ struct test_suite;
/* Tests */
int test__rdpmc(struct test_suite *test, int subtest);
#ifdef HAVE_EXTRA_TESTS
int test__insn_x86(struct test_suite *test, int subtest);
#endif
int test__intel_pt_pkt_decoder(struct test_suite *test, int subtest);
int test__intel_pt_hybrid_compat(struct test_suite *test, int subtest);
int test__bp_modify(struct test_suite *test, int subtest);
int test__x86_sample_parsing(struct test_suite *test, int subtest);
int test__amd_ibs_via_core_pmu(struct test_suite *test, int subtest);
int test__hybrid(struct test_suite *test, int subtest);
extern struct test_suite *arch_tests[];

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