u64 intel_ctrl_host_mask;
struct perf_guest_switch_msr guest_switch_msrs[X86_PMC_IDX_MAX];
+ /*
+ * Intel checkpoint mask
+ */
+ u64 intel_cp_status;
+
/*
* manage shared (per-core, per-cpu) registers
* used on Intel NHM/WSM/SNB
int lbr_nr; /* hardware stack size */
u64 lbr_sel_mask; /* LBR_SELECT valid bits */
const int *lbr_sel_map; /* lbr_select mappings */
+ bool lbr_double_abort; /* duplicated lbr aborts */
/*
* Extra registers for events
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");
-EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
+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");
+EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
struct attribute *nhm_events_attrs[] = {
EVENT_PTR(mem_ld_nhm),
wrmsrl(hwc->config_base, ctrl_val);
}
+static inline bool event_is_checkpointed(struct perf_event *event)
+{
+ return (event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
+}
+
static void intel_pmu_disable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
+ cpuc->intel_cp_status &= ~(1ull << hwc->idx);
/*
* must disable before any actual event
if (event->attr.exclude_guest)
cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx);
+ if (unlikely(event_is_checkpointed(event)))
+ cpuc->intel_cp_status |= (1ull << hwc->idx);
+
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_enable_fixed(hwc);
return;
int intel_pmu_save_and_restart(struct perf_event *event)
{
x86_perf_event_update(event);
+ /*
+ * For a checkpointed counter always reset back to 0. This
+ * avoids a situation where the counter overflows, aborts the
+ * transaction and is then set back to shortly before the
+ * overflow, and overflows and aborts again.
+ */
+ if (unlikely(event_is_checkpointed(event))) {
+ /* No race with NMIs because the counter should not be armed */
+ wrmsrl(event->hw.event_base, 0);
+ local64_set(&event->hw.prev_count, 0);
+ }
return x86_perf_event_set_period(event);
}
x86_pmu.drain_pebs(regs);
}
+ /*
+ * Checkpointed counters can lead to 'spurious' PMIs because the
+ * rollback caused by the PMI will have cleared the overflow status
+ * bit. Therefore always force probe these counters.
+ */
+ status |= cpuc->intel_cp_status;
+
for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
struct perf_event *event = cpuc->events[bit];
event->attr.precise_ip > 0))
return -EOPNOTSUPP;
+ if (event_is_checkpointed(event)) {
+ /*
+ * Sampling of checkpointed events can cause situations where
+ * the CPU constantly aborts because of a overflow, which is
+ * then checkpointed back and ignored. Forbid checkpointing
+ * for sampling.
+ *
+ * But still allow a long sampling period, so that perf stat
+ * from KVM works.
+ */
+ if (event->attr.sample_period > 0 &&
+ event->attr.sample_period < 0x7fffffff)
+ return -EOPNOTSUPP;
+ }
return 0;
}
}
}
-EVENT_ATTR_STR(mem-loads, mem_ld_hsw, "event=0xcd,umask=0x1,ldlat=3");
-EVENT_ATTR_STR(mem-stores, mem_st_hsw, "event=0xd0,umask=0x82")
+EVENT_ATTR_STR(mem-loads, mem_ld_hsw, "event=0xcd,umask=0x1,ldlat=3");
+EVENT_ATTR_STR(mem-stores, mem_st_hsw, "event=0xd0,umask=0x82")
+
+/* Haswell special events */
+EVENT_ATTR_STR(tx-start, tx_start, "event=0xc9,umask=0x1");
+EVENT_ATTR_STR(tx-commit, tx_commit, "event=0xc9,umask=0x2");
+EVENT_ATTR_STR(tx-abort, tx_abort, "event=0xc9,umask=0x4");
+EVENT_ATTR_STR(tx-capacity, tx_capacity, "event=0x54,umask=0x2");
+EVENT_ATTR_STR(tx-conflict, tx_conflict, "event=0x54,umask=0x1");
+EVENT_ATTR_STR(el-start, el_start, "event=0xc8,umask=0x1");
+EVENT_ATTR_STR(el-commit, el_commit, "event=0xc8,umask=0x2");
+EVENT_ATTR_STR(el-abort, el_abort, "event=0xc8,umask=0x4");
+EVENT_ATTR_STR(el-capacity, el_capacity, "event=0x54,umask=0x2");
+EVENT_ATTR_STR(el-conflict, el_conflict, "event=0x54,umask=0x1");
+EVENT_ATTR_STR(cycles-t, cycles_t, "event=0x3c,in_tx=1");
+EVENT_ATTR_STR(cycles-ct, cycles_ct, "event=0x3c,in_tx=1,in_tx_cp=1");
static struct attribute *hsw_events_attrs[] = {
+ EVENT_PTR(tx_start),
+ EVENT_PTR(tx_commit),
+ EVENT_PTR(tx_abort),
+ EVENT_PTR(tx_capacity),
+ EVENT_PTR(tx_conflict),
+ EVENT_PTR(el_start),
+ EVENT_PTR(el_commit),
+ EVENT_PTR(el_abort),
+ EVENT_PTR(el_capacity),
+ EVENT_PTR(el_conflict),
+ EVENT_PTR(cycles_t),
+ EVENT_PTR(cycles_ct),
EVENT_PTR(mem_ld_hsw),
EVENT_PTR(mem_st_hsw),
NULL
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
x86_pmu.cpu_events = hsw_events_attrs;
+ x86_pmu.lbr_double_abort = true;
pr_cont("Haswell events, ");
break;
* Same as pebs_record_nhm, with two additional fields.
*/
struct pebs_record_hsw {
- struct pebs_record_nhm nhm;
- /*
- * Real IP of the event. In the Intel documentation this
- * is called eventingrip.
- */
- u64 real_ip;
- /*
- * TSX tuning information field: abort cycles and abort flags.
- */
- u64 tsx_tuning;
+ u64 flags, ip;
+ u64 ax, bx, cx, dx;
+ u64 si, di, bp, sp;
+ u64 r8, r9, r10, r11;
+ u64 r12, r13, r14, r15;
+ u64 status, dla, dse, lat;
+ u64 real_ip, tsx_tuning;
+};
+
+union hsw_tsx_tuning {
+ struct {
+ u32 cycles_last_block : 32,
+ hle_abort : 1,
+ rtm_abort : 1,
+ instruction_abort : 1,
+ non_instruction_abort : 1,
+ retry : 1,
+ data_conflict : 1,
+ capacity_writes : 1,
+ capacity_reads : 1;
+ };
+ u64 value;
};
+#define PEBS_HSW_TSX_FLAGS 0xff00000000ULL
+
void init_debug_store_on_cpu(int cpu)
{
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
return 0;
}
+static inline u64 intel_hsw_weight(struct pebs_record_hsw *pebs)
+{
+ if (pebs->tsx_tuning) {
+ union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning };
+ return tsx.cycles_last_block;
+ }
+ return 0;
+}
+
+static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs)
+{
+ u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
+
+ /* For RTM XABORTs also log the abort code from AX */
+ if ((txn & PERF_TXN_TRANSACTION) && (pebs->ax & 1))
+ txn |= ((pebs->ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
+ return txn;
+}
+
static void __intel_pmu_pebs_event(struct perf_event *event,
struct pt_regs *iregs, void *__pebs)
{
/*
- * We cast to pebs_record_nhm to get the load latency data
- * if extra_reg MSR_PEBS_LD_LAT_THRESHOLD used
+ * We cast to the biggest pebs_record but are careful not to
+ * unconditionally access the 'extra' entries.
*/
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- struct pebs_record_nhm *pebs = __pebs;
- struct pebs_record_hsw *pebs_hsw = __pebs;
+ struct pebs_record_hsw *pebs = __pebs;
struct perf_sample_data data;
struct pt_regs regs;
u64 sample_type;
regs.sp = pebs->sp;
if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
- regs.ip = pebs_hsw->real_ip;
+ regs.ip = pebs->real_ip;
regs.flags |= PERF_EFLAGS_EXACT;
} else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(®s))
regs.flags |= PERF_EFLAGS_EXACT;
regs.flags &= ~PERF_EFLAGS_EXACT;
if ((event->attr.sample_type & PERF_SAMPLE_ADDR) &&
- x86_pmu.intel_cap.pebs_format >= 1)
+ x86_pmu.intel_cap.pebs_format >= 1)
data.addr = pebs->dla;
+ if (x86_pmu.intel_cap.pebs_format >= 2) {
+ /* Only set the TSX weight when no memory weight. */
+ if ((event->attr.sample_type & PERF_SAMPLE_WEIGHT) && !fll)
+ data.weight = intel_hsw_weight(pebs);
+
+ if (event->attr.sample_type & PERF_SAMPLE_TRANSACTION)
+ data.txn = intel_hsw_transaction(pebs);
+ }
+
if (has_branch_stack(event))
data.br_stack = &cpuc->lbr_stack;
__intel_pmu_pebs_event(event, iregs, at);
}
-static void __intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, void *at,
- void *top)
+static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
struct debug_store *ds = cpuc->ds;
struct perf_event *event = NULL;
+ void *at, *top;
u64 status = 0;
int bit;
+ if (!x86_pmu.pebs_active)
+ return;
+
+ at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
+ top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
+
ds->pebs_index = ds->pebs_buffer_base;
+ if (unlikely(at > top))
+ return;
+
+ /*
+ * Should not happen, we program the threshold at 1 and do not
+ * set a reset value.
+ */
+ WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size,
+ "Unexpected number of pebs records %ld\n",
+ (long)(top - at) / x86_pmu.pebs_record_size);
+
for (; at < top; at += x86_pmu.pebs_record_size) {
struct pebs_record_nhm *p = at;
}
}
-static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- struct debug_store *ds = cpuc->ds;
- struct pebs_record_nhm *at, *top;
- int n;
-
- if (!x86_pmu.pebs_active)
- return;
-
- at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
- top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
-
- ds->pebs_index = ds->pebs_buffer_base;
-
- n = top - at;
- if (n <= 0)
- return;
-
- /*
- * Should not happen, we program the threshold at 1 and do not
- * set a reset value.
- */
- WARN_ONCE(n > x86_pmu.max_pebs_events,
- "Unexpected number of pebs records %d\n", n);
-
- return __intel_pmu_drain_pebs_nhm(iregs, at, top);
-}
-
-static void intel_pmu_drain_pebs_hsw(struct pt_regs *iregs)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- struct debug_store *ds = cpuc->ds;
- struct pebs_record_hsw *at, *top;
- int n;
-
- if (!x86_pmu.pebs_active)
- return;
-
- at = (struct pebs_record_hsw *)(unsigned long)ds->pebs_buffer_base;
- top = (struct pebs_record_hsw *)(unsigned long)ds->pebs_index;
-
- n = top - at;
- if (n <= 0)
- return;
- /*
- * Should not happen, we program the threshold at 1 and do not
- * set a reset value.
- */
- WARN_ONCE(n > x86_pmu.max_pebs_events,
- "Unexpected number of pebs records %d\n", n);
-
- return __intel_pmu_drain_pebs_nhm(iregs, at, top);
-}
-
/*
* BTS, PEBS probe and setup
*/
case 2:
pr_cont("PEBS fmt2%c, ", pebs_type);
x86_pmu.pebs_record_size = sizeof(struct pebs_record_hsw);
- x86_pmu.drain_pebs = intel_pmu_drain_pebs_hsw;
+ x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
break;
default:
int lbr_format = x86_pmu.intel_cap.lbr_format;
u64 tos = intel_pmu_lbr_tos();
int i;
+ int out = 0;
for (i = 0; i < x86_pmu.lbr_nr; i++) {
unsigned long lbr_idx = (tos - i) & mask;
}
from = (u64)((((s64)from) << skip) >> skip);
- cpuc->lbr_entries[i].from = from;
- cpuc->lbr_entries[i].to = to;
- cpuc->lbr_entries[i].mispred = mis;
- cpuc->lbr_entries[i].predicted = pred;
- cpuc->lbr_entries[i].in_tx = in_tx;
- cpuc->lbr_entries[i].abort = abort;
- cpuc->lbr_entries[i].reserved = 0;
+ /*
+ * Some CPUs report duplicated abort records,
+ * with the second entry not having an abort bit set.
+ * Skip them here. This loop runs backwards,
+ * so we need to undo the previous record.
+ * If the abort just happened outside the window
+ * the extra entry cannot be removed.
+ */
+ if (abort && x86_pmu.lbr_double_abort && out > 0)
+ out--;
+
+ cpuc->lbr_entries[out].from = from;
+ cpuc->lbr_entries[out].to = to;
+ cpuc->lbr_entries[out].mispred = mis;
+ cpuc->lbr_entries[out].predicted = pred;
+ cpuc->lbr_entries[out].in_tx = in_tx;
+ cpuc->lbr_entries[out].abort = abort;
+ cpuc->lbr_entries[out].reserved = 0;
+ out++;
}
- cpuc->lbr_stack.nr = i;
+ cpuc->lbr_stack.nr = out;
}
void intel_pmu_lbr_read(void)
struct perf_regs_user regs_user;
u64 stack_user_size;
u64 weight;
+ /*
+ * Transaction flags for abort events:
+ */
+ u64 txn;
};
static inline void perf_sample_data_init(struct perf_sample_data *data,
data->stack_user_size = 0;
data->weight = 0;
data->data_src.val = 0;
+ data->txn = 0;
}
extern void perf_output_sample(struct perf_output_handle *handle,
PERF_SAMPLE_WEIGHT = 1U << 14,
PERF_SAMPLE_DATA_SRC = 1U << 15,
PERF_SAMPLE_IDENTIFIER = 1U << 16,
+ PERF_SAMPLE_TRANSACTION = 1U << 17,
- PERF_SAMPLE_MAX = 1U << 17, /* non-ABI */
+ PERF_SAMPLE_MAX = 1U << 18, /* non-ABI */
};
/*
PERF_SAMPLE_REGS_ABI_64 = 2,
};
+/*
+ * Values for the memory transaction event qualifier, mostly for
+ * abort events. Multiple bits can be set.
+ */
+enum {
+ PERF_TXN_ELISION = (1 << 0), /* From elision */
+ PERF_TXN_TRANSACTION = (1 << 1), /* From transaction */
+ PERF_TXN_SYNC = (1 << 2), /* Instruction is related */
+ PERF_TXN_ASYNC = (1 << 3), /* Instruction not related */
+ PERF_TXN_RETRY = (1 << 4), /* Retry possible */
+ PERF_TXN_CONFLICT = (1 << 5), /* Conflict abort */
+ PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */
+ PERF_TXN_CAPACITY_READ = (1 << 7), /* Capacity read abort */
+
+ PERF_TXN_MAX = (1 << 8), /* non-ABI */
+
+ /* bits 32..63 are reserved for the abort code */
+
+ PERF_TXN_ABORT_MASK = (0xffffffffULL << 32),
+ PERF_TXN_ABORT_SHIFT = 32,
+};
+
/*
* The format of the data returned by read() on a perf event fd,
* as specified by attr.read_format:
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- int ret = proc_dointvec(table, write, buffer, lenp, ppos);
+ int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret || !write)
return ret;
if (sample_type & PERF_SAMPLE_DATA_SRC)
size += sizeof(data->data_src.val);
+ if (sample_type & PERF_SAMPLE_TRANSACTION)
+ size += sizeof(data->txn);
+
event->header_size = size;
}
if (sample_type & PERF_SAMPLE_DATA_SRC)
perf_output_put(handle, data->data_src.val);
+ if (sample_type & PERF_SAMPLE_TRANSACTION)
+ perf_output_put(handle, data->txn);
+
if (!event->attr.watermark) {
int wakeup_events = event->attr.wakeup_events;
.maxlen = sizeof(sysctl_perf_event_sample_rate),
.mode = 0644,
.proc_handler = perf_proc_update_handler,
+ .extra1 = &one,
},
{
.procname = "perf_cpu_time_max_percent",
- u: only when the branch target is at the user level
- k: only when the branch target is in the kernel
- hv: only when the target is at the hypervisor level
+ - in_tx: only when the target is in a hardware transaction
+ - no_tx: only when the target is not in a hardware transaction
+ - abort_tx: only when the target is a hardware transaction abort
+
The option requires at least one branch type among any, any_call, any_ret, ind_call.
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.
--W::
--weight::
Enable weightened sampling. An additional weight is recorded per sample and can be
displayed with the weight and local_weight sort keys. This currently works for TSX
abort events and some memory events in precise mode on modern Intel CPUs.
+--transaction::
+Record transaction flags for transaction related events.
+
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-list[1]
entries are displayed as "[other]".
- cpu: cpu number the task ran at the time of sample
- srcline: filename and line number executed at the time of sample. The
- DWARF debuggin info must be provided.
+ DWARF debugging info must be provided.
+ - weight: Event specific weight, e.g. memory latency or transaction
+ abort cost. This is the global weight.
+ - local_weight: Local weight version of the weight above.
+ - transaction: Transaction abort flags.
By default, comm, dso and symbol keys are used.
(i.e. --sort comm,dso,symbol)
- symbol_from: name of function branched from
- symbol_to: name of function branched to
- mispredict: "N" for predicted branch, "Y" for mispredicted branch
+ - in_tx: branch in TSX transaction
+ - abort: TSX transaction abort.
And default sort keys are changed to comm, dso_from, symbol_from, dso_to
and symbol_to, see '--branch-stack'.
After starting the program, wait msecs before measuring. This is useful to
filter out the startup phase of the program, which is often very different.
+-T::
+--transaction::
+
+Print statistics of transactional execution if supported.
+
EXAMPLES
--------
-s::
--sort::
- Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight, local_weight.
+ Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight,
+ local_weight, abort, in_tx, transaction
-n::
--show-nr-samples::
return 0;
}
- he = __hists__add_entry(&evsel->hists, al, NULL, 1, 1);
+ he = __hists__add_entry(&evsel->hists, al, NULL, 1, 1, 0);
if (he == NULL)
return -ENOMEM;
static int hists__add_entry(struct hists *self,
struct addr_location *al, u64 period,
- u64 weight)
+ u64 weight, u64 transaction)
{
- if (__hists__add_entry(self, al, NULL, period, weight) != NULL)
+ if (__hists__add_entry(self, al, NULL, period, weight, transaction)
+ != NULL)
return 0;
return -ENOMEM;
}
if (al.filtered)
return 0;
- if (hists__add_entry(&evsel->hists, &al, sample->period, sample->weight)) {
+ if (hists__add_entry(&evsel->hists, &al, sample->period,
+ sample->weight, sample->transaction)) {
pr_warning("problem incrementing symbol period, skipping event\n");
return -1;
}
BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL),
BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN),
BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL),
+ BRANCH_OPT("abort_tx", PERF_SAMPLE_BRANCH_ABORT_TX),
+ BRANCH_OPT("in_tx", PERF_SAMPLE_BRANCH_IN_TX),
+ BRANCH_OPT("no_tx", PERF_SAMPLE_BRANCH_NO_TX),
BRANCH_END
};
parse_branch_stack),
OPT_BOOLEAN('W', "weight", &record.opts.sample_weight,
"sample by weight (on special events only)"),
+ OPT_BOOLEAN(0, "transaction", &record.opts.sample_transaction,
+ "sample transaction flags (special events only)"),
OPT_END()
};
}
he = __hists__add_entry(&evsel->hists, al, parent, sample->period,
- sample->weight);
+ sample->weight, sample->transaction);
if (he == NULL)
return -ENOMEM;
"sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline,"
" dso_to, dso_from, symbol_to, symbol_from, mispredict,"
" weight, local_weight, mem, symbol_daddr, dso_daddr, tlb, "
- "snoop, locked"),
+ "snoop, locked, abort, in_tx, transaction"),
OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
"Show sample percentage for different cpu modes"),
OPT_STRING('p', "parent", &parent_pattern, "regex",
#include "util/util.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
+#include "util/pmu.h"
#include "util/event.h"
#include "util/evlist.h"
#include "util/evsel.h"
static void print_counter(struct perf_evsel *counter, char *prefix);
static void print_aggr(char *prefix);
+/* Default events used for perf stat -T */
+static const char * const transaction_attrs[] = {
+ "task-clock",
+ "{"
+ "instructions,"
+ "cycles,"
+ "cpu/cycles-t/,"
+ "cpu/tx-start/,"
+ "cpu/el-start/,"
+ "cpu/cycles-ct/"
+ "}"
+};
+
+/* More limited version when the CPU does not have all events. */
+static const char * const transaction_limited_attrs[] = {
+ "task-clock",
+ "{"
+ "instructions,"
+ "cycles,"
+ "cpu/cycles-t/,"
+ "cpu/tx-start/"
+ "}"
+};
+
+/* must match transaction_attrs and the beginning limited_attrs */
+enum {
+ T_TASK_CLOCK,
+ T_INSTRUCTIONS,
+ T_CYCLES,
+ T_CYCLES_IN_TX,
+ T_TRANSACTION_START,
+ T_ELISION_START,
+ T_CYCLES_IN_TX_CP,
+};
+
static struct perf_evlist *evsel_list;
static struct perf_target target = {
static volatile pid_t child_pid = -1;
static bool null_run = false;
static int detailed_run = 0;
+static bool transaction_run;
static bool big_num = true;
static int big_num_opt = -1;
static const char *csv_sep = NULL;
static struct stats runtime_ll_cache_stats[MAX_NR_CPUS];
static struct stats runtime_itlb_cache_stats[MAX_NR_CPUS];
static struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS];
+static struct stats runtime_cycles_in_tx_stats[MAX_NR_CPUS];
static struct stats walltime_nsecs_stats;
+static struct stats runtime_transaction_stats[MAX_NR_CPUS];
+static struct stats runtime_elision_stats[MAX_NR_CPUS];
static void perf_stat__reset_stats(struct perf_evlist *evlist)
{
memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));
memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));
memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));
+ memset(runtime_cycles_in_tx_stats, 0,
+ sizeof(runtime_cycles_in_tx_stats));
+ memset(runtime_transaction_stats, 0,
+ sizeof(runtime_transaction_stats));
+ memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
}
return 0;
}
+static struct perf_evsel *nth_evsel(int n)
+{
+ static struct perf_evsel **array;
+ static int array_len;
+ struct perf_evsel *ev;
+ int j;
+
+ /* Assumes this only called when evsel_list does not change anymore. */
+ if (!array) {
+ list_for_each_entry(ev, &evsel_list->entries, node)
+ array_len++;
+ array = malloc(array_len * sizeof(void *));
+ if (!array)
+ exit(ENOMEM);
+ j = 0;
+ list_for_each_entry(ev, &evsel_list->entries, node)
+ array[j++] = ev;
+ }
+ if (n < array_len)
+ return array[n];
+ return NULL;
+}
+
/*
* Update various tracking values we maintain to print
* more semantic information such as miss/hit ratios,
update_stats(&runtime_nsecs_stats[0], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
update_stats(&runtime_cycles_stats[0], count[0]);
+ else if (transaction_run &&
+ perf_evsel__cmp(counter, nth_evsel(T_CYCLES_IN_TX)))
+ update_stats(&runtime_cycles_in_tx_stats[0], count[0]);
+ else if (transaction_run &&
+ perf_evsel__cmp(counter, nth_evsel(T_TRANSACTION_START)))
+ update_stats(&runtime_transaction_stats[0], count[0]);
+ else if (transaction_run &&
+ perf_evsel__cmp(counter, nth_evsel(T_ELISION_START)))
+ update_stats(&runtime_elision_stats[0], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
update_stats(&runtime_stalled_cycles_front_stats[0], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
{
- double total, ratio = 0.0;
+ double total, ratio = 0.0, total2;
const char *fmt;
if (csv_output)
ratio = 1.0 * avg / total;
fprintf(output, " # %8.3f GHz ", ratio);
+ } else if (transaction_run &&
+ perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX))) {
+ total = avg_stats(&runtime_cycles_stats[cpu]);
+ if (total)
+ fprintf(output,
+ " # %5.2f%% transactional cycles ",
+ 100.0 * (avg / total));
+ } else if (transaction_run &&
+ perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX_CP))) {
+ total = avg_stats(&runtime_cycles_stats[cpu]);
+ total2 = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
+ if (total2 < avg)
+ total2 = avg;
+ if (total)
+ fprintf(output,
+ " # %5.2f%% aborted cycles ",
+ 100.0 * ((total2-avg) / total));
+ } else if (transaction_run &&
+ perf_evsel__cmp(evsel, nth_evsel(T_TRANSACTION_START)) &&
+ avg > 0 &&
+ runtime_cycles_in_tx_stats[cpu].n != 0) {
+ total = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
+
+ if (total)
+ ratio = total / avg;
+
+ fprintf(output, " # %8.0f cycles / transaction ", ratio);
+ } else if (transaction_run &&
+ perf_evsel__cmp(evsel, nth_evsel(T_ELISION_START)) &&
+ avg > 0 &&
+ runtime_cycles_in_tx_stats[cpu].n != 0) {
+ total = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
+
+ if (total)
+ ratio = total / avg;
+
+ fprintf(output, " # %8.0f cycles / elision ", ratio);
} else if (runtime_nsecs_stats[cpu].n != 0) {
char unit = 'M';
return 0;
}
+static int setup_events(const char * const *attrs, unsigned len)
+{
+ unsigned i;
+
+ for (i = 0; i < len; i++) {
+ if (parse_events(evsel_list, attrs[i]))
+ return -1;
+ }
+ return 0;
+}
/*
* Add default attributes, if there were no attributes specified or
if (null_run)
return 0;
+ if (transaction_run) {
+ int err;
+ if (pmu_have_event("cpu", "cycles-ct") &&
+ pmu_have_event("cpu", "el-start"))
+ err = setup_events(transaction_attrs,
+ ARRAY_SIZE(transaction_attrs));
+ else
+ err = setup_events(transaction_limited_attrs,
+ ARRAY_SIZE(transaction_limited_attrs));
+ if (err < 0) {
+ fprintf(stderr, "Cannot set up transaction events\n");
+ return -1;
+ }
+ return 0;
+ }
+
if (!evsel_list->nr_entries) {
if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0)
return -1;
int output_fd = 0;
const char *output_name = NULL;
const struct option options[] = {
+ OPT_BOOLEAN('T', "transaction", &transaction_run,
+ "hardware transaction statistics"),
OPT_CALLBACK('e', "event", &evsel_list, "event",
"event selector. use 'perf list' to list available events",
parse_events_option),
pthread_mutex_lock(&evsel->hists.lock);
he = __hists__add_entry(&evsel->hists, al, NULL, sample->period,
- sample->weight);
+ sample->weight, sample->transaction);
pthread_mutex_unlock(&evsel->hists.lock);
-
if (he == NULL)
return NULL;
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
- "sort by key(s): pid, comm, dso, symbol, parent, weight, local_weight"),
+ "sort by key(s): pid, comm, dso, symbol, parent, weight, local_weight,"
+ " abort, in_tx, transaction"),
OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
"Show a column with the number of samples"),
OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts,
struct branch_flags {
u64 mispred:1;
u64 predicted:1;
- u64 reserved:62;
+ u64 in_tx:1;
+ u64 abort:1;
+ u64 reserved:60;
};
struct branch_entry {
u64 default_interval;
u64 user_interval;
u16 stack_dump_size;
+ bool sample_transaction;
};
#endif
&sample) < 0)
goto out;
- he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 1);
+ he = __hists__add_entry(&evsel->hists, &al, NULL,
+ 1, 1, 0);
if (he == NULL)
goto out;
&sample) < 0)
goto out;
- he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 1);
+ he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 1,
+ 0);
if (he == NULL)
goto out;
u64 stream_id;
u64 period;
u64 weight;
+ u64 transaction;
u32 cpu;
u32 raw_size;
u64 data_src;
attr->mmap2 = track && !perf_missing_features.mmap2;
attr->comm = track;
+ if (opts->sample_transaction)
+ attr->sample_type |= PERF_SAMPLE_TRANSACTION;
+
/*
* XXX see the function comment above
*
array++;
}
+ data->transaction = 0;
+ if (type & PERF_SAMPLE_TRANSACTION) {
+ data->transaction = *array;
+ array++;
+ }
+
return 0;
}
(e1->attr.config == e2->attr.config);
}
+#define perf_evsel__cmp(a, b) \
+ ((a) && \
+ (b) && \
+ (a)->attr.type == (b)->attr.type && \
+ (a)->attr.config == (b)->attr.config)
+
int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
int cpu, int thread, bool scale);
hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3);
hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12);
hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12);
+
+ if (h->transaction)
+ hists__new_col_len(hists, HISTC_TRANSACTION,
+ hist_entry__transaction_len());
}
void hists__output_recalc_col_len(struct hists *hists, int max_rows)
struct rb_node **p;
struct rb_node *parent = NULL;
struct hist_entry *he;
- int cmp;
+ int64_t cmp;
p = &hists->entries_in->rb_node;
struct hist_entry *__hists__add_entry(struct hists *self,
struct addr_location *al,
struct symbol *sym_parent, u64 period,
- u64 weight)
+ u64 weight, u64 transaction)
{
struct hist_entry entry = {
.thread = al->thread,
.hists = self,
.branch_info = NULL,
.mem_info = NULL,
+ .transaction = transaction,
};
return add_hist_entry(self, &entry, al, period, weight);
struct rb_node **p;
struct rb_node *parent = NULL;
struct hist_entry *he;
- int cmp;
+ int64_t cmp;
if (sort__need_collapse)
root = &hists->entries_collapsed;
HISTC_CPU,
HISTC_SRCLINE,
HISTC_MISPREDICT,
+ HISTC_IN_TX,
+ HISTC_ABORT,
HISTC_SYMBOL_FROM,
HISTC_SYMBOL_TO,
HISTC_DSO_FROM,
HISTC_MEM_TLB,
HISTC_MEM_LVL,
HISTC_MEM_SNOOP,
+ HISTC_TRANSACTION,
HISTC_NR_COLS, /* Last entry */
};
struct hist_entry *__hists__add_entry(struct hists *self,
struct addr_location *al,
struct symbol *parent, u64 period,
- u64 weight);
+ u64 weight, u64 transaction);
int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
+int hist_entry__transaction_len(void);
int hist_entry__sort_snprintf(struct hist_entry *self, char *bf, size_t size,
struct hists *hists);
void hist_entry__free(struct hist_entry *);
printf("\n");
free(aliases);
}
+
+bool pmu_have_event(const char *pname, const char *name)
+{
+ struct perf_pmu *pmu;
+ struct perf_pmu_alias *alias;
+
+ pmu = NULL;
+ while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+ if (strcmp(pname, pmu->name))
+ continue;
+ list_for_each_entry(alias, &pmu->aliases, list)
+ if (!strcmp(alias->name, name))
+ return true;
+ }
+ return false;
+}
struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
void print_pmu_events(const char *event_glob, bool name_only);
+bool pmu_have_event(const char *pname, const char *name);
int perf_pmu__test(void);
#endif /* __PMU_H */
if (sample_type & PERF_SAMPLE_DATA_SRC)
printf(" . data_src: 0x%"PRIx64"\n", sample->data_src);
+ if (sample_type & PERF_SAMPLE_TRANSACTION)
+ printf("... transaction: %" PRIx64 "\n", sample->transaction);
+
if (sample_type & PERF_SAMPLE_READ)
sample_read__printf(sample, evsel->attr.read_format);
}
.se_width_idx = HISTC_MEM_SNOOP,
};
+static int64_t
+sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ return left->branch_info->flags.abort !=
+ right->branch_info->flags.abort;
+}
+
+static int hist_entry__abort_snprintf(struct hist_entry *self, char *bf,
+ size_t size, unsigned int width)
+{
+ static const char *out = ".";
+
+ if (self->branch_info->flags.abort)
+ out = "A";
+ return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
+struct sort_entry sort_abort = {
+ .se_header = "Transaction abort",
+ .se_cmp = sort__abort_cmp,
+ .se_snprintf = hist_entry__abort_snprintf,
+ .se_width_idx = HISTC_ABORT,
+};
+
+static int64_t
+sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ return left->branch_info->flags.in_tx !=
+ right->branch_info->flags.in_tx;
+}
+
+static int hist_entry__in_tx_snprintf(struct hist_entry *self, char *bf,
+ size_t size, unsigned int width)
+{
+ static const char *out = ".";
+
+ if (self->branch_info->flags.in_tx)
+ out = "T";
+
+ return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
+struct sort_entry sort_in_tx = {
+ .se_header = "Branch in transaction",
+ .se_cmp = sort__in_tx_cmp,
+ .se_snprintf = hist_entry__in_tx_snprintf,
+ .se_width_idx = HISTC_IN_TX,
+};
+
+static int64_t
+sort__transaction_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ return left->transaction - right->transaction;
+}
+
+static inline char *add_str(char *p, const char *str)
+{
+ strcpy(p, str);
+ return p + strlen(str);
+}
+
+static struct txbit {
+ unsigned flag;
+ const char *name;
+ int skip_for_len;
+} txbits[] = {
+ { PERF_TXN_ELISION, "EL ", 0 },
+ { PERF_TXN_TRANSACTION, "TX ", 1 },
+ { PERF_TXN_SYNC, "SYNC ", 1 },
+ { PERF_TXN_ASYNC, "ASYNC ", 0 },
+ { PERF_TXN_RETRY, "RETRY ", 0 },
+ { PERF_TXN_CONFLICT, "CON ", 0 },
+ { PERF_TXN_CAPACITY_WRITE, "CAP-WRITE ", 1 },
+ { PERF_TXN_CAPACITY_READ, "CAP-READ ", 0 },
+ { 0, NULL, 0 }
+};
+
+int hist_entry__transaction_len(void)
+{
+ int i;
+ int len = 0;
+
+ for (i = 0; txbits[i].name; i++) {
+ if (!txbits[i].skip_for_len)
+ len += strlen(txbits[i].name);
+ }
+ len += 4; /* :XX<space> */
+ return len;
+}
+
+static int hist_entry__transaction_snprintf(struct hist_entry *self, char *bf,
+ size_t size, unsigned int width)
+{
+ u64 t = self->transaction;
+ char buf[128];
+ char *p = buf;
+ int i;
+
+ buf[0] = 0;
+ for (i = 0; txbits[i].name; i++)
+ if (txbits[i].flag & t)
+ p = add_str(p, txbits[i].name);
+ if (t && !(t & (PERF_TXN_SYNC|PERF_TXN_ASYNC)))
+ p = add_str(p, "NEITHER ");
+ if (t & PERF_TXN_ABORT_MASK) {
+ sprintf(p, ":%" PRIx64,
+ (t & PERF_TXN_ABORT_MASK) >>
+ PERF_TXN_ABORT_SHIFT);
+ p += strlen(p);
+ }
+
+ return repsep_snprintf(bf, size, "%-*s", width, buf);
+}
+
+struct sort_entry sort_transaction = {
+ .se_header = "Transaction ",
+ .se_cmp = sort__transaction_cmp,
+ .se_snprintf = hist_entry__transaction_snprintf,
+ .se_width_idx = HISTC_TRANSACTION,
+};
+
struct sort_dimension {
const char *name;
struct sort_entry *entry;
DIM(SORT_SRCLINE, "srcline", sort_srcline),
DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
+ DIM(SORT_TRANSACTION, "transaction", sort_transaction),
};
#undef DIM
DIM(SORT_SYM_FROM, "symbol_from", sort_sym_from),
DIM(SORT_SYM_TO, "symbol_to", sort_sym_to),
DIM(SORT_MISPREDICT, "mispredict", sort_mispredict),
+ DIM(SORT_IN_TX, "in_tx", sort_in_tx),
+ DIM(SORT_ABORT, "abort", sort_abort),
};
#undef DIM
struct map_symbol ms;
struct thread *thread;
u64 ip;
+ u64 transaction;
s32 cpu;
struct hist_entry_diff diff;
SORT_SRCLINE,
SORT_LOCAL_WEIGHT,
SORT_GLOBAL_WEIGHT,
+ SORT_TRANSACTION,
/* branch stack specific sort keys */
__SORT_BRANCH_STACK,
SORT_SYM_FROM,
SORT_SYM_TO,
SORT_MISPREDICT,
+ SORT_ABORT,
+ SORT_IN_TX,
/* memory mode specific sort keys */
__SORT_MEMORY_MODE,