Merge branch 'perf/urgent' into perf/core
Conflicts:
tools/perf/builtin-record.c
tools/perf/builtin-top.c
tools/perf/util/hist.h
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index cc16faa..fd00bb2 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -164,6 +164,11 @@
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
*/
@@ -440,6 +445,7 @@
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
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index f31a165..0fa4f24 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -190,9 +190,9 @@
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),
@@ -1184,6 +1184,11 @@
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;
@@ -1197,6 +1202,7 @@
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
@@ -1271,6 +1277,9 @@
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;
@@ -1289,6 +1298,17 @@
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);
}
@@ -1372,6 +1392,13 @@
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];
@@ -1837,6 +1864,20 @@
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;
}
@@ -2182,10 +2223,36 @@
}
}
-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
@@ -2452,6 +2519,7 @@
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;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index ab3ba1c..c1760ff 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -12,6 +12,7 @@
#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
#define PEBS_BUFFER_SIZE PAGE_SIZE
+#define PEBS_FIXUP_SIZE PAGE_SIZE
/*
* pebs_record_32 for p4 and core not supported
@@ -182,18 +183,32 @@
* 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;
@@ -214,12 +229,14 @@
wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
}
+static DEFINE_PER_CPU(void *, insn_buffer);
+
static int alloc_pebs_buffer(int cpu)
{
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
int node = cpu_to_node(cpu);
int max, thresh = 1; /* always use a single PEBS record */
- void *buffer;
+ void *buffer, *ibuffer;
if (!x86_pmu.pebs)
return 0;
@@ -228,6 +245,19 @@
if (unlikely(!buffer))
return -ENOMEM;
+ /*
+ * HSW+ already provides us the eventing ip; no need to allocate this
+ * buffer then.
+ */
+ if (x86_pmu.intel_cap.pebs_format < 2) {
+ ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
+ if (!ibuffer) {
+ kfree(buffer);
+ return -ENOMEM;
+ }
+ per_cpu(insn_buffer, cpu) = ibuffer;
+ }
+
max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
ds->pebs_buffer_base = (u64)(unsigned long)buffer;
@@ -248,6 +278,9 @@
if (!ds || !x86_pmu.pebs)
return;
+ kfree(per_cpu(insn_buffer, cpu));
+ per_cpu(insn_buffer, cpu) = NULL;
+
kfree((void *)(unsigned long)ds->pebs_buffer_base);
ds->pebs_buffer_base = 0;
}
@@ -715,6 +748,7 @@
unsigned long old_to, to = cpuc->lbr_entries[0].to;
unsigned long ip = regs->ip;
int is_64bit = 0;
+ void *kaddr;
/*
* We don't need to fixup if the PEBS assist is fault like
@@ -738,7 +772,7 @@
* unsigned math, either ip is before the start (impossible) or
* the basic block is larger than 1 page (sanity)
*/
- if ((ip - to) > PAGE_SIZE)
+ if ((ip - to) > PEBS_FIXUP_SIZE)
return 0;
/*
@@ -749,29 +783,33 @@
return 1;
}
+ if (!kernel_ip(ip)) {
+ int size, bytes;
+ u8 *buf = this_cpu_read(insn_buffer);
+
+ size = ip - to; /* Must fit our buffer, see above */
+ bytes = copy_from_user_nmi(buf, (void __user *)to, size);
+ if (bytes != size)
+ return 0;
+
+ kaddr = buf;
+ } else {
+ kaddr = (void *)to;
+ }
+
do {
struct insn insn;
- u8 buf[MAX_INSN_SIZE];
- void *kaddr;
old_to = to;
- if (!kernel_ip(ip)) {
- int bytes, size = MAX_INSN_SIZE;
-
- bytes = copy_from_user_nmi(buf, (void __user *)to, size);
- if (bytes != size)
- return 0;
-
- kaddr = buf;
- } else
- kaddr = (void *)to;
#ifdef CONFIG_X86_64
is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32);
#endif
insn_init(&insn, kaddr, is_64bit);
insn_get_length(&insn);
+
to += insn.length;
+ kaddr += insn.length;
} while (to < ip);
if (to == ip) {
@@ -786,16 +824,34 @@
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;
@@ -854,7 +910,7 @@
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;
@@ -862,9 +918,18 @@
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;
@@ -913,17 +978,34 @@
__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;
@@ -951,61 +1033,6 @@
}
}
-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
*/
@@ -1040,7 +1067,7 @@
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:
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index d5be06a..90ee6c1 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -284,6 +284,7 @@
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;
@@ -306,15 +307,27 @@
}
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)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c8ba627..2e069d1 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -584,6 +584,10 @@
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,
@@ -599,6 +603,7 @@
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,
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 009a655..da48837d 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -136,8 +136,9 @@
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 */
};
/*
@@ -181,6 +182,28 @@
};
/*
+ * 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:
*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 953c143..5bd7fe4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -193,7 +193,7 @@
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;
@@ -1201,6 +1201,9 @@
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;
}
@@ -4572,6 +4575,9 @@
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;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b2f06f3..2a9db91 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1049,6 +1049,7 @@
.maxlen = sizeof(sysctl_perf_event_sample_rate),
.mode = 0644,
.proc_handler = perf_proc_update_handler,
+ .extra1 = &one,
},
{
.procname = "perf_cpu_time_max_percent",
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index ca6cb77..fc15020 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -134,14 +134,14 @@
print_install =
else
Q = @
- print_compile = echo ' CC '$(OBJ);
- print_app_build = echo ' BUILD '$(OBJ);
- print_fpic_compile = echo ' CC FPIC '$(OBJ);
- print_shared_lib_compile = echo ' BUILD SHARED LIB '$(OBJ);
- print_plugin_obj_compile = echo ' CC PLUGIN OBJ '$(OBJ);
- print_plugin_build = echo ' CC PLUGI '$(OBJ);
- print_static_lib_build = echo ' BUILD STATIC LIB '$(OBJ);
- print_install = echo ' INSTALL '$1' to $(DESTDIR_SQ)$2';
+ print_compile = echo ' CC '$(OBJ);
+ print_app_build = echo ' BUILD '$(OBJ);
+ print_fpic_compile = echo ' CC FPIC '$(OBJ);
+ print_shared_lib_compile = echo ' BUILD SHARED LIB '$(OBJ);
+ print_plugin_obj_compile = echo ' BUILD PLUGIN OBJ '$(OBJ);
+ print_plugin_build = echo ' BUILD PLUGIN '$(OBJ);
+ print_static_lib_build = echo ' BUILD STATIC LIB '$(OBJ);
+ print_install = echo ' INSTALL '$1' to $(DESTDIR_SQ)$2';
endif
do_fpic_compile = \
@@ -268,7 +268,7 @@
TRACEEVENT-CFLAGS: force
@FLAGS='$(TRACK_CFLAGS)'; \
if test x"$$FLAGS" != x"`cat TRACEEVENT-CFLAGS 2>/dev/null`" ; then \
- echo 1>&2 " * new build flags or cross compiler"; \
+ echo 1>&2 " FLAGS: * new build flags or cross compiler"; \
echo "$$FLAGS" >TRACEEVENT-CFLAGS; \
fi
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 8f8fbc2..782d86e 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -13,6 +13,7 @@
common-cmds.h
perf.data
perf.data.old
+output.svg
perf-archive
tags
TAGS
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index 5a37a7c..3ba1c0b 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -145,16 +145,17 @@
ifneq ($(findstring $(MAKEFLAGS),s),s)
ifneq ($(V),1)
- QUIET_ASCIIDOC = @echo ' ' ASCIIDOC $@;
- QUIET_XMLTO = @echo ' ' XMLTO $@;
- QUIET_DB2TEXI = @echo ' ' DB2TEXI $@;
- QUIET_MAKEINFO = @echo ' ' MAKEINFO $@;
- QUIET_DBLATEX = @echo ' ' DBLATEX $@;
- QUIET_XSLTPROC = @echo ' ' XSLTPROC $@;
- QUIET_GEN = @echo ' ' GEN $@;
+ QUIET_ASCIIDOC = @echo ' ASCIIDOC '$@;
+ QUIET_XMLTO = @echo ' XMLTO '$@;
+ QUIET_DB2TEXI = @echo ' DB2TEXI '$@;
+ QUIET_MAKEINFO = @echo ' MAKEINFO '$@;
+ QUIET_DBLATEX = @echo ' DBLATEX '$@;
+ QUIET_XSLTPROC = @echo ' XSLTPROC '$@;
+ QUIET_GEN = @echo ' GEN '$@;
QUIET_STDERR = 2> /dev/null
QUIET_SUBDIR0 = +@subdir=
- QUIET_SUBDIR1 = ;$(NO_SUBDIR) echo ' ' SUBDIR $$subdir; \
+ QUIET_SUBDIR1 = ;$(NO_SUBDIR) \
+ echo ' SUBDIR ' $$subdir; \
$(MAKE) $(PRINT_DIR) -C $$subdir
export V
endif
@@ -183,47 +184,43 @@
endif
do-install-man: man
- $(INSTALL) -d -m 755 $(DESTDIR)$(man1dir)
-# $(INSTALL) -d -m 755 $(DESTDIR)$(man5dir)
-# $(INSTALL) -d -m 755 $(DESTDIR)$(man7dir)
- $(INSTALL) -m 644 $(DOC_MAN1) $(DESTDIR)$(man1dir)
-# $(INSTALL) -m 644 $(DOC_MAN5) $(DESTDIR)$(man5dir)
-# $(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir)
+ $(call QUIET_INSTALL, Documentation-man) \
+ $(INSTALL) -d -m 755 $(DESTDIR)$(man1dir); \
+# $(INSTALL) -d -m 755 $(DESTDIR)$(man5dir); \
+# $(INSTALL) -d -m 755 $(DESTDIR)$(man7dir); \
+ $(INSTALL) -m 644 $(DOC_MAN1) $(DESTDIR)$(man1dir); \
+# $(INSTALL) -m 644 $(DOC_MAN5) $(DESTDIR)$(man5dir); \
+# $(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir)
install-man: check-man-tools man
-try-install-man:
ifdef missing_tools
- $(warning Please install $(missing_tools) to have the man pages installed)
+ DO_INSTALL_MAN = $(warning Please install $(missing_tools) to have the man pages installed)
else
- $(MAKE) do-install-man
+ DO_INSTALL_MAN = do-install-man
endif
+try-install-man: $(DO_INSTALL_MAN)
+
install-info: info
- $(INSTALL) -d -m 755 $(DESTDIR)$(infodir)
- $(INSTALL) -m 644 $(OUTPUT)perf.info $(OUTPUT)perfman.info $(DESTDIR)$(infodir)
+ $(call QUIET_INSTALL, Documentation-info) \
+ $(INSTALL) -d -m 755 $(DESTDIR)$(infodir); \
+ $(INSTALL) -m 644 $(OUTPUT)perf.info $(OUTPUT)perfman.info $(DESTDIR)$(infodir); \
if test -r $(DESTDIR)$(infodir)/dir; then \
- $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perf.info ;\
- $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perfman.info ;\
+ $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perf.info ;\
+ $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perfman.info ;\
else \
echo "No directory found in $(DESTDIR)$(infodir)" >&2 ; \
fi
install-pdf: pdf
- $(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir)
- $(INSTALL) -m 644 $(OUTPUT)user-manual.pdf $(DESTDIR)$(pdfdir)
+ $(call QUIET_INSTALL, Documentation-pdf) \
+ $(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir); \
+ $(INSTALL) -m 644 $(OUTPUT)user-manual.pdf $(DESTDIR)$(pdfdir)
#install-html: html
# '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
-ifneq ($(MAKECMDGOALS),clean)
-ifneq ($(MAKECMDGOALS),tags)
-$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
- $(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) $(OUTPUT)PERF-VERSION-FILE
-
--include $(OUTPUT)PERF-VERSION-FILE
-endif
-endif
#
# Determine "include::" file references in asciidoc files.
@@ -253,15 +250,17 @@
$(PERL_PATH) ./cmd-list.perl ../command-list.txt $(QUIET_STDERR) && \
date >$@
+CLEAN_FILES = \
+ $(MAN_XML) $(addsuffix +,$(MAN_XML)) \
+ $(MAN_HTML) $(addsuffix +,$(MAN_HTML)) \
+ $(DOC_HTML) $(DOC_MAN1) $(DOC_MAN5) $(DOC_MAN7) \
+ $(OUTPUT)*.texi $(OUTPUT)*.texi+ $(OUTPUT)*.texi++ \
+ $(OUTPUT)perf.info $(OUTPUT)perfman.info \
+ $(OUTPUT)howto-index.txt $(OUTPUT)howto/*.html $(OUTPUT)doc.dep \
+ $(OUTPUT)technical/api-*.html $(OUTPUT)technical/api-index.txt \
+ $(cmds_txt) $(OUTPUT)*.made
clean:
- $(RM) $(MAN_XML) $(addsuffix +,$(MAN_XML))
- $(RM) $(MAN_HTML) $(addsuffix +,$(MAN_HTML))
- $(RM) $(DOC_HTML) $(DOC_MAN1) $(DOC_MAN5) $(DOC_MAN7)
- $(RM) $(OUTPUT)*.texi $(OUTPUT)*.texi+ $(OUTPUT)*.texi++
- $(RM) $(OUTPUT)perf.info $(OUTPUT)perfman.info
- $(RM) $(OUTPUT)howto-index.txt $(OUTPUT)howto/*.html $(OUTPUT)doc.dep
- $(RM) $(OUTPUT)technical/api-*.html $(OUTPUT)technical/api-index.txt
- $(RM) $(cmds_txt) $(OUTPUT)*.made
+ $(call QUIET_CLEAN, Documentation) $(RM) $(CLEAN_FILES)
$(MAN_HTML): $(OUTPUT)%.html : %.txt
$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
@@ -342,5 +341,3 @@
#quick-install-html:
# '$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(HTML_REF) $(DESTDIR)$(htmldir)
-
-.PHONY: .FORCE-PERF-VERSION-FILE
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index e9a8349..fd77d81 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -21,6 +21,19 @@
-a::
--add=::
Add specified file to the cache.
+-k::
+--kcore::
+ Add specified kcore file to the cache. For the current host that is
+ /proc/kcore which requires root permissions to read. Be aware that
+ running 'perf buildid-cache' as root may update root's build-id cache
+ not the user's. Use the -v option to see where the file is created.
+ Note that the copied file contains only code sections not the whole core
+ image. Note also that files "kallsyms" and "modules" must also be in the
+ same directory and are also copied. All 3 files are created with read
+ permissions for root only. kcore will not be added if there is already a
+ kcore in the cache (with the same build-id) that has the same modules at
+ the same addresses. Use the -v option to see if a copy of kcore is
+ actually made.
-r::
--remove=::
Remove specified file from the cache.
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index ac84db2..6a06cef 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -109,7 +109,9 @@
-m::
--mmap-pages=::
- Number of mmap data pages. Must be a power of two.
+ Number of mmap data pages (must be a power of two) or size
+ specification with appended unit character - B/K/M/G. The
+ size is rounded up to have nearest pages power of two value.
-a::
--all-cpus::
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index c7f5f55..ab25be2 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -48,7 +48,7 @@
-k::
--key=<value>::
Sorting key. Possible values: acquired (default), contended,
- wait_total, wait_max, wait_min.
+ avg_wait, wait_total, wait_max, wait_min.
INFO OPTIONS
------------
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index ca0d3d9..052f7c4 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -87,7 +87,9 @@
-m::
--mmap-pages=::
- Number of mmap data pages. Must be a power of two.
+ Number of mmap data pages (must be a power of two) or size
+ specification with appended unit character - B/K/M/G. The
+ size is rounded up to have nearest pages power of two value.
-g::
Enables call-graph (stack chain/backtrace) recording.
@@ -178,6 +180,9 @@
- 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.
@@ -188,12 +193,14 @@
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]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 2b8097e..10a2798 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -71,7 +71,11 @@
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)
@@ -85,6 +89,8 @@
- 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'.
@@ -135,6 +141,14 @@
Default: fractal,0.5,callee,function.
+--max-stack::
+ Set the stack depth limit when parsing the callchain, anything
+ beyond the specified depth will be ignored. This is a trade-off
+ between information loss and faster processing especially for
+ workloads that can have a very long callchain stack.
+
+ Default: 127
+
-G::
--inverted::
alias for inverted caller based call graph.
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 73c9759..80c7da6 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -137,6 +137,11 @@
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
--------
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index 1632b0e..3ff8bd4 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -8,7 +8,8 @@
SYNOPSIS
--------
[verse]
-'perf timechart' {record}
+'perf timechart' record <command>
+'perf timechart' [<options>]
DESCRIPTION
-----------
@@ -41,6 +42,18 @@
--symfs=<directory>::
Look for files with symbols relative to this directory.
+EXAMPLES
+--------
+
+$ perf timechart record git pull
+
+ [ perf record: Woken up 13 times to write data ]
+ [ perf record: Captured and wrote 4.253 MB perf.data (~185801 samples) ]
+
+$ perf timechart
+
+ Written 10.2 seconds of trace to output.svg.
+
SEE ALSO
--------
linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 6a118e7..7de01dd 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -68,7 +68,9 @@
-m <pages>::
--mmap-pages=<pages>::
- Number of mmapped data pages.
+ Number of mmap data pages (must be a power of two) or size
+ specification with appended unit character - B/K/M/G. The
+ size is rounded up to have nearest pages power of two value.
-p <pid>::
--pid=<pid>::
@@ -112,7 +114,8 @@
-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::
@@ -147,6 +150,14 @@
Setup and enable call-graph (stack chain/backtrace) recording,
implies -G.
+--max-stack::
+ Set the stack depth limit when parsing the callchain, anything
+ beyond the specified depth will be ignored. This is a trade-off
+ between information loss and faster processing especially for
+ workloads that can have a very long callchain stack.
+
+ Default: 127
+
--ignore-callees=<regex>::
Ignore callees of the function(s) matching the given regex.
This has the effect of collecting the callers of each such
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index daccd2c..7b0497f 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -9,6 +9,7 @@
--------
[verse]
'perf trace'
+'perf trace record'
DESCRIPTION
-----------
@@ -16,9 +17,14 @@
syscalls, but other system events like pagefaults, task lifetime events,
scheduling events, etc.
-Initially this is a live mode only tool, but eventually will work with
-perf.data files like the other tools, allowing a detached 'record' from
-analysis phases.
+This is a live mode tool in addition to working with perf.data files like
+the other perf tools. Files can be generated using the 'perf record' command
+but the session needs to include the raw_syscalls events (-e 'raw_syscalls:*').
+Alernatively, the 'perf trace record' can be used as a shortcut to
+automatically include the raw_syscalls events when writing events to a file.
+
+The following options apply to perf trace; options to perf trace record are
+found in the perf record man page.
OPTIONS
-------
@@ -59,7 +65,9 @@
-m::
--mmap-pages=::
- Number of mmap data pages. Must be a power of two.
+ Number of mmap data pages (must be a power of two) or size
+ specification with appended unit character - B/K/M/G. The
+ size is rounded up to have nearest pages power of two value.
-C::
--cpu::
@@ -78,6 +86,21 @@
--input
Process events from a given perf data file.
+-T
+--time
+ Print full timestamp rather time relative to first sample.
+
+--comm::
+ Show process COMM right beside its ID, on by default, disable with --no-comm.
+
+--summary::
+ Show a summary of syscalls by thread with min, max, and average times (in
+ msec) and relative stddev.
+
+--tool_stats::
+ Show tool stats such as number of times fd->pathname was discovered thru
+ hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script[1]
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 64c043b..4835618 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -1,819 +1,79 @@
-include ../scripts/Makefile.include
-
-# The default target of this Makefile is...
-all:
-
-include config/utilities.mak
-
-# Define V to have a more verbose compile.
#
-# Define O to save output files in a separate directory.
+# This is a simple wrapper Makefile that calls the main Makefile.perf
+# with a -j option to do parallel builds
#
-# Define ARCH as name of target architecture if you want cross-builds.
-#
-# Define CROSS_COMPILE as prefix name of compiler if you want cross-builds.
-#
-# Define NO_LIBPERL to disable perl script extension.
-#
-# Define NO_LIBPYTHON to disable python script extension.
-#
-# Define PYTHON to point to the python binary if the default
-# `python' is not correct; for example: PYTHON=python2
-#
-# Define PYTHON_CONFIG to point to the python-config binary if
-# the default `$(PYTHON)-config' is not correct.
-#
-# Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8
-#
-# Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72.
-#
-# Define LDFLAGS=-static to build a static binary.
-#
-# Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds.
-#
-# Define NO_DWARF if you do not want debug-info analysis feature at all.
-#
-# 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 NO_GTK2 if you do not want GTK+ GUI support.
-#
-# Define NO_DEMANGLE if you do not want C++ symbol demangling.
-#
-# Define NO_LIBELF if you do not want libelf dependency (e.g. cross-builds)
-#
-# Define NO_LIBUNWIND if you do not want libunwind dependency for dwarf
-# backtrace post unwind.
-#
-# Define NO_BACKTRACE if you do not want stack backtrace debug feature
-#
-# Define NO_LIBNUMA if you do not want numa perf benchmark
-#
-# Define NO_LIBAUDIT if you do not want libaudit support
-#
-# Define NO_LIBBIONIC if you do not want bionic support
-
-ifeq ($(srctree),)
-srctree := $(patsubst %/,%,$(dir $(shell pwd)))
-srctree := $(patsubst %/,%,$(dir $(srctree)))
-#$(info Determined 'srctree' to be $(srctree))
-endif
-
-ifneq ($(objtree),)
-#$(info Determined 'objtree' to be $(objtree))
-endif
-
-ifneq ($(OUTPUT),)
-#$(info Determined 'OUTPUT' to be $(OUTPUT))
-endif
-
-$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
- @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
-
-CC = $(CROSS_COMPILE)gcc
-AR = $(CROSS_COMPILE)ar
-
-RM = rm -f
-MKDIR = mkdir
-FIND = find
-INSTALL = install
-FLEX = flex
-BISON = bison
-STRIP = strip
-
-LK_DIR = $(srctree)/tools/lib/lk/
-TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
-
-# include config/Makefile by default and rule out
-# non-config cases
-config := 1
-
-NON_CONFIG_TARGETS := clean TAGS tags cscope help
-
-ifdef MAKECMDGOALS
-ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
- config := 0
-endif
-endif
-
-ifeq ($(config),1)
-include config/Makefile
-endif
-
-export prefix bindir sharedir sysconfdir
-
-# sparse is architecture-neutral, which means that we need to tell it
-# explicitly what architecture to check for. Fix this up for yours..
-SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
-
-# Guard against environment variables
-BUILTIN_OBJS =
-LIB_H =
-LIB_OBJS =
-PYRF_OBJS =
-SCRIPT_SH =
-
-SCRIPT_SH += perf-archive.sh
-
-grep-libs = $(filter -l%,$(1))
-strip-libs = $(filter-out -l%,$(1))
-
-ifneq ($(OUTPUT),)
- TE_PATH=$(OUTPUT)
-ifneq ($(subdir),)
- LK_PATH=$(OUTPUT)/../lib/lk/
-else
- LK_PATH=$(OUTPUT)
-endif
-else
- TE_PATH=$(TRACE_EVENT_DIR)
- LK_PATH=$(LK_DIR)
-endif
-
-LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
-export LIBTRACEEVENT
-
-LIBLK = $(LK_PATH)liblk.a
-export LIBLK
-
-# python extension build directories
-PYTHON_EXTBUILD := $(OUTPUT)python_ext_build/
-PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/
-PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/
-export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP
-
-python-clean := rm -rf $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so
-
-PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
-PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBLK)
-
-$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
- $(QUIET_GEN)CFLAGS='$(CFLAGS)' $(PYTHON_WORD) util/setup.py \
- --quiet build_ext; \
- mkdir -p $(OUTPUT)python && \
- cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/
-#
-# No Perl scripts right now:
+# If you want to invoke the perf build in some non-standard way then
+# you can use the 'make -f Makefile.perf' method to invoke it.
#
-SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
+#
+# Clear out the built-in rules GNU make defines by default (such as .o targets),
+# so that we pass through all targets to Makefile.perf:
+#
+.SUFFIXES:
#
-# Single 'perf' binary right now:
+# We don't want to pass along options like -j:
#
-PROGRAMS += $(OUTPUT)perf
+unexport MAKEFLAGS
-# what 'all' will build and 'install' will install, in perfexecdir
-ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
-
-# what 'all' will build but not install in perfexecdir
-OTHER_PROGRAMS = $(OUTPUT)perf
-
-# Set paths to tools early so that they can be used for version tests.
-ifndef SHELL_PATH
- SHELL_PATH = /bin/sh
-endif
-ifndef PERL_PATH
- PERL_PATH = /usr/bin/perl
-endif
-
-export PERL_PATH
-
-$(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
- $(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c
-
-$(OUTPUT)util/parse-events-bison.c: util/parse-events.y
- $(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c -p parse_events_
-
-$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
- $(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/pmu-flex.h -t util/pmu.l > $(OUTPUT)util/pmu-flex.c
-
-$(OUTPUT)util/pmu-bison.c: util/pmu.y
- $(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c -p perf_pmu_
-
-$(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
-$(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
-
-LIB_FILE=$(OUTPUT)libperf.a
-
-LIB_H += ../../include/uapi/linux/perf_event.h
-LIB_H += ../../include/linux/rbtree.h
-LIB_H += ../../include/linux/list.h
-LIB_H += ../../include/uapi/linux/const.h
-LIB_H += ../../include/linux/hash.h
-LIB_H += ../../include/linux/stringify.h
-LIB_H += util/include/linux/bitmap.h
-LIB_H += util/include/linux/bitops.h
-LIB_H += util/include/linux/compiler.h
-LIB_H += util/include/linux/const.h
-LIB_H += util/include/linux/ctype.h
-LIB_H += util/include/linux/kernel.h
-LIB_H += util/include/linux/list.h
-LIB_H += util/include/linux/export.h
-LIB_H += util/include/linux/magic.h
-LIB_H += util/include/linux/poison.h
-LIB_H += util/include/linux/prefetch.h
-LIB_H += util/include/linux/rbtree.h
-LIB_H += util/include/linux/rbtree_augmented.h
-LIB_H += util/include/linux/string.h
-LIB_H += util/include/linux/types.h
-LIB_H += util/include/linux/linkage.h
-LIB_H += util/include/asm/asm-offsets.h
-LIB_H += util/include/asm/bug.h
-LIB_H += util/include/asm/byteorder.h
-LIB_H += util/include/asm/hweight.h
-LIB_H += util/include/asm/swab.h
-LIB_H += util/include/asm/system.h
-LIB_H += util/include/asm/uaccess.h
-LIB_H += util/include/dwarf-regs.h
-LIB_H += util/include/asm/dwarf2.h
-LIB_H += util/include/asm/cpufeature.h
-LIB_H += util/include/asm/unistd_32.h
-LIB_H += util/include/asm/unistd_64.h
-LIB_H += perf.h
-LIB_H += util/annotate.h
-LIB_H += util/cache.h
-LIB_H += util/callchain.h
-LIB_H += util/build-id.h
-LIB_H += util/debug.h
-LIB_H += util/sysfs.h
-LIB_H += util/pmu.h
-LIB_H += util/event.h
-LIB_H += util/evsel.h
-LIB_H += util/evlist.h
-LIB_H += util/exec_cmd.h
-LIB_H += util/types.h
-LIB_H += util/levenshtein.h
-LIB_H += util/machine.h
-LIB_H += util/map.h
-LIB_H += util/parse-options.h
-LIB_H += util/parse-events.h
-LIB_H += util/quote.h
-LIB_H += util/util.h
-LIB_H += util/xyarray.h
-LIB_H += util/header.h
-LIB_H += util/help.h
-LIB_H += util/session.h
-LIB_H += util/strbuf.h
-LIB_H += util/strlist.h
-LIB_H += util/strfilter.h
-LIB_H += util/svghelper.h
-LIB_H += util/tool.h
-LIB_H += util/run-command.h
-LIB_H += util/sigchain.h
-LIB_H += util/dso.h
-LIB_H += util/symbol.h
-LIB_H += util/color.h
-LIB_H += util/values.h
-LIB_H += util/sort.h
-LIB_H += util/hist.h
-LIB_H += util/thread.h
-LIB_H += util/thread_map.h
-LIB_H += util/trace-event.h
-LIB_H += util/probe-finder.h
-LIB_H += util/dwarf-aux.h
-LIB_H += util/probe-event.h
-LIB_H += util/pstack.h
-LIB_H += util/cpumap.h
-LIB_H += util/top.h
-LIB_H += $(ARCH_INCLUDE)
-LIB_H += util/cgroup.h
-LIB_H += $(LIB_INCLUDE)traceevent/event-parse.h
-LIB_H += util/target.h
-LIB_H += util/rblist.h
-LIB_H += util/intlist.h
-LIB_H += util/perf_regs.h
-LIB_H += util/unwind.h
-LIB_H += util/vdso.h
-LIB_H += ui/helpline.h
-LIB_H += ui/progress.h
-LIB_H += ui/util.h
-LIB_H += ui/ui.h
-
-LIB_OBJS += $(OUTPUT)util/abspath.o
-LIB_OBJS += $(OUTPUT)util/alias.o
-LIB_OBJS += $(OUTPUT)util/annotate.o
-LIB_OBJS += $(OUTPUT)util/build-id.o
-LIB_OBJS += $(OUTPUT)util/config.o
-LIB_OBJS += $(OUTPUT)util/ctype.o
-LIB_OBJS += $(OUTPUT)util/sysfs.o
-LIB_OBJS += $(OUTPUT)util/pmu.o
-LIB_OBJS += $(OUTPUT)util/environment.o
-LIB_OBJS += $(OUTPUT)util/event.o
-LIB_OBJS += $(OUTPUT)util/evlist.o
-LIB_OBJS += $(OUTPUT)util/evsel.o
-LIB_OBJS += $(OUTPUT)util/exec_cmd.o
-LIB_OBJS += $(OUTPUT)util/help.o
-LIB_OBJS += $(OUTPUT)util/levenshtein.o
-LIB_OBJS += $(OUTPUT)util/parse-options.o
-LIB_OBJS += $(OUTPUT)util/parse-events.o
-LIB_OBJS += $(OUTPUT)util/path.o
-LIB_OBJS += $(OUTPUT)util/rbtree.o
-LIB_OBJS += $(OUTPUT)util/bitmap.o
-LIB_OBJS += $(OUTPUT)util/hweight.o
-LIB_OBJS += $(OUTPUT)util/run-command.o
-LIB_OBJS += $(OUTPUT)util/quote.o
-LIB_OBJS += $(OUTPUT)util/strbuf.o
-LIB_OBJS += $(OUTPUT)util/string.o
-LIB_OBJS += $(OUTPUT)util/strlist.o
-LIB_OBJS += $(OUTPUT)util/strfilter.o
-LIB_OBJS += $(OUTPUT)util/top.o
-LIB_OBJS += $(OUTPUT)util/usage.o
-LIB_OBJS += $(OUTPUT)util/wrapper.o
-LIB_OBJS += $(OUTPUT)util/sigchain.o
-LIB_OBJS += $(OUTPUT)util/dso.o
-LIB_OBJS += $(OUTPUT)util/symbol.o
-LIB_OBJS += $(OUTPUT)util/symbol-elf.o
-LIB_OBJS += $(OUTPUT)util/color.o
-LIB_OBJS += $(OUTPUT)util/pager.o
-LIB_OBJS += $(OUTPUT)util/header.o
-LIB_OBJS += $(OUTPUT)util/callchain.o
-LIB_OBJS += $(OUTPUT)util/values.o
-LIB_OBJS += $(OUTPUT)util/debug.o
-LIB_OBJS += $(OUTPUT)util/machine.o
-LIB_OBJS += $(OUTPUT)util/map.o
-LIB_OBJS += $(OUTPUT)util/pstack.o
-LIB_OBJS += $(OUTPUT)util/session.o
-LIB_OBJS += $(OUTPUT)util/thread.o
-LIB_OBJS += $(OUTPUT)util/thread_map.o
-LIB_OBJS += $(OUTPUT)util/trace-event-parse.o
-LIB_OBJS += $(OUTPUT)util/parse-events-flex.o
-LIB_OBJS += $(OUTPUT)util/parse-events-bison.o
-LIB_OBJS += $(OUTPUT)util/pmu-flex.o
-LIB_OBJS += $(OUTPUT)util/pmu-bison.o
-LIB_OBJS += $(OUTPUT)util/trace-event-read.o
-LIB_OBJS += $(OUTPUT)util/trace-event-info.o
-LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o
-LIB_OBJS += $(OUTPUT)util/svghelper.o
-LIB_OBJS += $(OUTPUT)util/sort.o
-LIB_OBJS += $(OUTPUT)util/hist.o
-LIB_OBJS += $(OUTPUT)util/probe-event.o
-LIB_OBJS += $(OUTPUT)util/util.o
-LIB_OBJS += $(OUTPUT)util/xyarray.o
-LIB_OBJS += $(OUTPUT)util/cpumap.o
-LIB_OBJS += $(OUTPUT)util/cgroup.o
-LIB_OBJS += $(OUTPUT)util/target.o
-LIB_OBJS += $(OUTPUT)util/rblist.o
-LIB_OBJS += $(OUTPUT)util/intlist.o
-LIB_OBJS += $(OUTPUT)util/vdso.o
-LIB_OBJS += $(OUTPUT)util/stat.o
-LIB_OBJS += $(OUTPUT)util/record.o
-
-LIB_OBJS += $(OUTPUT)ui/setup.o
-LIB_OBJS += $(OUTPUT)ui/helpline.o
-LIB_OBJS += $(OUTPUT)ui/progress.o
-LIB_OBJS += $(OUTPUT)ui/util.o
-LIB_OBJS += $(OUTPUT)ui/hist.o
-LIB_OBJS += $(OUTPUT)ui/stdio/hist.o
-
-LIB_OBJS += $(OUTPUT)arch/common.o
-
-LIB_OBJS += $(OUTPUT)tests/parse-events.o
-LIB_OBJS += $(OUTPUT)tests/dso-data.o
-LIB_OBJS += $(OUTPUT)tests/attr.o
-LIB_OBJS += $(OUTPUT)tests/vmlinux-kallsyms.o
-LIB_OBJS += $(OUTPUT)tests/open-syscall.o
-LIB_OBJS += $(OUTPUT)tests/open-syscall-all-cpus.o
-LIB_OBJS += $(OUTPUT)tests/open-syscall-tp-fields.o
-LIB_OBJS += $(OUTPUT)tests/mmap-basic.o
-LIB_OBJS += $(OUTPUT)tests/perf-record.o
-LIB_OBJS += $(OUTPUT)tests/rdpmc.o
-LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o
-LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o
-LIB_OBJS += $(OUTPUT)tests/pmu.o
-LIB_OBJS += $(OUTPUT)tests/hists_link.o
-LIB_OBJS += $(OUTPUT)tests/python-use.o
-LIB_OBJS += $(OUTPUT)tests/bp_signal.o
-LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o
-LIB_OBJS += $(OUTPUT)tests/task-exit.o
-LIB_OBJS += $(OUTPUT)tests/sw-clock.o
-ifeq ($(ARCH),x86)
-LIB_OBJS += $(OUTPUT)tests/perf-time-to-tsc.o
-endif
-LIB_OBJS += $(OUTPUT)tests/code-reading.o
-LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
-LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o
-
-BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
-BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
-# Benchmark modules
-BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
-BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
-ifeq ($(RAW_ARCH),x86_64)
-BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
-BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o
-endif
-BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
-BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o
-
-BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
-BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o
-BUILTIN_OBJS += $(OUTPUT)builtin-help.o
-BUILTIN_OBJS += $(OUTPUT)builtin-sched.o
-BUILTIN_OBJS += $(OUTPUT)builtin-buildid-list.o
-BUILTIN_OBJS += $(OUTPUT)builtin-buildid-cache.o
-BUILTIN_OBJS += $(OUTPUT)builtin-list.o
-BUILTIN_OBJS += $(OUTPUT)builtin-record.o
-BUILTIN_OBJS += $(OUTPUT)builtin-report.o
-BUILTIN_OBJS += $(OUTPUT)builtin-stat.o
-BUILTIN_OBJS += $(OUTPUT)builtin-timechart.o
-BUILTIN_OBJS += $(OUTPUT)builtin-top.o
-BUILTIN_OBJS += $(OUTPUT)builtin-script.o
-BUILTIN_OBJS += $(OUTPUT)builtin-probe.o
-BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o
-BUILTIN_OBJS += $(OUTPUT)builtin-lock.o
-BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o
-BUILTIN_OBJS += $(OUTPUT)builtin-inject.o
-BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o
-BUILTIN_OBJS += $(OUTPUT)builtin-mem.o
-
-PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT)
-
-# We choose to avoid "if .. else if .. else .. endif endif"
-# because maintaining the nesting to match is a pain. If
-# we had "elif" things would have been much nicer...
-
--include arch/$(ARCH)/Makefile
-
-ifneq ($(OUTPUT),)
- CFLAGS += -I$(OUTPUT)
-endif
-
-ifdef NO_LIBELF
-EXTLIBS := $(filter-out -lelf,$(EXTLIBS))
-
-# Remove ELF/DWARF dependent codes
-LIB_OBJS := $(filter-out $(OUTPUT)util/symbol-elf.o,$(LIB_OBJS))
-LIB_OBJS := $(filter-out $(OUTPUT)util/dwarf-aux.o,$(LIB_OBJS))
-LIB_OBJS := $(filter-out $(OUTPUT)util/probe-event.o,$(LIB_OBJS))
-LIB_OBJS := $(filter-out $(OUTPUT)util/probe-finder.o,$(LIB_OBJS))
-
-BUILTIN_OBJS := $(filter-out $(OUTPUT)builtin-probe.o,$(BUILTIN_OBJS))
-
-# Use minimal symbol handling
-LIB_OBJS += $(OUTPUT)util/symbol-minimal.o
-
-else # NO_LIBELF
-ifndef NO_DWARF
- LIB_OBJS += $(OUTPUT)util/probe-finder.o
- LIB_OBJS += $(OUTPUT)util/dwarf-aux.o
-endif # NO_DWARF
-endif # NO_LIBELF
-
-ifndef NO_LIBUNWIND
- LIB_OBJS += $(OUTPUT)util/unwind.o
-endif
-LIB_OBJS += $(OUTPUT)tests/keep-tracking.o
-
-ifndef NO_LIBAUDIT
- BUILTIN_OBJS += $(OUTPUT)builtin-trace.o
-endif
-
-ifndef NO_SLANG
- LIB_OBJS += $(OUTPUT)ui/browser.o
- LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o
- LIB_OBJS += $(OUTPUT)ui/browsers/hists.o
- LIB_OBJS += $(OUTPUT)ui/browsers/map.o
- LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o
- LIB_OBJS += $(OUTPUT)ui/tui/setup.o
- LIB_OBJS += $(OUTPUT)ui/tui/util.o
- LIB_OBJS += $(OUTPUT)ui/tui/helpline.o
- LIB_OBJS += $(OUTPUT)ui/tui/progress.o
- LIB_H += ui/browser.h
- LIB_H += ui/browsers/map.h
- LIB_H += ui/keysyms.h
- LIB_H += ui/libslang.h
-endif
-
-ifndef NO_GTK2
- LIB_OBJS += $(OUTPUT)ui/gtk/browser.o
- LIB_OBJS += $(OUTPUT)ui/gtk/hists.o
- LIB_OBJS += $(OUTPUT)ui/gtk/setup.o
- LIB_OBJS += $(OUTPUT)ui/gtk/util.o
- LIB_OBJS += $(OUTPUT)ui/gtk/helpline.o
- LIB_OBJS += $(OUTPUT)ui/gtk/progress.o
- LIB_OBJS += $(OUTPUT)ui/gtk/annotate.o
-endif
-
-ifndef NO_LIBPERL
- LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o
- LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o
-endif
-
-ifndef NO_LIBPYTHON
- LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
- LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
-endif
-
-ifeq ($(NO_PERF_REGS),0)
- ifeq ($(ARCH),x86)
- LIB_H += arch/x86/include/perf_regs.h
+#
+# Do a parallel build with multiple jobs, based on the number of CPUs online
+# in this system: 'make -j8' on a 8-CPU system, etc.
+#
+# (To override it, run 'make JOBS=1' and similar.)
+#
+ifeq ($(JOBS),)
+ JOBS := $(shell grep -c ^processor /proc/cpuinfo 2>/dev/null)
+ ifeq ($(JOBS),)
+ JOBS := 1
endif
endif
-ifndef NO_LIBNUMA
- BUILTIN_OBJS += $(OUTPUT)bench/numa.o
+#
+# Only pass canonical directory names as the output directory:
+#
+ifneq ($(O),)
+ FULL_O := $(shell readlink -f $(O) || echo $(O))
endif
-ifdef ASCIIDOC8
- export ASCIIDOC8
+#
+# Only accept the 'DEBUG' variable from the command line:
+#
+ifeq ("$(origin DEBUG)", "command line")
+ ifeq ($(DEBUG),)
+ override DEBUG = 0
+ else
+ SET_DEBUG = "DEBUG=$(DEBUG)"
+ endif
+else
+ override DEBUG = 0
endif
-LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
+define print_msg
+ @printf ' BUILD: Doing '\''make \033[33m-j'$(JOBS)'\033[m'\'' parallel build\n'
+endef
-export INSTALL SHELL_PATH
+define make
+ @$(MAKE) -f Makefile.perf --no-print-directory -j$(JOBS) O=$(FULL_O) $(SET_DEBUG) $@
+endef
-### Build rules
+#
+# Needed if no target specified:
+#
+all:
+ $(print_msg)
+ $(make)
-SHELL = $(SHELL_PATH)
+#
+# The clean target is not really parallel, don't print the jobs info:
+#
+clean:
+ $(make)
-all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
-
-please_set_SHELL_PATH_to_a_more_modern_shell:
- @$$(:)
-
-shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell
-
-strip: $(PROGRAMS) $(OUTPUT)perf
- $(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf
-
-$(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -include $(OUTPUT)PERF-VERSION-FILE \
- '-DPERF_HTML_PATH="$(htmldir_SQ)"' \
- $(CFLAGS) -c $(filter %.c,$^) -o $@
-
-$(OUTPUT)perf: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
- $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OUTPUT)perf.o \
- $(BUILTIN_OBJS) $(LIBS) -o $@
-
-$(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
- '-DPERF_HTML_PATH="$(htmldir_SQ)"' \
- '-DPERF_MAN_PATH="$(mandir_SQ)"' \
- '-DPERF_INFO_PATH="$(infodir_SQ)"' $<
-
-$(OUTPUT)builtin-timechart.o: builtin-timechart.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
- '-DPERF_HTML_PATH="$(htmldir_SQ)"' \
- '-DPERF_MAN_PATH="$(mandir_SQ)"' \
- '-DPERF_INFO_PATH="$(infodir_SQ)"' $<
-
-$(OUTPUT)common-cmds.h: util/generate-cmdlist.sh command-list.txt
-
-$(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
- $(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@
-
-$(SCRIPTS) : % : %.sh
- $(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@'
-
-# These can record PERF_VERSION
-$(OUTPUT)perf.o perf.spec \
- $(SCRIPTS) \
- : $(OUTPUT)PERF-VERSION-FILE
-
-.SUFFIXES:
-.SUFFIXES: .o .c .S .s
-
-# These two need to be here so that when O= is not used they take precedence
-# over the general rule for .o
-
-$(OUTPUT)util/%-flex.o: $(OUTPUT)util/%-flex.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -w $<
-
-$(OUTPUT)util/%-bison.o: $(OUTPUT)util/%-bison.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $<
-
-$(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $<
-$(OUTPUT)%.i: %.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $<
-$(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -S $(CFLAGS) $<
-$(OUTPUT)%.o: %.S
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $<
-$(OUTPUT)%.s: %.S
- $(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $<
-
-$(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
- '-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \
- '-DPREFIX="$(prefix_SQ)"' \
- $<
-
-$(OUTPUT)tests/attr.o: tests/attr.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
- '-DBINDIR="$(bindir_SQ)"' -DPYTHON='"$(PYTHON_WORD)"' \
- $<
-
-$(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
- -DPYTHONPATH='"$(OUTPUT)python"' \
- -DPYTHON='"$(PYTHON_WORD)"' \
- $<
-
-$(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
-
-$(OUTPUT)ui/browser.o: ui/browser.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
-
-$(OUTPUT)ui/browsers/annotate.o: ui/browsers/annotate.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
-
-$(OUTPUT)ui/browsers/hists.o: ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
-
-$(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
-
-$(OUTPUT)ui/browsers/scripts.o: ui/browsers/scripts.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
-
-$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
-
-$(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $<
-
-$(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default $<
-
-$(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs -Wno-undef -Wno-switch-default $<
-
-$(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
-
-$(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
-
-$(OUTPUT)perf-%: %.o $(PERFLIBS)
- $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS)
-
-$(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
-$(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
-
-# we compile into subdirectories. if the target directory is not the source directory, they might not exists. So
-# we depend the various files onto their directories.
-DIRECTORY_DEPS = $(LIB_OBJS) $(BUILTIN_OBJS) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h
-$(DIRECTORY_DEPS): | $(sort $(dir $(DIRECTORY_DEPS)))
-# In the second step, we make a rule to actually create these directories
-$(sort $(dir $(DIRECTORY_DEPS))):
- $(QUIET_MKDIR)$(MKDIR) -p $@ 2>/dev/null
-
-$(LIB_FILE): $(LIB_OBJS)
- $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIB_OBJS)
-
-# libtraceevent.a
-$(LIBTRACEEVENT):
- $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) libtraceevent.a
-
-$(LIBTRACEEVENT)-clean:
- $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) clean
-
-# if subdir is set, we've been called from above so target has been built
-# already
-$(LIBLK):
-ifeq ($(subdir),)
- $(QUIET_SUBDIR0)$(LK_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) liblk.a
-endif
-
-$(LIBLK)-clean:
-ifeq ($(subdir),)
- $(QUIET_SUBDIR0)$(LK_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) clean
-endif
-
-help:
- @echo 'Perf make targets:'
- @echo ' doc - make *all* documentation (see below)'
- @echo ' man - make manpage documentation (access with man <foo>)'
- @echo ' html - make html documentation'
- @echo ' info - make GNU info documentation (access with info <foo>)'
- @echo ' pdf - make pdf documentation'
- @echo ' TAGS - use etags to make tag information for source browsing'
- @echo ' tags - use ctags to make tag information for source browsing'
- @echo ' cscope - use cscope to make interactive browsing database'
- @echo ''
- @echo 'Perf install targets:'
- @echo ' NOTE: documentation build requires asciidoc, xmlto packages to be installed'
- @echo ' HINT: use "make prefix=<path> <install target>" to install to a particular'
- @echo ' path like make prefix=/usr/local install install-doc'
- @echo ' install - install compiled binaries'
- @echo ' install-doc - install *all* documentation'
- @echo ' install-man - install manpage documentation'
- @echo ' install-html - install html documentation'
- @echo ' install-info - install GNU info documentation'
- @echo ' install-pdf - install pdf documentation'
- @echo ''
- @echo ' quick-install-doc - alias for quick-install-man'
- @echo ' quick-install-man - install the documentation quickly'
- @echo ' quick-install-html - install the html documentation quickly'
- @echo ''
- @echo 'Perf maintainer targets:'
- @echo ' clean - clean all binary objects and build output'
-
-
-DOC_TARGETS := doc man html info pdf
-
-INSTALL_DOC_TARGETS := $(patsubst %,install-%,$(DOC_TARGETS)) try-install-man
-INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html
-
-# 'make doc' should call 'make -C Documentation all'
-$(DOC_TARGETS):
- $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all)
-
-TAGS:
- $(RM) TAGS
- $(FIND) . -name '*.[hcS]' -print | xargs etags -a
-
-tags:
- $(RM) tags
- $(FIND) . -name '*.[hcS]' -print | xargs ctags -a
-
-cscope:
- $(RM) cscope*
- $(FIND) . -name '*.[hcS]' -print | xargs cscope -b
-
-### Detect prefix changes
-TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\
- $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ)
-
-$(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS
- @FLAGS='$(TRACK_CFLAGS)'; \
- if test x"$$FLAGS" != x"`cat $(OUTPUT)PERF-CFLAGS 2>/dev/null`" ; then \
- echo 1>&2 " * new build flags or prefix"; \
- echo "$$FLAGS" >$(OUTPUT)PERF-CFLAGS; \
- fi
-
-### Testing rules
-
-# GNU make supports exporting all variables by "export" without parameters.
-# However, the environment gets quite big, and some programs have problems
-# with that.
-
-check: $(OUTPUT)common-cmds.h
- if sparse; \
- then \
- for i in *.c */*.c; \
- do \
- sparse $(CFLAGS) $(SPARSE_FLAGS) $$i || exit; \
- done; \
- else \
- exit 1; \
- fi
-
-### Installation rules
-
-install-bin: all
- $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
- $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'
- $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
- $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
-ifndef NO_LIBPERL
- $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
- $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
- $(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
- $(INSTALL) scripts/perl/*.pl -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'
- $(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
-endif
-ifndef NO_LIBPYTHON
- $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'
- $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
- $(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'
- $(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'
- $(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
-endif
- $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'
- $(INSTALL) bash_completion '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
- $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'
- $(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'
- $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
- $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
-
-install: install-bin try-install-man
-
-install-python_ext:
- $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
-
-# 'make install-doc' should call 'make -C Documentation install'
-$(INSTALL_DOC_TARGETS):
- $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:-doc=)
-
-### Cleaning rules
-
-clean: $(LIBTRACEEVENT)-clean $(LIBLK)-clean
- $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS)
- $(RM) $(ALL_PROGRAMS) perf
- $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
- $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
- $(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS
- $(RM) $(OUTPUT)util/*-bison*
- $(RM) $(OUTPUT)util/*-flex*
- $(python-clean)
-
-.PHONY: all install clean strip $(LIBTRACEEVENT) $(LIBLK)
-.PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
-.PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS
+#
+# All other targets get passed through:
+#
+%:
+ $(print_msg)
+ $(make)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
new file mode 100644
index 0000000..8a9ca38
--- /dev/null
+++ b/tools/perf/Makefile.perf
@@ -0,0 +1,889 @@
+include ../scripts/Makefile.include
+
+# The default target of this Makefile is...
+all:
+
+include config/utilities.mak
+
+# Define V to have a more verbose compile.
+#
+# Define O to save output files in a separate directory.
+#
+# Define ARCH as name of target architecture if you want cross-builds.
+#
+# Define CROSS_COMPILE as prefix name of compiler if you want cross-builds.
+#
+# Define NO_LIBPERL to disable perl script extension.
+#
+# Define NO_LIBPYTHON to disable python script extension.
+#
+# Define PYTHON to point to the python binary if the default
+# `python' is not correct; for example: PYTHON=python2
+#
+# Define PYTHON_CONFIG to point to the python-config binary if
+# the default `$(PYTHON)-config' is not correct.
+#
+# Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8
+#
+# Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72.
+#
+# Define LDFLAGS=-static to build a static binary.
+#
+# Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds.
+#
+# Define NO_DWARF if you do not want debug-info analysis feature at all.
+#
+# 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 NO_GTK2 if you do not want GTK+ GUI support.
+#
+# Define NO_DEMANGLE if you do not want C++ symbol demangling.
+#
+# Define NO_LIBELF if you do not want libelf dependency (e.g. cross-builds)
+#
+# Define NO_LIBUNWIND if you do not want libunwind dependency for dwarf
+# backtrace post unwind.
+#
+# Define NO_BACKTRACE if you do not want stack backtrace debug feature
+#
+# Define NO_LIBNUMA if you do not want numa perf benchmark
+#
+# Define NO_LIBAUDIT if you do not want libaudit support
+#
+# Define NO_LIBBIONIC if you do not want bionic support
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
+ifneq ($(objtree),)
+#$(info Determined 'objtree' to be $(objtree))
+endif
+
+ifneq ($(OUTPUT),)
+#$(info Determined 'OUTPUT' to be $(OUTPUT))
+endif
+
+$(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD
+ @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
+ @touch $(OUTPUT)PERF-VERSION-FILE
+
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
+
+RM = rm -f
+LN = ln -f
+MKDIR = mkdir
+FIND = find
+INSTALL = install
+FLEX = flex
+BISON = bison
+STRIP = strip
+
+LK_DIR = $(srctree)/tools/lib/lk/
+TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
+
+# include config/Makefile by default and rule out
+# non-config cases
+config := 1
+
+NON_CONFIG_TARGETS := clean TAGS tags cscope help
+
+ifdef MAKECMDGOALS
+ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
+ config := 0
+endif
+endif
+
+ifeq ($(config),1)
+include config/Makefile
+endif
+
+export prefix bindir sharedir sysconfdir
+
+# sparse is architecture-neutral, which means that we need to tell it
+# explicitly what architecture to check for. Fix this up for yours..
+SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
+
+# Guard against environment variables
+BUILTIN_OBJS =
+LIB_H =
+LIB_OBJS =
+GTK_OBJS =
+PYRF_OBJS =
+SCRIPT_SH =
+
+SCRIPT_SH += perf-archive.sh
+
+grep-libs = $(filter -l%,$(1))
+strip-libs = $(filter-out -l%,$(1))
+
+ifneq ($(OUTPUT),)
+ TE_PATH=$(OUTPUT)
+ifneq ($(subdir),)
+ LK_PATH=$(OUTPUT)/../lib/lk/
+else
+ LK_PATH=$(OUTPUT)
+endif
+else
+ TE_PATH=$(TRACE_EVENT_DIR)
+ LK_PATH=$(LK_DIR)
+endif
+
+LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
+export LIBTRACEEVENT
+
+LIBLK = $(LK_PATH)liblk.a
+export LIBLK
+
+# python extension build directories
+PYTHON_EXTBUILD := $(OUTPUT)python_ext_build/
+PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/
+PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/
+export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP
+
+python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so
+
+PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
+PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBLK)
+
+$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
+ $(QUIET_GEN)CFLAGS='$(CFLAGS)' $(PYTHON_WORD) util/setup.py \
+ --quiet build_ext; \
+ mkdir -p $(OUTPUT)python && \
+ cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/
+#
+# No Perl scripts right now:
+#
+
+SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
+
+#
+# Single 'perf' binary right now:
+#
+PROGRAMS += $(OUTPUT)perf
+
+# what 'all' will build and 'install' will install, in perfexecdir
+ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
+
+# what 'all' will build but not install in perfexecdir
+OTHER_PROGRAMS = $(OUTPUT)perf
+
+# Set paths to tools early so that they can be used for version tests.
+ifndef SHELL_PATH
+ SHELL_PATH = /bin/sh
+endif
+ifndef PERL_PATH
+ PERL_PATH = /usr/bin/perl
+endif
+
+export PERL_PATH
+
+$(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
+ $(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c
+
+$(OUTPUT)util/parse-events-bison.c: util/parse-events.y
+ $(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c -p parse_events_
+
+$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
+ $(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/pmu-flex.h -t util/pmu.l > $(OUTPUT)util/pmu-flex.c
+
+$(OUTPUT)util/pmu-bison.c: util/pmu.y
+ $(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c -p perf_pmu_
+
+$(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
+$(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
+
+LIB_FILE=$(OUTPUT)libperf.a
+
+LIB_H += ../../include/uapi/linux/perf_event.h
+LIB_H += ../../include/linux/rbtree.h
+LIB_H += ../../include/linux/list.h
+LIB_H += ../../include/uapi/linux/const.h
+LIB_H += ../../include/linux/hash.h
+LIB_H += ../../include/linux/stringify.h
+LIB_H += util/include/linux/bitmap.h
+LIB_H += util/include/linux/bitops.h
+LIB_H += util/include/linux/compiler.h
+LIB_H += util/include/linux/const.h
+LIB_H += util/include/linux/ctype.h
+LIB_H += util/include/linux/kernel.h
+LIB_H += util/include/linux/list.h
+LIB_H += util/include/linux/export.h
+LIB_H += util/include/linux/magic.h
+LIB_H += util/include/linux/poison.h
+LIB_H += util/include/linux/prefetch.h
+LIB_H += util/include/linux/rbtree.h
+LIB_H += util/include/linux/rbtree_augmented.h
+LIB_H += util/include/linux/string.h
+LIB_H += util/include/linux/types.h
+LIB_H += util/include/linux/linkage.h
+LIB_H += util/include/asm/asm-offsets.h
+LIB_H += util/include/asm/bug.h
+LIB_H += util/include/asm/byteorder.h
+LIB_H += util/include/asm/hweight.h
+LIB_H += util/include/asm/swab.h
+LIB_H += util/include/asm/system.h
+LIB_H += util/include/asm/uaccess.h
+LIB_H += util/include/dwarf-regs.h
+LIB_H += util/include/asm/dwarf2.h
+LIB_H += util/include/asm/cpufeature.h
+LIB_H += util/include/asm/unistd_32.h
+LIB_H += util/include/asm/unistd_64.h
+LIB_H += perf.h
+LIB_H += util/annotate.h
+LIB_H += util/cache.h
+LIB_H += util/callchain.h
+LIB_H += util/build-id.h
+LIB_H += util/debug.h
+LIB_H += util/sysfs.h
+LIB_H += util/pmu.h
+LIB_H += util/event.h
+LIB_H += util/evsel.h
+LIB_H += util/evlist.h
+LIB_H += util/exec_cmd.h
+LIB_H += util/types.h
+LIB_H += util/levenshtein.h
+LIB_H += util/machine.h
+LIB_H += util/map.h
+LIB_H += util/parse-options.h
+LIB_H += util/parse-events.h
+LIB_H += util/quote.h
+LIB_H += util/util.h
+LIB_H += util/xyarray.h
+LIB_H += util/header.h
+LIB_H += util/help.h
+LIB_H += util/session.h
+LIB_H += util/strbuf.h
+LIB_H += util/strlist.h
+LIB_H += util/strfilter.h
+LIB_H += util/svghelper.h
+LIB_H += util/tool.h
+LIB_H += util/run-command.h
+LIB_H += util/sigchain.h
+LIB_H += util/dso.h
+LIB_H += util/symbol.h
+LIB_H += util/color.h
+LIB_H += util/values.h
+LIB_H += util/sort.h
+LIB_H += util/hist.h
+LIB_H += util/thread.h
+LIB_H += util/thread_map.h
+LIB_H += util/trace-event.h
+LIB_H += util/probe-finder.h
+LIB_H += util/dwarf-aux.h
+LIB_H += util/probe-event.h
+LIB_H += util/pstack.h
+LIB_H += util/cpumap.h
+LIB_H += util/top.h
+LIB_H += $(ARCH_INCLUDE)
+LIB_H += util/cgroup.h
+LIB_H += $(LIB_INCLUDE)traceevent/event-parse.h
+LIB_H += util/target.h
+LIB_H += util/rblist.h
+LIB_H += util/intlist.h
+LIB_H += util/perf_regs.h
+LIB_H += util/unwind.h
+LIB_H += util/vdso.h
+LIB_H += ui/helpline.h
+LIB_H += ui/progress.h
+LIB_H += ui/util.h
+LIB_H += ui/ui.h
+
+LIB_OBJS += $(OUTPUT)util/abspath.o
+LIB_OBJS += $(OUTPUT)util/alias.o
+LIB_OBJS += $(OUTPUT)util/annotate.o
+LIB_OBJS += $(OUTPUT)util/build-id.o
+LIB_OBJS += $(OUTPUT)util/config.o
+LIB_OBJS += $(OUTPUT)util/ctype.o
+LIB_OBJS += $(OUTPUT)util/sysfs.o
+LIB_OBJS += $(OUTPUT)util/pmu.o
+LIB_OBJS += $(OUTPUT)util/environment.o
+LIB_OBJS += $(OUTPUT)util/event.o
+LIB_OBJS += $(OUTPUT)util/evlist.o
+LIB_OBJS += $(OUTPUT)util/evsel.o
+LIB_OBJS += $(OUTPUT)util/exec_cmd.o
+LIB_OBJS += $(OUTPUT)util/help.o
+LIB_OBJS += $(OUTPUT)util/levenshtein.o
+LIB_OBJS += $(OUTPUT)util/parse-options.o
+LIB_OBJS += $(OUTPUT)util/parse-events.o
+LIB_OBJS += $(OUTPUT)util/path.o
+LIB_OBJS += $(OUTPUT)util/rbtree.o
+LIB_OBJS += $(OUTPUT)util/bitmap.o
+LIB_OBJS += $(OUTPUT)util/hweight.o
+LIB_OBJS += $(OUTPUT)util/run-command.o
+LIB_OBJS += $(OUTPUT)util/quote.o
+LIB_OBJS += $(OUTPUT)util/strbuf.o
+LIB_OBJS += $(OUTPUT)util/string.o
+LIB_OBJS += $(OUTPUT)util/strlist.o
+LIB_OBJS += $(OUTPUT)util/strfilter.o
+LIB_OBJS += $(OUTPUT)util/top.o
+LIB_OBJS += $(OUTPUT)util/usage.o
+LIB_OBJS += $(OUTPUT)util/wrapper.o
+LIB_OBJS += $(OUTPUT)util/sigchain.o
+LIB_OBJS += $(OUTPUT)util/dso.o
+LIB_OBJS += $(OUTPUT)util/symbol.o
+LIB_OBJS += $(OUTPUT)util/symbol-elf.o
+LIB_OBJS += $(OUTPUT)util/color.o
+LIB_OBJS += $(OUTPUT)util/pager.o
+LIB_OBJS += $(OUTPUT)util/header.o
+LIB_OBJS += $(OUTPUT)util/callchain.o
+LIB_OBJS += $(OUTPUT)util/values.o
+LIB_OBJS += $(OUTPUT)util/debug.o
+LIB_OBJS += $(OUTPUT)util/machine.o
+LIB_OBJS += $(OUTPUT)util/map.o
+LIB_OBJS += $(OUTPUT)util/pstack.o
+LIB_OBJS += $(OUTPUT)util/session.o
+LIB_OBJS += $(OUTPUT)util/thread.o
+LIB_OBJS += $(OUTPUT)util/thread_map.o
+LIB_OBJS += $(OUTPUT)util/trace-event-parse.o
+LIB_OBJS += $(OUTPUT)util/parse-events-flex.o
+LIB_OBJS += $(OUTPUT)util/parse-events-bison.o
+LIB_OBJS += $(OUTPUT)util/pmu-flex.o
+LIB_OBJS += $(OUTPUT)util/pmu-bison.o
+LIB_OBJS += $(OUTPUT)util/trace-event-read.o
+LIB_OBJS += $(OUTPUT)util/trace-event-info.o
+LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o
+LIB_OBJS += $(OUTPUT)util/svghelper.o
+LIB_OBJS += $(OUTPUT)util/sort.o
+LIB_OBJS += $(OUTPUT)util/hist.o
+LIB_OBJS += $(OUTPUT)util/probe-event.o
+LIB_OBJS += $(OUTPUT)util/util.o
+LIB_OBJS += $(OUTPUT)util/xyarray.o
+LIB_OBJS += $(OUTPUT)util/cpumap.o
+LIB_OBJS += $(OUTPUT)util/cgroup.o
+LIB_OBJS += $(OUTPUT)util/target.o
+LIB_OBJS += $(OUTPUT)util/rblist.o
+LIB_OBJS += $(OUTPUT)util/intlist.o
+LIB_OBJS += $(OUTPUT)util/vdso.o
+LIB_OBJS += $(OUTPUT)util/stat.o
+LIB_OBJS += $(OUTPUT)util/record.o
+LIB_OBJS += $(OUTPUT)util/srcline.o
+LIB_OBJS += $(OUTPUT)util/data.o
+
+LIB_OBJS += $(OUTPUT)ui/setup.o
+LIB_OBJS += $(OUTPUT)ui/helpline.o
+LIB_OBJS += $(OUTPUT)ui/progress.o
+LIB_OBJS += $(OUTPUT)ui/util.o
+LIB_OBJS += $(OUTPUT)ui/hist.o
+LIB_OBJS += $(OUTPUT)ui/stdio/hist.o
+
+LIB_OBJS += $(OUTPUT)arch/common.o
+
+LIB_OBJS += $(OUTPUT)tests/parse-events.o
+LIB_OBJS += $(OUTPUT)tests/dso-data.o
+LIB_OBJS += $(OUTPUT)tests/attr.o
+LIB_OBJS += $(OUTPUT)tests/vmlinux-kallsyms.o
+LIB_OBJS += $(OUTPUT)tests/open-syscall.o
+LIB_OBJS += $(OUTPUT)tests/open-syscall-all-cpus.o
+LIB_OBJS += $(OUTPUT)tests/open-syscall-tp-fields.o
+LIB_OBJS += $(OUTPUT)tests/mmap-basic.o
+LIB_OBJS += $(OUTPUT)tests/perf-record.o
+LIB_OBJS += $(OUTPUT)tests/rdpmc.o
+LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o
+LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o
+LIB_OBJS += $(OUTPUT)tests/pmu.o
+LIB_OBJS += $(OUTPUT)tests/hists_link.o
+LIB_OBJS += $(OUTPUT)tests/python-use.o
+LIB_OBJS += $(OUTPUT)tests/bp_signal.o
+LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o
+LIB_OBJS += $(OUTPUT)tests/task-exit.o
+LIB_OBJS += $(OUTPUT)tests/sw-clock.o
+ifeq ($(ARCH),x86)
+LIB_OBJS += $(OUTPUT)tests/perf-time-to-tsc.o
+endif
+LIB_OBJS += $(OUTPUT)tests/code-reading.o
+LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
+LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o
+
+BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
+BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
+# Benchmark modules
+BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
+BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
+ifeq ($(RAW_ARCH),x86_64)
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o
+endif
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o
+
+BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
+BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o
+BUILTIN_OBJS += $(OUTPUT)builtin-help.o
+BUILTIN_OBJS += $(OUTPUT)builtin-sched.o
+BUILTIN_OBJS += $(OUTPUT)builtin-buildid-list.o
+BUILTIN_OBJS += $(OUTPUT)builtin-buildid-cache.o
+BUILTIN_OBJS += $(OUTPUT)builtin-list.o
+BUILTIN_OBJS += $(OUTPUT)builtin-record.o
+BUILTIN_OBJS += $(OUTPUT)builtin-report.o
+BUILTIN_OBJS += $(OUTPUT)builtin-stat.o
+BUILTIN_OBJS += $(OUTPUT)builtin-timechart.o
+BUILTIN_OBJS += $(OUTPUT)builtin-top.o
+BUILTIN_OBJS += $(OUTPUT)builtin-script.o
+BUILTIN_OBJS += $(OUTPUT)builtin-probe.o
+BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o
+BUILTIN_OBJS += $(OUTPUT)builtin-lock.o
+BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o
+BUILTIN_OBJS += $(OUTPUT)builtin-inject.o
+BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o
+BUILTIN_OBJS += $(OUTPUT)builtin-mem.o
+
+PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT)
+
+# We choose to avoid "if .. else if .. else .. endif endif"
+# because maintaining the nesting to match is a pain. If
+# we had "elif" things would have been much nicer...
+
+-include arch/$(ARCH)/Makefile
+
+ifneq ($(OUTPUT),)
+ CFLAGS += -I$(OUTPUT)
+endif
+
+ifdef NO_LIBELF
+EXTLIBS := $(filter-out -lelf,$(EXTLIBS))
+
+# Remove ELF/DWARF dependent codes
+LIB_OBJS := $(filter-out $(OUTPUT)util/symbol-elf.o,$(LIB_OBJS))
+LIB_OBJS := $(filter-out $(OUTPUT)util/dwarf-aux.o,$(LIB_OBJS))
+LIB_OBJS := $(filter-out $(OUTPUT)util/probe-event.o,$(LIB_OBJS))
+LIB_OBJS := $(filter-out $(OUTPUT)util/probe-finder.o,$(LIB_OBJS))
+
+BUILTIN_OBJS := $(filter-out $(OUTPUT)builtin-probe.o,$(BUILTIN_OBJS))
+
+# Use minimal symbol handling
+LIB_OBJS += $(OUTPUT)util/symbol-minimal.o
+
+else # NO_LIBELF
+ifndef NO_DWARF
+ LIB_OBJS += $(OUTPUT)util/probe-finder.o
+ LIB_OBJS += $(OUTPUT)util/dwarf-aux.o
+endif # NO_DWARF
+endif # NO_LIBELF
+
+ifndef NO_LIBUNWIND
+ LIB_OBJS += $(OUTPUT)util/unwind.o
+endif
+LIB_OBJS += $(OUTPUT)tests/keep-tracking.o
+
+ifndef NO_LIBAUDIT
+ BUILTIN_OBJS += $(OUTPUT)builtin-trace.o
+endif
+
+ifndef NO_SLANG
+ LIB_OBJS += $(OUTPUT)ui/browser.o
+ LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o
+ LIB_OBJS += $(OUTPUT)ui/browsers/hists.o
+ LIB_OBJS += $(OUTPUT)ui/browsers/map.o
+ LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o
+ LIB_OBJS += $(OUTPUT)ui/tui/setup.o
+ LIB_OBJS += $(OUTPUT)ui/tui/util.o
+ LIB_OBJS += $(OUTPUT)ui/tui/helpline.o
+ LIB_OBJS += $(OUTPUT)ui/tui/progress.o
+ LIB_H += ui/tui/tui.h
+ LIB_H += ui/browser.h
+ LIB_H += ui/browsers/map.h
+ LIB_H += ui/keysyms.h
+ LIB_H += ui/libslang.h
+endif
+
+ifndef NO_GTK2
+ ALL_PROGRAMS += $(OUTPUT)libperf-gtk.so
+
+ GTK_OBJS += $(OUTPUT)ui/gtk/browser.o
+ GTK_OBJS += $(OUTPUT)ui/gtk/hists.o
+ GTK_OBJS += $(OUTPUT)ui/gtk/setup.o
+ GTK_OBJS += $(OUTPUT)ui/gtk/util.o
+ GTK_OBJS += $(OUTPUT)ui/gtk/helpline.o
+ GTK_OBJS += $(OUTPUT)ui/gtk/progress.o
+ GTK_OBJS += $(OUTPUT)ui/gtk/annotate.o
+
+install-gtk: $(OUTPUT)libperf-gtk.so
+ $(call QUIET_INSTALL, 'GTK UI') \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \
+ $(INSTALL) $(OUTPUT)libperf-gtk.so '$(DESTDIR_SQ)$(libdir_SQ)'
+endif
+
+ifndef NO_LIBPERL
+ LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o
+ LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o
+endif
+
+ifndef NO_LIBPYTHON
+ LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
+ LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
+endif
+
+ifeq ($(NO_PERF_REGS),0)
+ ifeq ($(ARCH),x86)
+ LIB_H += arch/x86/include/perf_regs.h
+ endif
+endif
+
+ifndef NO_LIBNUMA
+ BUILTIN_OBJS += $(OUTPUT)bench/numa.o
+endif
+
+ifdef ASCIIDOC8
+ export ASCIIDOC8
+endif
+
+LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
+
+export INSTALL SHELL_PATH
+
+### Build rules
+
+SHELL = $(SHELL_PATH)
+
+all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
+
+please_set_SHELL_PATH_to_a_more_modern_shell:
+ @$$(:)
+
+shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell
+
+strip: $(PROGRAMS) $(OUTPUT)perf
+ $(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf
+
+$(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -include $(OUTPUT)PERF-VERSION-FILE \
+ '-DPERF_HTML_PATH="$(htmldir_SQ)"' \
+ $(CFLAGS) -c $(filter %.c,$^) -o $@
+
+$(OUTPUT)perf: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
+ $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OUTPUT)perf.o \
+ $(BUILTIN_OBJS) $(LIBS) -o $@
+
+$(GTK_OBJS): $(OUTPUT)%.o: %.c $(LIB_H)
+ $(QUIET_CC)$(CC) -o $@ -c -fPIC $(CFLAGS) $(GTK_CFLAGS) $<
+
+$(OUTPUT)libperf-gtk.so: $(GTK_OBJS) $(PERFLIBS)
+ $(QUIET_LINK)$(CC) -o $@ -shared $(ALL_LDFLAGS) $(filter %.o,$^) $(GTK_LIBS)
+
+$(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
+ '-DPERF_HTML_PATH="$(htmldir_SQ)"' \
+ '-DPERF_MAN_PATH="$(mandir_SQ)"' \
+ '-DPERF_INFO_PATH="$(infodir_SQ)"' $<
+
+$(OUTPUT)builtin-timechart.o: builtin-timechart.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
+ '-DPERF_HTML_PATH="$(htmldir_SQ)"' \
+ '-DPERF_MAN_PATH="$(mandir_SQ)"' \
+ '-DPERF_INFO_PATH="$(infodir_SQ)"' $<
+
+$(OUTPUT)common-cmds.h: util/generate-cmdlist.sh command-list.txt
+
+$(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
+ $(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@
+
+$(SCRIPTS) : % : %.sh
+ $(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@'
+
+# These can record PERF_VERSION
+$(OUTPUT)perf.o perf.spec \
+ $(SCRIPTS) \
+ : $(OUTPUT)PERF-VERSION-FILE
+
+.SUFFIXES:
+
+#
+# If a target does not match any of the later rules then prefix it by $(OUTPUT)
+# This makes targets like 'make O=/tmp/perf perf.o' work in a natural way.
+#
+ifneq ($(OUTPUT),)
+%.o: $(OUTPUT)%.o
+ @echo " # Redirected target $@ => $(OUTPUT)$@"
+util/%.o: $(OUTPUT)util/%.o
+ @echo " # Redirected target $@ => $(OUTPUT)$@"
+bench/%.o: $(OUTPUT)bench/%.o
+ @echo " # Redirected target $@ => $(OUTPUT)$@"
+tests/%.o: $(OUTPUT)tests/%.o
+ @echo " # Redirected target $@ => $(OUTPUT)$@"
+endif
+
+# These two need to be here so that when O= is not used they take precedence
+# over the general rule for .o
+
+$(OUTPUT)util/%-flex.o: $(OUTPUT)util/%-flex.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -w $<
+
+$(OUTPUT)util/%-bison.o: $(OUTPUT)util/%-bison.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $<
+
+$(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $<
+$(OUTPUT)%.i: %.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $<
+$(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -S $(CFLAGS) $<
+$(OUTPUT)%.o: %.S
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $<
+$(OUTPUT)%.s: %.S
+ $(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $<
+
+$(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
+ '-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \
+ '-DPREFIX="$(prefix_SQ)"' \
+ $<
+
+$(OUTPUT)tests/attr.o: tests/attr.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
+ '-DBINDIR="$(bindir_SQ)"' -DPYTHON='"$(PYTHON_WORD)"' \
+ $<
+
+$(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
+ -DPYTHONPATH='"$(OUTPUT)python"' \
+ -DPYTHON='"$(PYTHON_WORD)"' \
+ $<
+
+$(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+
+$(OUTPUT)ui/setup.o: ui/setup.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DLIBDIR='"$(libdir_SQ)"' $<
+
+$(OUTPUT)ui/browser.o: ui/browser.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
+
+$(OUTPUT)ui/browsers/annotate.o: ui/browsers/annotate.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
+
+$(OUTPUT)ui/browsers/hists.o: ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
+
+$(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
+
+$(OUTPUT)ui/browsers/scripts.o: ui/browsers/scripts.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
+
+$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+
+$(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $<
+
+$(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default $<
+
+$(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs -Wno-undef -Wno-switch-default $<
+
+$(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
+
+$(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
+
+$(OUTPUT)perf-%: %.o $(PERFLIBS)
+ $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS)
+
+$(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
+$(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
+
+# we compile into subdirectories. if the target directory is not the source directory, they might not exists. So
+# we depend the various files onto their directories.
+DIRECTORY_DEPS = $(LIB_OBJS) $(BUILTIN_OBJS) $(GTK_OBJS)
+DIRECTORY_DEPS += $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h
+$(DIRECTORY_DEPS): | $(sort $(dir $(DIRECTORY_DEPS)))
+# In the second step, we make a rule to actually create these directories
+$(sort $(dir $(DIRECTORY_DEPS))):
+ $(QUIET_MKDIR)$(MKDIR) -p $@ 2>/dev/null
+
+$(LIB_FILE): $(LIB_OBJS)
+ $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIB_OBJS)
+
+# libtraceevent.a
+TE_SOURCES = $(wildcard $(TRACE_EVENT_DIR)*.[ch])
+
+$(LIBTRACEEVENT): $(TE_SOURCES)
+ $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) libtraceevent.a
+
+$(LIBTRACEEVENT)-clean:
+ $(call QUIET_CLEAN, libtraceevent)
+ @$(MAKE) -C $(TRACE_EVENT_DIR) O=$(OUTPUT) clean >/dev/null
+
+LIBLK_SOURCES = $(wildcard $(LK_PATH)*.[ch])
+
+# if subdir is set, we've been called from above so target has been built
+# already
+$(LIBLK): $(LIBLK_SOURCES)
+ifeq ($(subdir),)
+ $(QUIET_SUBDIR0)$(LK_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) liblk.a
+endif
+
+$(LIBLK)-clean:
+ifeq ($(subdir),)
+ $(call QUIET_CLEAN, liblk)
+ @$(MAKE) -C $(LK_DIR) O=$(OUTPUT) clean >/dev/null
+endif
+
+help:
+ @echo 'Perf make targets:'
+ @echo ' doc - make *all* documentation (see below)'
+ @echo ' man - make manpage documentation (access with man <foo>)'
+ @echo ' html - make html documentation'
+ @echo ' info - make GNU info documentation (access with info <foo>)'
+ @echo ' pdf - make pdf documentation'
+ @echo ' TAGS - use etags to make tag information for source browsing'
+ @echo ' tags - use ctags to make tag information for source browsing'
+ @echo ' cscope - use cscope to make interactive browsing database'
+ @echo ''
+ @echo 'Perf install targets:'
+ @echo ' NOTE: documentation build requires asciidoc, xmlto packages to be installed'
+ @echo ' HINT: use "make prefix=<path> <install target>" to install to a particular'
+ @echo ' path like make prefix=/usr/local install install-doc'
+ @echo ' install - install compiled binaries'
+ @echo ' install-doc - install *all* documentation'
+ @echo ' install-man - install manpage documentation'
+ @echo ' install-html - install html documentation'
+ @echo ' install-info - install GNU info documentation'
+ @echo ' install-pdf - install pdf documentation'
+ @echo ''
+ @echo ' quick-install-doc - alias for quick-install-man'
+ @echo ' quick-install-man - install the documentation quickly'
+ @echo ' quick-install-html - install the html documentation quickly'
+ @echo ''
+ @echo 'Perf maintainer targets:'
+ @echo ' clean - clean all binary objects and build output'
+
+
+DOC_TARGETS := doc man html info pdf
+
+INSTALL_DOC_TARGETS := $(patsubst %,install-%,$(DOC_TARGETS)) try-install-man
+INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html
+
+# 'make doc' should call 'make -C Documentation all'
+$(DOC_TARGETS):
+ $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all)
+
+TAGS:
+ $(RM) TAGS
+ $(FIND) . -name '*.[hcS]' -print | xargs etags -a
+
+tags:
+ $(RM) tags
+ $(FIND) . -name '*.[hcS]' -print | xargs ctags -a
+
+cscope:
+ $(RM) cscope*
+ $(FIND) . -name '*.[hcS]' -print | xargs cscope -b
+
+### Detect prefix changes
+TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\
+ $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ)
+
+$(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS
+ @FLAGS='$(TRACK_CFLAGS)'; \
+ if test x"$$FLAGS" != x"`cat $(OUTPUT)PERF-CFLAGS 2>/dev/null`" ; then \
+ echo 1>&2 " FLAGS: * new build flags or prefix"; \
+ echo "$$FLAGS" >$(OUTPUT)PERF-CFLAGS; \
+ fi
+
+### Testing rules
+
+# GNU make supports exporting all variables by "export" without parameters.
+# However, the environment gets quite big, and some programs have problems
+# with that.
+
+check: $(OUTPUT)common-cmds.h
+ if sparse; \
+ then \
+ for i in *.c */*.c; \
+ do \
+ sparse $(CFLAGS) $(SPARSE_FLAGS) $$i || exit; \
+ done; \
+ else \
+ exit 1; \
+ fi
+
+### Installation rules
+
+install-gtk:
+
+install-bin: all install-gtk
+ $(call QUIET_INSTALL, binaries) \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'; \
+ $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'; \
+ $(LN) '$(DESTDIR_SQ)$(bindir_SQ)/perf' '$(DESTDIR_SQ)$(bindir_SQ)/trace'
+ $(call QUIET_INSTALL, libexec) \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+ $(call QUIET_INSTALL, perf-archive) \
+ $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+ifndef NO_LIBPERL
+ $(call QUIET_INSTALL, perl-scripts) \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
+ $(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
+ $(INSTALL) scripts/perl/*.pl -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'; \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'; \
+ $(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
+endif
+ifndef NO_LIBPYTHON
+ $(call QUIET_INSTALL, python-scripts) \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'; \
+ $(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \
+ $(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \
+ $(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
+endif
+ $(call QUIET_INSTALL, bash_completion-script) \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
+ $(INSTALL) bash_completion '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
+ $(call QUIET_INSTALL, tests) \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
+ $(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
+ $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
+
+install: install-bin try-install-man
+
+install-python_ext:
+ $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
+
+# 'make install-doc' should call 'make -C Documentation install'
+$(INSTALL_DOC_TARGETS):
+ $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:-doc=)
+
+### Cleaning rules
+
+#
+# This is here, not in config/Makefile, because config/Makefile does
+# not get included for the clean target:
+#
+config-clean:
+ $(call QUIET_CLEAN, config)
+ @$(MAKE) -C config/feature-checks clean >/dev/null
+
+clean: $(LIBTRACEEVENT)-clean $(LIBLK)-clean config-clean
+ $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
+ $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
+ $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
+ $(call QUIET_CLEAN, Documentation)
+ @$(MAKE) -C Documentation O=$(OUTPUT) clean >/dev/null
+ $(python-clean)
+
+#
+# Trick: if ../../.git does not exist - we are building out of tree for example,
+# then force version regeneration:
+#
+ifeq ($(wildcard ../../.git/HEAD),)
+ GIT-HEAD-PHONY = ../../.git/HEAD
+else
+ GIT-HEAD-PHONY =
+endif
+
+.PHONY: all install clean config-clean strip install-gtk
+.PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
+.PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope .FORCE-PERF-CFLAGS
+
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index 7fcdcdb..e84ca76 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -5,7 +5,7 @@
#include "../../util/types.h"
#include <asm/perf_regs.h>
-#ifndef ARCH_X86_64
+#ifndef HAVE_ARCH_X86_64_SUPPORT
#define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
#else
#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
@@ -52,7 +52,7 @@
return "FS";
case PERF_REG_X86_GS:
return "GS";
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
case PERF_REG_X86_R8:
return "R8";
case PERF_REG_X86_R9:
@@ -69,7 +69,7 @@
return "R14";
case PERF_REG_X86_R15:
return "R15";
-#endif /* ARCH_X86_64 */
+#endif /* HAVE_ARCH_X86_64_SUPPORT */
default:
return NULL;
}
diff --git a/tools/perf/arch/x86/util/unwind.c b/tools/perf/arch/x86/util/unwind.c
index 78d956e..456a88c 100644
--- a/tools/perf/arch/x86/util/unwind.c
+++ b/tools/perf/arch/x86/util/unwind.c
@@ -4,7 +4,7 @@
#include "perf_regs.h"
#include "../../util/unwind.h"
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
int unwind__arch_reg_id(int regnum)
{
int id;
@@ -108,4 +108,4 @@
return id;
}
-#endif /* ARCH_X86_64 */
+#endif /* HAVE_ARCH_X86_64_SUPPORT */
diff --git a/tools/perf/bash_completion b/tools/perf/bash_completion
index 56e6a12..62e157db 100644
--- a/tools/perf/bash_completion
+++ b/tools/perf/bash_completion
@@ -1,17 +1,87 @@
# perf completion
-function_exists()
+# Taken from git.git's completion script.
+__my_reassemble_comp_words_by_ref()
{
- declare -F $1 > /dev/null
- return $?
+ local exclude i j first
+ # Which word separators to exclude?
+ exclude="${1//[^$COMP_WORDBREAKS]}"
+ cword_=$COMP_CWORD
+ if [ -z "$exclude" ]; then
+ words_=("${COMP_WORDS[@]}")
+ return
+ fi
+ # List of word completion separators has shrunk;
+ # re-assemble words to complete.
+ for ((i=0, j=0; i < ${#COMP_WORDS[@]}; i++, j++)); do
+ # Append each nonempty word consisting of just
+ # word separator characters to the current word.
+ first=t
+ while
+ [ $i -gt 0 ] &&
+ [ -n "${COMP_WORDS[$i]}" ] &&
+ # word consists of excluded word separators
+ [ "${COMP_WORDS[$i]//[^$exclude]}" = "${COMP_WORDS[$i]}" ]
+ do
+ # Attach to the previous token,
+ # unless the previous token is the command name.
+ if [ $j -ge 2 ] && [ -n "$first" ]; then
+ ((j--))
+ fi
+ first=
+ words_[$j]=${words_[j]}${COMP_WORDS[i]}
+ if [ $i = $COMP_CWORD ]; then
+ cword_=$j
+ fi
+ if (($i < ${#COMP_WORDS[@]} - 1)); then
+ ((i++))
+ else
+ # Done.
+ return
+ fi
+ done
+ words_[$j]=${words_[j]}${COMP_WORDS[i]}
+ if [ $i = $COMP_CWORD ]; then
+ cword_=$j
+ fi
+ done
}
-function_exists __ltrim_colon_completions ||
+type _get_comp_words_by_ref &>/dev/null ||
+_get_comp_words_by_ref()
+{
+ local exclude cur_ words_ cword_
+ if [ "$1" = "-n" ]; then
+ exclude=$2
+ shift 2
+ fi
+ __my_reassemble_comp_words_by_ref "$exclude"
+ cur_=${words_[cword_]}
+ while [ $# -gt 0 ]; do
+ case "$1" in
+ cur)
+ cur=$cur_
+ ;;
+ prev)
+ prev=${words_[$cword_-1]}
+ ;;
+ words)
+ words=("${words_[@]}")
+ ;;
+ cword)
+ cword=$cword_
+ ;;
+ esac
+ shift
+ done
+}
+
+type __ltrim_colon_completions &>/dev/null ||
__ltrim_colon_completions()
{
if [[ "$1" == *:* && "$COMP_WORDBREAKS" == *:* ]]; then
# Remove colon-word prefix from COMPREPLY items
- local colon_word=${1%${1##*:}}
+ local colon_word=${1%"${1##*:}"}
local i=${#COMPREPLY[*]}
while [[ $((--i)) -ge 0 ]]; do
COMPREPLY[$i]=${COMPREPLY[$i]#"$colon_word"}
@@ -19,23 +89,18 @@
fi
}
-have perf &&
+type perf &>/dev/null &&
_perf()
{
- local cur prev cmd
+ local cur words cword prev cmd
COMPREPLY=()
- if function_exists _get_comp_words_by_ref; then
- _get_comp_words_by_ref -n : cur prev
- else
- cur=$(_get_cword :)
- prev=${COMP_WORDS[COMP_CWORD-1]}
- fi
+ _get_comp_words_by_ref -n =: cur words cword prev
- cmd=${COMP_WORDS[0]}
+ cmd=${words[0]}
# List perf subcommands or long options
- if [ $COMP_CWORD -eq 1 ]; then
+ if [ $cword -eq 1 ]; then
if [[ $cur == --* ]]; then
COMPREPLY=( $( compgen -W '--help --version \
--exec-path --html-path --paginate --no-pager \
@@ -45,18 +110,17 @@
COMPREPLY=( $( compgen -W '$cmds' -- "$cur" ) )
fi
# List possible events for -e option
- elif [[ $prev == "-e" && "${COMP_WORDS[1]}" == @(record|stat|top) ]]; then
+ elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then
evts=$($cmd list --raw-dump)
COMPREPLY=( $( compgen -W '$evts' -- "$cur" ) )
__ltrim_colon_completions $cur
# List long option names
elif [[ $cur == --* ]]; then
- subcmd=${COMP_WORDS[1]}
+ subcmd=${words[1]}
opts=$($cmd $subcmd --list-opts)
COMPREPLY=( $( compgen -W '$opts' -- "$cur" ) )
- # Fall down to list regular files
- else
- _filedir
fi
} &&
-complete -F _perf perf
+
+complete -o bashdefault -o default -o nospace -F _perf perf 2>/dev/null \
+ || complete -o default -o nospace -F _perf perf
diff --git a/tools/perf/bench/mem-memcpy-arch.h b/tools/perf/bench/mem-memcpy-arch.h
index a72e36c..57b4ed8 100644
--- a/tools/perf/bench/mem-memcpy-arch.h
+++ b/tools/perf/bench/mem-memcpy-arch.h
@@ -1,5 +1,5 @@
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
#define MEMCPY_FN(fn, name, desc) \
extern void *fn(void *, const void *, size_t);
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 8cdca43..5ce71d3 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -58,7 +58,7 @@
{ "default",
"Default memcpy() provided by glibc",
memcpy },
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
#define MEMCPY_FN(fn, name, desc) { name, desc, fn },
#include "mem-memcpy-x86-64-asm-def.h"
diff --git a/tools/perf/bench/mem-memset-arch.h b/tools/perf/bench/mem-memset-arch.h
index a040fa7..633800c 100644
--- a/tools/perf/bench/mem-memset-arch.h
+++ b/tools/perf/bench/mem-memset-arch.h
@@ -1,5 +1,5 @@
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
#define MEMSET_FN(fn, name, desc) \
extern void *fn(void *, int, size_t);
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
index 4a2f120..9af79d2 100644
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -58,7 +58,7 @@
{ "default",
"Default memset() provided by glibc",
memset },
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
#define MEMSET_FN(fn, name, desc) { name, desc, fn },
#include "mem-memset-x86-64-asm-def.h"
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 30d1c322..d4c83c6 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -429,14 +429,14 @@
return 0;
}
-static void parse_setup_cpu_list(void)
+static int parse_setup_cpu_list(void)
{
struct thread_data *td;
char *str0, *str;
int t;
if (!g->p.cpu_list_str)
- return;
+ return 0;
dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks);
@@ -500,8 +500,12 @@
dprintf("CPUs: %d_%d-%d#%dx%d\n", bind_cpu_0, bind_len, bind_cpu_1, step, mul);
- BUG_ON(bind_cpu_0 < 0 || bind_cpu_0 >= g->p.nr_cpus);
- BUG_ON(bind_cpu_1 < 0 || bind_cpu_1 >= g->p.nr_cpus);
+ if (bind_cpu_0 >= g->p.nr_cpus || bind_cpu_1 >= g->p.nr_cpus) {
+ printf("\nTest not applicable, system has only %d CPUs.\n", g->p.nr_cpus);
+ return -1;
+ }
+
+ BUG_ON(bind_cpu_0 < 0 || bind_cpu_1 < 0);
BUG_ON(bind_cpu_0 > bind_cpu_1);
for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) {
@@ -541,6 +545,7 @@
printf("# NOTE: %d tasks bound, %d tasks unbound\n", t, g->p.nr_tasks - t);
free(str0);
+ return 0;
}
static int parse_cpus_opt(const struct option *opt __maybe_unused,
@@ -561,14 +566,14 @@
return 0;
}
-static void parse_setup_node_list(void)
+static int parse_setup_node_list(void)
{
struct thread_data *td;
char *str0, *str;
int t;
if (!g->p.node_list_str)
- return;
+ return 0;
dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks);
@@ -619,8 +624,12 @@
dprintf("NODEs: %d-%d #%d\n", bind_node_0, bind_node_1, step);
- BUG_ON(bind_node_0 < 0 || bind_node_0 >= g->p.nr_nodes);
- BUG_ON(bind_node_1 < 0 || bind_node_1 >= g->p.nr_nodes);
+ if (bind_node_0 >= g->p.nr_nodes || bind_node_1 >= g->p.nr_nodes) {
+ printf("\nTest not applicable, system has only %d nodes.\n", g->p.nr_nodes);
+ return -1;
+ }
+
+ BUG_ON(bind_node_0 < 0 || bind_node_1 < 0);
BUG_ON(bind_node_0 > bind_node_1);
for (bind_node = bind_node_0; bind_node <= bind_node_1; bind_node += step) {
@@ -651,6 +660,7 @@
printf("# NOTE: %d tasks mem-bound, %d tasks unbound\n", t, g->p.nr_tasks - t);
free(str0);
+ return 0;
}
static int parse_nodes_opt(const struct option *opt __maybe_unused,
@@ -1110,7 +1120,7 @@
/* Check whether our max runtime timed out: */
if (g->p.nr_secs) {
timersub(&stop, &start0, &diff);
- if (diff.tv_sec >= g->p.nr_secs) {
+ if ((u32)diff.tv_sec >= g->p.nr_secs) {
g->stop_work = true;
break;
}
@@ -1157,7 +1167,7 @@
runtime_ns_max += diff.tv_usec * 1000;
if (details >= 0) {
- printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016lx]\n",
+ printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016"PRIx64"]\n",
process_nr, thread_nr, runtime_ns_max / bytes_done, val);
}
fflush(stdout);
@@ -1356,8 +1366,8 @@
init_thread_data();
tprintf("#\n");
- parse_setup_cpu_list();
- parse_setup_node_list();
+ if (parse_setup_cpu_list() || parse_setup_node_list())
+ return -1;
tprintf("#\n");
print_summary();
@@ -1600,7 +1610,6 @@
return 0;
err:
- usage_with_options(numa_usage, options);
return -1;
}
@@ -1701,8 +1710,7 @@
BUG_ON(ret < 0);
for (i = 0; i < nr; i++) {
- if (run_bench_numa(tests[i][0], tests[i] + 1))
- return -1;
+ run_bench_numa(tests[i][0], tests[i] + 1);
}
printf("\n");
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 69cfba8..07a8d7646a 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -7,9 +7,7 @@
* Based on pipe-test-1m.c by Ingo Molnar <mingo@redhat.com>
* http://people.redhat.com/mingo/cfs-scheduler/tools/pipe-test-1m.c
* Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
- *
*/
-
#include "../perf.h"
#include "../util/util.h"
#include "../util/parse-options.h"
@@ -28,12 +26,24 @@
#include <sys/time.h>
#include <sys/types.h>
+#include <pthread.h>
+
+struct thread_data {
+ int nr;
+ int pipe_read;
+ int pipe_write;
+ pthread_t pthread;
+};
+
#define LOOPS_DEFAULT 1000000
-static int loops = LOOPS_DEFAULT;
+static int loops = LOOPS_DEFAULT;
+
+/* Use processes by default: */
+static bool threaded;
static const struct option options[] = {
- OPT_INTEGER('l', "loop", &loops,
- "Specify number of loops"),
+ OPT_INTEGER('l', "loop", &loops, "Specify number of loops"),
+ OPT_BOOLEAN('T', "threaded", &threaded, "Specify threads/process based task setup"),
OPT_END()
};
@@ -42,13 +52,37 @@
NULL
};
-int bench_sched_pipe(int argc, const char **argv,
- const char *prefix __maybe_unused)
+static void *worker_thread(void *__tdata)
{
- int pipe_1[2], pipe_2[2];
+ struct thread_data *td = __tdata;
int m = 0, i;
+ int ret;
+
+ for (i = 0; i < loops; i++) {
+ if (!td->nr) {
+ ret = read(td->pipe_read, &m, sizeof(int));
+ BUG_ON(ret != sizeof(int));
+ ret = write(td->pipe_write, &m, sizeof(int));
+ BUG_ON(ret != sizeof(int));
+ } else {
+ ret = write(td->pipe_write, &m, sizeof(int));
+ BUG_ON(ret != sizeof(int));
+ ret = read(td->pipe_read, &m, sizeof(int));
+ BUG_ON(ret != sizeof(int));
+ }
+ }
+
+ return NULL;
+}
+
+int bench_sched_pipe(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+ struct thread_data threads[2], *td;
+ int pipe_1[2], pipe_2[2];
struct timeval start, stop, diff;
unsigned long long result_usec = 0;
+ int nr_threads = 2;
+ int t;
/*
* why does "ret" exist?
@@ -58,43 +92,66 @@
int __maybe_unused ret, wait_stat;
pid_t pid, retpid __maybe_unused;
- argc = parse_options(argc, argv, options,
- bench_sched_pipe_usage, 0);
+ argc = parse_options(argc, argv, options, bench_sched_pipe_usage, 0);
BUG_ON(pipe(pipe_1));
BUG_ON(pipe(pipe_2));
- pid = fork();
- assert(pid >= 0);
-
gettimeofday(&start, NULL);
- if (!pid) {
- for (i = 0; i < loops; i++) {
- ret = read(pipe_1[0], &m, sizeof(int));
- ret = write(pipe_2[1], &m, sizeof(int));
+ for (t = 0; t < nr_threads; t++) {
+ td = threads + t;
+
+ td->nr = t;
+
+ if (t == 0) {
+ td->pipe_read = pipe_1[0];
+ td->pipe_write = pipe_2[1];
+ } else {
+ td->pipe_write = pipe_1[1];
+ td->pipe_read = pipe_2[0];
}
+ }
+
+
+ if (threaded) {
+
+ for (t = 0; t < nr_threads; t++) {
+ td = threads + t;
+
+ ret = pthread_create(&td->pthread, NULL, worker_thread, td);
+ BUG_ON(ret);
+ }
+
+ for (t = 0; t < nr_threads; t++) {
+ td = threads + t;
+
+ ret = pthread_join(td->pthread, NULL);
+ BUG_ON(ret);
+ }
+
} else {
- for (i = 0; i < loops; i++) {
- ret = write(pipe_1[1], &m, sizeof(int));
- ret = read(pipe_2[0], &m, sizeof(int));
+ pid = fork();
+ assert(pid >= 0);
+
+ if (!pid) {
+ worker_thread(threads + 0);
+ exit(0);
+ } else {
+ worker_thread(threads + 1);
}
+
+ retpid = waitpid(pid, &wait_stat, 0);
+ assert((retpid == pid) && WIFEXITED(wait_stat));
}
gettimeofday(&stop, NULL);
timersub(&stop, &start, &diff);
- if (pid) {
- retpid = waitpid(pid, &wait_stat, 0);
- assert((retpid == pid) && WIFEXITED(wait_stat));
- } else {
- exit(0);
- }
-
switch (bench_format) {
case BENCH_FORMAT_DEFAULT:
- printf("# Executed %d pipe operations between two tasks\n\n",
- loops);
+ printf("# Executed %d pipe operations between two %s\n\n",
+ loops, threaded ? "threads" : "processes");
result_usec = diff.tv_sec * 1000000;
result_usec += diff.tv_usec;
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 5ebd0c3..6c5ae57 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -28,8 +28,10 @@
#include "util/hist.h"
#include "util/session.h"
#include "util/tool.h"
+#include "util/data.h"
#include "arch/common.h"
+#include <dlfcn.h>
#include <linux/bitmap.h>
struct perf_annotate {
@@ -63,7 +65,7 @@
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;
@@ -116,11 +118,11 @@
ann->print_line, ann->full_paths, 0, 0);
}
-static void hists__find_annotations(struct hists *self,
+static void hists__find_annotations(struct hists *hists,
struct perf_evsel *evsel,
struct perf_annotate *ann)
{
- struct rb_node *nd = rb_first(&self->entries), *next;
+ struct rb_node *nd = rb_first(&hists->entries), *next;
int key = K_RIGHT;
while (nd) {
@@ -142,8 +144,18 @@
if (use_browser == 2) {
int ret;
+ int (*annotate)(struct hist_entry *he,
+ struct perf_evsel *evsel,
+ struct hist_browser_timer *hbt);
- ret = hist_entry__gtk_annotate(he, evsel, NULL);
+ annotate = dlsym(perf_gtk_handle,
+ "hist_entry__gtk_annotate");
+ if (annotate == NULL) {
+ ui__error("GTK browser not found!\n");
+ return;
+ }
+
+ ret = annotate(he, evsel, NULL);
if (!ret || !ann->skip_missing)
return;
@@ -188,9 +200,13 @@
struct perf_session *session;
struct perf_evsel *pos;
u64 total_nr_samples;
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ .force = ann->force,
+ };
- session = perf_session__new(input_name, O_RDONLY,
- ann->force, false, &ann->tool);
+ session = perf_session__new(&file, false, &ann->tool);
if (session == NULL)
return -ENOMEM;
@@ -231,7 +247,7 @@
if (nr_samples > 0) {
total_nr_samples += nr_samples;
- hists__collapse_resort(hists);
+ hists__collapse_resort(hists, NULL);
hists__output_resort(hists);
if (symbol_conf.event_group &&
@@ -243,12 +259,21 @@
}
if (total_nr_samples == 0) {
- ui__error("The %s file has no samples!\n", session->filename);
+ ui__error("The %s file has no samples!\n", file.path);
goto out_delete;
}
- if (use_browser == 2)
- perf_gtk__show_annotations();
+ if (use_browser == 2) {
+ void (*show_annotations)(void);
+
+ show_annotations = dlsym(perf_gtk_handle,
+ "perf_gtk__show_annotations");
+ if (show_annotations == NULL) {
+ ui__error("GTK browser not found!\n");
+ goto out_delete;
+ }
+ show_annotations();
+ }
out_delete:
/*
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 77298bf..e47f90c 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -1,21 +1,18 @@
/*
- *
* builtin-bench.c
*
- * General benchmarking subsystem provided by perf
+ * General benchmarking collections provided by perf
*
* Copyright (C) 2009, Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
- *
*/
/*
+ * Available benchmark collection list:
*
- * Available subsystem list:
- * sched ... scheduler and IPC mechanism
+ * sched ... scheduler and IPC performance
* mem ... memory access performance
- *
+ * numa ... NUMA scheduling and MM performance
*/
-
#include "perf.h"
#include "util/util.h"
#include "util/parse-options.h"
@@ -25,112 +22,92 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+#include <sys/prctl.h>
-struct bench_suite {
- const char *name;
- const char *summary;
- int (*fn)(int, const char **, const char *);
+typedef int (*bench_fn_t)(int argc, const char **argv, const char *prefix);
+
+struct bench {
+ const char *name;
+ const char *summary;
+ bench_fn_t fn;
};
- \
-/* sentinel: easy for help */
-#define suite_all { "all", "Test all benchmark suites", NULL }
-#ifdef LIBNUMA_SUPPORT
-static struct bench_suite numa_suites[] = {
- { "mem",
- "Benchmark for NUMA workloads",
- bench_numa },
- suite_all,
- { NULL,
- NULL,
- NULL }
+#ifdef HAVE_LIBNUMA_SUPPORT
+static struct bench numa_benchmarks[] = {
+ { "mem", "Benchmark for NUMA workloads", bench_numa },
+ { "all", "Test all NUMA benchmarks", NULL },
+ { NULL, NULL, NULL }
};
#endif
-static struct bench_suite sched_suites[] = {
- { "messaging",
- "Benchmark for scheduler and IPC mechanisms",
- bench_sched_messaging },
- { "pipe",
- "Flood of communication over pipe() between two processes",
- bench_sched_pipe },
- suite_all,
- { NULL,
- NULL,
- NULL }
+static struct bench sched_benchmarks[] = {
+ { "messaging", "Benchmark for scheduling and IPC", bench_sched_messaging },
+ { "pipe", "Benchmark for pipe() between two processes", bench_sched_pipe },
+ { "all", "Test all scheduler benchmarks", NULL },
+ { NULL, NULL, NULL }
};
-static struct bench_suite mem_suites[] = {
- { "memcpy",
- "Simple memory copy in various ways",
- bench_mem_memcpy },
- { "memset",
- "Simple memory set in various ways",
- bench_mem_memset },
- suite_all,
- { NULL,
- NULL,
- NULL }
+static struct bench mem_benchmarks[] = {
+ { "memcpy", "Benchmark for memcpy()", bench_mem_memcpy },
+ { "memset", "Benchmark for memset() tests", bench_mem_memset },
+ { "all", "Test all memory benchmarks", NULL },
+ { NULL, NULL, NULL }
};
-struct bench_subsys {
- const char *name;
- const char *summary;
- struct bench_suite *suites;
+struct collection {
+ const char *name;
+ const char *summary;
+ struct bench *benchmarks;
};
-static struct bench_subsys subsystems[] = {
-#ifdef LIBNUMA_SUPPORT
- { "numa",
- "NUMA scheduling and MM behavior",
- numa_suites },
+static struct collection collections[] = {
+ { "sched", "Scheduler and IPC benchmarks", sched_benchmarks },
+ { "mem", "Memory access benchmarks", mem_benchmarks },
+#ifdef HAVE_LIBNUMA_SUPPORT
+ { "numa", "NUMA scheduling and MM benchmarks", numa_benchmarks },
#endif
- { "sched",
- "scheduler and IPC mechanism",
- sched_suites },
- { "mem",
- "memory access performance",
- mem_suites },
- { "all", /* sentinel: easy for help */
- "all benchmark subsystem",
- NULL },
- { NULL,
- NULL,
- NULL }
+ { "all", "All benchmarks", NULL },
+ { NULL, NULL, NULL }
};
-static void dump_suites(int subsys_index)
+/* Iterate over all benchmark collections: */
+#define for_each_collection(coll) \
+ for (coll = collections; coll->name; coll++)
+
+/* Iterate over all benchmarks within a collection: */
+#define for_each_bench(coll, bench) \
+ for (bench = coll->benchmarks; bench->name; bench++)
+
+static void dump_benchmarks(struct collection *coll)
{
- int i;
+ struct bench *bench;
- printf("# List of available suites for %s...\n\n",
- subsystems[subsys_index].name);
+ printf("\n # List of available benchmarks for collection '%s':\n\n", coll->name);
- for (i = 0; subsystems[subsys_index].suites[i].name; i++)
- printf("%14s: %s\n",
- subsystems[subsys_index].suites[i].name,
- subsystems[subsys_index].suites[i].summary);
+ for_each_bench(coll, bench)
+ printf("%14s: %s\n", bench->name, bench->summary);
printf("\n");
- return;
}
static const char *bench_format_str;
+
+/* Output/formatting style, exported to benchmark modules: */
int bench_format = BENCH_FORMAT_DEFAULT;
static const struct option bench_options[] = {
- OPT_STRING('f', "format", &bench_format_str, "default",
- "Specify format style"),
+ OPT_STRING('f', "format", &bench_format_str, "default", "Specify format style"),
OPT_END()
};
static const char * const bench_usage[] = {
- "perf bench [<common options>] <subsystem> <suite> [<options>]",
+ "perf bench [<common options>] <collection> <benchmark> [<options>]",
NULL
};
static void print_usage(void)
{
+ struct collection *coll;
int i;
printf("Usage: \n");
@@ -138,11 +115,10 @@
printf("\t%s\n", bench_usage[i]);
printf("\n");
- printf("# List of available subsystems...\n\n");
+ printf(" # List of all available benchmark collections:\n\n");
- for (i = 0; subsystems[i].name; i++)
- printf("%14s: %s\n",
- subsystems[i].name, subsystems[i].summary);
+ for_each_collection(coll)
+ printf("%14s: %s\n", coll->name, coll->summary);
printf("\n");
}
@@ -159,44 +135,74 @@
return BENCH_FORMAT_UNKNOWN;
}
-static void all_suite(struct bench_subsys *subsys) /* FROM HERE */
+/*
+ * Run a specific benchmark but first rename the running task's ->comm[]
+ * to something meaningful:
+ */
+static int run_bench(const char *coll_name, const char *bench_name, bench_fn_t fn,
+ int argc, const char **argv, const char *prefix)
{
- int i;
+ int size;
+ char *name;
+ int ret;
+
+ size = strlen(coll_name) + 1 + strlen(bench_name) + 1;
+
+ name = zalloc(size);
+ BUG_ON(!name);
+
+ scnprintf(name, size, "%s-%s", coll_name, bench_name);
+
+ prctl(PR_SET_NAME, name);
+ argv[0] = name;
+
+ ret = fn(argc, argv, prefix);
+
+ free(name);
+
+ return ret;
+}
+
+static void run_collection(struct collection *coll)
+{
+ struct bench *bench;
const char *argv[2];
- struct bench_suite *suites = subsys->suites;
argv[1] = NULL;
/*
* TODO:
- * preparing preset parameters for
+ *
+ * Preparing preset parameters for
* embedded, ordinary PC, HPC, etc...
- * will be helpful
+ * would be helpful.
*/
- for (i = 0; suites[i].fn; i++) {
- printf("# Running %s/%s benchmark...\n",
- subsys->name,
- suites[i].name);
+ for_each_bench(coll, bench) {
+ if (!bench->fn)
+ break;
+ printf("# Running %s/%s benchmark...\n", coll->name, bench->name);
fflush(stdout);
- argv[1] = suites[i].name;
- suites[i].fn(1, argv, NULL);
+ argv[1] = bench->name;
+ run_bench(coll->name, bench->name, bench->fn, 1, argv, NULL);
printf("\n");
}
}
-static void all_subsystem(void)
+static void run_all_collections(void)
{
- int i;
- for (i = 0; subsystems[i].suites; i++)
- all_suite(&subsystems[i]);
+ struct collection *coll;
+
+ for_each_collection(coll)
+ run_collection(coll);
}
int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused)
{
- int i, j, status = 0;
+ struct collection *coll;
+ int ret = 0;
if (argc < 2) {
- /* No subsystem specified. */
+ /* No collection specified. */
print_usage();
goto end;
}
@@ -206,7 +212,7 @@
bench_format = bench_str2int(bench_format_str);
if (bench_format == BENCH_FORMAT_UNKNOWN) {
- printf("Unknown format descriptor:%s\n", bench_format_str);
+ printf("Unknown format descriptor: '%s'\n", bench_format_str);
goto end;
}
@@ -216,52 +222,51 @@
}
if (!strcmp(argv[0], "all")) {
- all_subsystem();
+ run_all_collections();
goto end;
}
- for (i = 0; subsystems[i].name; i++) {
- if (strcmp(subsystems[i].name, argv[0]))
+ for_each_collection(coll) {
+ struct bench *bench;
+
+ if (strcmp(coll->name, argv[0]))
continue;
if (argc < 2) {
- /* No suite specified. */
- dump_suites(i);
+ /* No bench specified. */
+ dump_benchmarks(coll);
goto end;
}
if (!strcmp(argv[1], "all")) {
- all_suite(&subsystems[i]);
+ run_collection(coll);
goto end;
}
- for (j = 0; subsystems[i].suites[j].name; j++) {
- if (strcmp(subsystems[i].suites[j].name, argv[1]))
+ for_each_bench(coll, bench) {
+ if (strcmp(bench->name, argv[1]))
continue;
if (bench_format == BENCH_FORMAT_DEFAULT)
- printf("# Running %s/%s benchmark...\n",
- subsystems[i].name,
- subsystems[i].suites[j].name);
+ printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name);
fflush(stdout);
- status = subsystems[i].suites[j].fn(argc - 1,
- argv + 1, prefix);
+ ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1, prefix);
goto end;
}
if (!strcmp(argv[1], "-h") || !strcmp(argv[1], "--help")) {
- dump_suites(i);
+ dump_benchmarks(coll);
goto end;
}
- printf("Unknown suite:%s for %s\n", argv[1], argv[0]);
- status = 1;
+ printf("Unknown benchmark: '%s' for collection '%s'\n", argv[1], argv[0]);
+ ret = 1;
goto end;
}
- printf("Unknown subsystem:%s\n", argv[0]);
- status = 1;
+ printf("Unknown collection: '%s'\n", argv[0]);
+ ret = 1;
end:
- return status;
+ return ret;
}
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index c96c8fa..cfede86 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -6,6 +6,11 @@
* Copyright (C) 2010, Red Hat Inc.
* Copyright (C) 2010, Arnaldo Carvalho de Melo <acme@redhat.com>
*/
+#include <sys/types.h>
+#include <sys/time.h>
+#include <time.h>
+#include <dirent.h>
+#include <unistd.h>
#include "builtin.h"
#include "perf.h"
#include "util/cache.h"
@@ -17,6 +22,140 @@
#include "util/session.h"
#include "util/symbol.h"
+static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid)
+{
+ char root_dir[PATH_MAX];
+ char notes[PATH_MAX];
+ u8 build_id[BUILD_ID_SIZE];
+ char *p;
+
+ strlcpy(root_dir, proc_dir, sizeof(root_dir));
+
+ p = strrchr(root_dir, '/');
+ if (!p)
+ return -1;
+ *p = '\0';
+
+ scnprintf(notes, sizeof(notes), "%s/sys/kernel/notes", root_dir);
+
+ if (sysfs__read_build_id(notes, build_id, sizeof(build_id)))
+ return -1;
+
+ build_id__sprintf(build_id, sizeof(build_id), sbuildid);
+
+ return 0;
+}
+
+static int build_id_cache__kcore_dir(char *dir, size_t sz)
+{
+ struct timeval tv;
+ struct tm tm;
+ char dt[32];
+
+ if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm))
+ return -1;
+
+ if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm))
+ return -1;
+
+ scnprintf(dir, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000);
+
+ return 0;
+}
+
+static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir,
+ size_t to_dir_sz)
+{
+ char from[PATH_MAX];
+ char to[PATH_MAX];
+ struct dirent *dent;
+ int ret = -1;
+ DIR *d;
+
+ d = opendir(to_dir);
+ if (!d)
+ return -1;
+
+ scnprintf(from, sizeof(from), "%s/modules", from_dir);
+
+ while (1) {
+ dent = readdir(d);
+ if (!dent)
+ break;
+ if (dent->d_type != DT_DIR)
+ continue;
+ scnprintf(to, sizeof(to), "%s/%s/modules", to_dir,
+ dent->d_name);
+ if (!compare_proc_modules(from, to)) {
+ scnprintf(to, sizeof(to), "%s/%s", to_dir,
+ dent->d_name);
+ strlcpy(to_dir, to, to_dir_sz);
+ ret = 0;
+ break;
+ }
+ }
+
+ closedir(d);
+
+ return ret;
+}
+
+static int build_id_cache__add_kcore(const char *filename, const char *debugdir)
+{
+ char dir[32], sbuildid[BUILD_ID_SIZE * 2 + 1];
+ char from_dir[PATH_MAX], to_dir[PATH_MAX];
+ char *p;
+
+ strlcpy(from_dir, filename, sizeof(from_dir));
+
+ p = strrchr(from_dir, '/');
+ if (!p || strcmp(p + 1, "kcore"))
+ return -1;
+ *p = '\0';
+
+ if (build_id_cache__kcore_buildid(from_dir, sbuildid))
+ return -1;
+
+ scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s",
+ debugdir, sbuildid);
+
+ if (!build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) {
+ pr_debug("same kcore found in %s\n", to_dir);
+ return 0;
+ }
+
+ if (build_id_cache__kcore_dir(dir, sizeof(dir)))
+ return -1;
+
+ scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s/%s",
+ debugdir, sbuildid, dir);
+
+ if (mkdir_p(to_dir, 0755))
+ return -1;
+
+ if (kcore_copy(from_dir, to_dir)) {
+ /* Remove YYYYmmddHHMMSShh directory */
+ if (!rmdir(to_dir)) {
+ p = strrchr(to_dir, '/');
+ if (p)
+ *p = '\0';
+ /* Try to remove buildid directory */
+ if (!rmdir(to_dir)) {
+ p = strrchr(to_dir, '/');
+ if (p)
+ *p = '\0';
+ /* Try to remove [kernel.kcore] directory */
+ rmdir(to_dir);
+ }
+ }
+ return -1;
+ }
+
+ pr_debug("kcore added to build-id cache directory %s\n", to_dir);
+
+ return 0;
+}
+
static int build_id_cache__add_file(const char *filename, const char *debugdir)
{
char sbuild_id[BUILD_ID_SIZE * 2 + 1];
@@ -82,8 +221,12 @@
static int build_id_cache__fprintf_missing(const char *filename, bool force, FILE *fp)
{
- struct perf_session *session = perf_session__new(filename, O_RDONLY,
- force, false, NULL);
+ struct perf_data_file file = {
+ .path = filename,
+ .mode = PERF_DATA_MODE_READ,
+ .force = force,
+ };
+ struct perf_session *session = perf_session__new(&file, false, NULL);
if (session == NULL)
return -1;
@@ -130,11 +273,14 @@
char const *add_name_list_str = NULL,
*remove_name_list_str = NULL,
*missing_filename = NULL,
- *update_name_list_str = NULL;
+ *update_name_list_str = NULL,
+ *kcore_filename;
const struct option buildid_cache_options[] = {
OPT_STRING('a', "add", &add_name_list_str,
"file list", "file(s) to add"),
+ OPT_STRING('k', "kcore", &kcore_filename,
+ "file", "kcore file to add"),
OPT_STRING('r', "remove", &remove_name_list_str, "file list",
"file(s) to remove"),
OPT_STRING('M', "missing", &missing_filename, "file",
@@ -217,5 +363,9 @@
}
}
+ if (kcore_filename &&
+ build_id_cache__add_kcore(kcore_filename, debugdir))
+ pr_warning("Couldn't add %s\n", kcore_filename);
+
return ret;
}
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index e74366a..ed3873b 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -15,6 +15,7 @@
#include "util/parse-options.h"
#include "util/session.h"
#include "util/symbol.h"
+#include "util/data.h"
static int sysfs__fprintf_build_id(FILE *fp)
{
@@ -52,6 +53,11 @@
static int perf_session__list_build_ids(bool force, bool with_hits)
{
struct perf_session *session;
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ .force = force,
+ };
symbol__elf_init();
/*
@@ -60,15 +66,14 @@
if (filename__fprintf_build_id(input_name, stdout))
goto out;
- session = perf_session__new(input_name, O_RDONLY, force, false,
- &build_id__mark_dso_hit_ops);
+ session = perf_session__new(&file, false, &build_id__mark_dso_hit_ops);
if (session == NULL)
return -1;
/*
* in pipe-mode, the only way to get the buildids is to parse
* the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
*/
- if (with_hits || session->fd_pipe)
+ if (with_hits || perf_data_file__is_pipe(&file))
perf_session__process_events(session, &build_id__mark_dso_hit_ops);
perf_session__fprintf_dsos_buildid(session, stdout, dso__skip_buildid, with_hits);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index f28799e..b605009 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -16,6 +16,7 @@
#include "util/sort.h"
#include "util/symbol.h"
#include "util/util.h"
+#include "util/data.h"
#include <stdlib.h>
#include <math.h>
@@ -42,7 +43,7 @@
struct data__file {
struct perf_session *session;
- const char *file;
+ struct perf_data_file file;
int idx;
struct hists *hists;
struct diff_hpp_fmt fmt[PERF_HPP_DIFF__MAX_INDEX];
@@ -302,11 +303,11 @@
return -1;
}
-static int hists__add_entry(struct hists *self,
+static int hists__add_entry(struct hists *hists,
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(hists, al, NULL, period, weight, transaction) != NULL)
return 0;
return -ENOMEM;
}
@@ -328,7 +329,8 @@
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;
}
@@ -367,7 +369,7 @@
list_for_each_entry(evsel, &evlist->entries, node) {
struct hists *hists = &evsel->hists;
- hists__collapse_resort(hists);
+ hists__collapse_resort(hists, NULL);
}
}
@@ -599,7 +601,7 @@
data__for_each_file(i, d)
fprintf(stdout, "# [%d] %s %s\n",
- d->idx, d->file,
+ d->idx, d->file.path,
!d->idx ? "(Baseline)" : "");
fprintf(stdout, "#\n");
@@ -661,17 +663,16 @@
int ret = -EINVAL, i;
data__for_each_file(i, d) {
- d->session = perf_session__new(d->file, O_RDONLY, force,
- false, &tool);
+ d->session = perf_session__new(&d->file, false, &tool);
if (!d->session) {
- pr_err("Failed to open %s\n", d->file);
+ pr_err("Failed to open %s\n", d->file.path);
ret = -ENOMEM;
goto out_delete;
}
ret = perf_session__process_events(d->session, &tool);
if (ret) {
- pr_err("Failed to process %s\n", d->file);
+ pr_err("Failed to process %s\n", d->file.path);
goto out_delete;
}
@@ -1014,7 +1015,12 @@
return -ENOMEM;
data__for_each_file(i, d) {
- d->file = use_default ? defaults[i] : argv[i];
+ struct perf_data_file *file = &d->file;
+
+ file->path = use_default ? defaults[i] : argv[i];
+ file->mode = PERF_DATA_MODE_READ,
+ file->force = force,
+
d->idx = i;
}
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index 05bd9df..20b0f12 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -14,13 +14,18 @@
#include "util/parse-events.h"
#include "util/parse-options.h"
#include "util/session.h"
+#include "util/data.h"
static int __cmd_evlist(const char *file_name, struct perf_attr_details *details)
{
struct perf_session *session;
struct perf_evsel *pos;
+ struct perf_data_file file = {
+ .path = file_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
- session = perf_session__new(file_name, O_RDONLY, 0, false, NULL);
+ session = perf_session__new(&file, 0, NULL);
if (session == NULL)
return -ENOMEM;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index afe377b..409ceaf 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -15,6 +15,7 @@
#include "util/tool.h"
#include "util/debug.h"
#include "util/build-id.h"
+#include "util/data.h"
#include "util/parse-options.h"
@@ -71,12 +72,17 @@
union perf_event *event,
struct perf_evlist **pevlist)
{
+ struct perf_inject *inject = container_of(tool, struct perf_inject,
+ tool);
int ret;
ret = perf_event__process_attr(tool, event, pevlist);
if (ret)
return ret;
+ if (!inject->pipe_output)
+ return 0;
+
return perf_event__repipe_synth(tool, event);
}
@@ -161,38 +167,38 @@
return err;
}
-static int dso__read_build_id(struct dso *self)
+static int dso__read_build_id(struct dso *dso)
{
- if (self->has_build_id)
+ if (dso->has_build_id)
return 0;
- if (filename__read_build_id(self->long_name, self->build_id,
- sizeof(self->build_id)) > 0) {
- self->has_build_id = true;
+ if (filename__read_build_id(dso->long_name, dso->build_id,
+ sizeof(dso->build_id)) > 0) {
+ dso->has_build_id = true;
return 0;
}
return -1;
}
-static int dso__inject_build_id(struct dso *self, struct perf_tool *tool,
+static int dso__inject_build_id(struct dso *dso, struct perf_tool *tool,
struct machine *machine)
{
u16 misc = PERF_RECORD_MISC_USER;
int err;
- if (dso__read_build_id(self) < 0) {
- pr_debug("no build_id found for %s\n", self->long_name);
+ if (dso__read_build_id(dso) < 0) {
+ pr_debug("no build_id found for %s\n", dso->long_name);
return -1;
}
- if (self->kernel)
+ if (dso->kernel)
misc = PERF_RECORD_MISC_KERNEL;
- err = perf_event__synthesize_build_id(tool, self, misc, perf_event__repipe,
+ err = perf_event__synthesize_build_id(tool, dso, misc, perf_event__repipe,
machine);
if (err) {
- pr_err("Can't synthesize build_id event for %s\n", self->long_name);
+ pr_err("Can't synthesize build_id event for %s\n", dso->long_name);
return -1;
}
@@ -231,7 +237,7 @@
* account this as unresolved.
*/
} else {
-#ifdef LIBELF_SUPPORT
+#ifdef HAVE_LIBELF_SUPPORT
pr_warning("no symbols found in %s, maybe "
"install a debug package?\n",
al.map->dso->long_name);
@@ -345,6 +351,10 @@
{
struct perf_session *session;
int ret = -EINVAL;
+ struct perf_data_file file = {
+ .path = inject->input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
signal(SIGINT, sig_handler);
@@ -355,7 +365,7 @@
inject->tool.tracing_data = perf_event__repipe_tracing_data;
}
- session = perf_session__new(inject->input_name, O_RDONLY, false, true, &inject->tool);
+ session = perf_session__new(&file, true, &inject->tool);
if (session == NULL)
return -ENOMEM;
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 9b5f077..1126382 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -13,6 +13,7 @@
#include "util/parse-options.h"
#include "util/trace-event.h"
+#include "util/data.h"
#include "util/debug.h"
@@ -486,8 +487,12 @@
{ "kmem:kfree", perf_evsel__process_free_event, },
{ "kmem:kmem_cache_free", perf_evsel__process_free_event, },
};
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
- session = perf_session__new(input_name, O_RDONLY, 0, false, &perf_kmem);
+ session = perf_session__new(&file, false, &perf_kmem);
if (session == NULL)
return -ENOMEM;
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index fbc2888..cb05f39 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -17,6 +17,7 @@
#include "util/tool.h"
#include "util/stat.h"
#include "util/top.h"
+#include "util/data.h"
#include <sys/prctl.h>
#include <sys/timerfd.h>
@@ -1222,10 +1223,13 @@
.comm = perf_event__process_comm,
.ordered_samples = true,
};
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
kvm->tool = eops;
- kvm->session = perf_session__new(kvm->file_name, O_RDONLY, 0, false,
- &kvm->tool);
+ kvm->session = perf_session__new(&file, false, &kvm->tool);
if (!kvm->session) {
pr_err("Initializing perf session failed\n");
return -EINVAL;
@@ -1433,8 +1437,9 @@
const struct option live_options[] = {
OPT_STRING('p', "pid", &kvm->opts.target.pid, "pid",
"record events on existing process id"),
- OPT_UINTEGER('m', "mmap-pages", &kvm->opts.mmap_pages,
- "number of mmap data pages"),
+ OPT_CALLBACK('m', "mmap-pages", &kvm->opts.mmap_pages, "pages",
+ "number of mmap data pages",
+ perf_evlist__parse_mmap_pages),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
OPT_BOOLEAN('a', "all-cpus", &kvm->opts.target.system_wide,
@@ -1456,6 +1461,9 @@
"perf kvm stat live [<options>]",
NULL
};
+ struct perf_data_file file = {
+ .mode = PERF_DATA_MODE_WRITE,
+ };
/* event handling */
@@ -1520,7 +1528,7 @@
/*
* perf session
*/
- kvm->session = perf_session__new(NULL, O_WRONLY, false, false, &kvm->tool);
+ kvm->session = perf_session__new(&file, false, &kvm->tool);
if (kvm->session == NULL) {
err = -ENOMEM;
goto out;
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index ee33ba2..33c7253 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -15,6 +15,7 @@
#include "util/debug.h"
#include "util/session.h"
#include "util/tool.h"
+#include "util/data.h"
#include <sys/types.h>
#include <sys/prctl.h>
@@ -56,7 +57,9 @@
unsigned int nr_readlock;
unsigned int nr_trylock;
+
/* these times are in nano sec. */
+ u64 avg_wait_time;
u64 wait_time_total;
u64 wait_time_min;
u64 wait_time_max;
@@ -208,6 +211,7 @@
SINGLE_KEY(nr_acquired)
SINGLE_KEY(nr_contended)
+SINGLE_KEY(avg_wait_time)
SINGLE_KEY(wait_time_total)
SINGLE_KEY(wait_time_max)
@@ -244,6 +248,7 @@
struct lock_key keys[] = {
DEF_KEY_LOCK(acquired, nr_acquired),
DEF_KEY_LOCK(contended, nr_contended),
+ DEF_KEY_LOCK(avg_wait, avg_wait_time),
DEF_KEY_LOCK(wait_total, wait_time_total),
DEF_KEY_LOCK(wait_min, wait_time_min),
DEF_KEY_LOCK(wait_max, wait_time_max),
@@ -321,10 +326,12 @@
new->addr = addr;
new->name = zalloc(sizeof(char) * strlen(name) + 1);
- if (!new->name)
+ if (!new->name) {
+ free(new);
goto alloc_failed;
- strcpy(new->name, name);
+ }
+ strcpy(new->name, name);
new->wait_time_min = ULLONG_MAX;
list_add(&new->hash_entry, entry);
@@ -400,17 +407,17 @@
ls = lock_stat_findnew(addr, name);
if (!ls)
- return -1;
+ return -ENOMEM;
if (ls->discard)
return 0;
ts = thread_stat_findnew(sample->tid);
if (!ts)
- return -1;
+ return -ENOMEM;
seq = get_seq(ts, addr);
if (!seq)
- return -1;
+ return -ENOMEM;
switch (seq->state) {
case SEQ_STATE_UNINITIALIZED:
@@ -446,7 +453,6 @@
list_del(&seq->list);
free(seq);
goto end;
- break;
default:
BUG_ON("Unknown state of lock sequence found!\n");
break;
@@ -473,17 +479,17 @@
ls = lock_stat_findnew(addr, name);
if (!ls)
- return -1;
+ return -ENOMEM;
if (ls->discard)
return 0;
ts = thread_stat_findnew(sample->tid);
if (!ts)
- return -1;
+ return -ENOMEM;
seq = get_seq(ts, addr);
if (!seq)
- return -1;
+ return -ENOMEM;
switch (seq->state) {
case SEQ_STATE_UNINITIALIZED:
@@ -508,8 +514,6 @@
list_del(&seq->list);
free(seq);
goto end;
- break;
-
default:
BUG_ON("Unknown state of lock sequence found!\n");
break;
@@ -517,6 +521,7 @@
seq->state = SEQ_STATE_ACQUIRED;
ls->nr_acquired++;
+ ls->avg_wait_time = ls->nr_contended ? ls->wait_time_total/ls->nr_contended : 0;
seq->prev_event_time = sample->time;
end:
return 0;
@@ -536,17 +541,17 @@
ls = lock_stat_findnew(addr, name);
if (!ls)
- return -1;
+ return -ENOMEM;
if (ls->discard)
return 0;
ts = thread_stat_findnew(sample->tid);
if (!ts)
- return -1;
+ return -ENOMEM;
seq = get_seq(ts, addr);
if (!seq)
- return -1;
+ return -ENOMEM;
switch (seq->state) {
case SEQ_STATE_UNINITIALIZED:
@@ -564,7 +569,6 @@
list_del(&seq->list);
free(seq);
goto end;
- break;
default:
BUG_ON("Unknown state of lock sequence found!\n");
break;
@@ -572,6 +576,7 @@
seq->state = SEQ_STATE_CONTENDED;
ls->nr_contended++;
+ ls->avg_wait_time = ls->wait_time_total/ls->nr_contended;
seq->prev_event_time = sample->time;
end:
return 0;
@@ -591,22 +596,21 @@
ls = lock_stat_findnew(addr, name);
if (!ls)
- return -1;
+ return -ENOMEM;
if (ls->discard)
return 0;
ts = thread_stat_findnew(sample->tid);
if (!ts)
- return -1;
+ return -ENOMEM;
seq = get_seq(ts, addr);
if (!seq)
- return -1;
+ return -ENOMEM;
switch (seq->state) {
case SEQ_STATE_UNINITIALIZED:
goto end;
- break;
case SEQ_STATE_ACQUIRED:
break;
case SEQ_STATE_READ_ACQUIRED:
@@ -624,7 +628,6 @@
ls->discard = 1;
bad_hist[BROKEN_RELEASE]++;
goto free_seq;
- break;
default:
BUG_ON("Unknown state of lock sequence found!\n");
break;
@@ -690,7 +693,7 @@
pr_info("\n=== output for debug===\n\n");
pr_info("bad: %d, total: %d\n", bad, total);
- pr_info("bad rate: %f %%\n", (double)bad / (double)total * 100);
+ pr_info("bad rate: %.2f %%\n", (double)bad / (double)total * 100);
pr_info("histogram of events caused bad sequence\n");
for (i = 0; i < BROKEN_MAX; i++)
pr_info(" %10s: %d\n", name[i], bad_hist[i]);
@@ -707,6 +710,7 @@
pr_info("%10s ", "acquired");
pr_info("%10s ", "contended");
+ pr_info("%15s ", "avg wait (ns)");
pr_info("%15s ", "total wait (ns)");
pr_info("%15s ", "max wait (ns)");
pr_info("%15s ", "min wait (ns)");
@@ -738,6 +742,7 @@
pr_info("%10u ", st->nr_acquired);
pr_info("%10u ", st->nr_contended);
+ pr_info("%15" PRIu64 " ", st->avg_wait_time);
pr_info("%15" PRIu64 " ", st->wait_time_total);
pr_info("%15" PRIu64 " ", st->wait_time_max);
pr_info("%15" PRIu64 " ", st->wait_time_min == ULLONG_MAX ?
@@ -822,34 +827,6 @@
return 0;
}
-static const struct perf_evsel_str_handler lock_tracepoints[] = {
- { "lock:lock_acquire", perf_evsel__process_lock_acquire, }, /* CONFIG_LOCKDEP */
- { "lock:lock_acquired", perf_evsel__process_lock_acquired, }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
- { "lock:lock_contended", perf_evsel__process_lock_contended, }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
- { "lock:lock_release", perf_evsel__process_lock_release, }, /* CONFIG_LOCKDEP */
-};
-
-static int read_events(void)
-{
- struct perf_tool eops = {
- .sample = process_sample_event,
- .comm = perf_event__process_comm,
- .ordered_samples = true,
- };
- session = perf_session__new(input_name, O_RDONLY, 0, false, &eops);
- if (!session) {
- pr_err("Initializing perf session failed\n");
- return -1;
- }
-
- if (perf_session__set_tracepoints_handlers(session, lock_tracepoints)) {
- pr_err("Initializing perf session tracepoint handlers failed\n");
- return -1;
- }
-
- return perf_session__process_events(session, &eops);
-}
-
static void sort_result(void)
{
unsigned int i;
@@ -862,18 +839,58 @@
}
}
-static int __cmd_report(void)
+static const struct perf_evsel_str_handler lock_tracepoints[] = {
+ { "lock:lock_acquire", perf_evsel__process_lock_acquire, }, /* CONFIG_LOCKDEP */
+ { "lock:lock_acquired", perf_evsel__process_lock_acquired, }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
+ { "lock:lock_contended", perf_evsel__process_lock_contended, }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
+ { "lock:lock_release", perf_evsel__process_lock_release, }, /* CONFIG_LOCKDEP */
+};
+
+static int __cmd_report(bool display_info)
{
+ int err = -EINVAL;
+ struct perf_tool eops = {
+ .sample = process_sample_event,
+ .comm = perf_event__process_comm,
+ .ordered_samples = true,
+ };
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
+
+ session = perf_session__new(&file, false, &eops);
+ if (!session) {
+ pr_err("Initializing perf session failed\n");
+ return -ENOMEM;
+ }
+
+ if (!perf_session__has_traces(session, "lock record"))
+ goto out_delete;
+
+ if (perf_session__set_tracepoints_handlers(session, lock_tracepoints)) {
+ pr_err("Initializing perf session tracepoint handlers failed\n");
+ goto out_delete;
+ }
+
+ if (select_key())
+ goto out_delete;
+
+ err = perf_session__process_events(session, &eops);
+ if (err)
+ goto out_delete;
+
setup_pager();
+ if (display_info) /* used for info subcommand */
+ err = dump_info();
+ else {
+ sort_result();
+ print_result();
+ }
- if ((select_key() != 0) ||
- (read_events() != 0))
- return -1;
-
- sort_result();
- print_result();
-
- return 0;
+out_delete:
+ perf_session__delete(session);
+ return err;
}
static int __cmd_record(int argc, const char **argv)
@@ -881,7 +898,7 @@
const char *record_args[] = {
"record", "-R", "-m", "1024", "-c", "1",
};
- unsigned int rec_argc, i, j;
+ unsigned int rec_argc, i, j, ret;
const char **rec_argv;
for (i = 0; i < ARRAY_SIZE(lock_tracepoints); i++) {
@@ -898,7 +915,7 @@
rec_argc += 2 * ARRAY_SIZE(lock_tracepoints);
rec_argv = calloc(rec_argc + 1, sizeof(char *));
- if (rec_argv == NULL)
+ if (!rec_argv)
return -ENOMEM;
for (i = 0; i < ARRAY_SIZE(record_args); i++)
@@ -914,7 +931,9 @@
BUG_ON(i != rec_argc);
- return cmd_record(i, rec_argv, NULL);
+ ret = cmd_record(i, rec_argv, NULL);
+ free(rec_argv);
+ return ret;
}
int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
@@ -934,7 +953,7 @@
};
const struct option report_options[] = {
OPT_STRING('k', "key", &sort_key, "acquired",
- "key for sorting (acquired / contended / wait_total / wait_max / wait_min)"),
+ "key for sorting (acquired / contended / avg_wait / wait_total / wait_max / wait_min)"),
/* TODO: type */
OPT_END()
};
@@ -972,7 +991,7 @@
if (argc)
usage_with_options(report_usage, report_options);
}
- __cmd_report();
+ rc = __cmd_report(false);
} else if (!strcmp(argv[0], "script")) {
/* Aliased to 'perf script' */
return cmd_script(argc, argv, prefix);
@@ -985,11 +1004,7 @@
}
/* recycling report_lock_ops */
trace_handler = &report_lock_ops;
- setup_pager();
- if (read_events() != 0)
- rc = -1;
- else
- rc = dump_info();
+ rc = __cmd_report(true);
} else {
usage_with_options(lock_usage, lock_options);
}
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 253133a..31c00f1 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -5,6 +5,7 @@
#include "util/trace-event.h"
#include "util/tool.h"
#include "util/session.h"
+#include "util/data.h"
#define MEM_OPERATION_LOAD "load"
#define MEM_OPERATION_STORE "store"
@@ -119,10 +120,14 @@
static int report_raw_events(struct perf_mem *mem)
{
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
int err = -EINVAL;
int ret;
- struct perf_session *session = perf_session__new(input_name, O_RDONLY,
- 0, false, &mem->tool);
+ struct perf_session *session = perf_session__new(&file, false,
+ &mem->tool);
if (session == NULL)
return -ENOMEM;
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index e8a66f9..89acc17 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -173,7 +173,7 @@
if (str && !params.target) {
if (!strcmp(opt->long_name, "exec"))
params.uprobes = true;
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
else if (!strcmp(opt->long_name, "module"))
params.uprobes = false;
#endif
@@ -187,7 +187,7 @@
return ret;
}
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
static int opt_show_lines(const struct option *opt __maybe_unused,
const char *str, int unset __maybe_unused)
{
@@ -257,7 +257,7 @@
"perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
"perf probe [<options>] --del '[GROUP:]EVENT' ...",
"perf probe --list",
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
"perf probe [<options>] --line 'LINEDESC'",
"perf probe [<options>] --vars 'PROBEPOINT'",
#endif
@@ -271,7 +271,7 @@
OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.",
opt_del_probe_event),
OPT_CALLBACK('a', "add", NULL,
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
"[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT"
" [[NAME=]ARG ...]",
#else
@@ -283,7 +283,7 @@
"\t\tFUNC:\tFunction name\n"
"\t\tOFF:\tOffset from function entry (in byte)\n"
"\t\t%return:\tPut the probe at function return\n"
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
"\t\tSRC:\tSource code path\n"
"\t\tRL:\tRelative line number from function entry.\n"
"\t\tAL:\tAbsolute line number in file.\n"
@@ -296,7 +296,7 @@
opt_add_probe_event),
OPT_BOOLEAN('f', "force", ¶ms.force_add, "forcibly add events"
" with existing name"),
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
OPT_CALLBACK('L', "line", NULL,
"FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]",
"Show source code lines.", opt_show_lines),
@@ -408,7 +408,7 @@
return ret;
}
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
if (params.show_lines && !params.uprobes) {
if (params.mod_events) {
pr_err(" Error: Don't use --line with"
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index d046514..8b45fce 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -24,12 +24,13 @@
#include "util/symbol.h"
#include "util/cpumap.h"
#include "util/thread_map.h"
+#include "util/data.h"
#include <unistd.h>
#include <sched.h>
#include <sys/mman.h>
-#ifndef HAVE_ON_EXIT
+#ifndef HAVE_ON_EXIT_SUPPORT
#ifndef ATEXIT_MAX
#define ATEXIT_MAX 32
#endif
@@ -65,12 +66,10 @@
struct perf_tool tool;
struct perf_record_opts opts;
u64 bytes_written;
- const char *output_name;
+ struct perf_data_file file;
struct perf_evlist *evlist;
struct perf_session *session;
const char *progname;
- int output;
- unsigned int page_size;
int realtime_prio;
bool no_buildid;
bool no_buildid_cache;
@@ -85,11 +84,13 @@
static int write_output(struct perf_record *rec, void *buf, size_t size)
{
+ struct perf_data_file *file = &rec->file;
+
while (size) {
- int ret = write(rec->output, buf, size);
+ int ret = write(file->fd, buf, size);
if (ret < 0) {
- pr_err("failed to write\n");
+ pr_err("failed to write perf data, error: %m\n");
return -1;
}
@@ -119,7 +120,7 @@
{
unsigned int head = perf_mmap__read_head(md);
unsigned int old = md->prev;
- unsigned char *data = md->base + rec->page_size;
+ unsigned char *data = md->base + page_size;
unsigned long size;
void *buf;
int rc = 0;
@@ -234,10 +235,6 @@
"or try again with a smaller value of -m/--mmap_pages.\n"
"(current value: %d)\n", opts->mmap_pages);
rc = -errno;
- } else if (!is_power_of_2(opts->mmap_pages) &&
- (opts->mmap_pages != UINT_MAX)) {
- pr_err("--mmap_pages/-m value must be a power of two.");
- rc = -EINVAL;
} else {
pr_err("failed to mmap with %d (%s)\n", errno, strerror(errno));
rc = -errno;
@@ -253,13 +250,14 @@
static int process_buildids(struct perf_record *rec)
{
- u64 size = lseek(rec->output, 0, SEEK_CUR);
+ struct perf_data_file *file = &rec->file;
+ struct perf_session *session = rec->session;
+ u64 size = lseek(file->fd, 0, SEEK_CUR);
if (size == 0)
return 0;
- rec->session->fd = rec->output;
- return __perf_session__process_events(rec->session, rec->post_processing_offset,
+ return __perf_session__process_events(session, rec->post_processing_offset,
size - rec->post_processing_offset,
size, &build_id__mark_dso_hit_ops);
}
@@ -267,17 +265,18 @@
static void perf_record__exit(int status, void *arg)
{
struct perf_record *rec = arg;
+ struct perf_data_file *file = &rec->file;
if (status != 0)
return;
- if (!rec->opts.pipe_output) {
+ if (!file->is_pipe) {
rec->session->header.data_size += rec->bytes_written;
if (!rec->no_buildid)
process_buildids(rec);
perf_session__write_header(rec->session, rec->evlist,
- rec->output, true);
+ file->fd, true);
perf_session__delete(rec->session);
perf_evlist__delete(rec->evlist);
symbol__exit();
@@ -345,62 +344,26 @@
static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
{
- struct stat st;
- int flags;
- int err, output, feat;
+ int err, feat;
unsigned long waking = 0;
const bool forks = argc > 0;
struct machine *machine;
struct perf_tool *tool = &rec->tool;
struct perf_record_opts *opts = &rec->opts;
struct perf_evlist *evsel_list = rec->evlist;
- const char *output_name = rec->output_name;
+ struct perf_data_file *file = &rec->file;
struct perf_session *session;
bool disabled = false;
rec->progname = argv[0];
- rec->page_size = sysconf(_SC_PAGE_SIZE);
-
on_exit(perf_record__sig_exit, rec);
signal(SIGCHLD, sig_handler);
signal(SIGINT, sig_handler);
signal(SIGUSR1, sig_handler);
signal(SIGTERM, sig_handler);
- if (!output_name) {
- if (!fstat(STDOUT_FILENO, &st) && S_ISFIFO(st.st_mode))
- opts->pipe_output = true;
- else
- rec->output_name = output_name = "perf.data";
- }
- if (output_name) {
- if (!strcmp(output_name, "-"))
- opts->pipe_output = true;
- else if (!stat(output_name, &st) && st.st_size) {
- char oldname[PATH_MAX];
- snprintf(oldname, sizeof(oldname), "%s.old",
- output_name);
- unlink(oldname);
- rename(output_name, oldname);
- }
- }
-
- flags = O_CREAT|O_RDWR|O_TRUNC;
-
- if (opts->pipe_output)
- output = STDOUT_FILENO;
- else
- output = open(output_name, flags, S_IRUSR | S_IWUSR);
- if (output < 0) {
- perror("failed to create output file");
- return -1;
- }
-
- rec->output = output;
-
- session = perf_session__new(output_name, O_WRONLY,
- true, false, NULL);
+ session = perf_session__new(file, false, NULL);
if (session == NULL) {
pr_err("Not enough memory for reading perf file header\n");
return -1;
@@ -422,7 +385,7 @@
if (forks) {
err = perf_evlist__prepare_workload(evsel_list, &opts->target,
- argv, opts->pipe_output,
+ argv, file->is_pipe,
true);
if (err < 0) {
pr_err("Couldn't run the workload!\n");
@@ -443,13 +406,13 @@
*/
on_exit(perf_record__exit, rec);
- if (opts->pipe_output) {
- err = perf_header__write_pipe(output);
+ if (file->is_pipe) {
+ err = perf_header__write_pipe(file->fd);
if (err < 0)
goto out_delete_session;
} else {
err = perf_session__write_header(session, evsel_list,
- output, false);
+ file->fd, false);
if (err < 0)
goto out_delete_session;
}
@@ -462,11 +425,11 @@
goto out_delete_session;
}
- rec->post_processing_offset = lseek(output, 0, SEEK_CUR);
+ rec->post_processing_offset = lseek(file->fd, 0, SEEK_CUR);
machine = &session->machines.host;
- if (opts->pipe_output) {
+ if (file->is_pipe) {
err = perf_event__synthesize_attrs(tool, session,
process_synthesized_event);
if (err < 0) {
@@ -483,7 +446,7 @@
* return this more properly and also
* propagate errors that now are calling die()
*/
- err = perf_event__synthesize_tracing_data(tool, output, evsel_list,
+ err = perf_event__synthesize_tracing_data(tool, file->fd, evsel_list,
process_synthesized_event);
if (err <= 0) {
pr_err("Couldn't record tracing data.\n");
@@ -590,7 +553,7 @@
fprintf(stderr,
"[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n",
(double)rec->bytes_written / 1024.0 / 1024.0,
- output_name,
+ file->path,
rec->bytes_written / 24);
return 0;
@@ -618,6 +581,9 @@
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
};
@@ -684,7 +650,7 @@
return ret;
}
-#ifdef LIBUNWIND_SUPPORT
+#ifdef HAVE_LIBUNWIND_SUPPORT
static int get_stack_size(char *str, unsigned long *_size)
{
char *endptr;
@@ -710,7 +676,7 @@
max_size, str);
return -1;
}
-#endif /* LIBUNWIND_SUPPORT */
+#endif /* HAVE_LIBUNWIND_SUPPORT */
int record_parse_callchain(const char *arg, struct perf_record_opts *opts)
{
@@ -739,7 +705,7 @@
"needed for -g fp\n");
break;
-#ifdef LIBUNWIND_SUPPORT
+#ifdef HAVE_LIBUNWIND_SUPPORT
/* Dwarf style */
} else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
const unsigned long default_stack_dump_size = 8192;
@@ -755,7 +721,7 @@
ret = get_stack_size(tok, &size);
opts->stack_dump_size = size;
}
-#endif /* LIBUNWIND_SUPPORT */
+#endif /* HAVE_LIBUNWIND_SUPPORT */
} else {
pr_err("callchain: Unknown --call-graph option "
"value: %s\n", arg);
@@ -841,7 +807,7 @@
#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: "
-#ifdef LIBUNWIND_SUPPORT
+#ifdef HAVE_LIBUNWIND_SUPPORT
const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf";
#else
const char record_callchain_help[] = CALLCHAIN_HELP "fp";
@@ -875,13 +841,14 @@
OPT_STRING('C', "cpu", &record.opts.target.cpu_list, "cpu",
"list of cpus to monitor"),
OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
- OPT_STRING('o', "output", &record.output_name, "file",
+ OPT_STRING('o', "output", &record.file.path, "file",
"output file name"),
OPT_BOOLEAN('i', "no-inherit", &record.opts.no_inherit,
"child tasks do not inherit counters"),
OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
- OPT_UINTEGER('m', "mmap-pages", &record.opts.mmap_pages,
- "number of mmap data pages"),
+ OPT_CALLBACK('m', "mmap-pages", &record.opts.mmap_pages, "pages",
+ "number of mmap data pages",
+ perf_evlist__parse_mmap_pages),
OPT_BOOLEAN(0, "group", &record.opts.group,
"put the counters into a counter group"),
OPT_CALLBACK_NOOPT('g', NULL, &record.opts,
@@ -920,6 +887,8 @@
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()
};
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 72eae74..98d38913 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -33,8 +33,10 @@
#include "util/thread.h"
#include "util/sort.h"
#include "util/hist.h"
+#include "util/data.h"
#include "arch/common.h"
+#include <dlfcn.h>
#include <linux/bitmap.h>
struct perf_report {
@@ -47,6 +49,7 @@
bool show_threads;
bool inverted_callchain;
bool mem_mode;
+ int max_stack;
struct perf_read_values show_threads_values;
const char *pretty_printing_style;
const char *cpu_list;
@@ -88,7 +91,8 @@
if ((sort__has_parent || symbol_conf.use_callchain) &&
sample->callchain) {
err = machine__resolve_callchain(machine, evsel, al->thread,
- sample, &parent, al);
+ sample, &parent, al,
+ rep->max_stack);
if (err)
return err;
}
@@ -179,7 +183,8 @@
if ((sort__has_parent || symbol_conf.use_callchain)
&& sample->callchain) {
err = machine__resolve_callchain(machine, evsel, al->thread,
- sample, &parent, al);
+ sample, &parent, al,
+ rep->max_stack);
if (err)
return err;
}
@@ -242,24 +247,27 @@
return err;
}
-static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
+static int perf_evsel__add_hist_entry(struct perf_tool *tool,
+ struct perf_evsel *evsel,
struct addr_location *al,
struct perf_sample *sample,
struct machine *machine)
{
+ struct perf_report *rep = container_of(tool, struct perf_report, tool);
struct symbol *parent = NULL;
int err = 0;
struct hist_entry *he;
if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
err = machine__resolve_callchain(machine, evsel, al->thread,
- sample, &parent, al);
+ sample, &parent, al,
+ rep->max_stack);
if (err)
return err;
}
he = __hists__add_entry(&evsel->hists, al, parent, sample->period,
- sample->weight);
+ sample->weight, sample->transaction);
if (he == NULL)
return -ENOMEM;
@@ -330,7 +338,8 @@
if (al.map != NULL)
al.map->dso->hit = 1;
- ret = perf_evsel__add_hist_entry(evsel, &al, sample, machine);
+ ret = perf_evsel__add_hist_entry(tool, evsel, &al, sample,
+ machine);
if (ret < 0)
pr_debug("problem incrementing symbol period, skipping event\n");
}
@@ -364,10 +373,11 @@
/* For pipe mode, sample_type is not currently set */
static int perf_report__setup_sample_type(struct perf_report *rep)
{
- struct perf_session *self = rep->session;
- u64 sample_type = perf_evlist__combined_sample_type(self->evlist);
+ struct perf_session *session = rep->session;
+ u64 sample_type = perf_evlist__combined_sample_type(session->evlist);
+ bool is_pipe = perf_data_file__is_pipe(session->file);
- if (!self->fd_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
+ if (!is_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
if (sort__has_parent) {
ui__error("Selected --sort parent, but no "
"callchain data. Did you call "
@@ -390,7 +400,7 @@
}
if (sort__mode == SORT_MODE__BRANCH) {
- if (!self->fd_pipe &&
+ if (!is_pipe &&
!(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
ui__error("Selected -b but no branch data. "
"Did you call perf record without -b?\n");
@@ -407,14 +417,14 @@
}
static size_t hists__fprintf_nr_sample_events(struct perf_report *rep,
- struct hists *self,
+ struct hists *hists,
const char *evname, FILE *fp)
{
size_t ret;
char unit;
- unsigned long nr_samples = self->stats.nr_events[PERF_RECORD_SAMPLE];
- u64 nr_events = self->stats.total_period;
- struct perf_evsel *evsel = hists_to_evsel(self);
+ unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
+ u64 nr_events = hists->stats.total_period;
+ struct perf_evsel *evsel = hists_to_evsel(hists);
char buf[512];
size_t size = sizeof(buf);
@@ -486,6 +496,8 @@
struct map *kernel_map;
struct kmap *kernel_kmap;
const char *help = "For a higher level overview, try: perf report --sort comm,dso";
+ struct ui_progress prog;
+ struct perf_data_file *file = session->file;
signal(SIGINT, sig_handler);
@@ -547,13 +559,19 @@
}
nr_samples = 0;
+ list_for_each_entry(pos, &session->evlist->entries, node)
+ nr_samples += pos->hists.nr_entries;
+
+ ui_progress__init(&prog, nr_samples, "Merging related events...");
+
+ nr_samples = 0;
list_for_each_entry(pos, &session->evlist->entries, node) {
struct hists *hists = &pos->hists;
if (pos->idx == 0)
hists->symbol_filter_str = rep->symbol_filter_str;
- hists__collapse_resort(hists);
+ hists__collapse_resort(hists, &prog);
nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
/* Non-group events are considered as leader */
@@ -565,12 +583,13 @@
hists__link(leader_hists, hists);
}
}
+ ui_progress__finish();
if (session_done())
return 0;
if (nr_samples == 0) {
- ui__error("The %s file has no samples!\n", session->filename);
+ ui__error("The %s file has no samples!\n", file->path);
return 0;
}
@@ -591,8 +610,19 @@
ret = 0;
} else if (use_browser == 2) {
- perf_evlist__gtk_browse_hists(session->evlist, help,
- NULL, rep->min_percent);
+ int (*hist_browser)(struct perf_evlist *,
+ const char *,
+ struct hist_browser_timer *,
+ float min_pcnt);
+
+ hist_browser = dlsym(perf_gtk_handle,
+ "perf_evlist__gtk_browse_hists");
+ if (hist_browser == NULL) {
+ ui__error("GTK browser not found!\n");
+ return ret;
+ }
+ hist_browser(session->evlist, help, NULL,
+ rep->min_percent);
}
} else
perf_evlist__tty_browse_hists(session->evlist, rep, help);
@@ -757,6 +787,7 @@
.ordered_samples = true,
.ordering_requires_timestamps = true,
},
+ .max_stack = PERF_MAX_STACK_DEPTH,
.pretty_printing_style = "normal",
};
const struct option options[] = {
@@ -787,7 +818,7 @@
"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",
@@ -797,6 +828,10 @@
OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
"Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
"Default: fractal,0.5,callee,function", &parse_callchain_opt, callchain_default_opt),
+ OPT_INTEGER(0, "max-stack", &report.max_stack,
+ "Set the maximum stack depth when parsing the callchain, "
+ "anything beyond the specified depth will be ignored. "
+ "Default: " __stringify(PERF_MAX_STACK_DEPTH)),
OPT_BOOLEAN('G', "inverted", &report.inverted_callchain,
"alias for inverted call graph"),
OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
@@ -845,6 +880,9 @@
"Don't show entries under that percent", parse_percent_limit),
OPT_END()
};
+ struct perf_data_file file = {
+ .mode = PERF_DATA_MODE_READ,
+ };
perf_config(perf_report_config, &report);
@@ -874,9 +912,11 @@
perf_hpp__init();
}
+ file.path = input_name;
+ file.force = report.force;
+
repeat:
- session = perf_session__new(input_name, O_RDONLY,
- report.force, false, &report.tool);
+ session = perf_session__new(&file, false, &report.tool);
if (session == NULL)
return -ENOMEM;
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index d8c51b2..ddb5dc1 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1446,8 +1446,12 @@
{ "sched:sched_migrate_task", process_sched_migrate_task_event, },
};
struct perf_session *session;
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
- session = perf_session__new(input_name, O_RDONLY, 0, false, &sched->tool);
+ session = perf_session__new(&file, false, &sched->tool);
if (session == NULL) {
pr_debug("No Memory for session\n");
return -1;
@@ -1651,29 +1655,27 @@
return cmd_record(i, rec_argv, NULL);
}
-static const char default_sort_order[] = "avg, max, switch, runtime";
-static struct perf_sched sched = {
- .tool = {
- .sample = perf_sched__process_tracepoint_sample,
- .comm = perf_event__process_comm,
- .lost = perf_event__process_lost,
- .fork = perf_sched__process_fork_event,
- .ordered_samples = true,
- },
- .cmp_pid = LIST_HEAD_INIT(sched.cmp_pid),
- .sort_list = LIST_HEAD_INIT(sched.sort_list),
- .start_work_mutex = PTHREAD_MUTEX_INITIALIZER,
- .work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER,
- .curr_pid = { [0 ... MAX_CPUS - 1] = -1 },
- .sort_order = default_sort_order,
- .replay_repeat = 10,
- .profile_cpu = -1,
- .next_shortname1 = 'A',
- .next_shortname2 = '0',
-};
-
int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
{
+ const char default_sort_order[] = "avg, max, switch, runtime";
+ struct perf_sched sched = {
+ .tool = {
+ .sample = perf_sched__process_tracepoint_sample,
+ .comm = perf_event__process_comm,
+ .lost = perf_event__process_lost,
+ .fork = perf_sched__process_fork_event,
+ .ordered_samples = true,
+ },
+ .cmp_pid = LIST_HEAD_INIT(sched.cmp_pid),
+ .sort_list = LIST_HEAD_INIT(sched.sort_list),
+ .start_work_mutex = PTHREAD_MUTEX_INITIALIZER,
+ .work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER,
+ .sort_order = default_sort_order,
+ .replay_repeat = 10,
+ .profile_cpu = -1,
+ .next_shortname1 = 'A',
+ .next_shortname2 = '0',
+ };
const struct option latency_options[] = {
OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]",
"sort by key(s): runtime, switch, avg, max"),
@@ -1729,6 +1731,10 @@
.switch_event = replay_switch_event,
.fork_event = replay_fork_event,
};
+ unsigned int i;
+
+ for (i = 0; i < ARRAY_SIZE(sched.curr_pid); i++)
+ sched.curr_pid[i] = -1;
argc = parse_options(argc, argv, sched_options, sched_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9c333ff..0ae88c2 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -15,6 +15,7 @@
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/sort.h"
+#include "util/data.h"
#include <linux/bitmap.h>
static char const *script_name;
@@ -409,7 +410,9 @@
printf(" => ");
/* print branch_to information */
- if (PRINT_FIELD(ADDR))
+ if (PRINT_FIELD(ADDR) ||
+ ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
+ !output[attr->type].user_set))
print_sample_addr(event, sample, machine, thread, attr);
printf("\n");
@@ -539,18 +542,9 @@
return 0;
}
-static struct perf_tool perf_script = {
- .sample = process_sample_event,
- .mmap = perf_event__process_mmap,
- .mmap2 = perf_event__process_mmap2,
- .comm = perf_event__process_comm,
- .exit = perf_event__process_exit,
- .fork = perf_event__process_fork,
- .attr = perf_event__process_attr,
- .tracing_data = perf_event__process_tracing_data,
- .build_id = perf_event__process_build_id,
- .ordered_samples = true,
- .ordering_requires_timestamps = true,
+struct perf_script {
+ struct perf_tool tool;
+ struct perf_session *session;
};
static void sig_handler(int sig __maybe_unused)
@@ -558,13 +552,13 @@
session_done = 1;
}
-static int __cmd_script(struct perf_session *session)
+static int __cmd_script(struct perf_script *script)
{
int ret;
signal(SIGINT, sig_handler);
- ret = perf_session__process_events(session, &perf_script);
+ ret = perf_session__process_events(script->session, &script->tool);
if (debug_mode)
pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered);
@@ -1113,10 +1107,14 @@
char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN];
DIR *scripts_dir, *lang_dir;
struct perf_session *session;
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
char *temp;
int i = 0;
- session = perf_session__new(input_name, O_RDONLY, 0, false, NULL);
+ session = perf_session__new(&file, false, NULL);
if (!session)
return -1;
@@ -1266,6 +1264,21 @@
char *script_path = NULL;
const char **__argv;
int i, j, err;
+ struct perf_script script = {
+ .tool = {
+ .sample = process_sample_event,
+ .mmap = perf_event__process_mmap,
+ .mmap2 = perf_event__process_mmap2,
+ .comm = perf_event__process_comm,
+ .exit = perf_event__process_exit,
+ .fork = perf_event__process_fork,
+ .attr = perf_event__process_attr,
+ .tracing_data = perf_event__process_tracing_data,
+ .build_id = perf_event__process_build_id,
+ .ordered_samples = true,
+ .ordering_requires_timestamps = true,
+ },
+ };
const struct option options[] = {
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
@@ -1317,12 +1330,17 @@
"perf script [<options>] <top-script> [script-args]",
NULL
};
+ struct perf_data_file file = {
+ .mode = PERF_DATA_MODE_READ,
+ };
setup_scripting();
argc = parse_options(argc, argv, options, script_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
+ file.path = input_name;
+
if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
if (!rec_script_path)
@@ -1486,11 +1504,12 @@
if (!script_name)
setup_pager();
- session = perf_session__new(input_name, O_RDONLY, 0, false,
- &perf_script);
+ session = perf_session__new(&file, false, &script.tool);
if (session == NULL)
return -ENOMEM;
+ script.session = session;
+
if (cpu_list) {
if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap))
return -1;
@@ -1514,7 +1533,7 @@
return -1;
}
- input = open(session->filename, O_RDONLY); /* input_name */
+ input = open(file.path, O_RDONLY); /* input_name */
if (input < 0) {
perror("failed to open file");
return -1;
@@ -1554,7 +1573,7 @@
if (err < 0)
goto out;
- err = __cmd_script(session);
+ err = __cmd_script(&script);
perf_session__delete(session);
cleanup_scripting();
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 5098f14..1a9c95d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -46,6 +46,7 @@
#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"
@@ -70,6 +71,41 @@
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 = {
@@ -90,6 +126,7 @@
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;
@@ -214,7 +251,10 @@
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)
{
@@ -236,6 +276,11 @@
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));
}
@@ -274,6 +319,29 @@
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,
@@ -285,6 +353,15 @@
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))
@@ -629,10 +706,13 @@
{
double msecs = avg / 1e6;
const char *fmt = csv_output ? "%.6f%s%s" : "%18.6f%s%-25s";
+ char name[25];
aggr_printout(evsel, cpu, nr);
- fprintf(output, fmt, msecs, csv_sep, perf_evsel__name(evsel));
+ scnprintf(name, sizeof(name), "%s%s",
+ perf_evsel__name(evsel), csv_output ? "" : " (msec)");
+ fprintf(output, fmt, msecs, csv_sep, name);
if (evsel->cgrp)
fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
@@ -828,7 +908,7 @@
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)
@@ -853,11 +933,10 @@
if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
total = avg_stats(&runtime_cycles_stats[cpu]);
- if (total)
+ if (total) {
ratio = avg / total;
-
- fprintf(output, " # %5.2f insns per cycle ", ratio);
-
+ fprintf(output, " # %5.2f insns per cycle ", ratio);
+ }
total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]);
total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu]));
@@ -920,10 +999,47 @@
} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
total = avg_stats(&runtime_nsecs_stats[cpu]);
+ if (total) {
+ ratio = 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)
- ratio = 1.0 * avg / 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]);
- fprintf(output, " # %8.3f GHz ", ratio);
+ 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';
@@ -1116,7 +1232,11 @@
if (!csv_output) {
fprintf(output, "\n");
fprintf(output, " Performance counter stats for ");
- if (!perf_target__has_task(&target)) {
+ if (target.system_wide)
+ fprintf(output, "\'system wide");
+ else if (target.cpu_list)
+ fprintf(output, "\'CPU(s) %s", target.cpu_list);
+ else if (!perf_target__has_task(&target)) {
fprintf(output, "\'%s", argv[0]);
for (i = 1; i < argc; i++)
fprintf(output, " %s", argv[i]);
@@ -1237,6 +1357,16 @@
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
@@ -1355,6 +1485,22 @@
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;
@@ -1389,6 +1535,8 @@
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),
@@ -1514,8 +1662,9 @@
} else if (big_num_opt == 0) /* User passed --no-big-num */
big_num = false;
- if (!argc && !perf_target__has_task(&target))
+ if (!argc && perf_target__none(&target))
usage_with_options(stat_usage, options);
+
if (run_count < 0) {
usage_with_options(stat_usage, options);
} else if (run_count == 0) {
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index c2e0231..e11c61d 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -36,6 +36,7 @@
#include "util/session.h"
#include "util/svghelper.h"
#include "util/tool.h"
+#include "util/data.h"
#define SUPPORT_OLD_POWER_EVENTS 1
#define PWR_EVENT_EXIT -1
@@ -990,8 +991,13 @@
{ "power:power_frequency", process_sample_power_frequency },
#endif
};
- struct perf_session *session = perf_session__new(input_name, O_RDONLY,
- 0, false, &perf_timechart);
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
+
+ struct perf_session *session = perf_session__new(&file, false,
+ &perf_timechart);
int ret = -EINVAL;
if (session == NULL)
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 5a11f13..a6ea956 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -247,9 +247,8 @@
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;
@@ -287,7 +286,7 @@
return;
}
- hists__collapse_resort(&top->sym_evsel->hists);
+ hists__collapse_resort(&top->sym_evsel->hists, NULL);
hists__output_resort(&top->sym_evsel->hists);
hists__decay_entries(&top->sym_evsel->hists,
top->hide_user_symbols,
@@ -553,7 +552,7 @@
if (t->evlist->selected != NULL)
t->sym_evsel = t->evlist->selected;
- hists__collapse_resort(&t->sym_evsel->hists);
+ hists__collapse_resort(&t->sym_evsel->hists, NULL);
hists__output_resort(&t->sym_evsel->hists);
hists__decay_entries(&t->sym_evsel->hists,
t->hide_user_symbols,
@@ -771,7 +770,8 @@
sample->callchain) {
err = machine__resolve_callchain(machine, evsel,
al.thread, sample,
- &parent, &al);
+ &parent, &al,
+ top->max_stack);
if (err)
return;
}
@@ -932,11 +932,8 @@
struct perf_record_opts *opts = &top->record_opts;
pthread_t thread;
int ret;
- /*
- * FIXME: perf_session__new should allow passing a O_MMAP, so that all this
- * mmap reading, etc is encapsulated in it. Use O_WRONLY for now.
- */
- top->session = perf_session__new(NULL, O_WRONLY, false, false, NULL);
+
+ top->session = perf_session__new(NULL, false, NULL);
if (top->session == NULL)
return -ENOMEM;
@@ -1053,10 +1050,11 @@
.user_freq = UINT_MAX,
.user_interval = ULLONG_MAX,
.freq = 4000, /* 4 KHz */
- .target = {
+ .target = {
.uses_mmap = true,
},
},
+ .max_stack = PERF_MAX_STACK_DEPTH,
.sym_pcnt_filter = 5,
};
struct perf_record_opts *opts = &top.record_opts;
@@ -1076,10 +1074,13 @@
"list of cpus to monitor"),
OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
"file", "vmlinux pathname"),
+ OPT_BOOLEAN(0, "ignore-vmlinux", &symbol_conf.ignore_vmlinux,
+ "don't load vmlinux even if found"),
OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols,
"hide kernel symbols"),
- OPT_UINTEGER('m', "mmap-pages", &opts->mmap_pages,
- "number of mmap data pages"),
+ OPT_CALLBACK('m', "mmap-pages", &opts->mmap_pages, "pages",
+ "number of mmap data pages",
+ perf_evlist__parse_mmap_pages),
OPT_INTEGER('r', "realtime", &top.realtime_prio,
"collect data with this RT SCHED_FIFO priority"),
OPT_INTEGER('d', "delay", &top.delay_secs,
@@ -1105,7 +1106,8 @@
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_NOOPT('G', NULL, &top.record_opts,
@@ -1114,6 +1116,9 @@
OPT_CALLBACK(0, "call-graph", &top.record_opts,
"mode[,dump_size]", record_callchain_help,
&parse_callchain_opt),
+ OPT_INTEGER(0, "max-stack", &top.max_stack,
+ "Set the maximum stack depth when parsing the callchain. "
+ "Default: " __stringify(PERF_MAX_STACK_DEPTH)),
OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
"ignore callees of these functions in call graphs",
report_parse_ignore_callees_opt),
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 99c8d9a..dc3da65 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -10,9 +10,11 @@
#include "util/strlist.h"
#include "util/intlist.h"
#include "util/thread_map.h"
+#include "util/stat.h"
#include <libaudit.h>
#include <stdlib.h>
+#include <sys/eventfd.h>
#include <sys/mman.h>
#include <linux/futex.h>
@@ -33,49 +35,96 @@
# define MADV_UNMERGEABLE 13
#endif
-static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
- unsigned long arg,
- u8 arg_idx __maybe_unused,
- u8 *arg_mask __maybe_unused)
+struct syscall_arg {
+ unsigned long val;
+ struct thread *thread;
+ struct trace *trace;
+ void *parm;
+ u8 idx;
+ u8 mask;
+};
+
+struct strarray {
+ int offset;
+ int nr_entries;
+ const char **entries;
+};
+
+#define DEFINE_STRARRAY(array) struct strarray strarray__##array = { \
+ .nr_entries = ARRAY_SIZE(array), \
+ .entries = array, \
+}
+
+#define DEFINE_STRARRAY_OFFSET(array, off) struct strarray strarray__##array = { \
+ .offset = off, \
+ .nr_entries = ARRAY_SIZE(array), \
+ .entries = array, \
+}
+
+static size_t __syscall_arg__scnprintf_strarray(char *bf, size_t size,
+ const char *intfmt,
+ struct syscall_arg *arg)
{
- return scnprintf(bf, size, "%#lx", arg);
+ struct strarray *sa = arg->parm;
+ int idx = arg->val - sa->offset;
+
+ if (idx < 0 || idx >= sa->nr_entries)
+ return scnprintf(bf, size, intfmt, arg->val);
+
+ return scnprintf(bf, size, "%s", sa->entries[idx]);
+}
+
+static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ return __syscall_arg__scnprintf_strarray(bf, size, "%d", arg);
+}
+
+#define SCA_STRARRAY syscall_arg__scnprintf_strarray
+
+static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ return __syscall_arg__scnprintf_strarray(bf, size, "%#x", arg);
+}
+
+#define SCA_STRHEXARRAY syscall_arg__scnprintf_strhexarray
+
+static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
+ struct syscall_arg *arg);
+
+#define SCA_FD syscall_arg__scnprintf_fd
+
+static size_t syscall_arg__scnprintf_fd_at(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ int fd = arg->val;
+
+ if (fd == AT_FDCWD)
+ return scnprintf(bf, size, "CWD");
+
+ return syscall_arg__scnprintf_fd(bf, size, arg);
+}
+
+#define SCA_FDAT syscall_arg__scnprintf_fd_at
+
+static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
+ struct syscall_arg *arg);
+
+#define SCA_CLOSE_FD syscall_arg__scnprintf_close_fd
+
+static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ return scnprintf(bf, size, "%#lx", arg->val);
}
#define SCA_HEX syscall_arg__scnprintf_hex
-static size_t syscall_arg__scnprintf_whence(char *bf, size_t size,
- unsigned long arg,
- u8 arg_idx __maybe_unused,
- u8 *arg_mask __maybe_unused)
-{
- int whence = arg;
-
- switch (whence) {
-#define P_WHENCE(n) case SEEK_##n: return scnprintf(bf, size, #n)
- P_WHENCE(SET);
- P_WHENCE(CUR);
- P_WHENCE(END);
-#ifdef SEEK_DATA
- P_WHENCE(DATA);
-#endif
-#ifdef SEEK_HOLE
- P_WHENCE(HOLE);
-#endif
-#undef P_WHENCE
- default: break;
- }
-
- return scnprintf(bf, size, "%#x", whence);
-}
-
-#define SCA_WHENCE syscall_arg__scnprintf_whence
-
static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
- unsigned long arg,
- u8 arg_idx __maybe_unused,
- u8 *arg_mask __maybe_unused)
+ struct syscall_arg *arg)
{
- int printed = 0, prot = arg;
+ int printed = 0, prot = arg->val;
if (prot == PROT_NONE)
return scnprintf(bf, size, "NONE");
@@ -104,10 +153,9 @@
#define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot
static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
- unsigned long arg, u8 arg_idx __maybe_unused,
- u8 *arg_mask __maybe_unused)
+ struct syscall_arg *arg)
{
- int printed = 0, flags = arg;
+ int printed = 0, flags = arg->val;
#define P_MMAP_FLAG(n) \
if (flags & MAP_##n) { \
@@ -148,10 +196,9 @@
#define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
- unsigned long arg, u8 arg_idx __maybe_unused,
- u8 *arg_mask __maybe_unused)
+ struct syscall_arg *arg)
{
- int behavior = arg;
+ int behavior = arg->val;
switch (behavior) {
#define P_MADV_BHV(n) case MADV_##n: return scnprintf(bf, size, #n)
@@ -190,8 +237,38 @@
#define SCA_MADV_BHV syscall_arg__scnprintf_madvise_behavior
-static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, unsigned long arg,
- u8 arg_idx __maybe_unused, u8 *arg_mask)
+static size_t syscall_arg__scnprintf_flock(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ int printed = 0, op = arg->val;
+
+ if (op == 0)
+ return scnprintf(bf, size, "NONE");
+#define P_CMD(cmd) \
+ if ((op & LOCK_##cmd) == LOCK_##cmd) { \
+ printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #cmd); \
+ op &= ~LOCK_##cmd; \
+ }
+
+ P_CMD(SH);
+ P_CMD(EX);
+ P_CMD(NB);
+ P_CMD(UN);
+ P_CMD(MAND);
+ P_CMD(RW);
+ P_CMD(READ);
+ P_CMD(WRITE);
+#undef P_OP
+
+ if (op)
+ printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", op);
+
+ return printed;
+}
+
+#define SCA_FLOCK syscall_arg__scnprintf_flock
+
+static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg)
{
enum syscall_futex_args {
SCF_UADDR = (1 << 0),
@@ -201,24 +278,24 @@
SCF_UADDR2 = (1 << 4),
SCF_VAL3 = (1 << 5),
};
- int op = arg;
+ int op = arg->val;
int cmd = op & FUTEX_CMD_MASK;
size_t printed = 0;
switch (cmd) {
#define P_FUTEX_OP(n) case FUTEX_##n: printed = scnprintf(bf, size, #n);
- P_FUTEX_OP(WAIT); *arg_mask |= SCF_VAL3|SCF_UADDR2; break;
- P_FUTEX_OP(WAKE); *arg_mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
- P_FUTEX_OP(FD); *arg_mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
- P_FUTEX_OP(REQUEUE); *arg_mask |= SCF_VAL3|SCF_TIMEOUT; break;
- P_FUTEX_OP(CMP_REQUEUE); *arg_mask |= SCF_TIMEOUT; break;
- P_FUTEX_OP(CMP_REQUEUE_PI); *arg_mask |= SCF_TIMEOUT; break;
+ P_FUTEX_OP(WAIT); arg->mask |= SCF_VAL3|SCF_UADDR2; break;
+ P_FUTEX_OP(WAKE); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+ P_FUTEX_OP(FD); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+ P_FUTEX_OP(REQUEUE); arg->mask |= SCF_VAL3|SCF_TIMEOUT; break;
+ P_FUTEX_OP(CMP_REQUEUE); arg->mask |= SCF_TIMEOUT; break;
+ P_FUTEX_OP(CMP_REQUEUE_PI); arg->mask |= SCF_TIMEOUT; break;
P_FUTEX_OP(WAKE_OP); break;
- P_FUTEX_OP(LOCK_PI); *arg_mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
- P_FUTEX_OP(UNLOCK_PI); *arg_mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
- P_FUTEX_OP(TRYLOCK_PI); *arg_mask |= SCF_VAL3|SCF_UADDR2; break;
- P_FUTEX_OP(WAIT_BITSET); *arg_mask |= SCF_UADDR2; break;
- P_FUTEX_OP(WAKE_BITSET); *arg_mask |= SCF_UADDR2; break;
+ P_FUTEX_OP(LOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+ P_FUTEX_OP(UNLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+ P_FUTEX_OP(TRYLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2; break;
+ P_FUTEX_OP(WAIT_BITSET); arg->mask |= SCF_UADDR2; break;
+ P_FUTEX_OP(WAKE_BITSET); arg->mask |= SCF_UADDR2; break;
P_FUTEX_OP(WAIT_REQUEUE_PI); break;
default: printed = scnprintf(bf, size, "%#x", cmd); break;
}
@@ -234,14 +311,194 @@
#define SCA_FUTEX_OP syscall_arg__scnprintf_futex_op
-static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
- unsigned long arg,
- u8 arg_idx, u8 *arg_mask)
+static const char *epoll_ctl_ops[] = { "ADD", "DEL", "MOD", };
+static DEFINE_STRARRAY_OFFSET(epoll_ctl_ops, 1);
+
+static const char *itimers[] = { "REAL", "VIRTUAL", "PROF", };
+static DEFINE_STRARRAY(itimers);
+
+static const char *whences[] = { "SET", "CUR", "END",
+#ifdef SEEK_DATA
+"DATA",
+#endif
+#ifdef SEEK_HOLE
+"HOLE",
+#endif
+};
+static DEFINE_STRARRAY(whences);
+
+static const char *fcntl_cmds[] = {
+ "DUPFD", "GETFD", "SETFD", "GETFL", "SETFL", "GETLK", "SETLK",
+ "SETLKW", "SETOWN", "GETOWN", "SETSIG", "GETSIG", "F_GETLK64",
+ "F_SETLK64", "F_SETLKW64", "F_SETOWN_EX", "F_GETOWN_EX",
+ "F_GETOWNER_UIDS",
+};
+static DEFINE_STRARRAY(fcntl_cmds);
+
+static const char *rlimit_resources[] = {
+ "CPU", "FSIZE", "DATA", "STACK", "CORE", "RSS", "NPROC", "NOFILE",
+ "MEMLOCK", "AS", "LOCKS", "SIGPENDING", "MSGQUEUE", "NICE", "RTPRIO",
+ "RTTIME",
+};
+static DEFINE_STRARRAY(rlimit_resources);
+
+static const char *sighow[] = { "BLOCK", "UNBLOCK", "SETMASK", };
+static DEFINE_STRARRAY(sighow);
+
+static const char *clockid[] = {
+ "REALTIME", "MONOTONIC", "PROCESS_CPUTIME_ID", "THREAD_CPUTIME_ID",
+ "MONOTONIC_RAW", "REALTIME_COARSE", "MONOTONIC_COARSE",
+};
+static DEFINE_STRARRAY(clockid);
+
+static const char *socket_families[] = {
+ "UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
+ "BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
+ "SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
+ "RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
+ "BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
+ "ALG", "NFC", "VSOCK",
+};
+static DEFINE_STRARRAY(socket_families);
+
+#ifndef SOCK_TYPE_MASK
+#define SOCK_TYPE_MASK 0xf
+#endif
+
+static size_t syscall_arg__scnprintf_socket_type(char *bf, size_t size,
+ struct syscall_arg *arg)
{
- int printed = 0, flags = arg;
+ size_t printed;
+ int type = arg->val,
+ flags = type & ~SOCK_TYPE_MASK;
+
+ type &= SOCK_TYPE_MASK;
+ /*
+ * Can't use a strarray, MIPS may override for ABI reasons.
+ */
+ switch (type) {
+#define P_SK_TYPE(n) case SOCK_##n: printed = scnprintf(bf, size, #n); break;
+ P_SK_TYPE(STREAM);
+ P_SK_TYPE(DGRAM);
+ P_SK_TYPE(RAW);
+ P_SK_TYPE(RDM);
+ P_SK_TYPE(SEQPACKET);
+ P_SK_TYPE(DCCP);
+ P_SK_TYPE(PACKET);
+#undef P_SK_TYPE
+ default:
+ printed = scnprintf(bf, size, "%#x", type);
+ }
+
+#define P_SK_FLAG(n) \
+ if (flags & SOCK_##n) { \
+ printed += scnprintf(bf + printed, size - printed, "|%s", #n); \
+ flags &= ~SOCK_##n; \
+ }
+
+ P_SK_FLAG(CLOEXEC);
+ P_SK_FLAG(NONBLOCK);
+#undef P_SK_FLAG
+
+ if (flags)
+ printed += scnprintf(bf + printed, size - printed, "|%#x", flags);
+
+ return printed;
+}
+
+#define SCA_SK_TYPE syscall_arg__scnprintf_socket_type
+
+#ifndef MSG_PROBE
+#define MSG_PROBE 0x10
+#endif
+#ifndef MSG_WAITFORONE
+#define MSG_WAITFORONE 0x10000
+#endif
+#ifndef MSG_SENDPAGE_NOTLAST
+#define MSG_SENDPAGE_NOTLAST 0x20000
+#endif
+#ifndef MSG_FASTOPEN
+#define MSG_FASTOPEN 0x20000000
+#endif
+
+static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ int printed = 0, flags = arg->val;
+
+ if (flags == 0)
+ return scnprintf(bf, size, "NONE");
+#define P_MSG_FLAG(n) \
+ if (flags & MSG_##n) { \
+ printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+ flags &= ~MSG_##n; \
+ }
+
+ P_MSG_FLAG(OOB);
+ P_MSG_FLAG(PEEK);
+ P_MSG_FLAG(DONTROUTE);
+ P_MSG_FLAG(TRYHARD);
+ P_MSG_FLAG(CTRUNC);
+ P_MSG_FLAG(PROBE);
+ P_MSG_FLAG(TRUNC);
+ P_MSG_FLAG(DONTWAIT);
+ P_MSG_FLAG(EOR);
+ P_MSG_FLAG(WAITALL);
+ P_MSG_FLAG(FIN);
+ P_MSG_FLAG(SYN);
+ P_MSG_FLAG(CONFIRM);
+ P_MSG_FLAG(RST);
+ P_MSG_FLAG(ERRQUEUE);
+ P_MSG_FLAG(NOSIGNAL);
+ P_MSG_FLAG(MORE);
+ P_MSG_FLAG(WAITFORONE);
+ P_MSG_FLAG(SENDPAGE_NOTLAST);
+ P_MSG_FLAG(FASTOPEN);
+ P_MSG_FLAG(CMSG_CLOEXEC);
+#undef P_MSG_FLAG
+
+ if (flags)
+ printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+ return printed;
+}
+
+#define SCA_MSG_FLAGS syscall_arg__scnprintf_msg_flags
+
+static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ size_t printed = 0;
+ int mode = arg->val;
+
+ if (mode == F_OK) /* 0 */
+ return scnprintf(bf, size, "F");
+#define P_MODE(n) \
+ if (mode & n##_OK) { \
+ printed += scnprintf(bf + printed, size - printed, "%s", #n); \
+ mode &= ~n##_OK; \
+ }
+
+ P_MODE(R);
+ P_MODE(W);
+ P_MODE(X);
+#undef P_MODE
+
+ if (mode)
+ printed += scnprintf(bf + printed, size - printed, "|%#x", mode);
+
+ return printed;
+}
+
+#define SCA_ACCMODE syscall_arg__scnprintf_access_mode
+
+static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ int printed = 0, flags = arg->val;
if (!(flags & O_CREAT))
- *arg_mask |= 1 << (arg_idx + 1); /* Mask the mode parm */
+ arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */
if (flags == 0)
return scnprintf(bf, size, "RDONLY");
@@ -291,32 +548,225 @@
#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
+static size_t syscall_arg__scnprintf_eventfd_flags(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ int printed = 0, flags = arg->val;
+
+ if (flags == 0)
+ return scnprintf(bf, size, "NONE");
+#define P_FLAG(n) \
+ if (flags & EFD_##n) { \
+ printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+ flags &= ~EFD_##n; \
+ }
+
+ P_FLAG(SEMAPHORE);
+ P_FLAG(CLOEXEC);
+ P_FLAG(NONBLOCK);
+#undef P_FLAG
+
+ if (flags)
+ printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+ return printed;
+}
+
+#define SCA_EFD_FLAGS syscall_arg__scnprintf_eventfd_flags
+
+static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ int printed = 0, flags = arg->val;
+
+#define P_FLAG(n) \
+ if (flags & O_##n) { \
+ printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+ flags &= ~O_##n; \
+ }
+
+ P_FLAG(CLOEXEC);
+ P_FLAG(NONBLOCK);
+#undef P_FLAG
+
+ if (flags)
+ printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+ return printed;
+}
+
+#define SCA_PIPE_FLAGS syscall_arg__scnprintf_pipe_flags
+
+static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg)
+{
+ int sig = arg->val;
+
+ switch (sig) {
+#define P_SIGNUM(n) case SIG##n: return scnprintf(bf, size, #n)
+ P_SIGNUM(HUP);
+ P_SIGNUM(INT);
+ P_SIGNUM(QUIT);
+ P_SIGNUM(ILL);
+ P_SIGNUM(TRAP);
+ P_SIGNUM(ABRT);
+ P_SIGNUM(BUS);
+ P_SIGNUM(FPE);
+ P_SIGNUM(KILL);
+ P_SIGNUM(USR1);
+ P_SIGNUM(SEGV);
+ P_SIGNUM(USR2);
+ P_SIGNUM(PIPE);
+ P_SIGNUM(ALRM);
+ P_SIGNUM(TERM);
+ P_SIGNUM(STKFLT);
+ P_SIGNUM(CHLD);
+ P_SIGNUM(CONT);
+ P_SIGNUM(STOP);
+ P_SIGNUM(TSTP);
+ P_SIGNUM(TTIN);
+ P_SIGNUM(TTOU);
+ P_SIGNUM(URG);
+ P_SIGNUM(XCPU);
+ P_SIGNUM(XFSZ);
+ P_SIGNUM(VTALRM);
+ P_SIGNUM(PROF);
+ P_SIGNUM(WINCH);
+ P_SIGNUM(IO);
+ P_SIGNUM(PWR);
+ P_SIGNUM(SYS);
+ default: break;
+ }
+
+ return scnprintf(bf, size, "%#x", sig);
+}
+
+#define SCA_SIGNUM syscall_arg__scnprintf_signum
+
+#define TCGETS 0x5401
+
+static const char *tioctls[] = {
+ "TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
+ "TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL",
+ "TIOCSCTTY", "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI",
+ "TIOCGWINSZ", "TIOCSWINSZ", "TIOCMGET", "TIOCMBIS", "TIOCMBIC",
+ "TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR", "FIONREAD", "TIOCLINUX",
+ "TIOCCONS", "TIOCGSERIAL", "TIOCSSERIAL", "TIOCPKT", "FIONBIO",
+ "TIOCNOTTY", "TIOCSETD", "TIOCGETD", "TCSBRKP", [0x27] = "TIOCSBRK",
+ "TIOCCBRK", "TIOCGSID", "TCGETS2", "TCSETS2", "TCSETSW2", "TCSETSF2",
+ "TIOCGRS485", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK",
+ "TIOCGDEV||TCGETX", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG",
+ "TIOCVHANGUP", "TIOCGPKT", "TIOCGPTLCK", "TIOCGEXCL",
+ [0x50] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG",
+ "TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS",
+ "TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI",
+ "TIOCMIWAIT", "TIOCGICOUNT", [0x60] = "FIOQSIZE",
+};
+
+static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);
+
+#define STRARRAY(arg, name, array) \
+ .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
+ .arg_parm = { [arg] = &strarray__##array, }
+
static struct syscall_fmt {
const char *name;
const char *alias;
- size_t (*arg_scnprintf[6])(char *bf, size_t size, unsigned long arg, u8 arg_idx, u8 *arg_mask);
+ size_t (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg);
+ void *arg_parm[6];
bool errmsg;
bool timeout;
bool hexret;
} syscall_fmts[] = {
- { .name = "access", .errmsg = true, },
+ { .name = "access", .errmsg = true,
+ .arg_scnprintf = { [1] = SCA_ACCMODE, /* mode */ }, },
{ .name = "arch_prctl", .errmsg = true, .alias = "prctl", },
{ .name = "brk", .hexret = true,
.arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
- { .name = "mmap", .hexret = true, },
+ { .name = "clock_gettime", .errmsg = true, STRARRAY(0, clk_id, clockid), },
+ { .name = "close", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, },
{ .name = "connect", .errmsg = true, },
- { .name = "fstat", .errmsg = true, .alias = "newfstat", },
- { .name = "fstatat", .errmsg = true, .alias = "newfstatat", },
+ { .name = "dup", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "dup2", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "dup3", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "epoll_ctl", .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), },
+ { .name = "eventfd2", .errmsg = true,
+ .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, },
+ { .name = "faccessat", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+ { .name = "fadvise64", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "fallocate", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "fchdir", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "fchmod", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "fchmodat", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+ { .name = "fchown", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "fchownat", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+ { .name = "fcntl", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */
+ [1] = SCA_STRARRAY, /* cmd */ },
+ .arg_parm = { [1] = &strarray__fcntl_cmds, /* cmd */ }, },
+ { .name = "fdatasync", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "flock", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */
+ [1] = SCA_FLOCK, /* cmd */ }, },
+ { .name = "fsetxattr", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "fstat", .errmsg = true, .alias = "newfstat",
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "fstatat", .errmsg = true, .alias = "newfstatat",
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+ { .name = "fstatfs", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "fsync", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "ftruncate", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "futex", .errmsg = true,
.arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
+ { .name = "futimesat", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+ { .name = "getdents", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "getdents64", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "getitimer", .errmsg = true, STRARRAY(0, which, itimers), },
+ { .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
{ .name = "ioctl", .errmsg = true,
- .arg_scnprintf = { [2] = SCA_HEX, /* arg */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */
+ [1] = SCA_STRHEXARRAY, /* cmd */
+ [2] = SCA_HEX, /* arg */ },
+ .arg_parm = { [1] = &strarray__tioctls, /* cmd */ }, },
+ { .name = "kill", .errmsg = true,
+ .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
+ { .name = "linkat", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
{ .name = "lseek", .errmsg = true,
- .arg_scnprintf = { [2] = SCA_WHENCE, /* whence */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */
+ [2] = SCA_STRARRAY, /* whence */ },
+ .arg_parm = { [2] = &strarray__whences, /* whence */ }, },
{ .name = "lstat", .errmsg = true, .alias = "newlstat", },
{ .name = "madvise", .errmsg = true,
.arg_scnprintf = { [0] = SCA_HEX, /* start */
[2] = SCA_MADV_BHV, /* behavior */ }, },
+ { .name = "mkdirat", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+ { .name = "mknodat", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+ { .name = "mlock", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
+ { .name = "mlockall", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
{ .name = "mmap", .hexret = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */
[2] = SCA_MMAP_PROT, /* prot */
@@ -327,24 +777,91 @@
{ .name = "mremap", .hexret = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */
[4] = SCA_HEX, /* new_addr */ }, },
+ { .name = "munlock", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
{ .name = "munmap", .errmsg = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
+ { .name = "name_to_handle_at", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+ { .name = "newfstatat", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "open", .errmsg = true,
.arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
{ .name = "open_by_handle_at", .errmsg = true,
- .arg_scnprintf = { [2] = SCA_OPEN_FLAGS, /* flags */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
+ [2] = SCA_OPEN_FLAGS, /* flags */ }, },
{ .name = "openat", .errmsg = true,
- .arg_scnprintf = { [2] = SCA_OPEN_FLAGS, /* flags */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
+ [2] = SCA_OPEN_FLAGS, /* flags */ }, },
+ { .name = "pipe2", .errmsg = true,
+ .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
{ .name = "poll", .errmsg = true, .timeout = true, },
{ .name = "ppoll", .errmsg = true, .timeout = true, },
- { .name = "pread", .errmsg = true, .alias = "pread64", },
- { .name = "pwrite", .errmsg = true, .alias = "pwrite64", },
- { .name = "read", .errmsg = true, },
- { .name = "recvfrom", .errmsg = true, },
+ { .name = "pread", .errmsg = true, .alias = "pread64",
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "preadv", .errmsg = true, .alias = "pread",
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "prlimit64", .errmsg = true, STRARRAY(1, resource, rlimit_resources), },
+ { .name = "pwrite", .errmsg = true, .alias = "pwrite64",
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "pwritev", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "read", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "readlinkat", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+ { .name = "readv", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "recvfrom", .errmsg = true,
+ .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
+ { .name = "recvmmsg", .errmsg = true,
+ .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
+ { .name = "recvmsg", .errmsg = true,
+ .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
+ { .name = "renameat", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+ { .name = "rt_sigaction", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, },
+ { .name = "rt_sigprocmask", .errmsg = true, STRARRAY(0, how, sighow), },
+ { .name = "rt_sigqueueinfo", .errmsg = true,
+ .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
+ { .name = "rt_tgsigqueueinfo", .errmsg = true,
+ .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
{ .name = "select", .errmsg = true, .timeout = true, },
- { .name = "socket", .errmsg = true, },
+ { .name = "sendmmsg", .errmsg = true,
+ .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
+ { .name = "sendmsg", .errmsg = true,
+ .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
+ { .name = "sendto", .errmsg = true,
+ .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
+ { .name = "setitimer", .errmsg = true, STRARRAY(0, which, itimers), },
+ { .name = "setrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
+ { .name = "shutdown", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "socket", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
+ [1] = SCA_SK_TYPE, /* type */ },
+ .arg_parm = { [0] = &strarray__socket_families, /* family */ }, },
+ { .name = "socketpair", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
+ [1] = SCA_SK_TYPE, /* type */ },
+ .arg_parm = { [0] = &strarray__socket_families, /* family */ }, },
{ .name = "stat", .errmsg = true, .alias = "newstat", },
+ { .name = "symlinkat", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+ { .name = "tgkill", .errmsg = true,
+ .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
+ { .name = "tkill", .errmsg = true,
+ .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
{ .name = "uname", .errmsg = true, .alias = "newuname", },
+ { .name = "unlinkat", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+ { .name = "utimensat", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, },
+ { .name = "write", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ { .name = "writev", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
};
static int syscall_fmt__cmp(const void *name, const void *fmtp)
@@ -364,8 +881,8 @@
const char *name;
bool filtered;
struct syscall_fmt *fmt;
- size_t (**arg_scnprintf)(char *bf, size_t size,
- unsigned long arg, u8 arg_idx, u8 *args_mask);
+ size_t (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
+ void **arg_parm;
};
static size_t fprintf_duration(unsigned long t, FILE *fp)
@@ -389,11 +906,24 @@
unsigned long nr_events;
char *entry_str;
double runtime_ms;
+ struct {
+ int max;
+ char **table;
+ } paths;
+
+ struct intlist *syscall_stats;
};
static struct thread_trace *thread_trace__new(void)
{
- return zalloc(sizeof(struct thread_trace));
+ struct thread_trace *ttrace = zalloc(sizeof(struct thread_trace));
+
+ if (ttrace)
+ ttrace->paths.max = -1;
+
+ ttrace->syscall_stats = intlist__new(NULL);
+
+ return ttrace;
}
static struct thread_trace *thread__trace(struct thread *thread, FILE *fp)
@@ -421,26 +951,140 @@
struct trace {
struct perf_tool tool;
- int audit_machine;
+ struct {
+ int machine;
+ int open_id;
+ } audit;
struct {
int max;
struct syscall *table;
} syscalls;
struct perf_record_opts opts;
- struct machine host;
+ struct machine *host;
u64 base_time;
+ bool full_time;
FILE *output;
unsigned long nr_events;
struct strlist *ev_qualifier;
bool not_ev_qualifier;
+ bool live;
+ const char *last_vfs_getname;
struct intlist *tid_list;
struct intlist *pid_list;
bool sched;
bool multiple_threads;
+ bool summary;
+ bool show_comm;
+ bool show_tool_stats;
double duration_filter;
double runtime_ms;
+ struct {
+ u64 vfs_getname, proc_getname;
+ } stats;
};
+static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
+{
+ struct thread_trace *ttrace = thread->priv;
+
+ if (fd > ttrace->paths.max) {
+ char **npath = realloc(ttrace->paths.table, (fd + 1) * sizeof(char *));
+
+ if (npath == NULL)
+ return -1;
+
+ if (ttrace->paths.max != -1) {
+ memset(npath + ttrace->paths.max + 1, 0,
+ (fd - ttrace->paths.max) * sizeof(char *));
+ } else {
+ memset(npath, 0, (fd + 1) * sizeof(char *));
+ }
+
+ ttrace->paths.table = npath;
+ ttrace->paths.max = fd;
+ }
+
+ ttrace->paths.table[fd] = strdup(pathname);
+
+ return ttrace->paths.table[fd] != NULL ? 0 : -1;
+}
+
+static int thread__read_fd_path(struct thread *thread, int fd)
+{
+ char linkname[PATH_MAX], pathname[PATH_MAX];
+ struct stat st;
+ int ret;
+
+ if (thread->pid_ == thread->tid) {
+ scnprintf(linkname, sizeof(linkname),
+ "/proc/%d/fd/%d", thread->pid_, fd);
+ } else {
+ scnprintf(linkname, sizeof(linkname),
+ "/proc/%d/task/%d/fd/%d", thread->pid_, thread->tid, fd);
+ }
+
+ if (lstat(linkname, &st) < 0 || st.st_size + 1 > (off_t)sizeof(pathname))
+ return -1;
+
+ ret = readlink(linkname, pathname, sizeof(pathname));
+
+ if (ret < 0 || ret > st.st_size)
+ return -1;
+
+ pathname[ret] = '\0';
+ return trace__set_fd_pathname(thread, fd, pathname);
+}
+
+static const char *thread__fd_path(struct thread *thread, int fd,
+ struct trace *trace)
+{
+ struct thread_trace *ttrace = thread->priv;
+
+ if (ttrace == NULL)
+ return NULL;
+
+ if (fd < 0)
+ return NULL;
+
+ if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL))
+ if (!trace->live)
+ return NULL;
+ ++trace->stats.proc_getname;
+ if (thread__read_fd_path(thread, fd)) {
+ return NULL;
+ }
+
+ return ttrace->paths.table[fd];
+}
+
+static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ int fd = arg->val;
+ size_t printed = scnprintf(bf, size, "%d", fd);
+ const char *path = thread__fd_path(arg->thread, fd, arg->trace);
+
+ if (path)
+ printed += scnprintf(bf + printed, size - printed, "<%s>", path);
+
+ return printed;
+}
+
+static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ int fd = arg->val;
+ size_t printed = syscall_arg__scnprintf_fd(bf, size, arg);
+ struct thread_trace *ttrace = arg->thread->priv;
+
+ if (ttrace && fd >= 0 && fd <= ttrace->paths.max) {
+ free(ttrace->paths.table[fd]);
+ ttrace->paths.table[fd] = NULL;
+ }
+
+ return printed;
+}
+
static bool trace__filter_duration(struct trace *trace, double t)
{
return t < (trace->duration_filter * NSEC_PER_MSEC);
@@ -454,10 +1098,12 @@
}
static bool done = false;
+static bool interrupted = false;
-static void sig_handler(int sig __maybe_unused)
+static void sig_handler(int sig)
{
done = true;
+ interrupted = sig == SIGINT;
}
static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
@@ -466,8 +1112,11 @@
size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
printed += fprintf_duration(duration, fp);
- if (trace->multiple_threads)
+ if (trace->multiple_threads) {
+ if (trace->show_comm)
+ printed += fprintf(fp, "%.14s/", thread->comm);
printed += fprintf(fp, "%d ", thread->tid);
+ }
return printed;
}
@@ -506,16 +1155,17 @@
if (err)
return err;
- machine__init(&trace->host, "", HOST_KERNEL_ID);
- machine__create_kernel_maps(&trace->host);
+ trace->host = machine__new_host();
+ if (trace->host == NULL)
+ return -ENOMEM;
if (perf_target__has_task(&trace->opts.target)) {
err = perf_event__synthesize_thread_map(&trace->tool, evlist->threads,
trace__tool_process,
- &trace->host);
+ trace->host);
} else {
err = perf_event__synthesize_threads(&trace->tool, trace__tool_process,
- &trace->host);
+ trace->host);
}
if (err)
@@ -533,6 +1183,9 @@
if (sc->arg_scnprintf == NULL)
return -1;
+ if (sc->fmt)
+ sc->arg_parm = sc->fmt->arg_parm;
+
for (field = sc->tp_format->format.fields->next; field; field = field->next) {
if (sc->fmt && sc->fmt->arg_scnprintf[idx])
sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
@@ -548,7 +1201,7 @@
{
char tp_name[128];
struct syscall *sc;
- const char *name = audit_syscall_to_name(id, trace->audit_machine);
+ const char *name = audit_syscall_to_name(id, trace->audit.machine);
if (name == NULL)
return -1;
@@ -603,32 +1256,52 @@
}
static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
- unsigned long *args)
+ unsigned long *args, struct trace *trace,
+ struct thread *thread)
{
- int i = 0;
size_t printed = 0;
if (sc->tp_format != NULL) {
struct format_field *field;
- u8 mask = 0, bit = 1;
+ u8 bit = 1;
+ struct syscall_arg arg = {
+ .idx = 0,
+ .mask = 0,
+ .trace = trace,
+ .thread = thread,
+ };
for (field = sc->tp_format->format.fields->next; field;
- field = field->next, ++i, bit <<= 1) {
- if (mask & bit)
+ field = field->next, ++arg.idx, bit <<= 1) {
+ if (arg.mask & bit)
+ continue;
+ /*
+ * Suppress this argument if its value is zero and
+ * and we don't have a string associated in an
+ * strarray for it.
+ */
+ if (args[arg.idx] == 0 &&
+ !(sc->arg_scnprintf &&
+ sc->arg_scnprintf[arg.idx] == SCA_STRARRAY &&
+ sc->arg_parm[arg.idx]))
continue;
printed += scnprintf(bf + printed, size - printed,
"%s%s: ", printed ? ", " : "", field->name);
-
- if (sc->arg_scnprintf && sc->arg_scnprintf[i]) {
- printed += sc->arg_scnprintf[i](bf + printed, size - printed,
- args[i], i, &mask);
+ if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) {
+ arg.val = args[arg.idx];
+ if (sc->arg_parm)
+ arg.parm = sc->arg_parm[arg.idx];
+ printed += sc->arg_scnprintf[arg.idx](bf + printed,
+ size - printed, &arg);
} else {
printed += scnprintf(bf + printed, size - printed,
- "%ld", args[i]);
+ "%ld", args[arg.idx]);
}
}
} else {
+ int i = 0;
+
while (i < 6) {
printed += scnprintf(bf + printed, size - printed,
"%sarg%d: %ld",
@@ -644,10 +1317,8 @@
struct perf_sample *sample);
static struct syscall *trace__syscall_info(struct trace *trace,
- struct perf_evsel *evsel,
- struct perf_sample *sample)
+ struct perf_evsel *evsel, int id)
{
- int id = perf_evsel__intval(evsel, sample, "id");
if (id < 0) {
@@ -688,6 +1359,32 @@
return NULL;
}
+static void thread__update_stats(struct thread_trace *ttrace,
+ int id, struct perf_sample *sample)
+{
+ struct int_node *inode;
+ struct stats *stats;
+ u64 duration = 0;
+
+ inode = intlist__findnew(ttrace->syscall_stats, id);
+ if (inode == NULL)
+ return;
+
+ stats = inode->priv;
+ if (stats == NULL) {
+ stats = malloc(sizeof(struct stats));
+ if (stats == NULL)
+ return;
+ init_stats(stats);
+ inode->priv = stats;
+ }
+
+ if (ttrace->entry_time && sample->time > ttrace->entry_time)
+ duration = sample->time - ttrace->entry_time;
+
+ update_stats(stats, duration);
+}
+
static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
struct perf_sample *sample)
{
@@ -695,7 +1392,8 @@
void *args;
size_t printed = 0;
struct thread *thread;
- struct syscall *sc = trace__syscall_info(trace, evsel, sample);
+ int id = perf_evsel__intval(evsel, sample, "id");
+ struct syscall *sc = trace__syscall_info(trace, evsel, id);
struct thread_trace *ttrace;
if (sc == NULL)
@@ -704,8 +1402,7 @@
if (sc->filtered)
return 0;
- thread = machine__findnew_thread(&trace->host, sample->pid,
- sample->tid);
+ thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
ttrace = thread__trace(thread, trace->output);
if (ttrace == NULL)
return -1;
@@ -728,7 +1425,8 @@
msg = ttrace->entry_str;
printed += scnprintf(msg + printed, 1024 - printed, "%s(", sc->name);
- printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed, args);
+ printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed,
+ args, trace, thread);
if (!strcmp(sc->name, "exit_group") || !strcmp(sc->name, "exit")) {
if (!trace->duration_filter) {
@@ -747,7 +1445,8 @@
int ret;
u64 duration = 0;
struct thread *thread;
- struct syscall *sc = trace__syscall_info(trace, evsel, sample);
+ int id = perf_evsel__intval(evsel, sample, "id");
+ struct syscall *sc = trace__syscall_info(trace, evsel, id);
struct thread_trace *ttrace;
if (sc == NULL)
@@ -756,14 +1455,22 @@
if (sc->filtered)
return 0;
- thread = machine__findnew_thread(&trace->host, sample->pid,
- sample->tid);
+ thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
ttrace = thread__trace(thread, trace->output);
if (ttrace == NULL)
return -1;
+ if (trace->summary)
+ thread__update_stats(ttrace, id, sample);
+
ret = perf_evsel__intval(evsel, sample, "ret");
+ if (id == trace->audit.open_id && ret >= 0 && trace->last_vfs_getname) {
+ trace__set_fd_pathname(thread, ret, trace->last_vfs_getname);
+ trace->last_vfs_getname = NULL;
+ ++trace->stats.vfs_getname;
+ }
+
ttrace = thread->priv;
ttrace->exit_time = sample->time;
@@ -808,12 +1515,19 @@
return 0;
}
+static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ trace->last_vfs_getname = perf_evsel__rawptr(evsel, sample, "pathname");
+ return 0;
+}
+
static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel,
struct perf_sample *sample)
{
u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
double runtime_ms = (double)runtime / NSEC_PER_MSEC;
- struct thread *thread = machine__findnew_thread(&trace->host,
+ struct thread *thread = machine__findnew_thread(trace->host,
sample->pid,
sample->tid);
struct thread_trace *ttrace = thread__trace(thread, trace->output);
@@ -861,7 +1575,7 @@
if (skip_sample(trace, sample))
return 0;
- if (trace->base_time == 0)
+ if (!trace->full_time && trace->base_time == 0)
trace->base_time = sample->time;
if (handler)
@@ -901,6 +1615,51 @@
return 0;
}
+static int trace__record(int argc, const char **argv)
+{
+ unsigned int rec_argc, i, j;
+ const char **rec_argv;
+ const char * const record_args[] = {
+ "record",
+ "-R",
+ "-m", "1024",
+ "-c", "1",
+ "-e", "raw_syscalls:sys_enter,raw_syscalls:sys_exit",
+ };
+
+ rec_argc = ARRAY_SIZE(record_args) + argc;
+ rec_argv = calloc(rec_argc + 1, sizeof(char *));
+
+ if (rec_argv == NULL)
+ return -ENOMEM;
+
+ for (i = 0; i < ARRAY_SIZE(record_args); i++)
+ rec_argv[i] = record_args[i];
+
+ for (j = 0; j < (unsigned int)argc; j++, i++)
+ rec_argv[i] = argv[j];
+
+ return cmd_record(i, rec_argv, NULL);
+}
+
+static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
+
+static void perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname",
+ evlist->nr_entries);
+ if (evsel == NULL)
+ return;
+
+ if (perf_evsel__field(evsel, "pathname") == NULL) {
+ perf_evsel__delete(evsel);
+ return;
+ }
+
+ evsel->handler.func = trace__vfs_getname;
+ perf_evlist__add(evlist, evsel);
+}
+
static int trace__run(struct trace *trace, int argc, const char **argv)
{
struct perf_evlist *evlist = perf_evlist__new();
@@ -909,23 +1668,23 @@
unsigned long before;
const bool forks = argc > 0;
+ trace->live = true;
+
if (evlist == NULL) {
fprintf(trace->output, "Not enough memory to run!\n");
goto out;
}
if (perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_enter", trace__sys_enter) ||
- perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_exit", trace__sys_exit)) {
- fprintf(trace->output, "Couldn't read the raw_syscalls tracepoints information!\n");
- goto out_delete_evlist;
- }
+ perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_exit", trace__sys_exit))
+ goto out_error_tp;
+
+ perf_evlist__add_vfs_getname(evlist);
if (trace->sched &&
- perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
- trace__sched_stat_runtime)) {
- fprintf(trace->output, "Couldn't read the sched_stat_runtime tracepoint information!\n");
- goto out_delete_evlist;
- }
+ perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
+ trace__sched_stat_runtime))
+ goto out_error_tp;
err = perf_evlist__create_maps(evlist, &trace->opts.target);
if (err < 0) {
@@ -954,10 +1713,8 @@
}
err = perf_evlist__open(evlist);
- if (err < 0) {
- fprintf(trace->output, "Couldn't create the events: %s\n", strerror(errno));
- goto out_delete_maps;
- }
+ if (err < 0)
+ goto out_error_open;
err = perf_evlist__mmap(evlist, UINT_MAX, false);
if (err < 0) {
@@ -990,11 +1747,11 @@
goto next_event;
}
- if (trace->base_time == 0)
+ if (!trace->full_time && trace->base_time == 0)
trace->base_time = sample.time;
if (type != PERF_RECORD_SAMPLE) {
- trace__process_event(trace, &trace->host, event);
+ trace__process_event(trace, trace->host, event);
continue;
}
@@ -1016,24 +1773,36 @@
next_event:
perf_evlist__mmap_consume(evlist, i);
- if (done)
- goto out_unmap_evlist;
+ if (interrupted)
+ goto out_disable;
}
}
if (trace->nr_events == before) {
- if (done)
- goto out_unmap_evlist;
+ int timeout = done ? 100 : -1;
- poll(evlist->pollfd, evlist->nr_fds, -1);
+ if (poll(evlist->pollfd, evlist->nr_fds, timeout) > 0)
+ goto again;
+ } else {
+ goto again;
}
- if (done)
- perf_evlist__disable(evlist);
+out_disable:
+ perf_evlist__disable(evlist);
- goto again;
+ if (!err) {
+ if (trace->summary)
+ trace__fprintf_thread_summary(trace, trace->output);
-out_unmap_evlist:
+ if (trace->show_tool_stats) {
+ fprintf(trace->output, "Stats:\n "
+ " vfs_getname : %" PRIu64 "\n"
+ " proc_getname: %" PRIu64 "\n",
+ trace->stats.vfs_getname,
+ trace->stats.proc_getname);
+ }
+ }
+
perf_evlist__munmap(evlist);
out_close_evlist:
perf_evlist__close(evlist);
@@ -1042,7 +1811,22 @@
out_delete_evlist:
perf_evlist__delete(evlist);
out:
+ trace->live = false;
return err;
+{
+ char errbuf[BUFSIZ];
+
+out_error_tp:
+ perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf));
+ goto out_error;
+
+out_error_open:
+ perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
+
+out_error:
+ fprintf(trace->output, "%s\n", errbuf);
+ goto out_delete_evlist;
+}
}
static int trace__replay(struct trace *trace)
@@ -1050,8 +1834,12 @@
const struct perf_evsel_str_handler handlers[] = {
{ "raw_syscalls:sys_enter", trace__sys_enter, },
{ "raw_syscalls:sys_exit", trace__sys_exit, },
+ { "probe:vfs_getname", trace__vfs_getname, },
};
-
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
struct perf_session *session;
int err = -1;
@@ -1074,11 +1862,12 @@
if (symbol__init() < 0)
return -1;
- session = perf_session__new(input_name, O_RDONLY, 0, false,
- &trace->tool);
+ session = perf_session__new(&file, false, &trace->tool);
if (session == NULL)
return -ENOMEM;
+ trace->host = &session->machines.host;
+
err = perf_session__set_tracepoints_handlers(session, handlers);
if (err)
goto out;
@@ -1103,6 +1892,9 @@
if (err)
pr_err("Failed to process events, error %d", err);
+ else if (trace->summary)
+ trace__fprintf_thread_summary(trace, trace->output);
+
out:
perf_session__delete(session);
@@ -1113,47 +1905,111 @@
{
size_t printed;
- printed = fprintf(fp, "\n _____________________________________________________________________\n");
- printed += fprintf(fp," __) Summary of events (__\n\n");
- printed += fprintf(fp," [ task - pid ] [ events ] [ ratio ] [ runtime ]\n");
- printed += fprintf(fp," _____________________________________________________________________\n\n");
+ printed = fprintf(fp, "\n _____________________________________________________________________________\n");
+ printed += fprintf(fp, " __) Summary of events (__\n\n");
+ printed += fprintf(fp, " [ task - pid ] [ events ] [ ratio ] [ runtime ]\n");
+ printed += fprintf(fp, " syscall count min max avg stddev\n");
+ printed += fprintf(fp, " msec msec msec %%\n");
+ printed += fprintf(fp, " _____________________________________________________________________________\n\n");
return printed;
}
-static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
+static size_t thread__dump_stats(struct thread_trace *ttrace,
+ struct trace *trace, FILE *fp)
{
- size_t printed = trace__fprintf_threads_header(fp);
- struct rb_node *nd;
+ struct stats *stats;
+ size_t printed = 0;
+ struct syscall *sc;
+ struct int_node *inode = intlist__first(ttrace->syscall_stats);
- for (nd = rb_first(&trace->host.threads); nd; nd = rb_next(nd)) {
- struct thread *thread = rb_entry(nd, struct thread, rb_node);
- struct thread_trace *ttrace = thread->priv;
- const char *color;
- double ratio;
+ if (inode == NULL)
+ return 0;
- if (ttrace == NULL)
- continue;
+ printed += fprintf(fp, "\n");
- ratio = (double)ttrace->nr_events / trace->nr_events * 100.0;
+ /* each int_node is a syscall */
+ while (inode) {
+ stats = inode->priv;
+ if (stats) {
+ double min = (double)(stats->min) / NSEC_PER_MSEC;
+ double max = (double)(stats->max) / NSEC_PER_MSEC;
+ double avg = avg_stats(stats);
+ double pct;
+ u64 n = (u64) stats->n;
- color = PERF_COLOR_NORMAL;
- if (ratio > 50.0)
- color = PERF_COLOR_RED;
- else if (ratio > 25.0)
- color = PERF_COLOR_GREEN;
- else if (ratio > 5.0)
- color = PERF_COLOR_YELLOW;
+ pct = avg ? 100.0 * stddev_stats(stats)/avg : 0.0;
+ avg /= NSEC_PER_MSEC;
- printed += color_fprintf(fp, color, "%20s", thread->comm);
- printed += fprintf(fp, " - %-5d :%11lu [", thread->tid, ttrace->nr_events);
- printed += color_fprintf(fp, color, "%5.1f%%", ratio);
- printed += fprintf(fp, " ] %10.3f ms\n", ttrace->runtime_ms);
+ sc = &trace->syscalls.table[inode->i];
+ printed += fprintf(fp, "%24s %14s : ", "", sc->name);
+ printed += fprintf(fp, "%5" PRIu64 " %8.3f %8.3f",
+ n, min, max);
+ printed += fprintf(fp, " %8.3f %6.2f\n", avg, pct);
+ }
+
+ inode = intlist__next(inode);
}
+ printed += fprintf(fp, "\n\n");
+
return printed;
}
+/* struct used to pass data to per-thread function */
+struct summary_data {
+ FILE *fp;
+ struct trace *trace;
+ size_t printed;
+};
+
+static int trace__fprintf_one_thread(struct thread *thread, void *priv)
+{
+ struct summary_data *data = priv;
+ FILE *fp = data->fp;
+ size_t printed = data->printed;
+ struct trace *trace = data->trace;
+ struct thread_trace *ttrace = thread->priv;
+ const char *color;
+ double ratio;
+
+ if (ttrace == NULL)
+ return 0;
+
+ ratio = (double)ttrace->nr_events / trace->nr_events * 100.0;
+
+ color = PERF_COLOR_NORMAL;
+ if (ratio > 50.0)
+ color = PERF_COLOR_RED;
+ else if (ratio > 25.0)
+ color = PERF_COLOR_GREEN;
+ else if (ratio > 5.0)
+ color = PERF_COLOR_YELLOW;
+
+ printed += color_fprintf(fp, color, "%20s", thread->comm);
+ printed += fprintf(fp, " - %-5d :%11lu [", thread->tid, ttrace->nr_events);
+ printed += color_fprintf(fp, color, "%5.1f%%", ratio);
+ printed += fprintf(fp, " ] %10.3f ms\n", ttrace->runtime_ms);
+ printed += thread__dump_stats(ttrace, trace, fp);
+
+ data->printed += printed;
+
+ return 0;
+}
+
+static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
+{
+ struct summary_data data = {
+ .fp = fp,
+ .trace = trace
+ };
+ data.printed = trace__fprintf_threads_header(fp);
+
+ machine__for_each_thread(trace->host, trace__fprintf_one_thread, &data);
+
+ return data.printed;
+}
+
static int trace__set_duration(const struct option *opt, const char *str,
int unset __maybe_unused)
{
@@ -1185,10 +2041,15 @@
const char * const trace_usage[] = {
"perf trace [<options>] [<command>]",
"perf trace [<options>] -- <command> [<options>]",
+ "perf trace record [<options>] [<command>]",
+ "perf trace record [<options>] -- <command> [<options>]",
NULL
};
struct trace trace = {
- .audit_machine = audit_detect_machine(),
+ .audit = {
+ .machine = audit_detect_machine(),
+ .open_id = audit_name_to_syscall("open", trace.audit.machine),
+ },
.syscalls = {
. max = -1,
},
@@ -1203,10 +2064,14 @@
.mmap_pages = 1024,
},
.output = stdout,
+ .show_comm = true,
};
const char *output_name = NULL;
const char *ev_qualifier_str = NULL;
const struct option trace_options[] = {
+ OPT_BOOLEAN(0, "comm", &trace.show_comm,
+ "show the thread COMM next to its id"),
+ OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
OPT_STRING('e', "expr", &ev_qualifier_str, "expr",
"list of events to trace"),
OPT_STRING('o', "output", &output_name, "file", "output file name"),
@@ -1221,8 +2086,9 @@
"list of cpus to monitor"),
OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit,
"child tasks do not inherit counters"),
- OPT_UINTEGER('m', "mmap-pages", &trace.opts.mmap_pages,
- "number of mmap data pages"),
+ OPT_CALLBACK('m', "mmap-pages", &trace.opts.mmap_pages, "pages",
+ "number of mmap data pages",
+ perf_evlist__parse_mmap_pages),
OPT_STRING('u', "uid", &trace.opts.target.uid_str, "user",
"user to profile"),
OPT_CALLBACK(0, "duration", &trace, "float",
@@ -1230,11 +2096,18 @@
trace__set_duration),
OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"),
OPT_INCR('v', "verbose", &verbose, "be more verbose"),
+ OPT_BOOLEAN('T', "time", &trace.full_time,
+ "Show full timestamp, not time relative to first start"),
+ OPT_BOOLEAN(0, "summary", &trace.summary,
+ "Show syscall summary with statistics"),
OPT_END()
};
int err;
char bf[BUFSIZ];
+ if ((argc > 1) && (strcmp(argv[1], "record") == 0))
+ return trace__record(argc-2, &argv[2]);
+
argc = parse_options(argc, argv, trace_options, trace_usage, 0);
if (output_name != NULL) {
@@ -1282,9 +2155,6 @@
else
err = trace__run(&trace, argc, argv);
- if (trace.sched && !err)
- trace__fprintf_thread_summary(&trace, trace.output);
-
out_close:
if (output_name != NULL)
fclose(trace.output);
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 5f6f9b3..543aa95 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -23,7 +23,7 @@
endif
ifeq (${IS_X86_64}, 1)
RAW_ARCH := x86_64
- CFLAGS += -DARCH_X86_64
+ CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT
ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
endif
NO_PERF_REGS := 0
@@ -31,7 +31,7 @@
endif
ifeq ($(NO_PERF_REGS),0)
- CFLAGS += -DHAVE_PERF_REGS
+ CFLAGS += -DHAVE_PERF_REGS_SUPPORT
endif
ifeq ($(src-perf),)
@@ -51,7 +51,6 @@
# include ARCH specific config
-include $(src-perf)/arch/$(ARCH)/Makefile
-include $(src-perf)/config/feature-tests.mak
include $(src-perf)/config/utilities.mak
ifeq ($(call get-executable,$(FLEX)),)
@@ -67,10 +66,11 @@
CFLAGS += -Werror
endif
-ifeq ("$(origin DEBUG)", "command line")
- PERF_DEBUG = $(DEBUG)
+ifndef DEBUG
+ DEBUG := 0
endif
-ifndef PERF_DEBUG
+
+ifeq ($(DEBUG),0)
CFLAGS += -O6
endif
@@ -89,20 +89,125 @@
EXTLIBS = -lelf -lpthread -lrt -lm -ldl
-ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y)
+ifneq ($(OUTPUT),)
+ OUTPUT_FEATURES = $(OUTPUT)config/feature-checks/
+ $(shell mkdir -p $(OUTPUT_FEATURES))
+endif
+
+feature_check = $(eval $(feature_check_code))
+define feature_check_code
+ feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) LDFLAGS=$(LDFLAGS) -C config/feature-checks test-$1 >/dev/null 2>/dev/null && echo 1 || echo 0)
+endef
+
+feature_set = $(eval $(feature_set_code))
+define feature_set_code
+ feature-$(1) := 1
+endef
+
+#
+# Build the feature check binaries in parallel, ignore errors, ignore return value and suppress output:
+#
+
+#
+# Note that this is not a complete list of all feature tests, just
+# those that are typically built on a fully configured system.
+#
+# [ Feature tests not mentioned here have to be built explicitly in
+# the rule that uses them - an example for that is the 'bionic'
+# feature check. ]
+#
+CORE_FEATURE_TESTS = \
+ backtrace \
+ dwarf \
+ fortify-source \
+ glibc \
+ gtk2 \
+ gtk2-infobar \
+ libaudit \
+ libbfd \
+ libelf \
+ libelf-getphdrnum \
+ libelf-mmap \
+ libnuma \
+ libperl \
+ libpython \
+ libpython-version \
+ libslang \
+ libunwind \
+ on-exit \
+ stackprotector \
+ stackprotector-all
+
+#
+# So here we detect whether test-all was rebuilt, to be able
+# to skip the print-out of the long features list if the file
+# existed before and after it was built:
+#
+ifeq ($(wildcard $(OUTPUT)config/feature-checks/test-all),)
+ test-all-failed := 1
+else
+ test-all-failed := 0
+endif
+
+#
+# Special fast-path for the 'all features are available' case:
+#
+$(call feature_check,all,$(MSG))
+
+#
+# Just in case the build freshly failed, make sure we print the
+# feature matrix:
+#
+ifeq ($(feature-all), 0)
+ test-all-failed := 1
+endif
+
+ifeq ($(test-all-failed),1)
+ $(info )
+ $(info Auto-detecting system features:)
+endif
+
+ifeq ($(feature-all), 1)
+ #
+ # test-all.c passed - just set all the core feature flags to 1:
+ #
+ $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_set,$(feat)))
+else
+ $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) LDFLAGS=$(LDFLAGS) -i -j -C config/feature-checks $(CORE_FEATURE_TESTS) >/dev/null 2>&1)
+ $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_check,$(feat)))
+endif
+
+#
+# Print the result of the feature test:
+#
+feature_print = $(eval $(feature_print_code)) $(info $(MSG))
+
+define feature_print_code
+ ifeq ($(feature-$(1)), 1)
+ MSG = $(shell printf '...%30s: [ \033[32mon\033[m ]' $(1))
+ else
+ MSG = $(shell printf '...%30s: [ \033[31mOFF\033[m ]' $(1))
+ endif
+endef
+
+#
+# Only print out our features if we rebuilt the testcases or if a test failed:
+#
+ifeq ($(test-all-failed), 1)
+ $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_print,$(feat)))
+ $(info )
+endif
+
+ifeq ($(feature-stackprotector-all), 1)
CFLAGS += -fstack-protector-all
endif
-ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wstack-protector,-Wstack-protector),y)
+ifeq ($(feature-stackprotector), 1)
CFLAGS += -Wstack-protector
endif
-ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wvolatile-register-var,-Wvolatile-register-var),y)
- CFLAGS += -Wvolatile-register-var
-endif
-
-ifndef PERF_DEBUG
- ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -D_FORTIFY_SOURCE=2,-D_FORTIFY_SOURCE=2),y)
+ifeq ($(DEBUG),0)
+ ifeq ($(feature-fortify-source), 1)
CFLAGS += -D_FORTIFY_SOURCE=2
endif
endif
@@ -128,84 +233,74 @@
CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
ifndef NO_BIONIC
-ifeq ($(call try-cc,$(SOURCE_BIONIC),$(CFLAGS),bionic),y)
- BIONIC := 1
- EXTLIBS := $(filter-out -lrt,$(EXTLIBS))
- EXTLIBS := $(filter-out -lpthread,$(EXTLIBS))
+ $(feature_check,bionic)
+ ifeq ($(feature-bionic), 1)
+ BIONIC := 1
+ EXTLIBS := $(filter-out -lrt,$(EXTLIBS))
+ EXTLIBS := $(filter-out -lpthread,$(EXTLIBS))
+ endif
endif
-endif # NO_BIONIC
ifdef NO_LIBELF
NO_DWARF := 1
NO_DEMANGLE := 1
NO_LIBUNWIND := 1
else
-FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS)
-ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF),libelf),y)
- FLAGS_GLIBC=$(CFLAGS) $(LDFLAGS)
- ifeq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC),glibc),y)
- LIBC_SUPPORT := 1
- endif
- ifeq ($(BIONIC),1)
- LIBC_SUPPORT := 1
- endif
- ifeq ($(LIBC_SUPPORT),1)
- msg := $(warning No libelf found, disables 'probe' tool, please install elfutils-libelf-devel/libelf-dev);
+ ifeq ($(feature-libelf), 0)
+ ifeq ($(feature-glibc), 1)
+ LIBC_SUPPORT := 1
+ endif
+ ifeq ($(BIONIC),1)
+ LIBC_SUPPORT := 1
+ endif
+ ifeq ($(LIBC_SUPPORT),1)
+ msg := $(warning No libelf found, disables 'probe' tool, please install elfutils-libelf-devel/libelf-dev);
- NO_LIBELF := 1
- NO_DWARF := 1
- NO_DEMANGLE := 1
+ NO_LIBELF := 1
+ NO_DWARF := 1
+ NO_DEMANGLE := 1
+ else
+ msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
+ endif
else
- msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
- endif
-else
- # for linking with debug library, run like:
- # make DEBUG=1 LIBDW_DIR=/opt/libdw/
- ifdef LIBDW_DIR
- LIBDW_CFLAGS := -I$(LIBDW_DIR)/include
- LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
- endif
+ # for linking with debug library, run like:
+ # make DEBUG=1 LIBDW_DIR=/opt/libdw/
+ ifdef LIBDW_DIR
+ LIBDW_CFLAGS := -I$(LIBDW_DIR)/include
+ LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
+ endif
- FLAGS_DWARF=$(CFLAGS) $(LIBDW_CFLAGS) -ldw -lz -lelf $(LIBDW_LDFLAGS) $(LDFLAGS) $(EXTLIBS)
- ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF),libdw),y)
- msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
- NO_DWARF := 1
- endif # Dwarf support
-endif # SOURCE_LIBELF
+ ifneq ($(feature-dwarf), 1)
+ msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
+ NO_DWARF := 1
+ endif # Dwarf support
+ endif # libelf support
endif # NO_LIBELF
ifndef NO_LIBELF
-CFLAGS += -DLIBELF_SUPPORT
-FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS)
-ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y)
- CFLAGS += -DLIBELF_MMAP
-endif
-ifeq ($(call try-cc,$(SOURCE_ELF_GETPHDRNUM),$(FLAGS_LIBELF),-DHAVE_ELF_GETPHDRNUM),y)
- CFLAGS += -DHAVE_ELF_GETPHDRNUM
-endif
+ CFLAGS += -DHAVE_LIBELF_SUPPORT
-# include ARCH specific config
--include $(src-perf)/arch/$(ARCH)/Makefile
+ ifeq ($(feature-libelf-mmap), 1)
+ CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT
+ endif
-ifndef NO_DWARF
-ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
- msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
- NO_DWARF := 1
-else
- CFLAGS += -DDWARF_SUPPORT $(LIBDW_CFLAGS)
- LDFLAGS += $(LIBDW_LDFLAGS)
- EXTLIBS += -lelf -ldw
-endif # PERF_HAVE_DWARF_REGS
-endif # NO_DWARF
+ ifeq ($(feature-libelf-getphdrnum), 1)
+ CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT
+ endif
-endif # NO_LIBELF
+ # include ARCH specific config
+ -include $(src-perf)/arch/$(ARCH)/Makefile
-ifndef NO_LIBELF
-CFLAGS += -DLIBELF_SUPPORT
-FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS)
-ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y)
- CFLAGS += -DLIBELF_MMAP
-endif # try-cc
+ ifndef NO_DWARF
+ ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
+ msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
+ NO_DWARF := 1
+ else
+ CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS)
+ LDFLAGS += $(LIBDW_LDFLAGS)
+ EXTLIBS += -lelf -ldw
+ endif # PERF_HAVE_DWARF_REGS
+ endif # NO_DWARF
endif # NO_LIBELF
# There's only x86 (both 32 and 64) support for CFI unwind so far
@@ -214,34 +309,35 @@
endif
ifndef NO_LIBUNWIND
-# for linking with debug library, run like:
-# make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
-ifdef LIBUNWIND_DIR
- LIBUNWIND_CFLAGS := -I$(LIBUNWIND_DIR)/include
- LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib
+ #
+ # For linking with debug library, run like:
+ #
+ # make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
+ #
+ ifdef LIBUNWIND_DIR
+ LIBUNWIND_CFLAGS := -I$(LIBUNWIND_DIR)/include
+ LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib
+ endif
+
+ ifneq ($(feature-libunwind), 1)
+ msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 0.99);
+ NO_LIBUNWIND := 1
+ endif
endif
-FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(CFLAGS) $(LIBUNWIND_LDFLAGS) $(LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS)
-ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND),libunwind),y)
- msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 0.99);
- NO_LIBUNWIND := 1
-endif # Libunwind support
-endif # NO_LIBUNWIND
-
ifndef NO_LIBUNWIND
- CFLAGS += -DLIBUNWIND_SUPPORT
+ CFLAGS += -DHAVE_LIBUNWIND_SUPPORT
EXTLIBS += $(LIBUNWIND_LIBS)
CFLAGS += $(LIBUNWIND_CFLAGS)
LDFLAGS += $(LIBUNWIND_LDFLAGS)
-endif # NO_LIBUNWIND
+endif
ifndef NO_LIBAUDIT
- FLAGS_LIBAUDIT = $(CFLAGS) $(LDFLAGS) -laudit
- ifneq ($(call try-cc,$(SOURCE_LIBAUDIT),$(FLAGS_LIBAUDIT),libaudit),y)
+ ifneq ($(feature-libaudit), 1)
msg := $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev);
NO_LIBAUDIT := 1
else
- CFLAGS += -DLIBAUDIT_SUPPORT
+ CFLAGS += -DHAVE_LIBAUDIT_SUPPORT
EXTLIBS += -laudit
endif
endif
@@ -251,30 +347,30 @@
endif
ifndef NO_SLANG
- FLAGS_SLANG=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -I/usr/include/slang -lslang
- ifneq ($(call try-cc,$(SOURCE_SLANG),$(FLAGS_SLANG),libslang),y)
+ ifneq ($(feature-libslang), 1)
msg := $(warning slang not found, disables TUI support. Please install slang-devel or libslang-dev);
NO_SLANG := 1
else
# Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
CFLAGS += -I/usr/include/slang
- CFLAGS += -DSLANG_SUPPORT
+ CFLAGS += -DHAVE_SLANG_SUPPORT
EXTLIBS += -lslang
endif
endif
ifndef NO_GTK2
FLAGS_GTK2=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
- ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2),gtk2),y)
+ ifneq ($(feature-gtk2), 1)
msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev);
NO_GTK2 := 1
else
- ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2),-DHAVE_GTK_INFO_BAR),y)
- CFLAGS += -DHAVE_GTK_INFO_BAR
+ ifeq ($(feature-gtk2-infobar), 1)
+ GTK_CFLAGS := -DHAVE_GTK_INFO_BAR_SUPPORT
endif
- CFLAGS += -DGTK2_SUPPORT
- CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null)
- EXTLIBS += $(shell pkg-config --libs gtk+-2.0 2>/dev/null)
+ CFLAGS += -DHAVE_GTK2_SUPPORT
+ GTK_CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null)
+ GTK_LIBS := $(shell pkg-config --libs gtk+-2.0 2>/dev/null)
+ EXTLIBS += -ldl
endif
endif
@@ -290,7 +386,7 @@
PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
- ifneq ($(call try-cc,$(SOURCE_PERL_EMBED),$(FLAGS_PERL_EMBED),perl),y)
+ ifneq ($(feature-libperl), 1)
CFLAGS += -DNO_LIBPERL
NO_LIBPERL := 1
else
@@ -335,11 +431,11 @@
PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
- ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED),python),y)
+ ifneq ($(feature-libpython), 1)
$(call disable-python,Python.h (for Python 2.x))
else
- ifneq ($(call try-cc,$(SOURCE_PYTHON_VERSION),$(FLAGS_PYTHON_EMBED),python version),y)
+ ifneq ($(feature-libpython-version), 1)
$(warning Python 3 is not yet supported; please set)
$(warning PYTHON and/or PYTHON_CONFIG appropriately.)
$(warning If you also have Python 2 installed, then)
@@ -362,33 +458,30 @@
endif
endif
+ifeq ($(feature-libbfd), 1)
+ EXTLIBS += -lbfd
+endif
+
ifdef NO_DEMANGLE
CFLAGS += -DNO_DEMANGLE
else
- ifdef HAVE_CPLUS_DEMANGLE
+ ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
EXTLIBS += -liberty
- CFLAGS += -DHAVE_CPLUS_DEMANGLE
+ CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT
else
- FLAGS_BFD=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -DPACKAGE='perf' -lbfd
- has_bfd := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD),libbfd)
- ifeq ($(has_bfd),y)
- EXTLIBS += -lbfd
- else
- FLAGS_BFD_IBERTY=$(FLAGS_BFD) -liberty
- has_bfd_iberty := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY),liberty)
- ifeq ($(has_bfd_iberty),y)
+ ifneq ($(feature-libbfd), 1)
+ $(feature_check,liberty)
+ ifeq ($(feature-liberty), 1)
EXTLIBS += -lbfd -liberty
else
- FLAGS_BFD_IBERTY_Z=$(FLAGS_BFD_IBERTY) -lz
- has_bfd_iberty_z := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY_Z),libz)
- ifeq ($(has_bfd_iberty_z),y)
+ $(feature_check,liberty-z)
+ ifeq ($(feature-liberty-z), 1)
EXTLIBS += -lbfd -liberty -lz
else
- FLAGS_CPLUS_DEMANGLE=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -liberty
- has_cplus_demangle := $(call try-cc,$(SOURCE_CPLUS_DEMANGLE),$(FLAGS_CPLUS_DEMANGLE),demangle)
- ifeq ($(has_cplus_demangle),y)
+ $(feature_check,cplus-demangle)
+ ifeq ($(feature-cplus-demangle), 1)
EXTLIBS += -liberty
- CFLAGS += -DHAVE_CPLUS_DEMANGLE
+ CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT
else
msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling)
CFLAGS += -DNO_DEMANGLE
@@ -399,31 +492,28 @@
endif
endif
-ifndef NO_STRLCPY
- ifeq ($(call try-cc,$(SOURCE_STRLCPY),,-DHAVE_STRLCPY),y)
- CFLAGS += -DHAVE_STRLCPY
- endif
+ifneq ($(filter -lbfd,$(EXTLIBS)),)
+ CFLAGS += -DHAVE_LIBBFD_SUPPORT
endif
ifndef NO_ON_EXIT
- ifeq ($(call try-cc,$(SOURCE_ON_EXIT),,-DHAVE_ON_EXIT),y)
- CFLAGS += -DHAVE_ON_EXIT
+ ifeq ($(feature-on-exit), 1)
+ CFLAGS += -DHAVE_ON_EXIT_SUPPORT
endif
endif
ifndef NO_BACKTRACE
- ifeq ($(call try-cc,$(SOURCE_BACKTRACE),,-DBACKTRACE_SUPPORT),y)
- CFLAGS += -DBACKTRACE_SUPPORT
+ ifeq ($(feature-backtrace), 1)
+ CFLAGS += -DHAVE_BACKTRACE_SUPPORT
endif
endif
ifndef NO_LIBNUMA
- FLAGS_LIBNUMA = $(CFLAGS) $(LDFLAGS) -lnuma
- ifneq ($(call try-cc,$(SOURCE_LIBNUMA),$(FLAGS_LIBNUMA),libnuma),y)
+ ifeq ($(feature-libnuma), 0)
msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numa-libs-devel or libnuma-dev);
NO_LIBNUMA := 1
else
- CFLAGS += -DLIBNUMA_SUPPORT
+ CFLAGS += -DHAVE_LIBNUMA_SUPPORT
EXTLIBS += -lnuma
endif
endif
@@ -459,7 +549,12 @@
sysconfdir = $(prefix)/etc
ETC_PERFCONFIG = etc/perfconfig
endif
+ifeq ($(IS_X86_64),1)
+lib = lib64
+else
lib = lib
+endif
+libdir = $(prefix)/$(lib)
# Shell quote (do not use $(call) to accommodate ancient setups);
ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG))
@@ -472,6 +567,7 @@
htmldir_SQ = $(subst ','\'',$(htmldir))
prefix_SQ = $(subst ','\'',$(prefix))
sysconfdir_SQ = $(subst ','\'',$(sysconfdir))
+libdir_SQ = $(subst ','\'',$(libdir))
ifneq ($(filter /%,$(firstword $(perfexecdir))),)
perfexec_instdir = $(perfexecdir)
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
new file mode 100644
index 0000000..452b67c
--- /dev/null
+++ b/tools/perf/config/feature-checks/Makefile
@@ -0,0 +1,144 @@
+
+FILES= \
+ test-all \
+ test-backtrace \
+ test-bionic \
+ test-dwarf \
+ test-fortify-source \
+ test-glibc \
+ test-gtk2 \
+ test-gtk2-infobar \
+ test-hello \
+ test-libaudit \
+ test-libbfd \
+ test-liberty \
+ test-liberty-z \
+ test-cplus-demangle \
+ test-libelf \
+ test-libelf-getphdrnum \
+ test-libelf-mmap \
+ test-libnuma \
+ test-libperl \
+ test-libpython \
+ test-libpython-version \
+ test-libslang \
+ test-libunwind \
+ test-on-exit \
+ test-stackprotector-all \
+ test-stackprotector
+
+CC := $(CC) -MD
+
+all: $(FILES)
+
+BUILD = $(CC) $(LDFLAGS) -o $(OUTPUT)$@ $@.c
+
+###############################
+
+test-all:
+ $(BUILD) -Werror -fstack-protector -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lunwind -lunwind-x86_64 -lelf -laudit -I/usr/include/slang -lslang $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
+
+test-hello:
+ $(BUILD)
+
+test-stackprotector-all:
+ $(BUILD) -Werror -fstack-protector-all
+
+test-stackprotector:
+ $(BUILD) -Werror -fstack-protector -Wstack-protector
+
+test-fortify-source:
+ $(BUILD) -O2 -Werror -D_FORTIFY_SOURCE=2
+
+test-bionic:
+ $(BUILD)
+
+test-libelf:
+ $(BUILD) -lelf
+
+test-glibc:
+ $(BUILD)
+
+test-dwarf:
+ $(BUILD) -ldw
+
+test-libelf-mmap:
+ $(BUILD) -lelf
+
+test-libelf-getphdrnum:
+ $(BUILD) -lelf
+
+test-libnuma:
+ $(BUILD) -lnuma
+
+test-libunwind:
+ $(BUILD) -lunwind -lunwind-x86_64 -lelf
+
+test-libaudit:
+ $(BUILD) -laudit
+
+test-libslang:
+ $(BUILD) -I/usr/include/slang -lslang
+
+test-gtk2:
+ $(BUILD) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
+
+test-gtk2-infobar:
+ $(BUILD) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
+
+grep-libs = $(filter -l%,$(1))
+strip-libs = $(filter-out -l%,$(1))
+
+PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null)
+PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
+PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
+PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
+FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
+
+test-libperl:
+ $(BUILD) $(FLAGS_PERL_EMBED)
+
+override PYTHON := python
+override PYTHON_CONFIG := python-config
+
+escape-for-shell-sq = $(subst ','\'',$(1))
+shell-sq = '$(escape-for-shell-sq)'
+
+PYTHON_CONFIG_SQ = $(call shell-sq,$(PYTHON_CONFIG))
+
+PYTHON_EMBED_LDOPTS = $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+PYTHON_EMBED_LDFLAGS = $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
+PYTHON_EMBED_LIBADD = $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
+PYTHON_EMBED_CCOPTS = $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+FLAGS_PYTHON_EMBED = $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
+
+test-libpython:
+ $(BUILD) $(FLAGS_PYTHON_EMBED)
+
+test-libpython-version:
+ $(BUILD) $(FLAGS_PYTHON_EMBED)
+
+test-libbfd:
+ $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
+
+test-liberty:
+ $(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty
+
+test-liberty-z:
+ $(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty -lz
+
+test-cplus-demangle:
+ $(BUILD) -liberty
+
+test-on-exit:
+ $(BUILD)
+
+test-backtrace:
+ $(BUILD)
+
+-include *.d
+
+###############################
+
+clean:
+ rm -f $(FILES) *.d
diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c
new file mode 100644
index 0000000..50d4318
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-all.c
@@ -0,0 +1,106 @@
+/*
+ * test-all.c: Try to build all the main testcases at once.
+ *
+ * A well-configured system will have all the prereqs installed, so we can speed
+ * up auto-detection on such systems.
+ */
+
+/*
+ * Quirk: Python and Perl headers cannot be in arbitrary places, so keep
+ * these 3 testcases at the top:
+ */
+#define main main_test_libpython
+# include "test-libpython.c"
+#undef main
+
+#define main main_test_libpython_version
+# include "test-libpython-version.c"
+#undef main
+
+#define main main_test_libperl
+# include "test-libperl.c"
+#undef main
+
+#define main main_test_hello
+# include "test-hello.c"
+#undef main
+
+#define main main_test_libelf
+# include "test-libelf.c"
+#undef main
+
+#define main main_test_libelf_mmap
+# include "test-libelf-mmap.c"
+#undef main
+
+#define main main_test_glibc
+# include "test-glibc.c"
+#undef main
+
+#define main main_test_dwarf
+# include "test-dwarf.c"
+#undef main
+
+#define main main_test_libelf_getphdrnum
+# include "test-libelf-getphdrnum.c"
+#undef main
+
+#define main main_test_libunwind
+# include "test-libunwind.c"
+#undef main
+
+#define main main_test_libaudit
+# include "test-libaudit.c"
+#undef main
+
+#define main main_test_libslang
+# include "test-libslang.c"
+#undef main
+
+#define main main_test_gtk2
+# include "test-gtk2.c"
+#undef main
+
+#define main main_test_gtk2_infobar
+# include "test-gtk2-infobar.c"
+#undef main
+
+#define main main_test_libbfd
+# include "test-libbfd.c"
+#undef main
+
+#define main main_test_on_exit
+# include "test-on-exit.c"
+#undef main
+
+#define main main_test_backtrace
+# include "test-backtrace.c"
+#undef main
+
+#define main main_test_libnuma
+# include "test-libnuma.c"
+#undef main
+
+int main(int argc, char *argv[])
+{
+ main_test_libpython();
+ main_test_libpython_version();
+ main_test_libperl();
+ main_test_hello();
+ main_test_libelf();
+ main_test_libelf_mmap();
+ main_test_glibc();
+ main_test_dwarf();
+ main_test_libelf_getphdrnum();
+ main_test_libunwind();
+ main_test_libaudit();
+ main_test_libslang();
+ main_test_gtk2(argc, argv);
+ main_test_gtk2_infobar(argc, argv);
+ main_test_libbfd();
+ main_test_on_exit();
+ main_test_backtrace();
+ main_test_libnuma();
+
+ return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-backtrace.c b/tools/perf/config/feature-checks/test-backtrace.c
new file mode 100644
index 0000000..7124aa1
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-backtrace.c
@@ -0,0 +1,13 @@
+#include <execinfo.h>
+#include <stdio.h>
+
+int main(void)
+{
+ void *backtrace_fns[10];
+ size_t entries;
+
+ entries = backtrace(backtrace_fns, 10);
+ backtrace_symbols_fd(backtrace_fns, entries, 1);
+
+ return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-bionic.c b/tools/perf/config/feature-checks/test-bionic.c
new file mode 100644
index 0000000..eac24e9
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-bionic.c
@@ -0,0 +1,6 @@
+#include <android/api-level.h>
+
+int main(void)
+{
+ return __ANDROID_API__;
+}
diff --git a/tools/perf/config/feature-checks/test-cplus-demangle.c b/tools/perf/config/feature-checks/test-cplus-demangle.c
new file mode 100644
index 0000000..610c686
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-cplus-demangle.c
@@ -0,0 +1,14 @@
+extern int printf(const char *format, ...);
+extern char *cplus_demangle(const char *, int);
+
+int main(void)
+{
+ char symbol[4096] = "FieldName__9ClassNameFd";
+ char *tmp;
+
+ tmp = cplus_demangle(symbol, 0);
+
+ printf("demangled symbol: {%s}\n", tmp);
+
+ return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-dwarf.c b/tools/perf/config/feature-checks/test-dwarf.c
new file mode 100644
index 0000000..3fc1801
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-dwarf.c
@@ -0,0 +1,10 @@
+#include <dwarf.h>
+#include <elfutils/libdw.h>
+#include <elfutils/version.h>
+
+int main(void)
+{
+ Dwarf *dbg = dwarf_begin(0, DWARF_C_READ);
+
+ return (long)dbg;
+}
diff --git a/tools/perf/config/feature-checks/test-fortify-source.c b/tools/perf/config/feature-checks/test-fortify-source.c
new file mode 100644
index 0000000..c9f398d
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-fortify-source.c
@@ -0,0 +1,6 @@
+#include <stdio.h>
+
+int main(void)
+{
+ return puts("hi");
+}
diff --git a/tools/perf/config/feature-checks/test-glibc.c b/tools/perf/config/feature-checks/test-glibc.c
new file mode 100644
index 0000000..b082034
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-glibc.c
@@ -0,0 +1,8 @@
+#include <gnu/libc-version.h>
+
+int main(void)
+{
+ const char *version = gnu_get_libc_version();
+
+ return (long)version;
+}
diff --git a/tools/perf/config/feature-checks/test-gtk2-infobar.c b/tools/perf/config/feature-checks/test-gtk2-infobar.c
new file mode 100644
index 0000000..397b464
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-gtk2-infobar.c
@@ -0,0 +1,11 @@
+#pragma GCC diagnostic ignored "-Wstrict-prototypes"
+#include <gtk/gtk.h>
+#pragma GCC diagnostic error "-Wstrict-prototypes"
+
+int main(int argc, char *argv[])
+{
+ gtk_init(&argc, &argv);
+ gtk_info_bar_new();
+
+ return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-gtk2.c b/tools/perf/config/feature-checks/test-gtk2.c
new file mode 100644
index 0000000..6bd80e5
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-gtk2.c
@@ -0,0 +1,10 @@
+#pragma GCC diagnostic ignored "-Wstrict-prototypes"
+#include <gtk/gtk.h>
+#pragma GCC diagnostic error "-Wstrict-prototypes"
+
+int main(int argc, char *argv[])
+{
+ gtk_init(&argc, &argv);
+
+ return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-hello.c b/tools/perf/config/feature-checks/test-hello.c
new file mode 100644
index 0000000..c9f398d
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-hello.c
@@ -0,0 +1,6 @@
+#include <stdio.h>
+
+int main(void)
+{
+ return puts("hi");
+}
diff --git a/tools/perf/config/feature-checks/test-libaudit.c b/tools/perf/config/feature-checks/test-libaudit.c
new file mode 100644
index 0000000..afc019f0
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libaudit.c
@@ -0,0 +1,10 @@
+#include <libaudit.h>
+
+extern int printf(const char *format, ...);
+
+int main(void)
+{
+ printf("error message: %s\n", audit_errno_to_name(0));
+
+ return audit_open();
+}
diff --git a/tools/perf/config/feature-checks/test-libbfd.c b/tools/perf/config/feature-checks/test-libbfd.c
new file mode 100644
index 0000000..2405990
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libbfd.c
@@ -0,0 +1,15 @@
+#include <bfd.h>
+
+extern int printf(const char *format, ...);
+
+int main(void)
+{
+ char symbol[4096] = "FieldName__9ClassNameFd";
+ char *tmp;
+
+ tmp = bfd_demangle(0, symbol, 0);
+
+ printf("demangled symbol: {%s}\n", tmp);
+
+ return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-libelf-getphdrnum.c b/tools/perf/config/feature-checks/test-libelf-getphdrnum.c
new file mode 100644
index 0000000..d710459
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libelf-getphdrnum.c
@@ -0,0 +1,8 @@
+#include <libelf.h>
+
+int main(void)
+{
+ size_t dst;
+
+ return elf_getphdrnum(0, &dst);
+}
diff --git a/tools/perf/config/feature-checks/test-libelf-mmap.c b/tools/perf/config/feature-checks/test-libelf-mmap.c
new file mode 100644
index 0000000..564427d
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libelf-mmap.c
@@ -0,0 +1,8 @@
+#include <libelf.h>
+
+int main(void)
+{
+ Elf *elf = elf_begin(0, ELF_C_READ_MMAP, 0);
+
+ return (long)elf;
+}
diff --git a/tools/perf/config/feature-checks/test-libelf.c b/tools/perf/config/feature-checks/test-libelf.c
new file mode 100644
index 0000000..08db322
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libelf.c
@@ -0,0 +1,8 @@
+#include <libelf.h>
+
+int main(void)
+{
+ Elf *elf = elf_begin(0, ELF_C_READ, 0);
+
+ return (long)elf;
+}
diff --git a/tools/perf/config/feature-checks/test-libnuma.c b/tools/perf/config/feature-checks/test-libnuma.c
new file mode 100644
index 0000000..4763d9c
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libnuma.c
@@ -0,0 +1,9 @@
+#include <numa.h>
+#include <numaif.h>
+
+int main(void)
+{
+ numa_available();
+
+ return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-libperl.c b/tools/perf/config/feature-checks/test-libperl.c
new file mode 100644
index 0000000..8871f6a
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libperl.c
@@ -0,0 +1,9 @@
+#include <EXTERN.h>
+#include <perl.h>
+
+int main(void)
+{
+ perl_alloc();
+
+ return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-libpython-version.c b/tools/perf/config/feature-checks/test-libpython-version.c
new file mode 100644
index 0000000..facea12
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libpython-version.c
@@ -0,0 +1,10 @@
+#include <Python.h>
+
+#if PY_VERSION_HEX >= 0x03000000
+ #error
+#endif
+
+int main(void)
+{
+ return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-libpython.c b/tools/perf/config/feature-checks/test-libpython.c
new file mode 100644
index 0000000..b24b28a
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libpython.c
@@ -0,0 +1,8 @@
+#include <Python.h>
+
+int main(void)
+{
+ Py_Initialize();
+
+ return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-libslang.c b/tools/perf/config/feature-checks/test-libslang.c
new file mode 100644
index 0000000..22ff22e
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libslang.c
@@ -0,0 +1,6 @@
+#include <slang.h>
+
+int main(void)
+{
+ return SLsmg_init_smg();
+}
diff --git a/tools/perf/config/feature-checks/test-libunwind.c b/tools/perf/config/feature-checks/test-libunwind.c
new file mode 100644
index 0000000..43b9369
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libunwind.c
@@ -0,0 +1,27 @@
+#include <libunwind.h>
+#include <stdlib.h>
+
+extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
+ unw_word_t ip,
+ unw_dyn_info_t *di,
+ unw_proc_info_t *pi,
+ int need_unwind_info, void *arg);
+
+
+#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
+
+static unw_accessors_t accessors;
+
+int main(void)
+{
+ unw_addr_space_t addr_space;
+
+ addr_space = unw_create_addr_space(&accessors, 0);
+ if (addr_space)
+ return 0;
+
+ unw_init_remote(NULL, addr_space, NULL);
+ dwarf_search_unwind_table(addr_space, 0, NULL, NULL, 0, NULL);
+
+ return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-on-exit.c b/tools/perf/config/feature-checks/test-on-exit.c
new file mode 100644
index 0000000..8e88b16
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-on-exit.c
@@ -0,0 +1,16 @@
+#include <stdio.h>
+#include <stdlib.h>
+
+static void exit_fn(int status, void *__data)
+{
+ printf("exit status: %d, data: %d\n", status, *(int *)__data);
+}
+
+static int data = 123;
+
+int main(void)
+{
+ on_exit(exit_fn, &data);
+
+ return 321;
+}
diff --git a/tools/perf/config/feature-checks/test-stackprotector-all.c b/tools/perf/config/feature-checks/test-stackprotector-all.c
new file mode 100644
index 0000000..c9f398d
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-stackprotector-all.c
@@ -0,0 +1,6 @@
+#include <stdio.h>
+
+int main(void)
+{
+ return puts("hi");
+}
diff --git a/tools/perf/config/feature-checks/test-stackprotector.c b/tools/perf/config/feature-checks/test-stackprotector.c
new file mode 100644
index 0000000..c9f398d
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-stackprotector.c
@@ -0,0 +1,6 @@
+#include <stdio.h>
+
+int main(void)
+{
+ return puts("hi");
+}
diff --git a/tools/perf/config/feature-checks/test-volatile-register-var.c b/tools/perf/config/feature-checks/test-volatile-register-var.c
new file mode 100644
index 0000000..c9f398d
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-volatile-register-var.c
@@ -0,0 +1,6 @@
+#include <stdio.h>
+
+int main(void)
+{
+ return puts("hi");
+}
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
deleted file mode 100644
index f793057..0000000
--- a/tools/perf/config/feature-tests.mak
+++ /dev/null
@@ -1,246 +0,0 @@
-define SOURCE_HELLO
-#include <stdio.h>
-int main(void)
-{
- return puts(\"hi\");
-}
-endef
-
-ifndef NO_DWARF
-define SOURCE_DWARF
-#include <dwarf.h>
-#include <elfutils/libdw.h>
-#include <elfutils/version.h>
-#ifndef _ELFUTILS_PREREQ
-#error
-#endif
-
-int main(void)
-{
- Dwarf *dbg = dwarf_begin(0, DWARF_C_READ);
- return (long)dbg;
-}
-endef
-endif
-
-define SOURCE_LIBELF
-#include <libelf.h>
-
-int main(void)
-{
- Elf *elf = elf_begin(0, ELF_C_READ, 0);
- return (long)elf;
-}
-endef
-
-define SOURCE_GLIBC
-#include <gnu/libc-version.h>
-
-int main(void)
-{
- const char *version = gnu_get_libc_version();
- return (long)version;
-}
-endef
-
-define SOURCE_BIONIC
-#include <android/api-level.h>
-
-int main(void)
-{
- return __ANDROID_API__;
-}
-endef
-
-define SOURCE_ELF_MMAP
-#include <libelf.h>
-int main(void)
-{
- Elf *elf = elf_begin(0, ELF_C_READ_MMAP, 0);
- return (long)elf;
-}
-endef
-
-define SOURCE_ELF_GETPHDRNUM
-#include <libelf.h>
-int main(void)
-{
- size_t dst;
- return elf_getphdrnum(0, &dst);
-}
-endef
-
-ifndef NO_SLANG
-define SOURCE_SLANG
-#include <slang.h>
-
-int main(void)
-{
- return SLsmg_init_smg();
-}
-endef
-endif
-
-ifndef NO_GTK2
-define SOURCE_GTK2
-#pragma GCC diagnostic ignored \"-Wstrict-prototypes\"
-#include <gtk/gtk.h>
-#pragma GCC diagnostic error \"-Wstrict-prototypes\"
-
-int main(int argc, char *argv[])
-{
- gtk_init(&argc, &argv);
-
- return 0;
-}
-endef
-
-define SOURCE_GTK2_INFOBAR
-#pragma GCC diagnostic ignored \"-Wstrict-prototypes\"
-#include <gtk/gtk.h>
-#pragma GCC diagnostic error \"-Wstrict-prototypes\"
-
-int main(void)
-{
- gtk_info_bar_new();
-
- return 0;
-}
-endef
-endif
-
-ifndef NO_LIBPERL
-define SOURCE_PERL_EMBED
-#include <EXTERN.h>
-#include <perl.h>
-
-int main(void)
-{
-perl_alloc();
-return 0;
-}
-endef
-endif
-
-ifndef NO_LIBPYTHON
-define SOURCE_PYTHON_VERSION
-#include <Python.h>
-#if PY_VERSION_HEX >= 0x03000000
- #error
-#endif
-int main(void)
-{
- return 0;
-}
-endef
-define SOURCE_PYTHON_EMBED
-#include <Python.h>
-int main(void)
-{
- Py_Initialize();
- return 0;
-}
-endef
-endif
-
-define SOURCE_BFD
-#include <bfd.h>
-
-int main(void)
-{
- bfd_demangle(0, 0, 0);
- return 0;
-}
-endef
-
-define SOURCE_CPLUS_DEMANGLE
-extern char *cplus_demangle(const char *, int);
-
-int main(void)
-{
- cplus_demangle(0, 0);
- return 0;
-}
-endef
-
-define SOURCE_STRLCPY
-#include <stdlib.h>
-extern size_t strlcpy(char *dest, const char *src, size_t size);
-
-int main(void)
-{
- strlcpy(NULL, NULL, 0);
- return 0;
-}
-endef
-
-ifndef NO_LIBUNWIND
-define SOURCE_LIBUNWIND
-#include <libunwind.h>
-#include <stdlib.h>
-
-extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
- unw_word_t ip,
- unw_dyn_info_t *di,
- unw_proc_info_t *pi,
- int need_unwind_info, void *arg);
-
-
-#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
-
-int main(void)
-{
- unw_addr_space_t addr_space;
- addr_space = unw_create_addr_space(NULL, 0);
- unw_init_remote(NULL, addr_space, NULL);
- dwarf_search_unwind_table(addr_space, 0, NULL, NULL, 0, NULL);
- return 0;
-}
-endef
-endif
-
-ifndef NO_BACKTRACE
-define SOURCE_BACKTRACE
-#include <execinfo.h>
-#include <stdio.h>
-
-int main(void)
-{
- backtrace(NULL, 0);
- backtrace_symbols(NULL, 0);
- return 0;
-}
-endef
-endif
-
-ifndef NO_LIBAUDIT
-define SOURCE_LIBAUDIT
-#include <libaudit.h>
-
-int main(void)
-{
- printf(\"error message: %s\", audit_errno_to_name(0));
- return audit_open();
-}
-endef
-endif
-
-define SOURCE_ON_EXIT
-#include <stdio.h>
-
-int main(void)
-{
- return on_exit(NULL, NULL);
-}
-endef
-
-define SOURCE_LIBNUMA
-#include <numa.h>
-#include <numaif.h>
-
-int main(void)
-{
- numa_available();
- return 0;
-}
-endef
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
index 94d2d4f..f168deb 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/perf/config/utilities.mak
@@ -179,16 +179,9 @@
_gea_warn = $(warning The path '$(1)' is not executable.)
_gea_err = $(if $(1),$(error Please set '$(1)' appropriately))
-# try-cc
-# Usage: option = $(call try-cc, source-to-build, cc-options, msg)
-ifneq ($(V),1)
-TRY_CC_OUTPUT= > /dev/null 2>&1
+ifneq ($(findstring $(MAKEFLAGS),s),s)
+ ifneq ($(V),1)
+ QUIET_CLEAN = @printf ' CLEAN %s\n' $1;
+ QUIET_INSTALL = @printf ' INSTALL %s\n' $1;
+ endif
endif
-TRY_CC_MSG=echo " CHK $(3)" 1>&2;
-
-try-cc = $(shell sh -c \
- 'TMP="$(OUTPUT)$(TMPOUT).$$$$"; \
- $(TRY_CC_MSG) \
- echo "$(1)" | \
- $(CC) -x c - $(2) -o "$$TMP" $(TRY_CC_OUTPUT) && echo y; \
- rm -f "$$TMP"')
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 85e1aed..8b38b4e 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -49,14 +49,14 @@
{ "version", cmd_version, 0 },
{ "script", cmd_script, 0 },
{ "sched", cmd_sched, 0 },
-#ifdef LIBELF_SUPPORT
+#ifdef HAVE_LIBELF_SUPPORT
{ "probe", cmd_probe, 0 },
#endif
{ "kmem", cmd_kmem, 0 },
{ "lock", cmd_lock, 0 },
{ "kvm", cmd_kvm, 0 },
{ "test", cmd_test, 0 },
-#ifdef LIBAUDIT_SUPPORT
+#ifdef HAVE_LIBAUDIT_SUPPORT
{ "trace", cmd_trace, 0 },
#endif
{ "inject", cmd_inject, 0 },
@@ -456,6 +456,7 @@
{
const char *cmd;
+ /* The page_size is placed in util object. */
page_size = sysconf(_SC_PAGE_SIZE);
cmd = perf_extract_argv0_path(argv[0]);
@@ -480,7 +481,14 @@
fprintf(stderr, "cannot handle %s internally", cmd);
goto out;
}
-
+#ifdef HAVE_LIBAUDIT_SUPPORT
+ if (!prefixcmp(cmd, "trace")) {
+ set_buildid_dir();
+ setup_path();
+ argv[0] = "trace";
+ return cmd_trace(argc, argv, NULL);
+ }
+#endif
/* Look for flags.. */
argv++;
argc--;
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index cf20187..f61c230 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -182,7 +182,9 @@
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 {
@@ -218,7 +220,6 @@
bool no_delay;
bool no_inherit;
bool no_samples;
- bool pipe_output;
bool raw_samples;
bool sample_address;
bool sample_weight;
@@ -231,6 +232,7 @@
u64 default_interval;
u64 user_interval;
u16 stack_dump_size;
+ bool sample_transaction;
};
#endif
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index dffe055..9cc81a3 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -35,6 +35,7 @@
if (size != write(fd, buf, size))
templ = NULL;
+ free(buf);
close(fd);
return templ;
}
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 4228ffc..b51abcb 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -222,7 +222,8 @@
&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;
@@ -244,7 +245,8 @@
&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;
@@ -465,7 +467,7 @@
goto out;
list_for_each_entry(evsel, &evlist->entries, node) {
- hists__collapse_resort(&evsel->hists);
+ hists__collapse_resort(&evsel->hists, NULL);
if (verbose > 2)
print_hists(&evsel->hists);
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 7923b06..93a62b0 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -45,7 +45,7 @@
};
cpu_set_t cpu_mask;
size_t cpu_mask_size = sizeof(cpu_mask);
- struct perf_evlist *evlist = perf_evlist__new();
+ struct perf_evlist *evlist = perf_evlist__new_default();
struct perf_evsel *evsel;
struct perf_sample sample;
const char *cmd = "sleep";
@@ -66,16 +66,6 @@
}
/*
- * We need at least one evsel in the evlist, use the default
- * one: "cycles".
- */
- err = perf_evlist__add_default(evlist);
- if (err < 0) {
- pr_debug("Not enough memory to create evsel\n");
- goto out_delete_evlist;
- }
-
- /*
* Create maps of threads and cpus to monitor. In this case
* we start with all threads and cpus (-1, -1) but then in
* perf_evlist__prepare_workload we'll fill in the only thread
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 77f598d..61c9da2 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -275,8 +275,8 @@
* Fail the test if it has not been updated when new sample format bits
* were added.
*/
- if (PERF_SAMPLE_MAX > PERF_SAMPLE_IDENTIFIER << 1) {
- pr_debug("sample format has changed - test needs updating\n");
+ if (PERF_SAMPLE_MAX > PERF_SAMPLE_TRANSACTION << 1) {
+ pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
return -1;
}
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index a3e6487..c33d95f 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -37,20 +37,11 @@
signal(SIGCHLD, sig_handler);
signal(SIGUSR1, sig_handler);
- evlist = perf_evlist__new();
+ evlist = perf_evlist__new_default();
if (evlist == NULL) {
- pr_debug("perf_evlist__new\n");
+ pr_debug("perf_evlist__new_default\n");
return -1;
}
- /*
- * We need at least one evsel in the evlist, use the default
- * one: "cycles".
- */
- err = perf_evlist__add_default(evlist);
- if (err < 0) {
- pr_debug("Not enough memory to create evsel\n");
- goto out_free_evlist;
- }
/*
* Create maps of threads and cpus to monitor. In this case
@@ -117,7 +108,6 @@
perf_evlist__close(evlist);
out_delete_maps:
perf_evlist__delete_maps(evlist);
-out_free_evlist:
perf_evlist__delete(evlist);
return err;
}
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 08545ae..f0697a3 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -442,35 +442,37 @@
{
struct map_symbol *ms = browser->b.priv;
struct disasm_line *dl = browser->selection;
- struct symbol *sym = ms->sym;
struct annotation *notes;
- struct symbol *target;
- u64 ip;
+ struct addr_map_symbol target = {
+ .map = ms->map,
+ .addr = map__objdump_2mem(ms->map, dl->ops.target.addr),
+ };
char title[SYM_TITLE_MAX_SIZE];
if (!ins__is_call(dl->ins))
return false;
- ip = ms->map->map_ip(ms->map, dl->ops.target.addr);
- target = map__find_symbol(ms->map, ip, NULL);
- if (target == NULL) {
+ if (map_groups__find_ams(&target, NULL) ||
+ map__rip_2objdump(target.map, target.map->map_ip(target.map,
+ target.addr)) !=
+ dl->ops.target.addr) {
ui_helpline__puts("The called function was not found.");
return true;
}
- notes = symbol__annotation(target);
+ notes = symbol__annotation(target.sym);
pthread_mutex_lock(¬es->lock);
- if (notes->src == NULL && symbol__alloc_hist(target) < 0) {
+ if (notes->src == NULL && symbol__alloc_hist(target.sym) < 0) {
pthread_mutex_unlock(¬es->lock);
ui__warning("Not enough memory for annotating '%s' symbol!\n",
- target->name);
+ target.sym->name);
return true;
}
pthread_mutex_unlock(¬es->lock);
- symbol__tui_annotate(target, ms->map, evsel, hbt);
- sym_title(sym, ms->map, title, sizeof(title));
+ symbol__tui_annotate(target.sym, target.map, evsel, hbt);
+ sym_title(ms->sym, ms->map, title, sizeof(title));
ui_browser__show_title(&browser->b, title);
return true;
}
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index f538794..9c7ff8d 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -154,9 +154,9 @@
return 0;
}
-int symbol__gtk_annotate(struct symbol *sym, struct map *map,
- struct perf_evsel *evsel,
- struct hist_browser_timer *hbt)
+static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
+ struct perf_evsel *evsel,
+ struct hist_browser_timer *hbt)
{
GtkWidget *window;
GtkWidget *notebook;
@@ -226,6 +226,13 @@
return 0;
}
+int hist_entry__gtk_annotate(struct hist_entry *he,
+ struct perf_evsel *evsel,
+ struct hist_browser_timer *hbt)
+{
+ return symbol__gtk_annotate(he->ms.sym, he->ms.map, evsel, hbt);
+}
+
void perf_gtk__show_annotations(void)
{
GtkWidget *window;
diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c
index c95012c..c24d912 100644
--- a/tools/perf/ui/gtk/browser.c
+++ b/tools/perf/ui/gtk/browser.c
@@ -43,7 +43,7 @@
return NULL;
}
-#ifdef HAVE_GTK_INFO_BAR
+#ifdef HAVE_GTK_INFO_BAR_SUPPORT
GtkWidget *perf_gtk__setup_info_bar(void)
{
GtkWidget *info_bar;
diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h
index 3d96785..0a9173f 100644
--- a/tools/perf/ui/gtk/gtk.h
+++ b/tools/perf/ui/gtk/gtk.h
@@ -12,7 +12,7 @@
GtkWidget *main_window;
GtkWidget *notebook;
-#ifdef HAVE_GTK_INFO_BAR
+#ifdef HAVE_GTK_INFO_BAR_SUPPORT
GtkWidget *info_bar;
GtkWidget *message_label;
#endif
@@ -20,6 +20,9 @@
guint statbar_ctx_id;
};
+int perf_gtk__init(void);
+void perf_gtk__exit(bool wait_for_ok);
+
extern struct perf_gtk_context *pgctx;
static inline bool perf_gtk__is_active_context(struct perf_gtk_context *ctx)
@@ -31,7 +34,7 @@
int perf_gtk__deactivate_context(struct perf_gtk_context **ctx);
void perf_gtk__init_helpline(void);
-void perf_gtk__init_progress(void);
+void gtk_ui_progress__init(void);
void perf_gtk__init_hpp(void);
void perf_gtk__signal(int sig);
@@ -39,7 +42,7 @@
const char *perf_gtk__get_percent_color(double percent);
GtkWidget *perf_gtk__setup_statusbar(void);
-#ifdef HAVE_GTK_INFO_BAR
+#ifdef HAVE_GTK_INFO_BAR_SUPPORT
GtkWidget *perf_gtk__setup_info_bar(void);
#else
static inline GtkWidget *perf_gtk__setup_info_bar(void)
@@ -48,4 +51,17 @@
}
#endif
+struct perf_evsel;
+struct perf_evlist;
+struct hist_entry;
+struct hist_browser_timer;
+
+int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help,
+ struct hist_browser_timer *hbt,
+ float min_pcnt);
+int hist_entry__gtk_annotate(struct hist_entry *he,
+ struct perf_evsel *evsel,
+ struct hist_browser_timer *hbt);
+void perf_gtk__show_annotations(void);
+
#endif /* _PERF_GTK_H_ */
diff --git a/tools/perf/ui/gtk/progress.c b/tools/perf/ui/gtk/progress.c
index 482bcf3..b656655 100644
--- a/tools/perf/ui/gtk/progress.c
+++ b/tools/perf/ui/gtk/progress.c
@@ -7,14 +7,14 @@
static GtkWidget *dialog;
static GtkWidget *progress;
-static void gtk_progress_update(u64 curr, u64 total, const char *title)
+static void gtk_ui_progress__update(struct ui_progress *p)
{
- double fraction = total ? 1.0 * curr / total : 0.0;
+ double fraction = p->total ? 1.0 * p->curr / p->total : 0.0;
char buf[1024];
if (dialog == NULL) {
GtkWidget *vbox = gtk_vbox_new(TRUE, 5);
- GtkWidget *label = gtk_label_new(title);
+ GtkWidget *label = gtk_label_new(p->title);
dialog = gtk_window_new(GTK_WINDOW_TOPLEVEL);
progress = gtk_progress_bar_new();
@@ -32,7 +32,7 @@
}
gtk_progress_bar_set_fraction(GTK_PROGRESS_BAR(progress), fraction);
- snprintf(buf, sizeof(buf), "%"PRIu64" / %"PRIu64, curr, total);
+ snprintf(buf, sizeof(buf), "%"PRIu64" / %"PRIu64, p->curr, p->total);
gtk_progress_bar_set_text(GTK_PROGRESS_BAR(progress), buf);
/* we didn't call gtk_main yet, so do it manually */
@@ -40,7 +40,7 @@
gtk_main_iteration();
}
-static void gtk_progress_finish(void)
+static void gtk_ui_progress__finish(void)
{
/* this will also destroy all of its children */
gtk_widget_destroy(dialog);
@@ -48,12 +48,12 @@
dialog = NULL;
}
-static struct ui_progress gtk_progress_fns = {
- .update = gtk_progress_update,
- .finish = gtk_progress_finish,
+static struct ui_progress_ops gtk_ui_progress__ops = {
+ .update = gtk_ui_progress__update,
+ .finish = gtk_ui_progress__finish,
};
-void perf_gtk__init_progress(void)
+void gtk_ui_progress__init(void)
{
- progress_fns = >k_progress_fns;
+ ui_progress__ops = >k_ui_progress__ops;
}
diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c
index 6c2dd2e..1d57676 100644
--- a/tools/perf/ui/gtk/setup.c
+++ b/tools/perf/ui/gtk/setup.c
@@ -8,7 +8,7 @@
{
perf_error__register(&perf_gtk_eops);
perf_gtk__init_helpline();
- perf_gtk__init_progress();
+ gtk_ui_progress__init();
perf_gtk__init_hpp();
return gtk_init_check(NULL, NULL) ? 0 : -1;
diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c
index c06942a..696c1fb 100644
--- a/tools/perf/ui/gtk/util.c
+++ b/tools/perf/ui/gtk/util.c
@@ -53,7 +53,7 @@
return 0;
}
-#ifdef HAVE_GTK_INFO_BAR
+#ifdef HAVE_GTK_INFO_BAR_SUPPORT
static int perf_gtk__warning_info_bar(const char *format, va_list args)
{
char *msg;
@@ -105,7 +105,7 @@
struct perf_error_ops perf_gtk_eops = {
.error = perf_gtk__error,
-#ifdef HAVE_GTK_INFO_BAR
+#ifdef HAVE_GTK_INFO_BAR_SUPPORT
.warning = perf_gtk__warning_info_bar,
#else
.warning = perf_gtk__warning_statusbar,
diff --git a/tools/perf/ui/progress.c b/tools/perf/ui/progress.c
index 3ec69560..a0f24c7 100644
--- a/tools/perf/ui/progress.c
+++ b/tools/perf/ui/progress.c
@@ -1,26 +1,38 @@
#include "../cache.h"
#include "progress.h"
-static void nop_progress_update(u64 curr __maybe_unused,
- u64 total __maybe_unused,
- const char *title __maybe_unused)
+static void null_progress__update(struct ui_progress *p __maybe_unused)
{
}
-static struct ui_progress default_progress_fns =
+static struct ui_progress_ops null_progress__ops =
{
- .update = nop_progress_update,
+ .update = null_progress__update,
};
-struct ui_progress *progress_fns = &default_progress_fns;
+struct ui_progress_ops *ui_progress__ops = &null_progress__ops;
-void ui_progress__update(u64 curr, u64 total, const char *title)
+void ui_progress__update(struct ui_progress *p, u64 adv)
{
- return progress_fns->update(curr, total, title);
+ p->curr += adv;
+
+ if (p->curr >= p->next) {
+ p->next += p->step;
+ ui_progress__ops->update(p);
+ }
+}
+
+void ui_progress__init(struct ui_progress *p, u64 total, const char *title)
+{
+ p->curr = 0;
+ p->next = p->step = total / 16;
+ p->total = total;
+ p->title = title;
+
}
void ui_progress__finish(void)
{
- if (progress_fns->finish)
- progress_fns->finish();
+ if (ui_progress__ops->finish)
+ ui_progress__ops->finish();
}
diff --git a/tools/perf/ui/progress.h b/tools/perf/ui/progress.h
index 257cc22..29ec8ef 100644
--- a/tools/perf/ui/progress.h
+++ b/tools/perf/ui/progress.h
@@ -3,16 +3,21 @@
#include <../types.h>
+void ui_progress__finish(void);
+
struct ui_progress {
- void (*update)(u64, u64, const char *);
+ const char *title;
+ u64 curr, next, step, total;
+};
+
+void ui_progress__init(struct ui_progress *p, u64 total, const char *title);
+void ui_progress__update(struct ui_progress *p, u64 adv);
+
+struct ui_progress_ops {
+ void (*update)(struct ui_progress *p);
void (*finish)(void);
};
-extern struct ui_progress *progress_fns;
-
-void ui_progress__init(void);
-
-void ui_progress__update(u64 curr, u64 total, const char *title);
-void ui_progress__finish(void);
+extern struct ui_progress_ops *ui_progress__ops;
#endif
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index 47d9a57..5df5140 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -1,10 +1,64 @@
#include <pthread.h>
+#include <dlfcn.h>
#include "../util/cache.h"
#include "../util/debug.h"
#include "../util/hist.h"
pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
+void *perf_gtk_handle;
+
+#ifdef HAVE_GTK2_SUPPORT
+static int setup_gtk_browser(void)
+{
+ int (*perf_ui_init)(void);
+
+ if (perf_gtk_handle)
+ return 0;
+
+ perf_gtk_handle = dlopen(PERF_GTK_DSO, RTLD_LAZY);
+ if (perf_gtk_handle == NULL) {
+ char buf[PATH_MAX];
+ scnprintf(buf, sizeof(buf), "%s/%s", LIBDIR, PERF_GTK_DSO);
+ perf_gtk_handle = dlopen(buf, RTLD_LAZY);
+ }
+ if (perf_gtk_handle == NULL)
+ return -1;
+
+ perf_ui_init = dlsym(perf_gtk_handle, "perf_gtk__init");
+ if (perf_ui_init == NULL)
+ goto out_close;
+
+ if (perf_ui_init() == 0)
+ return 0;
+
+out_close:
+ dlclose(perf_gtk_handle);
+ return -1;
+}
+
+static void exit_gtk_browser(bool wait_for_ok)
+{
+ void (*perf_ui_exit)(bool);
+
+ if (perf_gtk_handle == NULL)
+ return;
+
+ perf_ui_exit = dlsym(perf_gtk_handle, "perf_gtk__exit");
+ if (perf_ui_exit == NULL)
+ goto out_close;
+
+ perf_ui_exit(wait_for_ok);
+
+out_close:
+ dlclose(perf_gtk_handle);
+
+ perf_gtk_handle = NULL;
+}
+#else
+static inline int setup_gtk_browser(void) { return -1; }
+static inline void exit_gtk_browser(bool wait_for_ok __maybe_unused) {}
+#endif
void setup_browser(bool fallback_to_pager)
{
@@ -17,8 +71,11 @@
switch (use_browser) {
case 2:
- if (perf_gtk__init() == 0)
+ if (setup_gtk_browser() == 0)
break;
+ printf("GTK browser requested but could not find %s\n",
+ PERF_GTK_DSO);
+ sleep(1);
/* fall through */
case 1:
use_browser = 1;
@@ -39,7 +96,7 @@
{
switch (use_browser) {
case 2:
- perf_gtk__exit(wait_for_ok);
+ exit_gtk_browser(wait_for_ok);
break;
case 1:
diff --git a/tools/perf/ui/tui/progress.c b/tools/perf/ui/tui/progress.c
index 6c2184d..3e2d936 100644
--- a/tools/perf/ui/tui/progress.c
+++ b/tools/perf/ui/tui/progress.c
@@ -2,9 +2,10 @@
#include "../progress.h"
#include "../libslang.h"
#include "../ui.h"
+#include "tui.h"
#include "../browser.h"
-static void tui_progress__update(u64 curr, u64 total, const char *title)
+static void tui_progress__update(struct ui_progress *p)
{
int bar, y;
/*
@@ -14,7 +15,7 @@
if (use_browser <= 0)
return;
- if (total == 0)
+ if (p->total == 0)
return;
ui__refresh_dimensions(true);
@@ -23,20 +24,20 @@
SLsmg_set_color(0);
SLsmg_draw_box(y, 0, 3, SLtt_Screen_Cols);
SLsmg_gotorc(y++, 1);
- SLsmg_write_string((char *)title);
+ SLsmg_write_string((char *)p->title);
SLsmg_set_color(HE_COLORSET_SELECTED);
- bar = ((SLtt_Screen_Cols - 2) * curr) / total;
+ bar = ((SLtt_Screen_Cols - 2) * p->curr) / p->total;
SLsmg_fill_region(y, 1, 1, bar, ' ');
SLsmg_refresh();
pthread_mutex_unlock(&ui__lock);
}
-static struct ui_progress tui_progress_fns =
+static struct ui_progress_ops tui_progress__ops =
{
.update = tui_progress__update,
};
-void ui_progress__init(void)
+void tui_progress__init(void)
{
- progress_fns = &tui_progress_fns;
+ ui_progress__ops = &tui_progress__ops;
}
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index b940148..2f61256 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -9,6 +9,7 @@
#include "../util.h"
#include "../libslang.h"
#include "../keysyms.h"
+#include "tui.h"
static volatile int ui__need_resize;
@@ -119,7 +120,7 @@
ui_helpline__init();
ui_browser__init();
- ui_progress__init();
+ tui_progress__init();
signal(SIGSEGV, ui__signal);
signal(SIGFPE, ui__signal);
diff --git a/tools/perf/ui/tui/tui.h b/tools/perf/ui/tui/tui.h
new file mode 100644
index 0000000..18961c7
--- /dev/null
+++ b/tools/perf/ui/tui/tui.h
@@ -0,0 +1,6 @@
+#ifndef _PERF_TUI_H_
+#define _PERF_TUI_H_ 1
+
+void tui_progress__init(void);
+
+#endif /* _PERF_TUI_H_ */
diff --git a/tools/perf/ui/ui.h b/tools/perf/ui/ui.h
index 70cb0d4..ab88383 100644
--- a/tools/perf/ui/ui.h
+++ b/tools/perf/ui/ui.h
@@ -6,13 +6,14 @@
#include <linux/compiler.h>
extern pthread_mutex_t ui__lock;
+extern void *perf_gtk_handle;
extern int use_browser;
void setup_browser(bool fallback_to_pager);
void exit_browser(bool wait_for_ok);
-#ifdef SLANG_SUPPORT
+#ifdef HAVE_SLANG_SUPPORT
int ui__init(void);
void ui__exit(bool wait_for_ok);
#else
@@ -23,17 +24,6 @@
static inline void ui__exit(bool wait_for_ok __maybe_unused) {}
#endif
-#ifdef GTK2_SUPPORT
-int perf_gtk__init(void);
-void perf_gtk__exit(bool wait_for_ok);
-#else
-static inline int perf_gtk__init(void)
-{
- return -1;
-}
-static inline void perf_gtk__exit(bool wait_for_ok __maybe_unused) {}
-#endif
-
void ui__refresh_dimensions(bool force);
#endif /* _PERF_UI_H_ */
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 15a77b7..ce7a804 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -40,7 +40,7 @@
VC=unset
fi
test "$VN" = "$VC" || {
- echo >&2 "PERF_VERSION = $VN"
+ echo >&2 " PERF_VERSION = $VN"
echo "#define PERF_VERSION \"$VN\"" >$GVF
}
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 7eae548..cf6242c 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -825,20 +825,16 @@
dl->ops.target.offset = dl->ops.target.addr -
map__rip_2objdump(map, sym->start);
- /*
- * kcore has no symbols, so add the call target name if it is on the
- * same map.
- */
+ /* kcore has no symbols, so add the call target name */
if (dl->ins && ins__is_call(dl->ins) && !dl->ops.target.name) {
- struct symbol *s;
- u64 ip = dl->ops.target.addr;
+ struct addr_map_symbol target = {
+ .map = map,
+ .addr = dl->ops.target.addr,
+ };
- if (ip >= map->start && ip <= map->end) {
- ip = map->map_ip(map, ip);
- s = map__find_symbol(map, ip, NULL);
- if (s && s->start == ip)
- dl->ops.target.name = strdup(s->name);
- }
+ if (!map_groups__find_ams(&target, NULL) &&
+ target.sym->start == target.al_addr)
+ dl->ops.target.name = strdup(target.sym->name);
}
disasm__add(¬es->src->source, dl);
@@ -879,6 +875,8 @@
FILE *file;
int err = 0;
char symfs_filename[PATH_MAX];
+ struct kcore_extract kce;
+ bool delete_extract = false;
if (filename) {
snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
@@ -940,6 +938,23 @@
pr_debug("annotating [%p] %30s : [%p] %30s\n",
dso, dso->long_name, sym, sym->name);
+ if (dso__is_kcore(dso)) {
+ kce.kcore_filename = symfs_filename;
+ kce.addr = map__rip_2objdump(map, sym->start);
+ kce.offs = sym->start;
+ kce.len = sym->end + 1 - sym->start;
+ if (!kcore_extract__create(&kce)) {
+ delete_extract = true;
+ strlcpy(symfs_filename, kce.extract_filename,
+ sizeof(symfs_filename));
+ if (free_filename) {
+ free(filename);
+ free_filename = false;
+ }
+ filename = symfs_filename;
+ }
+ }
+
snprintf(command, sizeof(command),
"%s %s%s --start-address=0x%016" PRIx64
" --stop-address=0x%016" PRIx64
@@ -972,6 +987,8 @@
pclose(file);
out_free_filename:
+ if (delete_extract)
+ kcore_extract__delete(&kce);
if (free_filename)
free(filename);
return err;
@@ -1070,7 +1087,7 @@
(sizeof(src_line->p) * (src_line->nr_pcnt - 1));
for (i = 0; i < len; i++) {
- free(src_line->path);
+ free_srcline(src_line->path);
src_line = (void *)src_line + sizeof_src_line;
}
@@ -1081,13 +1098,11 @@
/* Get the filename:line for the colored entries */
static int symbol__get_source_line(struct symbol *sym, struct map *map,
struct perf_evsel *evsel,
- struct rb_root *root, int len,
- const char *filename)
+ struct rb_root *root, int len)
{
u64 start;
int i, k;
int evidx = evsel->idx;
- char cmd[PATH_MAX * 2];
struct source_line *src_line;
struct annotation *notes = symbol__annotation(sym);
struct sym_hist *h = annotation__histogram(notes, evidx);
@@ -1115,10 +1130,7 @@
start = map__rip_2objdump(map, sym->start);
for (i = 0; i < len; i++) {
- char *path = NULL;
- size_t line_len;
u64 offset;
- FILE *fp;
double percent_max = 0.0;
src_line->nr_pcnt = nr_pcnt;
@@ -1135,23 +1147,9 @@
goto next;
offset = start + i;
- sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset);
- fp = popen(cmd, "r");
- if (!fp)
- goto next;
-
- if (getline(&path, &line_len, fp) < 0 || !line_len)
- goto next_close;
-
- src_line->path = malloc(sizeof(char) * line_len + 1);
- if (!src_line->path)
- goto next_close;
-
- strcpy(src_line->path, path);
+ src_line->path = get_srcline(map->dso, offset);
insert_source_line(&tmp_root, src_line);
- next_close:
- pclose(fp);
next:
src_line = (void *)src_line + sizeof_src_line;
}
@@ -1192,7 +1190,7 @@
path = src_line->path;
color = get_percent_color(percent_max);
- color_fprintf(stdout, color, " %s", path);
+ color_fprintf(stdout, color, " %s\n", path);
node = rb_next(node);
}
@@ -1356,7 +1354,6 @@
bool full_paths, int min_pcnt, int max_lines)
{
struct dso *dso = map->dso;
- const char *filename = dso->long_name;
struct rb_root source_line = RB_ROOT;
u64 len;
@@ -1366,9 +1363,8 @@
len = symbol__size(sym);
if (print_lines) {
- symbol__get_source_line(sym, map, evsel, &source_line,
- len, filename);
- print_summary(&source_line, filename);
+ symbol__get_source_line(sym, map, evsel, &source_line, len);
+ print_summary(&source_line, dso->long_name);
}
symbol__annotate_printf(sym, map, evsel, full_paths,
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index af75515..834b7b5 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -150,7 +150,7 @@
struct perf_evsel *evsel, bool print_lines,
bool full_paths, int min_pcnt, int max_lines);
-#ifdef SLANG_SUPPORT
+#ifdef HAVE_SLANG_SUPPORT
int symbol__tui_annotate(struct symbol *sym, struct map *map,
struct perf_evsel *evsel,
struct hist_browser_timer *hbt);
@@ -165,30 +165,6 @@
}
#endif
-#ifdef GTK2_SUPPORT
-int symbol__gtk_annotate(struct symbol *sym, struct map *map,
- struct perf_evsel *evsel,
- struct hist_browser_timer *hbt);
-
-static inline int hist_entry__gtk_annotate(struct hist_entry *he,
- struct perf_evsel *evsel,
- struct hist_browser_timer *hbt)
-{
- return symbol__gtk_annotate(he->ms.sym, he->ms.map, evsel, hbt);
-}
-
-void perf_gtk__show_annotations(void);
-#else
-static inline int hist_entry__gtk_annotate(struct hist_entry *he __maybe_unused,
- struct perf_evsel *evsel __maybe_unused,
- struct hist_browser_timer *hbt __maybe_unused)
-{
- return 0;
-}
-
-static inline void perf_gtk__show_annotations(void) {}
-#endif
-
extern const char *disassembler_style;
#endif /* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 7ded71d..a92770c 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -89,14 +89,14 @@
return raw - build_id;
}
-char *dso__build_id_filename(struct dso *self, char *bf, size_t size)
+char *dso__build_id_filename(struct dso *dso, char *bf, size_t size)
{
char build_id_hex[BUILD_ID_SIZE * 2 + 1];
- if (!self->has_build_id)
+ if (!dso->has_build_id)
return NULL;
- build_id__sprintf(self->build_id, sizeof(self->build_id), build_id_hex);
+ build_id__sprintf(dso->build_id, sizeof(dso->build_id), build_id_hex);
if (bf == NULL) {
if (asprintf(&bf, "%s/.build-id/%.2s/%s", buildid_dir,
build_id_hex, build_id_hex + 2) < 0)
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 26e3672..7b176dd 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -70,8 +70,7 @@
extern char *perf_pathdup(const char *fmt, ...)
__attribute__((format (printf, 1, 2)));
-#ifndef HAVE_STRLCPY
+/* Matches the libc/libbsd function attribute so we declare this unconditionally: */
extern size_t strlcpy(char *dest, const char *src, size_t size);
-#endif
#endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 482f680..e3970e3 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -21,12 +21,6 @@
__thread struct callchain_cursor callchain_cursor;
-#define chain_for_each_child(child, parent) \
- list_for_each_entry(child, &parent->children, siblings)
-
-#define chain_for_each_child_safe(child, next, parent) \
- list_for_each_entry_safe(child, next, &parent->children, siblings)
-
static void
rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
enum chain_mode mode)
@@ -71,10 +65,16 @@
__sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node,
u64 min_hit)
{
+ struct rb_node *n;
struct callchain_node *child;
- chain_for_each_child(child, node)
+ n = rb_first(&node->rb_root_in);
+ while (n) {
+ child = rb_entry(n, struct callchain_node, rb_node_in);
+ n = rb_next(n);
+
__sort_chain_flat(rb_root, child, min_hit);
+ }
if (node->hit && node->hit >= min_hit)
rb_insert_callchain(rb_root, node, CHAIN_FLAT);
@@ -94,11 +94,16 @@
static void __sort_chain_graph_abs(struct callchain_node *node,
u64 min_hit)
{
+ struct rb_node *n;
struct callchain_node *child;
node->rb_root = RB_ROOT;
+ n = rb_first(&node->rb_root_in);
- chain_for_each_child(child, node) {
+ while (n) {
+ child = rb_entry(n, struct callchain_node, rb_node_in);
+ n = rb_next(n);
+
__sort_chain_graph_abs(child, min_hit);
if (callchain_cumul_hits(child) >= min_hit)
rb_insert_callchain(&node->rb_root, child,
@@ -117,13 +122,18 @@
static void __sort_chain_graph_rel(struct callchain_node *node,
double min_percent)
{
+ struct rb_node *n;
struct callchain_node *child;
u64 min_hit;
node->rb_root = RB_ROOT;
min_hit = ceil(node->children_hit * min_percent);
- chain_for_each_child(child, node) {
+ n = rb_first(&node->rb_root_in);
+ while (n) {
+ child = rb_entry(n, struct callchain_node, rb_node_in);
+ n = rb_next(n);
+
__sort_chain_graph_rel(child, min_percent);
if (callchain_cumul_hits(child) >= min_hit)
rb_insert_callchain(&node->rb_root, child,
@@ -173,19 +183,26 @@
return NULL;
}
new->parent = parent;
- INIT_LIST_HEAD(&new->children);
INIT_LIST_HEAD(&new->val);
if (inherit_children) {
- struct callchain_node *next;
+ struct rb_node *n;
+ struct callchain_node *child;
- list_splice(&parent->children, &new->children);
- INIT_LIST_HEAD(&parent->children);
+ new->rb_root_in = parent->rb_root_in;
+ parent->rb_root_in = RB_ROOT;
- chain_for_each_child(next, new)
- next->parent = new;
+ n = rb_first(&new->rb_root_in);
+ while (n) {
+ child = rb_entry(n, struct callchain_node, rb_node_in);
+ child->parent = new;
+ n = rb_next(n);
+ }
+
+ /* make it the first child */
+ rb_link_node(&new->rb_node_in, NULL, &parent->rb_root_in.rb_node);
+ rb_insert_color(&new->rb_node_in, &parent->rb_root_in);
}
- list_add_tail(&new->siblings, &parent->children);
return new;
}
@@ -223,7 +240,7 @@
}
}
-static void
+static struct callchain_node *
add_child(struct callchain_node *parent,
struct callchain_cursor *cursor,
u64 period)
@@ -235,6 +252,19 @@
new->children_hit = 0;
new->hit = period;
+ return new;
+}
+
+static s64 match_chain(struct callchain_cursor_node *node,
+ struct callchain_list *cnode)
+{
+ struct symbol *sym = node->sym;
+
+ if (cnode->ms.sym && sym &&
+ callchain_param.key == CCKEY_FUNCTION)
+ return cnode->ms.sym->start - sym->start;
+ else
+ return cnode->ip - node->ip;
}
/*
@@ -272,9 +302,33 @@
/* create a new child for the new branch if any */
if (idx_total < cursor->nr) {
+ struct callchain_node *first;
+ struct callchain_list *cnode;
+ struct callchain_cursor_node *node;
+ struct rb_node *p, **pp;
+
parent->hit = 0;
- add_child(parent, cursor, period);
parent->children_hit += period;
+
+ node = callchain_cursor_current(cursor);
+ new = add_child(parent, cursor, period);
+
+ /*
+ * This is second child since we moved parent's children
+ * to new (first) child above.
+ */
+ p = parent->rb_root_in.rb_node;
+ first = rb_entry(p, struct callchain_node, rb_node_in);
+ cnode = list_first_entry(&first->val, struct callchain_list,
+ list);
+
+ if (match_chain(node, cnode) < 0)
+ pp = &p->rb_left;
+ else
+ pp = &p->rb_right;
+
+ rb_link_node(&new->rb_node_in, p, pp);
+ rb_insert_color(&new->rb_node_in, &parent->rb_root_in);
} else {
parent->hit = period;
}
@@ -291,16 +345,40 @@
u64 period)
{
struct callchain_node *rnode;
+ struct callchain_cursor_node *node;
+ struct rb_node **p = &root->rb_root_in.rb_node;
+ struct rb_node *parent = NULL;
+
+ node = callchain_cursor_current(cursor);
+ if (!node)
+ return;
/* lookup in childrens */
- chain_for_each_child(rnode, root) {
- unsigned int ret = append_chain(rnode, cursor, period);
+ while (*p) {
+ s64 ret;
+ struct callchain_list *cnode;
- if (!ret)
+ parent = *p;
+ rnode = rb_entry(parent, struct callchain_node, rb_node_in);
+ cnode = list_first_entry(&rnode->val, struct callchain_list,
+ list);
+
+ /* just check first entry */
+ ret = match_chain(node, cnode);
+ if (ret == 0) {
+ append_chain(rnode, cursor, period);
goto inc_children_hit;
+ }
+
+ if (ret < 0)
+ p = &parent->rb_left;
+ else
+ p = &parent->rb_right;
}
/* nothing in children, add to the current node */
- add_child(root, cursor, period);
+ rnode = add_child(root, cursor, period);
+ rb_link_node(&rnode->rb_node_in, parent, p);
+ rb_insert_color(&rnode->rb_node_in, &root->rb_root_in);
inc_children_hit:
root->children_hit += period;
@@ -325,28 +403,20 @@
*/
list_for_each_entry(cnode, &root->val, list) {
struct callchain_cursor_node *node;
- struct symbol *sym;
node = callchain_cursor_current(cursor);
if (!node)
break;
- sym = node->sym;
-
- if (cnode->ms.sym && sym &&
- callchain_param.key == CCKEY_FUNCTION) {
- if (cnode->ms.sym->start != sym->start)
- break;
- } else if (cnode->ip != node->ip)
+ if (match_chain(node, cnode) != 0)
break;
- if (!found)
- found = true;
+ found = true;
callchain_cursor_advance(cursor);
}
- /* matches not, relay on the parent */
+ /* matches not, relay no the parent */
if (!found) {
cursor->curr = curr_snap;
cursor->pos = start;
@@ -395,8 +465,9 @@
struct callchain_node *dst, struct callchain_node *src)
{
struct callchain_cursor_node **old_last = cursor->last;
- struct callchain_node *child, *next_child;
+ struct callchain_node *child;
struct callchain_list *list, *next_list;
+ struct rb_node *n;
int old_pos = cursor->nr;
int err = 0;
@@ -412,12 +483,16 @@
append_chain_children(dst, cursor, src->hit);
}
- chain_for_each_child_safe(child, next_child, src) {
+ n = rb_first(&src->rb_root_in);
+ while (n) {
+ child = container_of(n, struct callchain_node, rb_node_in);
+ n = rb_next(n);
+ rb_erase(&child->rb_node_in, &src->rb_root_in);
+
err = merge_chain_branch(cursor, dst, child);
if (err)
break;
- list_del(&child->siblings);
free(child);
}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 9e99060..4f7f989 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -21,11 +21,11 @@
struct callchain_node {
struct callchain_node *parent;
- struct list_head siblings;
- struct list_head children;
struct list_head val;
- struct rb_node rb_node; /* to sort nodes in an rbtree */
- struct rb_root rb_root; /* sorted tree of children */
+ struct rb_node rb_node_in; /* to insert nodes in an rbtree */
+ struct rb_node rb_node; /* to sort nodes in an output tree */
+ struct rb_root rb_root_in; /* input tree of children */
+ struct rb_root rb_root; /* sorted output tree of children */
unsigned int val_nr;
u64 hit;
u64 children_hit;
@@ -86,13 +86,12 @@
static inline void callchain_init(struct callchain_root *root)
{
- INIT_LIST_HEAD(&root->node.siblings);
- INIT_LIST_HEAD(&root->node.children);
INIT_LIST_HEAD(&root->node.val);
root->node.parent = NULL;
root->node.hit = 0;
root->node.children_hit = 0;
+ root->node.rb_root_in = RB_ROOT;
root->max_depth = 0;
}
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
new file mode 100644
index 0000000..7d09faf
--- /dev/null
+++ b/tools/perf/util/data.c
@@ -0,0 +1,120 @@
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <string.h>
+
+#include "data.h"
+#include "util.h"
+
+static bool check_pipe(struct perf_data_file *file)
+{
+ struct stat st;
+ bool is_pipe = false;
+ int fd = perf_data_file__is_read(file) ?
+ STDIN_FILENO : STDOUT_FILENO;
+
+ if (!file->path) {
+ if (!fstat(fd, &st) && S_ISFIFO(st.st_mode))
+ is_pipe = true;
+ } else {
+ if (!strcmp(file->path, "-"))
+ is_pipe = true;
+ }
+
+ if (is_pipe)
+ file->fd = fd;
+
+ return file->is_pipe = is_pipe;
+}
+
+static int check_backup(struct perf_data_file *file)
+{
+ struct stat st;
+
+ if (!stat(file->path, &st) && st.st_size) {
+ /* TODO check errors properly */
+ char oldname[PATH_MAX];
+ snprintf(oldname, sizeof(oldname), "%s.old",
+ file->path);
+ unlink(oldname);
+ rename(file->path, oldname);
+ }
+
+ return 0;
+}
+
+static int open_file_read(struct perf_data_file *file)
+{
+ struct stat st;
+ int fd;
+
+ fd = open(file->path, O_RDONLY);
+ if (fd < 0) {
+ int err = errno;
+
+ pr_err("failed to open %s: %s", file->path, strerror(err));
+ if (err == ENOENT && !strcmp(file->path, "perf.data"))
+ pr_err(" (try 'perf record' first)");
+ pr_err("\n");
+ return -err;
+ }
+
+ if (fstat(fd, &st) < 0)
+ goto out_close;
+
+ if (!file->force && st.st_uid && (st.st_uid != geteuid())) {
+ pr_err("file %s not owned by current user or root\n",
+ file->path);
+ goto out_close;
+ }
+
+ if (!st.st_size) {
+ pr_info("zero-sized file (%s), nothing to do!\n",
+ file->path);
+ goto out_close;
+ }
+
+ file->size = st.st_size;
+ return fd;
+
+ out_close:
+ close(fd);
+ return -1;
+}
+
+static int open_file_write(struct perf_data_file *file)
+{
+ if (check_backup(file))
+ return -1;
+
+ return open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR);
+}
+
+static int open_file(struct perf_data_file *file)
+{
+ int fd;
+
+ fd = perf_data_file__is_read(file) ?
+ open_file_read(file) : open_file_write(file);
+
+ file->fd = fd;
+ return fd < 0 ? -1 : 0;
+}
+
+int perf_data_file__open(struct perf_data_file *file)
+{
+ if (check_pipe(file))
+ return 0;
+
+ if (!file->path)
+ file->path = "perf.data";
+
+ return open_file(file);
+}
+
+void perf_data_file__close(struct perf_data_file *file)
+{
+ close(file->fd);
+}
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
new file mode 100644
index 0000000..8c2df80
--- /dev/null
+++ b/tools/perf/util/data.h
@@ -0,0 +1,48 @@
+#ifndef __PERF_DATA_H
+#define __PERF_DATA_H
+
+#include <stdbool.h>
+
+enum perf_data_mode {
+ PERF_DATA_MODE_WRITE,
+ PERF_DATA_MODE_READ,
+};
+
+struct perf_data_file {
+ const char *path;
+ int fd;
+ bool is_pipe;
+ bool force;
+ unsigned long size;
+ enum perf_data_mode mode;
+};
+
+static inline bool perf_data_file__is_read(struct perf_data_file *file)
+{
+ return file->mode == PERF_DATA_MODE_READ;
+}
+
+static inline bool perf_data_file__is_write(struct perf_data_file *file)
+{
+ return file->mode == PERF_DATA_MODE_WRITE;
+}
+
+static inline int perf_data_file__is_pipe(struct perf_data_file *file)
+{
+ return file->is_pipe;
+}
+
+static inline int perf_data_file__fd(struct perf_data_file *file)
+{
+ return file->fd;
+}
+
+static inline unsigned long perf_data_file__size(struct perf_data_file *file)
+{
+ return file->size;
+}
+
+int perf_data_file__open(struct perf_data_file *file);
+void perf_data_file__close(struct perf_data_file *file);
+
+#endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index e3c1ff8..af4c687c 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -7,19 +7,20 @@
char dso__symtab_origin(const struct dso *dso)
{
static const char origin[] = {
- [DSO_BINARY_TYPE__KALLSYMS] = 'k',
- [DSO_BINARY_TYPE__VMLINUX] = 'v',
- [DSO_BINARY_TYPE__JAVA_JIT] = 'j',
- [DSO_BINARY_TYPE__DEBUGLINK] = 'l',
- [DSO_BINARY_TYPE__BUILD_ID_CACHE] = 'B',
- [DSO_BINARY_TYPE__FEDORA_DEBUGINFO] = 'f',
- [DSO_BINARY_TYPE__UBUNTU_DEBUGINFO] = 'u',
- [DSO_BINARY_TYPE__BUILDID_DEBUGINFO] = 'b',
- [DSO_BINARY_TYPE__SYSTEM_PATH_DSO] = 'd',
- [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE] = 'K',
- [DSO_BINARY_TYPE__GUEST_KALLSYMS] = 'g',
- [DSO_BINARY_TYPE__GUEST_KMODULE] = 'G',
- [DSO_BINARY_TYPE__GUEST_VMLINUX] = 'V',
+ [DSO_BINARY_TYPE__KALLSYMS] = 'k',
+ [DSO_BINARY_TYPE__VMLINUX] = 'v',
+ [DSO_BINARY_TYPE__JAVA_JIT] = 'j',
+ [DSO_BINARY_TYPE__DEBUGLINK] = 'l',
+ [DSO_BINARY_TYPE__BUILD_ID_CACHE] = 'B',
+ [DSO_BINARY_TYPE__FEDORA_DEBUGINFO] = 'f',
+ [DSO_BINARY_TYPE__UBUNTU_DEBUGINFO] = 'u',
+ [DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO] = 'o',
+ [DSO_BINARY_TYPE__BUILDID_DEBUGINFO] = 'b',
+ [DSO_BINARY_TYPE__SYSTEM_PATH_DSO] = 'd',
+ [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE] = 'K',
+ [DSO_BINARY_TYPE__GUEST_KALLSYMS] = 'g',
+ [DSO_BINARY_TYPE__GUEST_KMODULE] = 'G',
+ [DSO_BINARY_TYPE__GUEST_VMLINUX] = 'V',
};
if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND)
@@ -64,6 +65,28 @@
symbol_conf.symfs, dso->long_name);
break;
+ case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
+ {
+ char *last_slash;
+ size_t len;
+ size_t dir_size;
+
+ last_slash = dso->long_name + dso->long_name_len;
+ while (last_slash != dso->long_name && *last_slash != '/')
+ last_slash--;
+
+ len = scnprintf(file, size, "%s", symbol_conf.symfs);
+ dir_size = last_slash - dso->long_name + 2;
+ if (dir_size > (size - len)) {
+ ret = -1;
+ break;
+ }
+ len += scnprintf(file + len, dir_size, "%s", dso->long_name);
+ len += scnprintf(file + len , size - len, ".debug%s",
+ last_slash);
+ break;
+ }
+
case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
if (!dso->has_build_id) {
ret = -1;
@@ -427,6 +450,7 @@
dso->rel = 0;
dso->sorted_by_name = 0;
dso->has_build_id = 0;
+ dso->has_srcline = 1;
dso->kernel = DSO_TYPE_USER;
dso->needs_swap = DSO_SWAP__UNSET;
INIT_LIST_HEAD(&dso->node);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index b793053..9ac666a 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -6,6 +6,7 @@
#include <stdbool.h>
#include "types.h"
#include "map.h"
+#include "build-id.h"
enum dso_binary_type {
DSO_BINARY_TYPE__KALLSYMS = 0,
@@ -23,6 +24,7 @@
DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
DSO_BINARY_TYPE__KCORE,
DSO_BINARY_TYPE__GUEST_KCORE,
+ DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
DSO_BINARY_TYPE__NOT_FOUND,
};
@@ -81,6 +83,7 @@
enum dso_binary_type data_type;
u8 adjust_symbols:1;
u8 has_build_id:1;
+ u8 has_srcline:1;
u8 hit:1;
u8 annotate_warned:1;
u8 sname_alloc:1;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index c67ecc4..752709c 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -61,6 +61,12 @@
u64 id;
};
+struct throttle_event {
+ struct perf_event_header header;
+ u64 time;
+ u64 id;
+ u64 stream_id;
+};
#define PERF_SAMPLE_MASK \
(PERF_SAMPLE_IP | PERF_SAMPLE_TID | \
@@ -69,6 +75,9 @@
PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD | \
PERF_SAMPLE_IDENTIFIER)
+/* perf sample has 16 bits size limit */
+#define PERF_SAMPLE_MAX_SIZE (1 << 16)
+
struct sample_event {
struct perf_event_header header;
u64 array[];
@@ -111,6 +120,7 @@
u64 stream_id;
u64 period;
u64 weight;
+ u64 transaction;
u32 cpu;
u32 raw_size;
u64 data_src;
@@ -177,6 +187,7 @@
struct fork_event fork;
struct lost_event lost;
struct read_event read;
+ struct throttle_event throttle;
struct sample_event sample;
struct attr_event attr;
struct event_type_event event_type;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e584cd3..0582f67 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -18,6 +18,7 @@
#include <unistd.h>
#include "parse-events.h"
+#include "parse-options.h"
#include <sys/mman.h>
@@ -49,6 +50,18 @@
return evlist;
}
+struct perf_evlist *perf_evlist__new_default(void)
+{
+ struct perf_evlist *evlist = perf_evlist__new();
+
+ if (evlist && perf_evlist__add_default(evlist)) {
+ perf_evlist__delete(evlist);
+ evlist = NULL;
+ }
+
+ return evlist;
+}
+
/**
* perf_evlist__set_id_pos - set the positions of event ids.
* @evlist: selected event list
@@ -527,7 +540,7 @@
if ((old & md->mask) + size != ((old + size) & md->mask)) {
unsigned int offset = old;
unsigned int len = min(sizeof(*event), size), cpy;
- void *dst = &md->event_copy;
+ void *dst = md->event_copy;
do {
cpy = min(md->mask + 1 - (offset & md->mask), len);
@@ -537,7 +550,7 @@
len -= cpy;
} while (len);
- event = &md->event_copy;
+ event = (union perf_event *) md->event_copy;
}
old += size;
@@ -602,9 +615,36 @@
return 0;
}
-static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int mask)
+static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
+ int prot, int mask, int cpu, int thread,
+ int *output)
{
struct perf_evsel *evsel;
+
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ int fd = FD(evsel, cpu, thread);
+
+ if (*output == -1) {
+ *output = fd;
+ if (__perf_evlist__mmap(evlist, idx, prot, mask,
+ *output) < 0)
+ return -1;
+ } else {
+ if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
+ return -1;
+ }
+
+ if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+ perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
+ return -1;
+ }
+
+ return 0;
+}
+
+static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot,
+ int mask)
+{
int cpu, thread;
int nr_cpus = cpu_map__nr(evlist->cpus);
int nr_threads = thread_map__nr(evlist->threads);
@@ -614,23 +654,9 @@
int output = -1;
for (thread = 0; thread < nr_threads; thread++) {
- list_for_each_entry(evsel, &evlist->entries, node) {
- int fd = FD(evsel, cpu, thread);
-
- if (output == -1) {
- output = fd;
- if (__perf_evlist__mmap(evlist, cpu,
- prot, mask, output) < 0)
- goto out_unmap;
- } else {
- if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
- goto out_unmap;
- }
-
- if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
- perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
- goto out_unmap;
- }
+ if (perf_evlist__mmap_per_evsel(evlist, cpu, prot, mask,
+ cpu, thread, &output))
+ goto out_unmap;
}
}
@@ -642,9 +668,9 @@
return -1;
}
-static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, int mask)
+static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot,
+ int mask)
{
- struct perf_evsel *evsel;
int thread;
int nr_threads = thread_map__nr(evlist->threads);
@@ -652,23 +678,9 @@
for (thread = 0; thread < nr_threads; thread++) {
int output = -1;
- list_for_each_entry(evsel, &evlist->entries, node) {
- int fd = FD(evsel, 0, thread);
-
- if (output == -1) {
- output = fd;
- if (__perf_evlist__mmap(evlist, thread,
- prot, mask, output) < 0)
- goto out_unmap;
- } else {
- if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
- goto out_unmap;
- }
-
- if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
- perf_evlist__id_add_fd(evlist, evsel, 0, thread, fd) < 0)
- goto out_unmap;
- }
+ if (perf_evlist__mmap_per_evsel(evlist, thread, prot, mask, 0,
+ thread, &output))
+ goto out_unmap;
}
return 0;
@@ -679,20 +691,76 @@
return -1;
}
-/** perf_evlist__mmap - Create per cpu maps to receive events
+static size_t perf_evlist__mmap_size(unsigned long pages)
+{
+ /* 512 kiB: default amount of unprivileged mlocked memory */
+ if (pages == UINT_MAX)
+ pages = (512 * 1024) / page_size;
+ else if (!is_power_of_2(pages))
+ return 0;
+
+ return (pages + 1) * page_size;
+}
+
+int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
+ int unset __maybe_unused)
+{
+ unsigned int *mmap_pages = opt->value;
+ unsigned long pages, val;
+ size_t size;
+ static struct parse_tag tags[] = {
+ { .tag = 'B', .mult = 1 },
+ { .tag = 'K', .mult = 1 << 10 },
+ { .tag = 'M', .mult = 1 << 20 },
+ { .tag = 'G', .mult = 1 << 30 },
+ { .tag = 0 },
+ };
+
+ val = parse_tag_value(str, tags);
+ if (val != (unsigned long) -1) {
+ /* we got file size value */
+ pages = PERF_ALIGN(val, page_size) / page_size;
+ if (pages < (1UL << 31) && !is_power_of_2(pages)) {
+ pages = next_pow2(pages);
+ pr_info("rounding mmap pages size to %lu (%lu pages)\n",
+ pages * page_size, pages);
+ }
+ } else {
+ /* we got pages count value */
+ char *eptr;
+ pages = strtoul(str, &eptr, 10);
+ if (*eptr != '\0') {
+ pr_err("failed to parse --mmap_pages/-m value\n");
+ return -1;
+ }
+ }
+
+ if (pages > UINT_MAX || pages > SIZE_MAX / page_size) {
+ pr_err("--mmap_pages/-m value too big\n");
+ return -1;
+ }
+
+ size = perf_evlist__mmap_size(pages);
+ if (!size) {
+ pr_err("--mmap_pages/-m value must be a power of two.");
+ return -1;
+ }
+
+ *mmap_pages = pages;
+ return 0;
+}
+
+/**
+ * perf_evlist__mmap - Create mmaps to receive events.
+ * @evlist: list of events
+ * @pages: map length in pages
+ * @overwrite: overwrite older events?
*
- * @evlist - list of events
- * @pages - map length in pages
- * @overwrite - overwrite older events?
+ * If @overwrite is %false the user needs to signal event consumption using
+ * perf_mmap__write_tail(). Using perf_evlist__mmap_read() does this
+ * automatically.
*
- * If overwrite is false the user needs to signal event consuption using:
- *
- * struct perf_mmap *m = &evlist->mmap[cpu];
- * unsigned int head = perf_mmap__read_head(m);
- *
- * perf_mmap__write_tail(m, head)
- *
- * Using perf_evlist__read_on_cpu does this automatically.
+ * Return: %0 on success, negative error code otherwise.
*/
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
bool overwrite)
@@ -702,14 +770,6 @@
const struct thread_map *threads = evlist->threads;
int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), mask;
- /* 512 kiB: default amount of unprivileged mlocked memory */
- if (pages == UINT_MAX)
- pages = (512 * 1024) / page_size;
- else if (!is_power_of_2(pages))
- return -EINVAL;
-
- mask = pages * page_size - 1;
-
if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
return -ENOMEM;
@@ -717,7 +777,9 @@
return -ENOMEM;
evlist->overwrite = overwrite;
- evlist->mmap_len = (pages + 1) * page_size;
+ evlist->mmap_len = perf_evlist__mmap_size(pages);
+ pr_debug("mmap size %zuB\n", evlist->mmap_len);
+ mask = evlist->mmap_len - page_size - 1;
list_for_each_entry(evsel, &evlist->entries, node) {
if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
@@ -1073,3 +1135,66 @@
return printed + fprintf(fp, "\n");;
}
+
+int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused,
+ int err, char *buf, size_t size)
+{
+ char sbuf[128];
+
+ switch (err) {
+ case ENOENT:
+ scnprintf(buf, size, "%s",
+ "Error:\tUnable to find debugfs\n"
+ "Hint:\tWas your kernel was compiled with debugfs support?\n"
+ "Hint:\tIs the debugfs filesystem mounted?\n"
+ "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'");
+ break;
+ case EACCES:
+ scnprintf(buf, size,
+ "Error:\tNo permissions to read %s/tracing/events/raw_syscalls\n"
+ "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
+ debugfs_mountpoint, debugfs_mountpoint);
+ break;
+ default:
+ scnprintf(buf, size, "%s", strerror_r(err, sbuf, sizeof(sbuf)));
+ break;
+ }
+
+ return 0;
+}
+
+int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
+ int err, char *buf, size_t size)
+{
+ int printed, value;
+ char sbuf[128], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+
+ switch (err) {
+ case EACCES:
+ case EPERM:
+ printed = scnprintf(buf, size,
+ "Error:\t%s.\n"
+ "Hint:\tCheck /proc/sys/kernel/perf_event_paranoid setting.", emsg);
+
+ if (filename__read_int("/proc/sys/kernel/perf_event_paranoid", &value))
+ break;
+
+ printed += scnprintf(buf + printed, size - printed, "\nHint:\t");
+
+ if (value >= 2) {
+ printed += scnprintf(buf + printed, size - printed,
+ "For your workloads it needs to be <= 1\nHint:\t");
+ }
+ printed += scnprintf(buf + printed, size - printed,
+ "For system wide tracing it needs to be set to -1");
+
+ printed += scnprintf(buf + printed, size - printed,
+ ".\nHint:\tThe current value is %d.", value);
+ break;
+ default:
+ scnprintf(buf, size, "%s", emsg);
+ break;
+ }
+
+ return 0;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 206d093..6e8acc9 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -21,7 +21,7 @@
void *base;
int mask;
unsigned int prev;
- union perf_event event_copy;
+ char event_copy[PERF_SAMPLE_MAX_SIZE];
};
struct perf_evlist {
@@ -31,7 +31,7 @@
int nr_groups;
int nr_fds;
int nr_mmaps;
- int mmap_len;
+ size_t mmap_len;
int id_pos;
int is_pos;
u64 combined_sample_type;
@@ -53,6 +53,7 @@
};
struct perf_evlist *perf_evlist__new(void);
+struct perf_evlist *perf_evlist__new_default(void);
void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
struct thread_map *threads);
void perf_evlist__exit(struct perf_evlist *evlist);
@@ -105,6 +106,10 @@
bool want_signal);
int perf_evlist__start_workload(struct perf_evlist *evlist);
+int perf_evlist__parse_mmap_pages(const struct option *opt,
+ const char *str,
+ int unset);
+
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
bool overwrite);
void perf_evlist__munmap(struct perf_evlist *evlist);
@@ -165,6 +170,9 @@
size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp);
+int perf_evlist__strerror_tp(struct perf_evlist *evlist, int err, char *buf, size_t size);
+int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size);
+
static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm)
{
struct perf_event_mmap_page *pc = mm->base;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 9f1ef9b..3a334f0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -680,6 +680,9 @@
attr->mmap = track;
attr->comm = track;
+ if (opts->sample_transaction)
+ attr->sample_type |= PERF_SAMPLE_TRANSACTION;
+
/*
* XXX see the function comment above
*
@@ -982,6 +985,7 @@
ret += PRINT_ATTR2(exclude_host, exclude_guest);
ret += PRINT_ATTR2N("excl.callchain_kern", exclude_callchain_kernel,
"excl.callchain_user", exclude_callchain_user);
+ ret += PRINT_ATTR_U32(mmap2);
ret += PRINT_ATTR_U32(wakeup_events);
ret += PRINT_ATTR_U32(wakeup_watermark);
@@ -1213,6 +1217,7 @@
sample->pid = u.val32[0];
sample->tid = u.val32[1];
+ array--;
}
return 0;
@@ -1452,6 +1457,9 @@
array = (void *)array + sz;
OVERFLOW_CHECK_u64(array);
data->user_stack.size = *array++;
+ if (WARN_ONCE(data->user_stack.size > sz,
+ "user stack dump failure\n"))
+ return -EFAULT;
}
}
@@ -1469,6 +1477,12 @@
array++;
}
+ data->transaction = 0;
+ if (type & PERF_SAMPLE_TRANSACTION) {
+ data->transaction = *array;
+ array++;
+ }
+
return 0;
}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4a7bdc7..5aa68cd 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -197,6 +197,12 @@
(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);
diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh
index 3ac3803..36a885d 100755
--- a/tools/perf/util/generate-cmdlist.sh
+++ b/tools/perf/util/generate-cmdlist.sh
@@ -22,7 +22,7 @@
}' "Documentation/perf-$cmd.txt"
done
-echo "#ifdef LIBELF_SUPPORT"
+echo "#ifdef HAVE_LIBELF_SUPPORT"
sed -n -e 's/^perf-\([^ ]*\)[ ].* full.*/\1/p' command-list.txt |
sort |
while read cmd
@@ -35,5 +35,5 @@
p
}' "Documentation/perf-$cmd.txt"
done
-echo "#endif /* LIBELF_SUPPORT */"
+echo "#endif /* HAVE_LIBELF_SUPPORT */"
echo "};"
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index c3e5a3b..26d9520 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -22,6 +22,7 @@
#include "vdso.h"
#include "strbuf.h"
#include "build-id.h"
+#include "data.h"
static bool no_buildid_cache = false;
@@ -2189,7 +2190,7 @@
{
struct header_print_data hd;
struct perf_header *header = &session->header;
- int fd = session->fd;
+ int fd = perf_data_file__fd(session->file);
hd.fp = fp;
hd.full = full;
@@ -2650,7 +2651,8 @@
struct perf_header *header = &session->header;
struct perf_pipe_file_header f_header;
- if (perf_file_header__read_pipe(&f_header, header, session->fd,
+ if (perf_file_header__read_pipe(&f_header, header,
+ perf_data_file__fd(session->file),
session->repipe) < 0) {
pr_debug("incompatible file format\n");
return -EINVAL;
@@ -2751,18 +2753,19 @@
int perf_session__read_header(struct perf_session *session)
{
+ struct perf_data_file *file = session->file;
struct perf_header *header = &session->header;
struct perf_file_header f_header;
struct perf_file_attr f_attr;
u64 f_id;
int nr_attrs, nr_ids, i, j;
- int fd = session->fd;
+ int fd = perf_data_file__fd(file);
session->evlist = perf_evlist__new();
if (session->evlist == NULL)
return -ENOMEM;
- if (session->fd_pipe)
+ if (perf_data_file__is_pipe(file))
return perf_header__read_pipe(session);
if (perf_file_header__read(&f_header, header, fd) < 0)
@@ -2777,7 +2780,7 @@
if (f_header.data.size == 0) {
pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n"
"Was the 'perf record' command properly terminated?\n",
- session->filename);
+ file->path);
}
nr_attrs = f_header.attrs.size / f_header.attr_size;
@@ -2990,18 +2993,19 @@
struct perf_session *session)
{
ssize_t size_read, padding, size = event->tracing_data.size;
- off_t offset = lseek(session->fd, 0, SEEK_CUR);
+ int fd = perf_data_file__fd(session->file);
+ off_t offset = lseek(fd, 0, SEEK_CUR);
char buf[BUFSIZ];
/* setup for reading amidst mmap */
- lseek(session->fd, offset + sizeof(struct tracing_data_event),
+ lseek(fd, offset + sizeof(struct tracing_data_event),
SEEK_SET);
- size_read = trace_report(session->fd, &session->pevent,
+ size_read = trace_report(fd, &session->pevent,
session->repipe);
padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read;
- if (readn(session->fd, buf, padding) < 0) {
+ if (readn(fd, buf, padding) < 0) {
pr_err("%s: reading input file", __func__);
return -1;
}
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 9ff6cf3..7e80253 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -160,6 +160,10 @@
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)
@@ -346,7 +350,7 @@
struct rb_node **p;
struct rb_node *parent = NULL;
struct hist_entry *he;
- int cmp;
+ int64_t cmp;
p = &hists->entries_in->rb_node;
@@ -395,6 +399,7 @@
if (!he)
return NULL;
+ hists->nr_entries++;
rb_link_node(&he->rb_node_in, parent, p);
rb_insert_color(&he->rb_node_in, hists->entries_in);
out:
@@ -402,7 +407,7 @@
return he;
}
-struct hist_entry *__hists__add_mem_entry(struct hists *self,
+struct hist_entry *__hists__add_mem_entry(struct hists *hists,
struct addr_location *al,
struct symbol *sym_parent,
struct mem_info *mi,
@@ -425,14 +430,14 @@
.level = al->level,
.parent = sym_parent,
.filtered = symbol__parent_filter(sym_parent),
- .hists = self,
+ .hists = hists,
.mem_info = mi,
.branch_info = NULL,
};
- return add_hist_entry(self, &entry, al, period, weight);
+ return add_hist_entry(hists, &entry, al, period, weight);
}
-struct hist_entry *__hists__add_branch_entry(struct hists *self,
+struct hist_entry *__hists__add_branch_entry(struct hists *hists,
struct addr_location *al,
struct symbol *sym_parent,
struct branch_info *bi,
@@ -456,17 +461,17 @@
.parent = sym_parent,
.filtered = symbol__parent_filter(sym_parent),
.branch_info = bi,
- .hists = self,
+ .hists = hists,
.mem_info = NULL,
};
- return add_hist_entry(self, &entry, al, period, weight);
+ return add_hist_entry(hists, &entry, al, period, weight);
}
-struct hist_entry *__hists__add_entry(struct hists *self,
+struct hist_entry *__hists__add_entry(struct hists *hists,
struct addr_location *al,
struct symbol *sym_parent, u64 period,
- u64 weight)
+ u64 weight, u64 transaction)
{
struct hist_entry entry = {
.thread = al->thread,
@@ -484,12 +489,13 @@
},
.parent = sym_parent,
.filtered = symbol__parent_filter(sym_parent),
- .hists = self,
+ .hists = hists,
.branch_info = NULL,
.mem_info = NULL,
+ .transaction = transaction,
};
- return add_hist_entry(self, &entry, al, period, weight);
+ return add_hist_entry(hists, &entry, al, period, weight);
}
int64_t
@@ -530,6 +536,7 @@
{
free(he->branch_info);
free(he->mem_info);
+ free_srcline(he->srcline);
free(he);
}
@@ -598,7 +605,7 @@
hists__filter_entry_by_symbol(hists, he);
}
-void hists__collapse_resort(struct hists *hists)
+void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
{
struct rb_root *root;
struct rb_node *next;
@@ -625,6 +632,8 @@
*/
hists__apply_filters(hists, n);
}
+ if (prog)
+ ui_progress__update(prog, 1);
}
}
@@ -884,7 +893,7 @@
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;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index ce8dc61..9d2d022 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -6,6 +6,7 @@
#include "callchain.h"
#include "header.h"
#include "color.h"
+#include "ui/progress.h"
extern struct callchain_param callchain_param;
@@ -46,6 +47,8 @@
HISTC_CPU,
HISTC_SRCLINE,
HISTC_MISPREDICT,
+ HISTC_IN_TX,
+ HISTC_ABORT,
HISTC_SYMBOL_FROM,
HISTC_SYMBOL_TO,
HISTC_DSO_FROM,
@@ -58,6 +61,7 @@
HISTC_MEM_TLB,
HISTC_MEM_LVL,
HISTC_MEM_SNOOP,
+ HISTC_TRANSACTION,
HISTC_NR_COLS, /* Last entry */
};
@@ -83,9 +87,10 @@
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 *);
@@ -105,7 +110,7 @@
u64 weight);
void hists__output_resort(struct hists *self);
-void hists__collapse_resort(struct hists *self);
+void hists__collapse_resort(struct hists *self, struct ui_progress *prog);
void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
void hists__output_recalc_col_len(struct hists *hists, int max_rows);
@@ -196,7 +201,7 @@
int refresh;
};
-#ifdef SLANG_SUPPORT
+#ifdef HAVE_SLANG_SUPPORT
#include "../ui/keysyms.h"
int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
struct hist_browser_timer *hbt);
@@ -237,20 +242,5 @@
#define K_SWITCH_INPUT_DATA -3000
#endif
-#ifdef GTK2_SUPPORT
-int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help,
- struct hist_browser_timer *hbt __maybe_unused,
- float min_pcnt);
-#else
-static inline
-int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused,
- const char *help __maybe_unused,
- struct hist_browser_timer *hbt __maybe_unused,
- float min_pcnt __maybe_unused)
-{
- return 0;
-}
-#endif
-
unsigned int hists__sort_list_width(struct hists *self);
#endif /* __PERF_HIST_H */
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index cf6727e..8f14965 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -1,7 +1,7 @@
#ifndef _PERF_DWARF_REGS_H_
#define _PERF_DWARF_REGS_H_
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
const char *get_arch_regstr(unsigned int n);
#endif
diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h
index 96b919d..b003ad7 100644
--- a/tools/perf/util/include/linux/compiler.h
+++ b/tools/perf/util/include/linux/compiler.h
@@ -2,20 +2,29 @@
#define _PERF_LINUX_COMPILER_H_
#ifndef __always_inline
-#define __always_inline inline
+# define __always_inline inline __attribute__((always_inline))
#endif
+
#define __user
+
#ifndef __attribute_const__
-#define __attribute_const__
+# define __attribute_const__
#endif
#ifndef __maybe_unused
-#define __maybe_unused __attribute__((unused))
+# define __maybe_unused __attribute__((unused))
#endif
-#define __packed __attribute__((__packed__))
+
+#ifndef __packed
+# define __packed __attribute__((__packed__))
+#endif
#ifndef __force
-#define __force
+# define __force
+#endif
+
+#ifndef __weak
+# define __weak __attribute__((weak))
#endif
#endif
diff --git a/tools/perf/util/intlist.c b/tools/perf/util/intlist.c
index 11a8d86..89715b6 100644
--- a/tools/perf/util/intlist.c
+++ b/tools/perf/util/intlist.c
@@ -20,6 +20,7 @@
if (node != NULL) {
node->i = i;
+ node->priv = NULL;
rc = &node->rb_node;
}
@@ -57,22 +58,36 @@
rblist__remove_node(&ilist->rblist, &node->rb_node);
}
-struct int_node *intlist__find(struct intlist *ilist, int i)
+static struct int_node *__intlist__findnew(struct intlist *ilist,
+ int i, bool create)
{
- struct int_node *node;
+ struct int_node *node = NULL;
struct rb_node *rb_node;
if (ilist == NULL)
return NULL;
- node = NULL;
- rb_node = rblist__find(&ilist->rblist, (void *)((long)i));
+ if (create)
+ rb_node = rblist__findnew(&ilist->rblist, (void *)((long)i));
+ else
+ rb_node = rblist__find(&ilist->rblist, (void *)((long)i));
+
if (rb_node)
node = container_of(rb_node, struct int_node, rb_node);
return node;
}
+struct int_node *intlist__find(struct intlist *ilist, int i)
+{
+ return __intlist__findnew(ilist, i, false);
+}
+
+struct int_node *intlist__findnew(struct intlist *ilist, int i)
+{
+ return __intlist__findnew(ilist, i, true);
+}
+
static int intlist__parse_list(struct intlist *ilist, const char *s)
{
char *sep;
diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h
index 62351da..aa6877d 100644
--- a/tools/perf/util/intlist.h
+++ b/tools/perf/util/intlist.h
@@ -9,6 +9,7 @@
struct int_node {
struct rb_node rb_node;
int i;
+ void *priv;
};
struct intlist {
@@ -23,6 +24,7 @@
struct int_node *intlist__entry(const struct intlist *ilist, unsigned int idx);
struct int_node *intlist__find(struct intlist *ilist, int i);
+struct int_node *intlist__findnew(struct intlist *ilist, int i);
static inline bool intlist__has_entry(struct intlist *ilist, int i)
{
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 6188d28..ea93425 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -46,6 +46,23 @@
return 0;
}
+struct machine *machine__new_host(void)
+{
+ struct machine *machine = malloc(sizeof(*machine));
+
+ if (machine != NULL) {
+ machine__init(machine, "", HOST_KERNEL_ID);
+
+ if (machine__create_kernel_maps(machine) < 0)
+ goto out_delete;
+ }
+
+ return machine;
+out_delete:
+ free(machine);
+ return NULL;
+}
+
static void dsos__delete(struct list_head *dsos)
{
struct dso *pos, *n;
@@ -776,75 +793,44 @@
return map_groups__set_modules_path_dir(&machine->kmaps, modules_path);
}
+static int machine__create_module(void *arg, const char *name, u64 start)
+{
+ struct machine *machine = arg;
+ struct map *map;
+
+ map = machine__new_module(machine, start, name);
+ if (map == NULL)
+ return -1;
+
+ dso__kernel_module_get_build_id(map->dso, machine->root_dir);
+
+ return 0;
+}
+
static int machine__create_modules(struct machine *machine)
{
- char *line = NULL;
- size_t n;
- FILE *file;
- struct map *map;
const char *modules;
char path[PATH_MAX];
- if (machine__is_default_guest(machine))
+ if (machine__is_default_guest(machine)) {
modules = symbol_conf.default_guest_modules;
- else {
- sprintf(path, "%s/proc/modules", machine->root_dir);
+ } else {
+ snprintf(path, PATH_MAX, "%s/proc/modules", machine->root_dir);
modules = path;
}
if (symbol__restricted_filename(modules, "/proc/modules"))
return -1;
- file = fopen(modules, "r");
- if (file == NULL)
+ if (modules__parse(modules, machine, machine__create_module))
return -1;
- while (!feof(file)) {
- char name[PATH_MAX];
- u64 start;
- char *sep;
- int line_len;
+ if (!machine__set_modules_path(machine))
+ return 0;
- line_len = getline(&line, &n, file);
- if (line_len < 0)
- break;
+ pr_debug("Problems setting modules path maps, continuing anyway...\n");
- if (!line)
- goto out_failure;
-
- line[--line_len] = '\0'; /* \n */
-
- sep = strrchr(line, 'x');
- if (sep == NULL)
- continue;
-
- hex2u64(sep + 1, &start);
-
- sep = strchr(line, ' ');
- if (sep == NULL)
- continue;
-
- *sep = '\0';
-
- snprintf(name, sizeof(name), "[%s]", line);
- map = machine__new_module(machine, start, name);
- if (map == NULL)
- goto out_delete_line;
- dso__kernel_module_get_build_id(map->dso, machine->root_dir);
- }
-
- free(line);
- fclose(file);
-
- if (machine__set_modules_path(machine) < 0) {
- pr_debug("Problems setting modules path maps, continuing anyway...\n");
- }
return 0;
-
-out_delete_line:
- free(line);
-out_failure:
- return -1;
}
int machine__create_kernel_maps(struct machine *machine)
@@ -1267,10 +1253,12 @@
struct thread *thread,
struct ip_callchain *chain,
struct symbol **parent,
- struct addr_location *root_al)
+ struct addr_location *root_al,
+ int max_stack)
{
u8 cpumode = PERF_RECORD_MISC_USER;
- unsigned int i;
+ int chain_nr = min(max_stack, (int)chain->nr);
+ int i;
int err;
callchain_cursor_reset(&callchain_cursor);
@@ -1280,7 +1268,7 @@
return 0;
}
- for (i = 0; i < chain->nr; i++) {
+ for (i = 0; i < chain_nr; i++) {
u64 ip;
struct addr_location al;
@@ -1352,12 +1340,14 @@
struct thread *thread,
struct perf_sample *sample,
struct symbol **parent,
- struct addr_location *root_al)
+ struct addr_location *root_al,
+ int max_stack)
{
int ret;
ret = machine__resolve_callchain_sample(machine, thread,
- sample->callchain, parent, root_al);
+ sample->callchain, parent,
+ root_al, max_stack);
if (ret)
return ret;
@@ -1376,3 +1366,26 @@
sample);
}
+
+int machine__for_each_thread(struct machine *machine,
+ int (*fn)(struct thread *thread, void *p),
+ void *priv)
+{
+ struct rb_node *nd;
+ struct thread *thread;
+ int rc = 0;
+
+ for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
+ thread = rb_entry(nd, struct thread, rb_node);
+ rc = fn(thread, priv);
+ if (rc != 0)
+ return rc;
+ }
+
+ list_for_each_entry(thread, &machine->dead_threads, node) {
+ rc = fn(thread, priv);
+ if (rc != 0)
+ return rc;
+ }
+ return rc;
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 58a6be1..4c1f5d5 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -74,6 +74,7 @@
void machines__set_symbol_filter(struct machines *machines,
symbol_filter_t symbol_filter);
+struct machine *machine__new_host(void);
int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
void machine__exit(struct machine *machine);
void machine__delete_dead_threads(struct machine *machine);
@@ -91,7 +92,8 @@
struct thread *thread,
struct perf_sample *sample,
struct symbol **parent,
- struct addr_location *root_al);
+ struct addr_location *root_al,
+ int max_stack);
/*
* Default guest kernel is defined by parameter --guestkallsyms
@@ -165,4 +167,8 @@
size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
+int machine__for_each_thread(struct machine *machine,
+ int (*fn)(struct thread *thread, void *p),
+ void *priv);
+
#endif /* __PERF_MACHINE_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 4f6680d..ef5bc91 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -172,7 +172,7 @@
pr_warning(", continuing without symbols\n");
return -1;
} else if (nr == 0) {
-#ifdef LIBELF_SUPPORT
+#ifdef HAVE_LIBELF_SUPPORT
const size_t len = strlen(name);
const size_t real_len = len - sizeof(DSO__DELETED);
@@ -252,10 +252,16 @@
return fprintf(fp, "%s", dsoname);
}
-/*
+/**
+ * map__rip_2objdump - convert symbol start address to objdump address.
+ * @map: memory map
+ * @rip: symbol start address
+ *
* objdump wants/reports absolute IPs for ET_EXEC, and RIPs for ET_DYN.
* map->dso->adjust_symbols==1 for ET_EXEC-like cases except ET_REL which is
* relative to section start.
+ *
+ * Return: Address suitable for passing to "objdump --start-address="
*/
u64 map__rip_2objdump(struct map *map, u64 rip)
{
@@ -268,6 +274,29 @@
return map->unmap_ip(map, rip);
}
+/**
+ * map__objdump_2mem - convert objdump address to a memory address.
+ * @map: memory map
+ * @ip: objdump address
+ *
+ * Closely related to map__rip_2objdump(), this function takes an address from
+ * objdump and converts it to a memory address. Note this assumes that @map
+ * contains the address. To be sure the result is valid, check it forwards
+ * e.g. map__rip_2objdump(map->map_ip(map, map__objdump_2mem(map, ip))) == ip
+ *
+ * Return: Memory address.
+ */
+u64 map__objdump_2mem(struct map *map, u64 ip)
+{
+ if (!map->dso->adjust_symbols)
+ return map->unmap_ip(map, ip);
+
+ if (map->dso->rel)
+ return map->unmap_ip(map, ip + map->pgoff);
+
+ return ip;
+}
+
void map_groups__init(struct map_groups *mg)
{
int i;
@@ -371,6 +400,23 @@
return NULL;
}
+int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
+{
+ if (ams->addr < ams->map->start || ams->addr > ams->map->end) {
+ if (ams->map->groups == NULL)
+ return -1;
+ ams->map = map_groups__find(ams->map->groups, ams->map->type,
+ ams->addr);
+ if (ams->map == NULL)
+ return -1;
+ }
+
+ ams->al_addr = ams->map->map_ip(ams->map, ams->addr);
+ ams->sym = map__find_symbol(ams->map, ams->al_addr, filter);
+
+ return ams->sym ? 0 : -1;
+}
+
size_t __map_groups__fprintf_maps(struct map_groups *mg,
enum map_type type, int verbose, FILE *fp)
{
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 4886ca2..e4e259c 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -84,6 +84,9 @@
/* rip/ip <-> addr suitable for passing to `objdump --start-address=` */
u64 map__rip_2objdump(struct map *map, u64 rip);
+/* objdump address -> memory address */
+u64 map__objdump_2mem(struct map *map, u64 ip);
+
struct symbol;
typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
@@ -167,6 +170,10 @@
struct map **mapp,
symbol_filter_t filter);
+struct addr_map_symbol;
+
+int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter);
+
static inline
struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
const char *name, struct map **mapp,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 9812531..c90e55c 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -998,8 +998,10 @@
char evt_path[MAXPATHLEN];
char dir_path[MAXPATHLEN];
- if (debugfs_valid_mountpoint(tracing_events_path))
+ if (debugfs_valid_mountpoint(tracing_events_path)) {
+ printf(" [ Tracepoints not available: %s ]\n", strerror(errno));
return;
+ }
sys_dir = opendir(tracing_events_path);
if (!sys_dir)
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 91346b7..3432995 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -126,6 +126,37 @@
}
+<config>{
+config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
+config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
+config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); }
+name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); }
+period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
+branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
+, { return ','; }
+"/" { BEGIN(INITIAL); return '/'; }
+{name_minus} { return str(yyscanner, PE_NAME); }
+}
+
+<mem>{
+{modifier_bp} { return str(yyscanner, PE_MODIFIER_BP); }
+: { return ':'; }
+{num_dec} { return value(yyscanner, 10); }
+{num_hex} { return value(yyscanner, 16); }
+ /*
+ * We need to separate 'mem:' scanner part, in order to get specific
+ * modifier bits parsed out. Otherwise we would need to handle PE_NAME
+ * and we'd need to parse it manually. During the escape from <mem>
+ * state we need to put the escaping char back, so we dont miss it.
+ */
+. { unput(*yytext); BEGIN(INITIAL); }
+ /*
+ * We destroy the scanner after reaching EOF,
+ * but anyway just to be sure get back to INIT state.
+ */
+<<EOF>> { BEGIN(INITIAL); }
+}
+
cpu-cycles|cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
stalled-cycles-frontend|idle-cycles-frontend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
stalled-cycles-backend|idle-cycles-backend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
@@ -162,18 +193,6 @@
refs|Reference|ops|access |
misses|miss { return str(yyscanner, PE_NAME_CACHE_OP_RESULT); }
-<config>{
-config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
-config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
-config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); }
-name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); }
-period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
-branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
-, { return ','; }
-"/" { BEGIN(INITIAL); return '/'; }
-{name_minus} { return str(yyscanner, PE_NAME); }
-}
-
mem: { BEGIN(mem); return PE_PREFIX_MEM; }
r{num_raw_hex} { return raw(yyscanner); }
{num_dec} { return value(yyscanner, 10); }
@@ -189,25 +208,7 @@
"}" { return '}'; }
= { return '='; }
\n { }
-
-<mem>{
-{modifier_bp} { return str(yyscanner, PE_MODIFIER_BP); }
-: { return ':'; }
-{num_dec} { return value(yyscanner, 10); }
-{num_hex} { return value(yyscanner, 16); }
- /*
- * We need to separate 'mem:' scanner part, in order to get specific
- * modifier bits parsed out. Otherwise we would need to handle PE_NAME
- * and we'd need to parse it manually. During the escape from <mem>
- * state we need to put the escaping char back, so we dont miss it.
- */
-. { unput(*yytext); BEGIN(INITIAL); }
- /*
- * We destroy the scanner after reaching EOF,
- * but anyway just to be sure get back to INIT state.
- */
-<<EOF>> { BEGIN(INITIAL); }
-}
+. { }
%%
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index a8c4954..5d13cb4 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -22,19 +22,23 @@
return ".";
}
-#ifndef HAVE_STRLCPY
-size_t strlcpy(char *dest, const char *src, size_t size)
+/*
+ * If libc has strlcpy() then that version will override this
+ * implementation:
+ */
+size_t __weak strlcpy(char *dest, const char *src, size_t size)
{
size_t ret = strlen(src);
if (size) {
size_t len = (ret >= size) ? size - 1 : ret;
+
memcpy(dest, src, len);
dest[len] = '\0';
}
+
return ret;
}
-#endif
static char *get_pathname(void)
{
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index 5a4f2b6f..a3d42cd 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -1,7 +1,7 @@
#ifndef __PERF_REGS_H
#define __PERF_REGS_H
-#ifdef HAVE_PERF_REGS
+#ifdef HAVE_PERF_REGS_SUPPORT
#include <perf_regs.h>
#else
#define PERF_REGS_MASK 0
@@ -10,5 +10,5 @@
{
return NULL;
}
-#endif /* HAVE_PERF_REGS */
+#endif /* HAVE_PERF_REGS_SUPPORT */
#endif /* __PERF_REGS_H */
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index bc9d806..64362fe 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -637,3 +637,19 @@
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;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 6b2cbe2..1179b26 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -42,6 +42,7 @@
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 */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index aa04bf9..9c6989c 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -47,7 +47,6 @@
#include "session.h"
#define MAX_CMDLEN 256
-#define MAX_PROBE_ARGS 128
#define PERFPROBE_GROUP "probe"
bool probe_event_dry_run; /* Dry run flag */
@@ -201,7 +200,7 @@
return 0;
}
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
/* Open new debuginfo of given module */
static struct debuginfo *open_debuginfo(const char *module)
{
@@ -630,7 +629,7 @@
return ret;
}
-#else /* !DWARF_SUPPORT */
+#else /* !HAVE_DWARF_SUPPORT */
static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
struct perf_probe_point *pp)
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index f069273..e41b094 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -273,12 +273,15 @@
/*
* Convert a location into trace_arg.
* If tvar == NULL, this just checks variable can be converted.
+ * If fentry == true and vr_die is a parameter, do huristic search
+ * for the location fuzzed by function entry mcount.
*/
static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
- Dwarf_Op *fb_ops,
+ Dwarf_Op *fb_ops, Dwarf_Die *sp_die,
struct probe_trace_arg *tvar)
{
Dwarf_Attribute attr;
+ Dwarf_Addr tmp = 0;
Dwarf_Op *op;
size_t nops;
unsigned int regn;
@@ -291,12 +294,29 @@
goto static_var;
/* TODO: handle more than 1 exprs */
- if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL ||
- dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0 ||
- nops == 0) {
- /* TODO: Support const_value */
+ if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
+ return -EINVAL; /* Broken DIE ? */
+ if (dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0) {
+ ret = dwarf_entrypc(sp_die, &tmp);
+ if (ret || addr != tmp ||
+ dwarf_tag(vr_die) != DW_TAG_formal_parameter ||
+ dwarf_highpc(sp_die, &tmp))
+ return -ENOENT;
+ /*
+ * This is fuzzed by fentry mcount. We try to find the
+ * parameter location at the earliest address.
+ */
+ for (addr += 1; addr <= tmp; addr++) {
+ if (dwarf_getlocation_addr(&attr, addr, &op,
+ &nops, 1) > 0)
+ goto found;
+ }
return -ENOENT;
}
+found:
+ if (nops == 0)
+ /* TODO: Support const_value */
+ return -ENOENT;
if (op->atom == DW_OP_addr) {
static_var:
@@ -600,7 +620,7 @@
dwarf_diename(vr_die));
ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
- pf->tvar);
+ &pf->sp_die, pf->tvar);
if (ret == -ENOENT)
pr_err("Failed to find the location of %s at this address.\n"
" Perhaps, it has been optimized out.\n", pf->pvar->var);
@@ -1136,12 +1156,80 @@
return ret;
}
+struct local_vars_finder {
+ struct probe_finder *pf;
+ struct perf_probe_arg *args;
+ int max_args;
+ int nargs;
+ int ret;
+};
+
+/* Collect available variables in this scope */
+static int copy_variables_cb(Dwarf_Die *die_mem, void *data)
+{
+ struct local_vars_finder *vf = data;
+ struct probe_finder *pf = vf->pf;
+ int tag;
+
+ tag = dwarf_tag(die_mem);
+ if (tag == DW_TAG_formal_parameter ||
+ tag == DW_TAG_variable) {
+ if (convert_variable_location(die_mem, vf->pf->addr,
+ vf->pf->fb_ops, &pf->sp_die,
+ NULL) == 0) {
+ vf->args[vf->nargs].var = (char *)dwarf_diename(die_mem);
+ if (vf->args[vf->nargs].var == NULL) {
+ vf->ret = -ENOMEM;
+ return DIE_FIND_CB_END;
+ }
+ pr_debug(" %s", vf->args[vf->nargs].var);
+ vf->nargs++;
+ }
+ }
+
+ if (dwarf_haspc(die_mem, vf->pf->addr))
+ return DIE_FIND_CB_CONTINUE;
+ else
+ return DIE_FIND_CB_SIBLING;
+}
+
+static int expand_probe_args(Dwarf_Die *sc_die, struct probe_finder *pf,
+ struct perf_probe_arg *args)
+{
+ Dwarf_Die die_mem;
+ int i;
+ int n = 0;
+ struct local_vars_finder vf = {.pf = pf, .args = args,
+ .max_args = MAX_PROBE_ARGS, .ret = 0};
+
+ for (i = 0; i < pf->pev->nargs; i++) {
+ /* var never be NULL */
+ if (strcmp(pf->pev->args[i].var, "$vars") == 0) {
+ pr_debug("Expanding $vars into:");
+ vf.nargs = n;
+ /* Special local variables */
+ die_find_child(sc_die, copy_variables_cb, (void *)&vf,
+ &die_mem);
+ pr_debug(" (%d)\n", vf.nargs - n);
+ if (vf.ret < 0)
+ return vf.ret;
+ n = vf.nargs;
+ } else {
+ /* Copy normal argument */
+ args[n] = pf->pev->args[i];
+ n++;
+ }
+ }
+ return n;
+}
+
/* Add a found probe point into trace event list */
static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
{
struct trace_event_finder *tf =
container_of(pf, struct trace_event_finder, pf);
struct probe_trace_event *tev;
+ struct perf_probe_arg *args;
int ret, i;
/* Check number of tevs */
@@ -1161,21 +1249,35 @@
pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
tev->point.offset);
- /* Find each argument */
- tev->nargs = pf->pev->nargs;
- tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
- if (tev->args == NULL)
+ /* Expand special probe argument if exist */
+ args = zalloc(sizeof(struct perf_probe_arg) * MAX_PROBE_ARGS);
+ if (args == NULL)
return -ENOMEM;
- for (i = 0; i < pf->pev->nargs; i++) {
- pf->pvar = &pf->pev->args[i];
+
+ ret = expand_probe_args(sc_die, pf, args);
+ if (ret < 0)
+ goto end;
+
+ tev->nargs = ret;
+ tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
+ if (tev->args == NULL) {
+ ret = -ENOMEM;
+ goto end;
+ }
+
+ /* Find each argument */
+ for (i = 0; i < tev->nargs; i++) {
+ pf->pvar = &args[i];
pf->tvar = &tev->args[i];
/* Variable should be found from scope DIE */
ret = find_variable(sc_die, pf);
if (ret != 0)
- return ret;
+ break;
}
- return 0;
+end:
+ free(args);
+ return ret;
}
/* Find probe_trace_events specified by perf_probe_event from debuginfo */
@@ -1222,7 +1324,8 @@
if (tag == DW_TAG_formal_parameter ||
tag == DW_TAG_variable) {
ret = convert_variable_location(die_mem, af->pf.addr,
- af->pf.fb_ops, NULL);
+ af->pf.fb_ops, &af->pf.sp_die,
+ NULL);
if (ret == 0) {
ret = die_get_varname(die_mem, buf, MAX_VAR_LEN);
pr_debug2("Add new var: %s\n", buf);
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 3b7d630..d6dab0e 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -7,6 +7,7 @@
#define MAX_PROBE_BUFFER 1024
#define MAX_PROBES 128
+#define MAX_PROBE_ARGS 128
static inline int is_c_varname(const char *name)
{
@@ -14,7 +15,7 @@
return isalpha(name[0]) || name[0] == '_';
}
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
#include "dwarf-aux.h"
@@ -105,6 +106,6 @@
int found;
};
-#endif /* DWARF_SUPPORT */
+#endif /* HAVE_DWARF_SUPPORT */
#endif /*_PROBE_FINDER_H */
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 2ac4bc9..4bf8ace 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -33,13 +33,6 @@
# define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size,
#endif
-struct throttle_event {
- struct perf_event_header header;
- u64 time;
- u64 id;
- u64 stream_id;
-};
-
PyMODINIT_FUNC initperf(void);
#define member_def(type, member, ptype, help) \
@@ -1038,6 +1031,7 @@
pyrf_cpu_map__setup_types() < 0)
return;
+ /* The page_size is placed in util object. */
page_size = sysconf(_SC_PAGE_SIZE);
Py_INCREF(&pyrf_evlist__type);
diff --git a/tools/perf/util/rblist.c b/tools/perf/util/rblist.c
index a16cdd2..0dfe27d 100644
--- a/tools/perf/util/rblist.c
+++ b/tools/perf/util/rblist.c
@@ -48,10 +48,12 @@
rblist->node_delete(rblist, rb_node);
}
-struct rb_node *rblist__find(struct rblist *rblist, const void *entry)
+static struct rb_node *__rblist__findnew(struct rblist *rblist,
+ const void *entry,
+ bool create)
{
struct rb_node **p = &rblist->entries.rb_node;
- struct rb_node *parent = NULL;
+ struct rb_node *parent = NULL, *new_node = NULL;
while (*p != NULL) {
int rc;
@@ -67,7 +69,26 @@
return parent;
}
- return NULL;
+ if (create) {
+ new_node = rblist->node_new(rblist, entry);
+ if (new_node) {
+ rb_link_node(new_node, parent, p);
+ rb_insert_color(new_node, &rblist->entries);
+ ++rblist->nr_entries;
+ }
+ }
+
+ return new_node;
+}
+
+struct rb_node *rblist__find(struct rblist *rblist, const void *entry)
+{
+ return __rblist__findnew(rblist, entry, false);
+}
+
+struct rb_node *rblist__findnew(struct rblist *rblist, const void *entry)
+{
+ return __rblist__findnew(rblist, entry, true);
}
void rblist__init(struct rblist *rblist)
diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h
index 6d0cae5..ff9913b 100644
--- a/tools/perf/util/rblist.h
+++ b/tools/perf/util/rblist.h
@@ -32,6 +32,7 @@
int rblist__add_node(struct rblist *rblist, const void *new_entry);
void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node);
struct rb_node *rblist__find(struct rblist *rblist, const void *entry);
+struct rb_node *rblist__findnew(struct rblist *rblist, const void *entry);
struct rb_node *rblist__entry(const struct rblist *rblist, unsigned int idx);
static inline bool rblist__empty(const struct rblist *rblist)
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 568b750..4ba7b54 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -16,73 +16,34 @@
#include "perf_regs.h"
#include "vdso.h"
-static int perf_session__open(struct perf_session *self, bool force)
+static int perf_session__open(struct perf_session *self)
{
- struct stat input_stat;
-
- if (!strcmp(self->filename, "-")) {
- self->fd_pipe = true;
- self->fd = STDIN_FILENO;
-
- if (perf_session__read_header(self) < 0)
- pr_err("incompatible file format (rerun with -v to learn more)");
-
- return 0;
- }
-
- self->fd = open(self->filename, O_RDONLY);
- if (self->fd < 0) {
- int err = errno;
-
- pr_err("failed to open %s: %s", self->filename, strerror(err));
- if (err == ENOENT && !strcmp(self->filename, "perf.data"))
- pr_err(" (try 'perf record' first)");
- pr_err("\n");
- return -errno;
- }
-
- if (fstat(self->fd, &input_stat) < 0)
- goto out_close;
-
- if (!force && input_stat.st_uid && (input_stat.st_uid != geteuid())) {
- pr_err("file %s not owned by current user or root\n",
- self->filename);
- goto out_close;
- }
-
- if (!input_stat.st_size) {
- pr_info("zero-sized file (%s), nothing to do!\n",
- self->filename);
- goto out_close;
- }
+ struct perf_data_file *file = self->file;
if (perf_session__read_header(self) < 0) {
pr_err("incompatible file format (rerun with -v to learn more)");
- goto out_close;
+ return -1;
}
+ if (perf_data_file__is_pipe(file))
+ return 0;
+
if (!perf_evlist__valid_sample_type(self->evlist)) {
pr_err("non matching sample_type");
- goto out_close;
+ return -1;
}
if (!perf_evlist__valid_sample_id_all(self->evlist)) {
pr_err("non matching sample_id_all");
- goto out_close;
+ return -1;
}
if (!perf_evlist__valid_read_format(self->evlist)) {
pr_err("non matching read_format");
- goto out_close;
+ return -1;
}
- self->size = input_stat.st_size;
return 0;
-
-out_close:
- close(self->fd);
- self->fd = -1;
- return -1;
}
void perf_session__set_id_hdr_size(struct perf_session *session)
@@ -106,39 +67,36 @@
machines__destroy_kernel_maps(&self->machines);
}
-struct perf_session *perf_session__new(const char *filename, int mode,
- bool force, bool repipe,
- struct perf_tool *tool)
+struct perf_session *perf_session__new(struct perf_data_file *file,
+ bool repipe, struct perf_tool *tool)
{
struct perf_session *self;
- struct stat st;
- size_t len;
- if (!filename || !strlen(filename)) {
- if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
- filename = "-";
- else
- filename = "perf.data";
- }
-
- len = strlen(filename);
- self = zalloc(sizeof(*self) + len);
-
- if (self == NULL)
+ self = zalloc(sizeof(*self));
+ if (!self)
goto out;
- memcpy(self->filename, filename, len);
self->repipe = repipe;
INIT_LIST_HEAD(&self->ordered_samples.samples);
INIT_LIST_HEAD(&self->ordered_samples.sample_cache);
INIT_LIST_HEAD(&self->ordered_samples.to_free);
machines__init(&self->machines);
- if (mode == O_RDONLY) {
- if (perf_session__open(self, force) < 0)
+ if (file) {
+ if (perf_data_file__open(file))
goto out_delete;
- perf_session__set_id_hdr_size(self);
- } else if (mode == O_WRONLY) {
+
+ self->file = file;
+
+ if (perf_data_file__is_read(file)) {
+ if (perf_session__open(self) < 0)
+ goto out_close;
+
+ perf_session__set_id_hdr_size(self);
+ }
+ }
+
+ if (!file || perf_data_file__is_write(file)) {
/*
* In O_RDONLY mode this will be performed when reading the
* kernel MMAP event, in perf_event__process_mmap().
@@ -153,10 +111,13 @@
tool->ordered_samples = false;
}
-out:
return self;
-out_delete:
+
+ out_close:
+ perf_data_file__close(file);
+ out_delete:
perf_session__delete(self);
+ out:
return NULL;
}
@@ -193,7 +154,8 @@
perf_session__delete_threads(self);
perf_session_env__delete(&self->header.env);
machines__exit(&self->machines);
- close(self->fd);
+ if (self->file)
+ perf_data_file__close(self->file);
free(self);
vdso__exit();
}
@@ -397,6 +359,17 @@
swap_sample_id_all(event, &event->read + 1);
}
+static void perf_event__throttle_swap(union perf_event *event,
+ bool sample_id_all)
+{
+ event->throttle.time = bswap_64(event->throttle.time);
+ event->throttle.id = bswap_64(event->throttle.id);
+ event->throttle.stream_id = bswap_64(event->throttle.stream_id);
+
+ if (sample_id_all)
+ swap_sample_id_all(event, &event->throttle + 1);
+}
+
static u8 revbyte(u8 b)
{
int rev = (b >> 4) | ((b & 0xf) << 4);
@@ -442,6 +415,9 @@
attr->bp_type = bswap_32(attr->bp_type);
attr->bp_addr = bswap_64(attr->bp_addr);
attr->bp_len = bswap_64(attr->bp_len);
+ attr->branch_sample_type = bswap_64(attr->branch_sample_type);
+ attr->sample_regs_user = bswap_64(attr->sample_regs_user);
+ attr->sample_stack_user = bswap_32(attr->sample_stack_user);
swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
}
@@ -482,6 +458,8 @@
[PERF_RECORD_EXIT] = perf_event__task_swap,
[PERF_RECORD_LOST] = perf_event__all64_swap,
[PERF_RECORD_READ] = perf_event__read_swap,
+ [PERF_RECORD_THROTTLE] = perf_event__throttle_swap,
+ [PERF_RECORD_UNTHROTTLE] = perf_event__throttle_swap,
[PERF_RECORD_SAMPLE] = perf_event__all64_swap,
[PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap,
[PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap,
@@ -525,13 +503,16 @@
struct perf_sample sample;
u64 limit = os->next_flush;
u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
- unsigned idx = 0, progress_next = os->nr_samples / 16;
bool show_progress = limit == ULLONG_MAX;
+ struct ui_progress prog;
int ret;
if (!tool->ordered_samples || !limit)
return 0;
+ if (show_progress)
+ ui_progress__init(&prog, os->nr_samples, "Processing time ordered events...");
+
list_for_each_entry_safe(iter, tmp, head, list) {
if (session_done())
return 0;
@@ -552,11 +533,9 @@
os->last_flush = iter->timestamp;
list_del(&iter->list);
list_add(&iter->list, &os->sample_cache);
- if (show_progress && (++idx >= progress_next)) {
- progress_next += os->nr_samples / 16;
- ui_progress__update(idx, os->nr_samples,
- "Processing time ordered events...");
- }
+
+ if (show_progress)
+ ui_progress__update(&prog, 1);
}
if (list_empty(head)) {
@@ -860,6 +839,9 @@
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);
}
@@ -1031,6 +1013,7 @@
static int perf_session__process_user_event(struct perf_session *session, union perf_event *event,
struct perf_tool *tool, u64 file_offset)
{
+ int fd = perf_data_file__fd(session->file);
int err;
dump_event(session, event, file_offset, NULL);
@@ -1044,7 +1027,7 @@
return err;
case PERF_RECORD_HEADER_TRACING_DATA:
/* setup for reading amidst mmap */
- lseek(session->fd, file_offset, SEEK_SET);
+ lseek(fd, file_offset, SEEK_SET);
return tool->tracing_data(tool, event, session);
case PERF_RECORD_HEADER_BUILD_ID:
return tool->build_id(tool, event, session);
@@ -1170,6 +1153,7 @@
static int __perf_session__process_pipe_events(struct perf_session *self,
struct perf_tool *tool)
{
+ int fd = perf_data_file__fd(self->file);
union perf_event *event;
uint32_t size, cur_size = 0;
void *buf = NULL;
@@ -1188,7 +1172,7 @@
return -errno;
more:
event = buf;
- err = readn(self->fd, event, sizeof(struct perf_event_header));
+ err = readn(fd, event, sizeof(struct perf_event_header));
if (err <= 0) {
if (err == 0)
goto done;
@@ -1220,7 +1204,7 @@
p += sizeof(struct perf_event_header);
if (size - sizeof(struct perf_event_header)) {
- err = readn(self->fd, p, size - sizeof(struct perf_event_header));
+ err = readn(fd, p, size - sizeof(struct perf_event_header));
if (err <= 0) {
if (err == 0) {
pr_err("unexpected end of event stream\n");
@@ -1247,7 +1231,9 @@
if (!session_done())
goto more;
done:
- err = 0;
+ /* do the final flush for ordered samples */
+ self->ordered_samples.next_flush = ULLONG_MAX;
+ err = flush_sample_queue(self, tool);
out_err:
free(buf);
perf_session__warn_about_errors(self, tool);
@@ -1299,12 +1285,14 @@
u64 data_offset, u64 data_size,
u64 file_size, struct perf_tool *tool)
{
- u64 head, page_offset, file_offset, file_pos, progress_next;
+ int fd = perf_data_file__fd(session->file);
+ u64 head, page_offset, file_offset, file_pos;
int err, mmap_prot, mmap_flags, map_idx = 0;
size_t mmap_size;
char *buf, *mmaps[NUM_MMAPS];
union perf_event *event;
uint32_t size;
+ struct ui_progress prog;
perf_tool__fill_defaults(tool);
@@ -1315,7 +1303,7 @@
if (data_size && (data_offset + data_size < file_size))
file_size = data_offset + data_size;
- progress_next = file_size / 16;
+ ui_progress__init(&prog, file_size, "Processing events...");
mmap_size = MMAP_SIZE;
if (mmap_size > file_size)
@@ -1331,7 +1319,7 @@
mmap_flags = MAP_PRIVATE;
}
remap:
- buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, session->fd,
+ buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, fd,
file_offset);
if (buf == MAP_FAILED) {
pr_err("failed to mmap file\n");
@@ -1370,19 +1358,15 @@
head += size;
file_pos += size;
- if (file_pos >= progress_next) {
- progress_next += file_size / 16;
- ui_progress__update(file_pos, file_size,
- "Processing events...");
- }
+ ui_progress__update(&prog, size);
- err = 0;
if (session_done())
- goto out_err;
+ goto out;
if (file_pos < file_size)
goto more;
+out:
/* do the final flush for ordered samples */
session->ordered_samples.next_flush = ULLONG_MAX;
err = flush_sample_queue(session, tool);
@@ -1396,16 +1380,17 @@
int perf_session__process_events(struct perf_session *self,
struct perf_tool *tool)
{
+ u64 size = perf_data_file__size(self->file);
int err;
if (perf_session__register_idle_thread(self) == NULL)
return -ENOMEM;
- if (!self->fd_pipe)
+ if (!perf_data_file__is_pipe(self->file))
err = __perf_session__process_events(self,
self->header.data_offset,
self->header.data_size,
- self->size, tool);
+ size, tool);
else
err = __perf_session__process_pipe_events(self, tool);
@@ -1525,7 +1510,8 @@
if (symbol_conf.use_callchain && sample->callchain) {
if (machine__resolve_callchain(machine, evsel, al.thread,
- sample, NULL, NULL) != 0) {
+ sample, NULL, NULL,
+ PERF_MAX_STACK_DEPTH) != 0) {
if (verbose)
error("Failed to resolve callchain. Skipping\n");
return;
@@ -1629,13 +1615,14 @@
void perf_session__fprintf_info(struct perf_session *session, FILE *fp,
bool full)
{
+ int fd = perf_data_file__fd(session->file);
struct stat st;
int ret;
if (session == NULL || fp == NULL)
return;
- ret = fstat(session->fd, &st);
+ ret = fstat(fd, &st);
if (ret == -1)
return;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 04bf737..27c74d3 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -7,6 +7,7 @@
#include "machine.h"
#include "symbol.h"
#include "thread.h"
+#include "data.h"
#include <linux/rbtree.h>
#include <linux/perf_event.h>
@@ -29,16 +30,13 @@
struct perf_session {
struct perf_header header;
- unsigned long size;
struct machines machines;
struct perf_evlist *evlist;
struct pevent *pevent;
struct events_stats stats;
- int fd;
- bool fd_pipe;
bool repipe;
struct ordered_samples ordered_samples;
- char filename[1];
+ struct perf_data_file *file;
};
#define PRINT_IP_OPT_IP (1<<0)
@@ -49,9 +47,8 @@
struct perf_tool;
-struct perf_session *perf_session__new(const char *filename, int mode,
- bool force, bool repipe,
- struct perf_tool *tool);
+struct perf_session *perf_session__new(struct perf_data_file *file,
+ bool repipe, struct perf_tool *tool);
void perf_session__delete(struct perf_session *session);
void perf_event_header__bswap(struct perf_event_header *self);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 5f118a0..19b4aa2 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -60,11 +60,11 @@
return right->thread->tid - left->thread->tid;
}
-static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%*s:%5d", width - 6,
- self->thread->comm ?: "", self->thread->tid);
+ he->thread->comm ?: "", he->thread->tid);
}
struct sort_entry sort_thread = {
@@ -94,10 +94,10 @@
return strcmp(comm_l, comm_r);
}
-static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return repsep_snprintf(bf, size, "%*s", width, self->thread->comm);
+ return repsep_snprintf(bf, size, "%*s", width, he->thread->comm);
}
struct sort_entry sort_comm = {
@@ -148,10 +148,10 @@
return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
}
-static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return _hist_entry__dso_snprintf(self->ms.map, bf, size, width);
+ return _hist_entry__dso_snprintf(he->ms.map, bf, size, width);
}
struct sort_entry sort_dso = {
@@ -182,9 +182,19 @@
static int64_t
sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
{
+ int64_t ret;
+
if (!left->ms.sym && !right->ms.sym)
return right->level - left->level;
+ /*
+ * comparing symbol address alone is not enough since it's a
+ * relative address within a dso.
+ */
+ ret = sort__dso_cmp(left, right);
+ if (ret != 0)
+ return ret;
+
return _sort__sym_cmp(left->ms.sym, right->ms.sym);
}
@@ -224,11 +234,11 @@
return ret;
}
-static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return _hist_entry__sym_snprintf(self->ms.map, self->ms.sym, self->ip,
- self->level, bf, size, width);
+ return _hist_entry__sym_snprintf(he->ms.map, he->ms.sym, he->ip,
+ he->level, bf, size, width);
}
struct sort_entry sort_sym = {
@@ -243,50 +253,32 @@
static int64_t
sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
{
- return (int64_t)(right->ip - left->ip);
+ if (!left->srcline) {
+ if (!left->ms.map)
+ left->srcline = SRCLINE_UNKNOWN;
+ else {
+ struct map *map = left->ms.map;
+ left->srcline = get_srcline(map->dso,
+ map__rip_2objdump(map, left->ip));
+ }
+ }
+ if (!right->srcline) {
+ if (!right->ms.map)
+ right->srcline = SRCLINE_UNKNOWN;
+ else {
+ struct map *map = right->ms.map;
+ right->srcline = get_srcline(map->dso,
+ map__rip_2objdump(map, right->ip));
+ }
+ }
+ return strcmp(left->srcline, right->srcline);
}
-static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
size_t size,
unsigned int width __maybe_unused)
{
- FILE *fp = NULL;
- char cmd[PATH_MAX + 2], *path = self->srcline, *nl;
- size_t line_len;
-
- if (path != NULL)
- goto out_path;
-
- if (!self->ms.map)
- goto out_ip;
-
- if (!strncmp(self->ms.map->dso->long_name, "/tmp/perf-", 10))
- goto out_ip;
-
- snprintf(cmd, sizeof(cmd), "addr2line -e %s %016" PRIx64,
- self->ms.map->dso->long_name, self->ip);
- fp = popen(cmd, "r");
- if (!fp)
- goto out_ip;
-
- if (getline(&path, &line_len, fp) < 0 || !line_len)
- goto out_ip;
- self->srcline = strdup(path);
- if (self->srcline == NULL)
- goto out_ip;
-
- nl = strchr(self->srcline, '\n');
- if (nl != NULL)
- *nl = '\0';
- path = self->srcline;
-out_path:
- if (fp)
- pclose(fp);
- return repsep_snprintf(bf, size, "%s", path);
-out_ip:
- if (fp)
- pclose(fp);
- return repsep_snprintf(bf, size, "%-#*llx", BITS_PER_LONG / 4, self->ip);
+ return repsep_snprintf(bf, size, "%s", he->srcline);
}
struct sort_entry sort_srcline = {
@@ -310,11 +302,11 @@
return strcmp(sym_l->name, sym_r->name);
}
-static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%-*s", width,
- self->parent ? self->parent->name : "[other]");
+ he->parent ? he->parent->name : "[other]");
}
struct sort_entry sort_parent = {
@@ -332,10 +324,10 @@
return right->cpu - left->cpu;
}
-static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf,
- size_t size, unsigned int width)
+static int hist_entry__cpu_snprintf(struct hist_entry *he, char *bf,
+ size_t size, unsigned int width)
{
- return repsep_snprintf(bf, size, "%*d", width, self->cpu);
+ return repsep_snprintf(bf, size, "%*d", width, he->cpu);
}
struct sort_entry sort_cpu = {
@@ -354,10 +346,10 @@
right->branch_info->from.map);
}
-static int hist_entry__dso_from_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return _hist_entry__dso_snprintf(self->branch_info->from.map,
+ return _hist_entry__dso_snprintf(he->branch_info->from.map,
bf, size, width);
}
@@ -368,10 +360,10 @@
right->branch_info->to.map);
}
-static int hist_entry__dso_to_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return _hist_entry__dso_snprintf(self->branch_info->to.map,
+ return _hist_entry__dso_snprintf(he->branch_info->to.map,
bf, size, width);
}
@@ -399,21 +391,21 @@
return _sort__sym_cmp(to_l->sym, to_r->sym);
}
-static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- struct addr_map_symbol *from = &self->branch_info->from;
+ struct addr_map_symbol *from = &he->branch_info->from;
return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
- self->level, bf, size, width);
+ he->level, bf, size, width);
}
-static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- struct addr_map_symbol *to = &self->branch_info->to;
+ struct addr_map_symbol *to = &he->branch_info->to;
return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
- self->level, bf, size, width);
+ he->level, bf, size, width);
}
@@ -456,13 +448,13 @@
return mp || p;
}
-static int hist_entry__mispredict_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width){
static const char *out = "N/A";
- if (self->branch_info->flags.predicted)
+ if (he->branch_info->flags.predicted)
out = "N";
- else if (self->branch_info->flags.mispred)
+ else if (he->branch_info->flags.mispred)
out = "Y";
return repsep_snprintf(bf, size, "%-*s", width, out);
@@ -482,19 +474,19 @@
return (int64_t)(r - l);
}
-static int hist_entry__daddr_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__daddr_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
uint64_t addr = 0;
struct map *map = NULL;
struct symbol *sym = NULL;
- if (self->mem_info) {
- addr = self->mem_info->daddr.addr;
- map = self->mem_info->daddr.map;
- sym = self->mem_info->daddr.sym;
+ if (he->mem_info) {
+ addr = he->mem_info->daddr.addr;
+ map = he->mem_info->daddr.map;
+ sym = he->mem_info->daddr.sym;
}
- return _hist_entry__sym_snprintf(map, sym, addr, self->level, bf, size,
+ return _hist_entry__sym_snprintf(map, sym, addr, he->level, bf, size,
width);
}
@@ -512,13 +504,13 @@
return _sort__dso_cmp(map_l, map_r);
}
-static int hist_entry__dso_daddr_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__dso_daddr_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
struct map *map = NULL;
- if (self->mem_info)
- map = self->mem_info->daddr.map;
+ if (he->mem_info)
+ map = he->mem_info->daddr.map;
return _hist_entry__dso_snprintf(map, bf, size, width);
}
@@ -542,14 +534,14 @@
return (int64_t)(data_src_r.mem_lock - data_src_l.mem_lock);
}
-static int hist_entry__locked_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__locked_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
const char *out;
u64 mask = PERF_MEM_LOCK_NA;
- if (self->mem_info)
- mask = self->mem_info->data_src.mem_lock;
+ if (he->mem_info)
+ mask = he->mem_info->data_src.mem_lock;
if (mask & PERF_MEM_LOCK_NA)
out = "N/A";
@@ -591,7 +583,7 @@
};
#define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *))
-static int hist_entry__tlb_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
char out[64];
@@ -602,8 +594,8 @@
out[0] = '\0';
- if (self->mem_info)
- m = self->mem_info->data_src.mem_dtlb;
+ if (he->mem_info)
+ m = he->mem_info->data_src.mem_dtlb;
hit = m & PERF_MEM_TLB_HIT;
miss = m & PERF_MEM_TLB_MISS;
@@ -668,7 +660,7 @@
};
#define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *))
-static int hist_entry__lvl_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
char out[64];
@@ -677,8 +669,8 @@
u64 m = PERF_MEM_LVL_NA;
u64 hit, miss;
- if (self->mem_info)
- m = self->mem_info->data_src.mem_lvl;
+ if (he->mem_info)
+ m = he->mem_info->data_src.mem_lvl;
out[0] = '\0';
@@ -736,7 +728,7 @@
};
#define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *))
-static int hist_entry__snoop_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
char out[64];
@@ -746,8 +738,8 @@
out[0] = '\0';
- if (self->mem_info)
- m = self->mem_info->data_src.mem_snoop;
+ if (he->mem_info)
+ m = he->mem_info->data_src.mem_snoop;
for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) {
if (!(m & 0x1))
@@ -784,10 +776,10 @@
return he_weight(left) - he_weight(right);
}
-static int hist_entry__local_weight_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__local_weight_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return repsep_snprintf(bf, size, "%-*llu", width, he_weight(self));
+ return repsep_snprintf(bf, size, "%-*llu", width, he_weight(he));
}
struct sort_entry sort_local_weight = {
@@ -803,10 +795,10 @@
return left->stat.weight - right->stat.weight;
}
-static int hist_entry__global_weight_snprintf(struct hist_entry *self, char *bf,
+static int hist_entry__global_weight_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return repsep_snprintf(bf, size, "%-*llu", width, self->stat.weight);
+ return repsep_snprintf(bf, size, "%-*llu", width, he->stat.weight);
}
struct sort_entry sort_global_weight = {
@@ -858,6 +850,127 @@
.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 *he, char *bf,
+ size_t size, unsigned int width)
+{
+ static const char *out = ".";
+
+ if (he->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 *he, char *bf,
+ size_t size, unsigned int width)
+{
+ static const char *out = ".";
+
+ if (he->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 *he, char *bf,
+ size_t size, unsigned int width)
+{
+ u64 t = he->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;
@@ -876,6 +989,7 @@
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
@@ -888,6 +1002,8 @@
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
@@ -1009,7 +1125,7 @@
return ret;
}
-static void sort_entry__setup_elide(struct sort_entry *self,
+static void sort_entry__setup_elide(struct sort_entry *se,
struct strlist *list,
const char *list_name, FILE *fp)
{
@@ -1017,7 +1133,7 @@
if (fp != NULL)
fprintf(fp, "# %s: %s\n", list_name,
strlist__entry(list, 0)->s);
- self->elide = true;
+ se->elide = true;
}
}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 4e80dbd..bf43336 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -85,6 +85,7 @@
struct map_symbol ms;
struct thread *thread;
u64 ip;
+ u64 transaction;
s32 cpu;
struct hist_entry_diff diff;
@@ -145,6 +146,7 @@
SORT_SRCLINE,
SORT_LOCAL_WEIGHT,
SORT_GLOBAL_WEIGHT,
+ SORT_TRANSACTION,
/* branch stack specific sort keys */
__SORT_BRANCH_STACK,
@@ -153,6 +155,8 @@
SORT_SYM_FROM,
SORT_SYM_TO,
SORT_MISPREDICT,
+ SORT_ABORT,
+ SORT_IN_TX,
/* memory mode specific sort keys */
__SORT_MEMORY_MODE,
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
new file mode 100644
index 0000000..d11aefb
--- /dev/null
+++ b/tools/perf/util/srcline.c
@@ -0,0 +1,265 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <linux/kernel.h>
+
+#include "util/dso.h"
+#include "util/util.h"
+#include "util/debug.h"
+
+#ifdef HAVE_LIBBFD_SUPPORT
+
+/*
+ * Implement addr2line using libbfd.
+ */
+#define PACKAGE "perf"
+#include <bfd.h>
+
+struct a2l_data {
+ const char *input;
+ unsigned long addr;
+
+ bool found;
+ const char *filename;
+ const char *funcname;
+ unsigned line;
+
+ bfd *abfd;
+ asymbol **syms;
+};
+
+static int bfd_error(const char *string)
+{
+ const char *errmsg;
+
+ errmsg = bfd_errmsg(bfd_get_error());
+ fflush(stdout);
+
+ if (string)
+ pr_debug("%s: %s\n", string, errmsg);
+ else
+ pr_debug("%s\n", errmsg);
+
+ return -1;
+}
+
+static int slurp_symtab(bfd *abfd, struct a2l_data *a2l)
+{
+ long storage;
+ long symcount;
+ asymbol **syms;
+ bfd_boolean dynamic = FALSE;
+
+ if ((bfd_get_file_flags(abfd) & HAS_SYMS) == 0)
+ return bfd_error(bfd_get_filename(abfd));
+
+ storage = bfd_get_symtab_upper_bound(abfd);
+ if (storage == 0L) {
+ storage = bfd_get_dynamic_symtab_upper_bound(abfd);
+ dynamic = TRUE;
+ }
+ if (storage < 0L)
+ return bfd_error(bfd_get_filename(abfd));
+
+ syms = malloc(storage);
+ if (dynamic)
+ symcount = bfd_canonicalize_dynamic_symtab(abfd, syms);
+ else
+ symcount = bfd_canonicalize_symtab(abfd, syms);
+
+ if (symcount < 0) {
+ free(syms);
+ return bfd_error(bfd_get_filename(abfd));
+ }
+
+ a2l->syms = syms;
+ return 0;
+}
+
+static void find_address_in_section(bfd *abfd, asection *section, void *data)
+{
+ bfd_vma pc, vma;
+ bfd_size_type size;
+ struct a2l_data *a2l = data;
+
+ if (a2l->found)
+ return;
+
+ if ((bfd_get_section_flags(abfd, section) & SEC_ALLOC) == 0)
+ return;
+
+ pc = a2l->addr;
+ vma = bfd_get_section_vma(abfd, section);
+ size = bfd_get_section_size(section);
+
+ if (pc < vma || pc >= vma + size)
+ return;
+
+ a2l->found = bfd_find_nearest_line(abfd, section, a2l->syms, pc - vma,
+ &a2l->filename, &a2l->funcname,
+ &a2l->line);
+}
+
+static struct a2l_data *addr2line_init(const char *path)
+{
+ bfd *abfd;
+ struct a2l_data *a2l = NULL;
+
+ abfd = bfd_openr(path, NULL);
+ if (abfd == NULL)
+ return NULL;
+
+ if (!bfd_check_format(abfd, bfd_object))
+ goto out;
+
+ a2l = zalloc(sizeof(*a2l));
+ if (a2l == NULL)
+ goto out;
+
+ a2l->abfd = abfd;
+ a2l->input = strdup(path);
+ if (a2l->input == NULL)
+ goto out;
+
+ if (slurp_symtab(abfd, a2l))
+ goto out;
+
+ return a2l;
+
+out:
+ if (a2l) {
+ free((void *)a2l->input);
+ free(a2l);
+ }
+ bfd_close(abfd);
+ return NULL;
+}
+
+static void addr2line_cleanup(struct a2l_data *a2l)
+{
+ if (a2l->abfd)
+ bfd_close(a2l->abfd);
+ free((void *)a2l->input);
+ free(a2l->syms);
+ free(a2l);
+}
+
+static int addr2line(const char *dso_name, unsigned long addr,
+ char **file, unsigned int *line)
+{
+ int ret = 0;
+ struct a2l_data *a2l;
+
+ a2l = addr2line_init(dso_name);
+ if (a2l == NULL) {
+ pr_warning("addr2line_init failed for %s\n", dso_name);
+ return 0;
+ }
+
+ a2l->addr = addr;
+ bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l);
+
+ if (a2l->found && a2l->filename) {
+ *file = strdup(a2l->filename);
+ *line = a2l->line;
+
+ if (*file)
+ ret = 1;
+ }
+
+ addr2line_cleanup(a2l);
+ return ret;
+}
+
+#else /* HAVE_LIBBFD_SUPPORT */
+
+static int addr2line(const char *dso_name, unsigned long addr,
+ char **file, unsigned int *line_nr)
+{
+ FILE *fp;
+ char cmd[PATH_MAX];
+ char *filename = NULL;
+ size_t len;
+ char *sep;
+ int ret = 0;
+
+ scnprintf(cmd, sizeof(cmd), "addr2line -e %s %016"PRIx64,
+ dso_name, addr);
+
+ fp = popen(cmd, "r");
+ if (fp == NULL) {
+ pr_warning("popen failed for %s\n", dso_name);
+ return 0;
+ }
+
+ if (getline(&filename, &len, fp) < 0 || !len) {
+ pr_warning("addr2line has no output for %s\n", dso_name);
+ goto out;
+ }
+
+ sep = strchr(filename, '\n');
+ if (sep)
+ *sep = '\0';
+
+ if (!strcmp(filename, "??:0")) {
+ pr_debug("no debugging info in %s\n", dso_name);
+ free(filename);
+ goto out;
+ }
+
+ sep = strchr(filename, ':');
+ if (sep) {
+ *sep++ = '\0';
+ *file = filename;
+ *line_nr = strtoul(sep, NULL, 0);
+ ret = 1;
+ }
+out:
+ pclose(fp);
+ return ret;
+}
+#endif /* HAVE_LIBBFD_SUPPORT */
+
+char *get_srcline(struct dso *dso, unsigned long addr)
+{
+ char *file = NULL;
+ unsigned line = 0;
+ char *srcline;
+ char *dso_name = dso->long_name;
+ size_t size;
+
+ if (!dso->has_srcline)
+ return SRCLINE_UNKNOWN;
+
+ if (dso_name[0] == '[')
+ goto out;
+
+ if (!strncmp(dso_name, "/tmp/perf-", 10))
+ goto out;
+
+ if (!addr2line(dso_name, addr, &file, &line))
+ goto out;
+
+ /* just calculate actual length */
+ size = snprintf(NULL, 0, "%s:%u", file, line) + 1;
+
+ srcline = malloc(size);
+ if (srcline)
+ snprintf(srcline, size, "%s:%u", file, line);
+ else
+ srcline = SRCLINE_UNKNOWN;
+
+ free(file);
+ return srcline;
+
+out:
+ dso->has_srcline = 0;
+ return SRCLINE_UNKNOWN;
+}
+
+void free_srcline(char *srcline)
+{
+ if (srcline && strcmp(srcline, SRCLINE_UNKNOWN) != 0)
+ free(srcline);
+}
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index 834c8eb..67e4a00 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -10,22 +10,22 @@
#define is_operator(c) ((c) == '|' || (c) == '&' || (c) == '!')
#define is_separator(c) (is_operator(c) || (c) == '(' || (c) == ')')
-static void strfilter_node__delete(struct strfilter_node *self)
+static void strfilter_node__delete(struct strfilter_node *node)
{
- if (self) {
- if (self->p && !is_operator(*self->p))
- free((char *)self->p);
- strfilter_node__delete(self->l);
- strfilter_node__delete(self->r);
- free(self);
+ if (node) {
+ if (node->p && !is_operator(*node->p))
+ free((char *)node->p);
+ strfilter_node__delete(node->l);
+ strfilter_node__delete(node->r);
+ free(node);
}
}
-void strfilter__delete(struct strfilter *self)
+void strfilter__delete(struct strfilter *filter)
{
- if (self) {
- strfilter_node__delete(self->root);
- free(self);
+ if (filter) {
+ strfilter_node__delete(filter->root);
+ free(filter);
}
}
@@ -170,30 +170,30 @@
return ret;
}
-static bool strfilter_node__compare(struct strfilter_node *self,
+static bool strfilter_node__compare(struct strfilter_node *node,
const char *str)
{
- if (!self || !self->p)
+ if (!node || !node->p)
return false;
- switch (*self->p) {
+ switch (*node->p) {
case '|': /* OR */
- return strfilter_node__compare(self->l, str) ||
- strfilter_node__compare(self->r, str);
+ return strfilter_node__compare(node->l, str) ||
+ strfilter_node__compare(node->r, str);
case '&': /* AND */
- return strfilter_node__compare(self->l, str) &&
- strfilter_node__compare(self->r, str);
+ return strfilter_node__compare(node->l, str) &&
+ strfilter_node__compare(node->r, str);
case '!': /* NOT */
- return !strfilter_node__compare(self->r, str);
+ return !strfilter_node__compare(node->r, str);
default:
- return strglobmatch(str, self->p);
+ return strglobmatch(str, node->p);
}
}
/* Return true if STR matches the filter rules */
-bool strfilter__compare(struct strfilter *self, const char *str)
+bool strfilter__compare(struct strfilter *node, const char *str)
{
- if (!self)
+ if (!node)
return false;
- return strfilter_node__compare(self->root, str);
+ return strfilter_node__compare(node->root, str);
}
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index a9c829b..eed0b96 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -8,7 +8,7 @@
#include "symbol.h"
#include "debug.h"
-#ifndef HAVE_ELF_GETPHDRNUM
+#ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
static int elf_getphdrnum(Elf *elf, size_t *dst)
{
GElf_Ehdr gehdr;
@@ -487,27 +487,27 @@
ek = elf_kind(elf);
if (ek != ELF_K_ELF)
- goto out_close;
+ goto out_elf_end;
if (gelf_getehdr(elf, &ehdr) == NULL) {
pr_err("%s: cannot get elf header.\n", __func__);
- goto out_close;
+ goto out_elf_end;
}
sec = elf_section_by_name(elf, &ehdr, &shdr,
".gnu_debuglink", NULL);
if (sec == NULL)
- goto out_close;
+ goto out_elf_end;
data = elf_getdata(sec, NULL);
if (data == NULL)
- goto out_close;
+ goto out_elf_end;
/* the start of this section is a zero-terminated string */
strncpy(debuglink, data->d_buf, size);
+out_elf_end:
elf_end(elf);
-
out_close:
close(fd);
out:
@@ -1018,6 +1018,601 @@
return err;
}
+static int copy_bytes(int from, off_t from_offs, int to, off_t to_offs, u64 len)
+{
+ ssize_t r;
+ size_t n;
+ int err = -1;
+ char *buf = malloc(page_size);
+
+ if (buf == NULL)
+ return -1;
+
+ if (lseek(to, to_offs, SEEK_SET) != to_offs)
+ goto out;
+
+ if (lseek(from, from_offs, SEEK_SET) != from_offs)
+ goto out;
+
+ while (len) {
+ n = page_size;
+ if (len < n)
+ n = len;
+ /* Use read because mmap won't work on proc files */
+ r = read(from, buf, n);
+ if (r < 0)
+ goto out;
+ if (!r)
+ break;
+ n = r;
+ r = write(to, buf, n);
+ if (r < 0)
+ goto out;
+ if ((size_t)r != n)
+ goto out;
+ len -= n;
+ }
+
+ err = 0;
+out:
+ free(buf);
+ return err;
+}
+
+struct kcore {
+ int fd;
+ int elfclass;
+ Elf *elf;
+ GElf_Ehdr ehdr;
+};
+
+static int kcore__open(struct kcore *kcore, const char *filename)
+{
+ GElf_Ehdr *ehdr;
+
+ kcore->fd = open(filename, O_RDONLY);
+ if (kcore->fd == -1)
+ return -1;
+
+ kcore->elf = elf_begin(kcore->fd, ELF_C_READ, NULL);
+ if (!kcore->elf)
+ goto out_close;
+
+ kcore->elfclass = gelf_getclass(kcore->elf);
+ if (kcore->elfclass == ELFCLASSNONE)
+ goto out_end;
+
+ ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr);
+ if (!ehdr)
+ goto out_end;
+
+ return 0;
+
+out_end:
+ elf_end(kcore->elf);
+out_close:
+ close(kcore->fd);
+ return -1;
+}
+
+static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
+ bool temp)
+{
+ GElf_Ehdr *ehdr;
+
+ kcore->elfclass = elfclass;
+
+ if (temp)
+ kcore->fd = mkstemp(filename);
+ else
+ kcore->fd = open(filename, O_WRONLY | O_CREAT | O_EXCL, 0400);
+ if (kcore->fd == -1)
+ return -1;
+
+ kcore->elf = elf_begin(kcore->fd, ELF_C_WRITE, NULL);
+ if (!kcore->elf)
+ goto out_close;
+
+ if (!gelf_newehdr(kcore->elf, elfclass))
+ goto out_end;
+
+ ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr);
+ if (!ehdr)
+ goto out_end;
+
+ return 0;
+
+out_end:
+ elf_end(kcore->elf);
+out_close:
+ close(kcore->fd);
+ unlink(filename);
+ return -1;
+}
+
+static void kcore__close(struct kcore *kcore)
+{
+ elf_end(kcore->elf);
+ close(kcore->fd);
+}
+
+static int kcore__copy_hdr(struct kcore *from, struct kcore *to, size_t count)
+{
+ GElf_Ehdr *ehdr = &to->ehdr;
+ GElf_Ehdr *kehdr = &from->ehdr;
+
+ memcpy(ehdr->e_ident, kehdr->e_ident, EI_NIDENT);
+ ehdr->e_type = kehdr->e_type;
+ ehdr->e_machine = kehdr->e_machine;
+ ehdr->e_version = kehdr->e_version;
+ ehdr->e_entry = 0;
+ ehdr->e_shoff = 0;
+ ehdr->e_flags = kehdr->e_flags;
+ ehdr->e_phnum = count;
+ ehdr->e_shentsize = 0;
+ ehdr->e_shnum = 0;
+ ehdr->e_shstrndx = 0;
+
+ if (from->elfclass == ELFCLASS32) {
+ ehdr->e_phoff = sizeof(Elf32_Ehdr);
+ ehdr->e_ehsize = sizeof(Elf32_Ehdr);
+ ehdr->e_phentsize = sizeof(Elf32_Phdr);
+ } else {
+ ehdr->e_phoff = sizeof(Elf64_Ehdr);
+ ehdr->e_ehsize = sizeof(Elf64_Ehdr);
+ ehdr->e_phentsize = sizeof(Elf64_Phdr);
+ }
+
+ if (!gelf_update_ehdr(to->elf, ehdr))
+ return -1;
+
+ if (!gelf_newphdr(to->elf, count))
+ return -1;
+
+ return 0;
+}
+
+static int kcore__add_phdr(struct kcore *kcore, int idx, off_t offset,
+ u64 addr, u64 len)
+{
+ GElf_Phdr gphdr;
+ GElf_Phdr *phdr;
+
+ phdr = gelf_getphdr(kcore->elf, idx, &gphdr);
+ if (!phdr)
+ return -1;
+
+ phdr->p_type = PT_LOAD;
+ phdr->p_flags = PF_R | PF_W | PF_X;
+ phdr->p_offset = offset;
+ phdr->p_vaddr = addr;
+ phdr->p_paddr = 0;
+ phdr->p_filesz = len;
+ phdr->p_memsz = len;
+ phdr->p_align = page_size;
+
+ if (!gelf_update_phdr(kcore->elf, idx, phdr))
+ return -1;
+
+ return 0;
+}
+
+static off_t kcore__write(struct kcore *kcore)
+{
+ return elf_update(kcore->elf, ELF_C_WRITE);
+}
+
+struct phdr_data {
+ off_t offset;
+ u64 addr;
+ u64 len;
+};
+
+struct kcore_copy_info {
+ u64 stext;
+ u64 etext;
+ u64 first_symbol;
+ u64 last_symbol;
+ u64 first_module;
+ u64 last_module_symbol;
+ struct phdr_data kernel_map;
+ struct phdr_data modules_map;
+};
+
+static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
+ u64 start)
+{
+ struct kcore_copy_info *kci = arg;
+
+ if (!symbol_type__is_a(type, MAP__FUNCTION))
+ return 0;
+
+ if (strchr(name, '[')) {
+ if (start > kci->last_module_symbol)
+ kci->last_module_symbol = start;
+ return 0;
+ }
+
+ if (!kci->first_symbol || start < kci->first_symbol)
+ kci->first_symbol = start;
+
+ if (!kci->last_symbol || start > kci->last_symbol)
+ kci->last_symbol = start;
+
+ if (!strcmp(name, "_stext")) {
+ kci->stext = start;
+ return 0;
+ }
+
+ if (!strcmp(name, "_etext")) {
+ kci->etext = start;
+ return 0;
+ }
+
+ return 0;
+}
+
+static int kcore_copy__parse_kallsyms(struct kcore_copy_info *kci,
+ const char *dir)
+{
+ char kallsyms_filename[PATH_MAX];
+
+ scnprintf(kallsyms_filename, PATH_MAX, "%s/kallsyms", dir);
+
+ if (symbol__restricted_filename(kallsyms_filename, "/proc/kallsyms"))
+ return -1;
+
+ if (kallsyms__parse(kallsyms_filename, kci,
+ kcore_copy__process_kallsyms) < 0)
+ return -1;
+
+ return 0;
+}
+
+static int kcore_copy__process_modules(void *arg,
+ const char *name __maybe_unused,
+ u64 start)
+{
+ struct kcore_copy_info *kci = arg;
+
+ if (!kci->first_module || start < kci->first_module)
+ kci->first_module = start;
+
+ return 0;
+}
+
+static int kcore_copy__parse_modules(struct kcore_copy_info *kci,
+ const char *dir)
+{
+ char modules_filename[PATH_MAX];
+
+ scnprintf(modules_filename, PATH_MAX, "%s/modules", dir);
+
+ if (symbol__restricted_filename(modules_filename, "/proc/modules"))
+ return -1;
+
+ if (modules__parse(modules_filename, kci,
+ kcore_copy__process_modules) < 0)
+ return -1;
+
+ return 0;
+}
+
+static void kcore_copy__map(struct phdr_data *p, u64 start, u64 end, u64 pgoff,
+ u64 s, u64 e)
+{
+ if (p->addr || s < start || s >= end)
+ return;
+
+ p->addr = s;
+ p->offset = (s - start) + pgoff;
+ p->len = e < end ? e - s : end - s;
+}
+
+static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data)
+{
+ struct kcore_copy_info *kci = data;
+ u64 end = start + len;
+
+ kcore_copy__map(&kci->kernel_map, start, end, pgoff, kci->stext,
+ kci->etext);
+
+ kcore_copy__map(&kci->modules_map, start, end, pgoff, kci->first_module,
+ kci->last_module_symbol);
+
+ return 0;
+}
+
+static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf)
+{
+ if (elf_read_maps(elf, true, kcore_copy__read_map, kci) < 0)
+ return -1;
+
+ return 0;
+}
+
+static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
+ Elf *elf)
+{
+ if (kcore_copy__parse_kallsyms(kci, dir))
+ return -1;
+
+ if (kcore_copy__parse_modules(kci, dir))
+ return -1;
+
+ if (kci->stext)
+ kci->stext = round_down(kci->stext, page_size);
+ else
+ kci->stext = round_down(kci->first_symbol, page_size);
+
+ if (kci->etext) {
+ kci->etext = round_up(kci->etext, page_size);
+ } else if (kci->last_symbol) {
+ kci->etext = round_up(kci->last_symbol, page_size);
+ kci->etext += page_size;
+ }
+
+ kci->first_module = round_down(kci->first_module, page_size);
+
+ if (kci->last_module_symbol) {
+ kci->last_module_symbol = round_up(kci->last_module_symbol,
+ page_size);
+ kci->last_module_symbol += page_size;
+ }
+
+ if (!kci->stext || !kci->etext)
+ return -1;
+
+ if (kci->first_module && !kci->last_module_symbol)
+ return -1;
+
+ return kcore_copy__read_maps(kci, elf);
+}
+
+static int kcore_copy__copy_file(const char *from_dir, const char *to_dir,
+ const char *name)
+{
+ char from_filename[PATH_MAX];
+ char to_filename[PATH_MAX];
+
+ scnprintf(from_filename, PATH_MAX, "%s/%s", from_dir, name);
+ scnprintf(to_filename, PATH_MAX, "%s/%s", to_dir, name);
+
+ return copyfile_mode(from_filename, to_filename, 0400);
+}
+
+static int kcore_copy__unlink(const char *dir, const char *name)
+{
+ char filename[PATH_MAX];
+
+ scnprintf(filename, PATH_MAX, "%s/%s", dir, name);
+
+ return unlink(filename);
+}
+
+static int kcore_copy__compare_fds(int from, int to)
+{
+ char *buf_from;
+ char *buf_to;
+ ssize_t ret;
+ size_t len;
+ int err = -1;
+
+ buf_from = malloc(page_size);
+ buf_to = malloc(page_size);
+ if (!buf_from || !buf_to)
+ goto out;
+
+ while (1) {
+ /* Use read because mmap won't work on proc files */
+ ret = read(from, buf_from, page_size);
+ if (ret < 0)
+ goto out;
+
+ if (!ret)
+ break;
+
+ len = ret;
+
+ if (readn(to, buf_to, len) != (int)len)
+ goto out;
+
+ if (memcmp(buf_from, buf_to, len))
+ goto out;
+ }
+
+ err = 0;
+out:
+ free(buf_to);
+ free(buf_from);
+ return err;
+}
+
+static int kcore_copy__compare_files(const char *from_filename,
+ const char *to_filename)
+{
+ int from, to, err = -1;
+
+ from = open(from_filename, O_RDONLY);
+ if (from < 0)
+ return -1;
+
+ to = open(to_filename, O_RDONLY);
+ if (to < 0)
+ goto out_close_from;
+
+ err = kcore_copy__compare_fds(from, to);
+
+ close(to);
+out_close_from:
+ close(from);
+ return err;
+}
+
+static int kcore_copy__compare_file(const char *from_dir, const char *to_dir,
+ const char *name)
+{
+ char from_filename[PATH_MAX];
+ char to_filename[PATH_MAX];
+
+ scnprintf(from_filename, PATH_MAX, "%s/%s", from_dir, name);
+ scnprintf(to_filename, PATH_MAX, "%s/%s", to_dir, name);
+
+ return kcore_copy__compare_files(from_filename, to_filename);
+}
+
+/**
+ * kcore_copy - copy kallsyms, modules and kcore from one directory to another.
+ * @from_dir: from directory
+ * @to_dir: to directory
+ *
+ * This function copies kallsyms, modules and kcore files from one directory to
+ * another. kallsyms and modules are copied entirely. Only code segments are
+ * copied from kcore. It is assumed that two segments suffice: one for the
+ * kernel proper and one for all the modules. The code segments are determined
+ * from kallsyms and modules files. The kernel map starts at _stext or the
+ * lowest function symbol, and ends at _etext or the highest function symbol.
+ * The module map starts at the lowest module address and ends at the highest
+ * module symbol. Start addresses are rounded down to the nearest page. End
+ * addresses are rounded up to the nearest page. An extra page is added to the
+ * highest kernel symbol and highest module symbol to, hopefully, encompass that
+ * symbol too. Because it contains only code sections, the resulting kcore is
+ * unusual. One significant peculiarity is that the mapping (start -> pgoff)
+ * is not the same for the kernel map and the modules map. That happens because
+ * the data is copied adjacently whereas the original kcore has gaps. Finally,
+ * kallsyms and modules files are compared with their copies to check that
+ * modules have not been loaded or unloaded while the copies were taking place.
+ *
+ * Return: %0 on success, %-1 on failure.
+ */
+int kcore_copy(const char *from_dir, const char *to_dir)
+{
+ struct kcore kcore;
+ struct kcore extract;
+ size_t count = 2;
+ int idx = 0, err = -1;
+ off_t offset = page_size, sz, modules_offset = 0;
+ struct kcore_copy_info kci = { .stext = 0, };
+ char kcore_filename[PATH_MAX];
+ char extract_filename[PATH_MAX];
+
+ if (kcore_copy__copy_file(from_dir, to_dir, "kallsyms"))
+ return -1;
+
+ if (kcore_copy__copy_file(from_dir, to_dir, "modules"))
+ goto out_unlink_kallsyms;
+
+ scnprintf(kcore_filename, PATH_MAX, "%s/kcore", from_dir);
+ scnprintf(extract_filename, PATH_MAX, "%s/kcore", to_dir);
+
+ if (kcore__open(&kcore, kcore_filename))
+ goto out_unlink_modules;
+
+ if (kcore_copy__calc_maps(&kci, from_dir, kcore.elf))
+ goto out_kcore_close;
+
+ if (kcore__init(&extract, extract_filename, kcore.elfclass, false))
+ goto out_kcore_close;
+
+ if (!kci.modules_map.addr)
+ count -= 1;
+
+ if (kcore__copy_hdr(&kcore, &extract, count))
+ goto out_extract_close;
+
+ if (kcore__add_phdr(&extract, idx++, offset, kci.kernel_map.addr,
+ kci.kernel_map.len))
+ goto out_extract_close;
+
+ if (kci.modules_map.addr) {
+ modules_offset = offset + kci.kernel_map.len;
+ if (kcore__add_phdr(&extract, idx, modules_offset,
+ kci.modules_map.addr, kci.modules_map.len))
+ goto out_extract_close;
+ }
+
+ sz = kcore__write(&extract);
+ if (sz < 0 || sz > offset)
+ goto out_extract_close;
+
+ if (copy_bytes(kcore.fd, kci.kernel_map.offset, extract.fd, offset,
+ kci.kernel_map.len))
+ goto out_extract_close;
+
+ if (modules_offset && copy_bytes(kcore.fd, kci.modules_map.offset,
+ extract.fd, modules_offset,
+ kci.modules_map.len))
+ goto out_extract_close;
+
+ if (kcore_copy__compare_file(from_dir, to_dir, "modules"))
+ goto out_extract_close;
+
+ if (kcore_copy__compare_file(from_dir, to_dir, "kallsyms"))
+ goto out_extract_close;
+
+ err = 0;
+
+out_extract_close:
+ kcore__close(&extract);
+ if (err)
+ unlink(extract_filename);
+out_kcore_close:
+ kcore__close(&kcore);
+out_unlink_modules:
+ if (err)
+ kcore_copy__unlink(to_dir, "modules");
+out_unlink_kallsyms:
+ if (err)
+ kcore_copy__unlink(to_dir, "kallsyms");
+
+ return err;
+}
+
+int kcore_extract__create(struct kcore_extract *kce)
+{
+ struct kcore kcore;
+ struct kcore extract;
+ size_t count = 1;
+ int idx = 0, err = -1;
+ off_t offset = page_size, sz;
+
+ if (kcore__open(&kcore, kce->kcore_filename))
+ return -1;
+
+ strcpy(kce->extract_filename, PERF_KCORE_EXTRACT);
+ if (kcore__init(&extract, kce->extract_filename, kcore.elfclass, true))
+ goto out_kcore_close;
+
+ if (kcore__copy_hdr(&kcore, &extract, count))
+ goto out_extract_close;
+
+ if (kcore__add_phdr(&extract, idx, offset, kce->addr, kce->len))
+ goto out_extract_close;
+
+ sz = kcore__write(&extract);
+ if (sz < 0 || sz > offset)
+ goto out_extract_close;
+
+ if (copy_bytes(kcore.fd, kce->offs, extract.fd, offset, kce->len))
+ goto out_extract_close;
+
+ err = 0;
+
+out_extract_close:
+ kcore__close(&extract);
+ if (err)
+ unlink(kce->extract_filename);
+out_kcore_close:
+ kcore__close(&kcore);
+
+ return err;
+}
+
+void kcore_extract__delete(struct kcore_extract *kce)
+{
+ unlink(kce->extract_filename);
+}
+
void symbol__elf_init(void)
{
elf_version(EV_CURRENT);
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 3a802c3..2d2dd05 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -308,6 +308,21 @@
return -1;
}
+int kcore_extract__create(struct kcore_extract *kce __maybe_unused)
+{
+ return -1;
+}
+
+void kcore_extract__delete(struct kcore_extract *kce __maybe_unused)
+{
+}
+
+int kcore_copy(const char *from_dir __maybe_unused,
+ const char *to_dir __maybe_unused)
+{
+ return -1;
+}
+
void symbol__elf_init(void)
{
}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 7eb0362..c0c3696 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -51,6 +51,7 @@
DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
DSO_BINARY_TYPE__GUEST_KMODULE,
DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+ DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
DSO_BINARY_TYPE__NOT_FOUND,
};
@@ -159,10 +160,12 @@
if (choose_best_symbol(curr, next) == SYMBOL_A) {
rb_erase(&next->rb_node, symbols);
+ symbol__delete(next);
goto again;
} else {
nd = rb_next(&curr->rb_node);
rb_erase(&curr->rb_node, symbols);
+ symbol__delete(curr);
}
}
}
@@ -499,6 +502,64 @@
return -1;
}
+int modules__parse(const char *filename, void *arg,
+ int (*process_module)(void *arg, const char *name,
+ u64 start))
+{
+ char *line = NULL;
+ size_t n;
+ FILE *file;
+ int err = 0;
+
+ file = fopen(filename, "r");
+ if (file == NULL)
+ return -1;
+
+ while (1) {
+ char name[PATH_MAX];
+ u64 start;
+ char *sep;
+ ssize_t line_len;
+
+ line_len = getline(&line, &n, file);
+ if (line_len < 0) {
+ if (feof(file))
+ break;
+ err = -1;
+ goto out;
+ }
+
+ if (!line) {
+ err = -1;
+ goto out;
+ }
+
+ line[--line_len] = '\0'; /* \n */
+
+ sep = strrchr(line, 'x');
+ if (sep == NULL)
+ continue;
+
+ hex2u64(sep + 1, &start);
+
+ sep = strchr(line, ' ');
+ if (sep == NULL)
+ continue;
+
+ *sep = '\0';
+
+ scnprintf(name, sizeof(name), "[%s]", line);
+
+ err = process_module(arg, name, start);
+ if (err)
+ break;
+ }
+out:
+ free(line);
+ fclose(file);
+ return err;
+}
+
struct process_kallsyms_args {
struct map *map;
struct dso *dso;
@@ -739,6 +800,219 @@
return restricted;
}
+struct module_info {
+ struct rb_node rb_node;
+ char *name;
+ u64 start;
+};
+
+static void add_module(struct module_info *mi, struct rb_root *modules)
+{
+ struct rb_node **p = &modules->rb_node;
+ struct rb_node *parent = NULL;
+ struct module_info *m;
+
+ while (*p != NULL) {
+ parent = *p;
+ m = rb_entry(parent, struct module_info, rb_node);
+ if (strcmp(mi->name, m->name) < 0)
+ p = &(*p)->rb_left;
+ else
+ p = &(*p)->rb_right;
+ }
+ rb_link_node(&mi->rb_node, parent, p);
+ rb_insert_color(&mi->rb_node, modules);
+}
+
+static void delete_modules(struct rb_root *modules)
+{
+ struct module_info *mi;
+ struct rb_node *next = rb_first(modules);
+
+ while (next) {
+ mi = rb_entry(next, struct module_info, rb_node);
+ next = rb_next(&mi->rb_node);
+ rb_erase(&mi->rb_node, modules);
+ free(mi->name);
+ free(mi);
+ }
+}
+
+static struct module_info *find_module(const char *name,
+ struct rb_root *modules)
+{
+ struct rb_node *n = modules->rb_node;
+
+ while (n) {
+ struct module_info *m;
+ int cmp;
+
+ m = rb_entry(n, struct module_info, rb_node);
+ cmp = strcmp(name, m->name);
+ if (cmp < 0)
+ n = n->rb_left;
+ else if (cmp > 0)
+ n = n->rb_right;
+ else
+ return m;
+ }
+
+ return NULL;
+}
+
+static int __read_proc_modules(void *arg, const char *name, u64 start)
+{
+ struct rb_root *modules = arg;
+ struct module_info *mi;
+
+ mi = zalloc(sizeof(struct module_info));
+ if (!mi)
+ return -ENOMEM;
+
+ mi->name = strdup(name);
+ mi->start = start;
+
+ if (!mi->name) {
+ free(mi);
+ return -ENOMEM;
+ }
+
+ add_module(mi, modules);
+
+ return 0;
+}
+
+static int read_proc_modules(const char *filename, struct rb_root *modules)
+{
+ if (symbol__restricted_filename(filename, "/proc/modules"))
+ return -1;
+
+ if (modules__parse(filename, modules, __read_proc_modules)) {
+ delete_modules(modules);
+ return -1;
+ }
+
+ return 0;
+}
+
+int compare_proc_modules(const char *from, const char *to)
+{
+ struct rb_root from_modules = RB_ROOT;
+ struct rb_root to_modules = RB_ROOT;
+ struct rb_node *from_node, *to_node;
+ struct module_info *from_m, *to_m;
+ int ret = -1;
+
+ if (read_proc_modules(from, &from_modules))
+ return -1;
+
+ if (read_proc_modules(to, &to_modules))
+ goto out_delete_from;
+
+ from_node = rb_first(&from_modules);
+ to_node = rb_first(&to_modules);
+ while (from_node) {
+ if (!to_node)
+ break;
+
+ from_m = rb_entry(from_node, struct module_info, rb_node);
+ to_m = rb_entry(to_node, struct module_info, rb_node);
+
+ if (from_m->start != to_m->start ||
+ strcmp(from_m->name, to_m->name))
+ break;
+
+ from_node = rb_next(from_node);
+ to_node = rb_next(to_node);
+ }
+
+ if (!from_node && !to_node)
+ ret = 0;
+
+ delete_modules(&to_modules);
+out_delete_from:
+ delete_modules(&from_modules);
+
+ return ret;
+}
+
+static int do_validate_kcore_modules(const char *filename, struct map *map,
+ struct map_groups *kmaps)
+{
+ struct rb_root modules = RB_ROOT;
+ struct map *old_map;
+ int err;
+
+ err = read_proc_modules(filename, &modules);
+ if (err)
+ return err;
+
+ old_map = map_groups__first(kmaps, map->type);
+ while (old_map) {
+ struct map *next = map_groups__next(old_map);
+ struct module_info *mi;
+
+ if (old_map == map || old_map->start == map->start) {
+ /* The kernel map */
+ old_map = next;
+ continue;
+ }
+
+ /* Module must be in memory at the same address */
+ mi = find_module(old_map->dso->short_name, &modules);
+ if (!mi || mi->start != old_map->start) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ old_map = next;
+ }
+out:
+ delete_modules(&modules);
+ return err;
+}
+
+/*
+ * If kallsyms is referenced by name then we look for filename in the same
+ * directory.
+ */
+static bool filename_from_kallsyms_filename(char *filename,
+ const char *base_name,
+ const char *kallsyms_filename)
+{
+ char *name;
+
+ strcpy(filename, kallsyms_filename);
+ name = strrchr(filename, '/');
+ if (!name)
+ return false;
+
+ name += 1;
+
+ if (!strcmp(name, "kallsyms")) {
+ strcpy(name, base_name);
+ return true;
+ }
+
+ return false;
+}
+
+static int validate_kcore_modules(const char *kallsyms_filename,
+ struct map *map)
+{
+ struct map_groups *kmaps = map__kmap(map)->kmaps;
+ char modules_filename[PATH_MAX];
+
+ if (!filename_from_kallsyms_filename(modules_filename, "modules",
+ kallsyms_filename))
+ return -EINVAL;
+
+ if (do_validate_kcore_modules(modules_filename, map, kmaps))
+ return -EINVAL;
+
+ return 0;
+}
+
struct kcore_mapfn_data {
struct dso *dso;
enum map_type type;
@@ -762,28 +1036,6 @@
return 0;
}
-/*
- * If kallsyms is referenced by name then we look for kcore in the same
- * directory.
- */
-static bool kcore_filename_from_kallsyms_filename(char *kcore_filename,
- const char *kallsyms_filename)
-{
- char *name;
-
- strcpy(kcore_filename, kallsyms_filename);
- name = strrchr(kcore_filename, '/');
- if (!name)
- return false;
-
- if (!strcmp(name, "/kallsyms")) {
- strcpy(name, "/kcore");
- return true;
- }
-
- return false;
-}
-
static int dso__load_kcore(struct dso *dso, struct map *map,
const char *kallsyms_filename)
{
@@ -800,8 +1052,12 @@
if (map != machine->vmlinux_maps[map->type])
return -EINVAL;
- if (!kcore_filename_from_kallsyms_filename(kcore_filename,
- kallsyms_filename))
+ if (!filename_from_kallsyms_filename(kcore_filename, "kcore",
+ kallsyms_filename))
+ return -EINVAL;
+
+ /* All modules must be present at their original addresses */
+ if (validate_kcore_modules(kallsyms_filename, map))
return -EINVAL;
md.dso = dso;
@@ -1188,6 +1444,105 @@
return err;
}
+static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz)
+{
+ char kallsyms_filename[PATH_MAX];
+ struct dirent *dent;
+ int ret = -1;
+ DIR *d;
+
+ d = opendir(dir);
+ if (!d)
+ return -1;
+
+ while (1) {
+ dent = readdir(d);
+ if (!dent)
+ break;
+ if (dent->d_type != DT_DIR)
+ continue;
+ scnprintf(kallsyms_filename, sizeof(kallsyms_filename),
+ "%s/%s/kallsyms", dir, dent->d_name);
+ if (!validate_kcore_modules(kallsyms_filename, map)) {
+ strlcpy(dir, kallsyms_filename, dir_sz);
+ ret = 0;
+ break;
+ }
+ }
+
+ closedir(d);
+
+ return ret;
+}
+
+static char *dso__find_kallsyms(struct dso *dso, struct map *map)
+{
+ u8 host_build_id[BUILD_ID_SIZE];
+ char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+ bool is_host = false;
+ char path[PATH_MAX];
+
+ if (!dso->has_build_id) {
+ /*
+ * Last resort, if we don't have a build-id and couldn't find
+ * any vmlinux file, try the running kernel kallsyms table.
+ */
+ goto proc_kallsyms;
+ }
+
+ if (sysfs__read_build_id("/sys/kernel/notes", host_build_id,
+ sizeof(host_build_id)) == 0)
+ is_host = dso__build_id_equal(dso, host_build_id);
+
+ build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+
+ /* Use /proc/kallsyms if possible */
+ if (is_host) {
+ DIR *d;
+ int fd;
+
+ /* If no cached kcore go with /proc/kallsyms */
+ scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s",
+ buildid_dir, sbuild_id);
+ d = opendir(path);
+ if (!d)
+ goto proc_kallsyms;
+ closedir(d);
+
+ /*
+ * Do not check the build-id cache, until we know we cannot use
+ * /proc/kcore.
+ */
+ fd = open("/proc/kcore", O_RDONLY);
+ if (fd != -1) {
+ close(fd);
+ /* If module maps match go with /proc/kallsyms */
+ if (!validate_kcore_modules("/proc/kallsyms", map))
+ goto proc_kallsyms;
+ }
+
+ /* Find kallsyms in build-id cache with kcore */
+ if (!find_matching_kcore(map, path, sizeof(path)))
+ return strdup(path);
+
+ goto proc_kallsyms;
+ }
+
+ scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
+ buildid_dir, sbuild_id);
+
+ if (access(path, F_OK)) {
+ pr_err("No kallsyms or vmlinux with build-id %s was found\n",
+ sbuild_id);
+ return NULL;
+ }
+
+ return strdup(path);
+
+proc_kallsyms:
+ return strdup("/proc/kallsyms");
+}
+
static int dso__load_kernel_sym(struct dso *dso, struct map *map,
symbol_filter_t filter)
{
@@ -1214,7 +1569,7 @@
goto do_kallsyms;
}
- if (symbol_conf.vmlinux_name != NULL) {
+ if (!symbol_conf.ignore_vmlinux && symbol_conf.vmlinux_name != NULL) {
err = dso__load_vmlinux(dso, map,
symbol_conf.vmlinux_name, filter);
if (err > 0) {
@@ -1226,7 +1581,7 @@
return err;
}
- if (vmlinux_path != NULL) {
+ if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) {
err = dso__load_vmlinux_path(dso, map, filter);
if (err > 0)
return err;
@@ -1236,51 +1591,11 @@
if (symbol_conf.symfs[0] != 0)
return -1;
- /*
- * Say the kernel DSO was created when processing the build-id header table,
- * we have a build-id, so check if it is the same as the running kernel,
- * using it if it is.
- */
- if (dso->has_build_id) {
- u8 kallsyms_build_id[BUILD_ID_SIZE];
- char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+ kallsyms_allocated_filename = dso__find_kallsyms(dso, map);
+ if (!kallsyms_allocated_filename)
+ return -1;
- if (sysfs__read_build_id("/sys/kernel/notes", kallsyms_build_id,
- sizeof(kallsyms_build_id)) == 0) {
- if (dso__build_id_equal(dso, kallsyms_build_id)) {
- kallsyms_filename = "/proc/kallsyms";
- goto do_kallsyms;
- }
- }
- /*
- * Now look if we have it on the build-id cache in
- * $HOME/.debug/[kernel.kallsyms].
- */
- build_id__sprintf(dso->build_id, sizeof(dso->build_id),
- sbuild_id);
-
- if (asprintf(&kallsyms_allocated_filename,
- "%s/.debug/[kernel.kallsyms]/%s",
- getenv("HOME"), sbuild_id) == -1) {
- pr_err("Not enough memory for kallsyms file lookup\n");
- return -1;
- }
-
- kallsyms_filename = kallsyms_allocated_filename;
-
- if (access(kallsyms_filename, F_OK)) {
- pr_err("No kallsyms or vmlinux with build-id %s "
- "was found\n", sbuild_id);
- free(kallsyms_allocated_filename);
- return -1;
- }
- } else {
- /*
- * Last resort, if we don't have a build-id and couldn't find
- * any vmlinux file, try the running kernel kallsyms table.
- */
- kallsyms_filename = "/proc/kallsyms";
- }
+ kallsyms_filename = kallsyms_allocated_filename;
do_kallsyms:
err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index fd5b70e..07de8fe 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -13,7 +13,7 @@
#include <libgen.h>
#include "build-id.h"
-#ifdef LIBELF_SUPPORT
+#ifdef HAVE_LIBELF_SUPPORT
#include <libelf.h>
#include <gelf.h>
#endif
@@ -21,7 +21,7 @@
#include "dso.h"
-#ifdef HAVE_CPLUS_DEMANGLE
+#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
extern char *cplus_demangle(const char *, int);
static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i)
@@ -46,7 +46,7 @@
* libelf 0.8.x and earlier do not support ELF_C_READ_MMAP;
* for newer versions we can use mmap to reduce memory usage:
*/
-#ifdef LIBELF_MMAP
+#ifdef HAVE_LIBELF_MMAP_SUPPORT
# define PERF_ELF_C_READ_MMAP ELF_C_READ_MMAP
#else
# define PERF_ELF_C_READ_MMAP ELF_C_READ
@@ -85,6 +85,7 @@
unsigned short priv_size;
unsigned short nr_events;
bool try_vmlinux_path,
+ ignore_vmlinux,
show_kernel_path,
use_modules,
sort_by_name,
@@ -178,7 +179,7 @@
int fd;
enum dso_binary_type type;
-#ifdef LIBELF_SUPPORT
+#ifdef HAVE_LIBELF_SUPPORT
Elf *elf;
GElf_Ehdr ehdr;
@@ -222,6 +223,9 @@
int kallsyms__parse(const char *filename, void *arg,
int (*process_symbol)(void *arg, const char *name,
char type, u64 start));
+int modules__parse(const char *filename, void *arg,
+ int (*process_module)(void *arg, const char *name,
+ u64 start));
int filename__read_debuglink(const char *filename, char *debuglink,
size_t size);
@@ -252,4 +256,21 @@
int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
bool *is_64_bit);
+#define PERF_KCORE_EXTRACT "/tmp/perf-kcore-XXXXXX"
+
+struct kcore_extract {
+ char *kcore_filename;
+ u64 addr;
+ u64 offs;
+ u64 len;
+ char extract_filename[sizeof(PERF_KCORE_EXTRACT)];
+ int fd;
+};
+
+int kcore_extract__create(struct kcore_extract *kce);
+void kcore_extract__delete(struct kcore_extract *kce);
+
+int kcore_copy(const char *from_dir, const char *to_dir);
+int compare_proc_modules(const char *from, const char *to);
+
#endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index e3d4a55..80d19a0 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -9,51 +9,51 @@
struct thread *thread__new(pid_t pid, pid_t tid)
{
- struct thread *self = zalloc(sizeof(*self));
+ struct thread *thread = zalloc(sizeof(*thread));
- if (self != NULL) {
- map_groups__init(&self->mg);
- self->pid_ = pid;
- self->tid = tid;
- self->ppid = -1;
- self->comm = malloc(32);
- if (self->comm)
- snprintf(self->comm, 32, ":%d", self->tid);
+ if (thread != NULL) {
+ map_groups__init(&thread->mg);
+ thread->pid_ = pid;
+ thread->tid = tid;
+ thread->ppid = -1;
+ thread->comm = malloc(32);
+ if (thread->comm)
+ snprintf(thread->comm, 32, ":%d", thread->tid);
}
- return self;
+ return thread;
}
-void thread__delete(struct thread *self)
+void thread__delete(struct thread *thread)
{
- map_groups__exit(&self->mg);
- free(self->comm);
- free(self);
+ map_groups__exit(&thread->mg);
+ free(thread->comm);
+ free(thread);
}
-int thread__set_comm(struct thread *self, const char *comm)
+int thread__set_comm(struct thread *thread, const char *comm)
{
int err;
- if (self->comm)
- free(self->comm);
- self->comm = strdup(comm);
- err = self->comm == NULL ? -ENOMEM : 0;
+ if (thread->comm)
+ free(thread->comm);
+ thread->comm = strdup(comm);
+ err = thread->comm == NULL ? -ENOMEM : 0;
if (!err) {
- self->comm_set = true;
+ thread->comm_set = true;
}
return err;
}
-int thread__comm_len(struct thread *self)
+int thread__comm_len(struct thread *thread)
{
- if (!self->comm_len) {
- if (!self->comm)
+ if (!thread->comm_len) {
+ if (!thread->comm)
return 0;
- self->comm_len = strlen(self->comm);
+ thread->comm_len = strlen(thread->comm);
}
- return self->comm_len;
+ return thread->comm_len;
}
size_t thread__fprintf(struct thread *thread, FILE *fp)
@@ -62,30 +62,30 @@
map_groups__fprintf(&thread->mg, verbose, fp);
}
-void thread__insert_map(struct thread *self, struct map *map)
+void thread__insert_map(struct thread *thread, struct map *map)
{
- map_groups__fixup_overlappings(&self->mg, map, verbose, stderr);
- map_groups__insert(&self->mg, map);
+ map_groups__fixup_overlappings(&thread->mg, map, verbose, stderr);
+ map_groups__insert(&thread->mg, map);
}
-int thread__fork(struct thread *self, struct thread *parent)
+int thread__fork(struct thread *thread, struct thread *parent)
{
int i;
if (parent->comm_set) {
- if (self->comm)
- free(self->comm);
- self->comm = strdup(parent->comm);
- if (!self->comm)
+ if (thread->comm)
+ free(thread->comm);
+ thread->comm = strdup(parent->comm);
+ if (!thread->comm)
return -ENOMEM;
- self->comm_set = true;
+ thread->comm_set = true;
}
for (i = 0; i < MAP__NR_TYPES; ++i)
- if (map_groups__clone(&self->mg, &parent->mg, i) < 0)
+ if (map_groups__clone(&thread->mg, &parent->mg, i) < 0)
return -ENOMEM;
- self->ppid = parent->tid;
+ thread->ppid = parent->tid;
return 0;
}
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index b554ffc..88cfeaf 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -24,6 +24,7 @@
u64 exact_samples;
u64 guest_us_samples, guest_kernel_samples;
int print_entries, count_filter, delay_secs;
+ int max_stack;
bool hide_kernel_symbols, hide_user_symbols, zero;
bool use_tui, use_stdio;
bool kptr_restrict_warned;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index e9e1c03..6681f71 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -120,42 +120,6 @@
return val;
}
-void *raw_field_ptr(struct event_format *event, const char *name, void *data)
-{
- struct format_field *field;
-
- field = pevent_find_any_field(event, name);
- if (!field)
- return NULL;
-
- if (field->flags & FIELD_IS_DYNAMIC) {
- int offset;
-
- offset = *(int *)(data + field->offset);
- offset &= 0xffff;
-
- return data + offset;
- }
-
- return data + field->offset;
-}
-
-int trace_parse_common_type(struct pevent *pevent, void *data)
-{
- struct pevent_record record;
-
- record.data = data;
- return pevent_data_type(pevent, &record);
-}
-
-int trace_parse_common_pid(struct pevent *pevent, void *data)
-{
- struct pevent_record record;
-
- record.data = data;
- return pevent_data_pid(pevent, &record);
-}
-
unsigned long long read_size(struct event_format *event, void *ptr, int size)
{
return pevent_read_number(event->pevent, ptr, size);
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index fafe1a4..04df631 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -11,8 +11,6 @@
struct perf_tool;
struct thread;
-extern struct pevent *perf_pevent;
-
int bigendian(void);
struct pevent *read_trace_init(int file_bigendian, int host_bigendian);
@@ -23,26 +21,19 @@
int parse_event_file(struct pevent *pevent,
char *buf, unsigned long size, char *sys);
-struct pevent_record *trace_peek_data(struct pevent *pevent, int cpu);
-
unsigned long long
raw_field_value(struct event_format *event, const char *name, void *data);
-void *raw_field_ptr(struct event_format *event, const char *name, void *data);
void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size);
void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size);
ssize_t trace_report(int fd, struct pevent **pevent, bool repipe);
-int trace_parse_common_type(struct pevent *pevent, void *data);
-int trace_parse_common_pid(struct pevent *pevent, void *data);
-
struct event_format *trace_find_next_event(struct pevent *pevent,
struct event_format *event);
unsigned long long read_size(struct event_format *event, void *ptr, int size);
unsigned long long eval_flag(const char *flag);
-struct pevent_record *trace_read_data(struct pevent *pevent, int cpu);
int read_tracing_data(int fd, struct list_head *pattrs);
struct tracing_data {
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index cb6bc50..ec0c71a 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -13,7 +13,7 @@
typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
-#ifdef LIBUNWIND_SUPPORT
+#ifdef HAVE_LIBUNWIND_SUPPORT
int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
struct machine *machine,
struct thread *thread,
@@ -31,5 +31,5 @@
{
return 0;
}
-#endif /* LIBUNWIND_SUPPORT */
+#endif /* HAVE_LIBUNWIND_SUPPORT */
#endif /* __UNWIND_H */
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 6d17b18..28a0a89 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,7 +1,7 @@
#include "../perf.h"
#include "util.h"
#include <sys/mman.h>
-#ifdef BACKTRACE_SUPPORT
+#ifdef HAVE_BACKTRACE_SUPPORT
#include <execinfo.h>
#endif
#include <stdio.h>
@@ -55,17 +55,20 @@
return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
}
-static int slow_copyfile(const char *from, const char *to)
+static int slow_copyfile(const char *from, const char *to, mode_t mode)
{
- int err = 0;
+ int err = -1;
char *line = NULL;
size_t n;
FILE *from_fp = fopen(from, "r"), *to_fp;
+ mode_t old_umask;
if (from_fp == NULL)
goto out;
+ old_umask = umask(mode ^ 0777);
to_fp = fopen(to, "w");
+ umask(old_umask);
if (to_fp == NULL)
goto out_fclose_from;
@@ -82,7 +85,7 @@
return err;
}
-int copyfile(const char *from, const char *to)
+int copyfile_mode(const char *from, const char *to, mode_t mode)
{
int fromfd, tofd;
struct stat st;
@@ -93,13 +96,13 @@
goto out;
if (st.st_size == 0) /* /proc? do it slowly... */
- return slow_copyfile(from, to);
+ return slow_copyfile(from, to, mode);
fromfd = open(from, O_RDONLY);
if (fromfd < 0)
goto out;
- tofd = creat(to, 0755);
+ tofd = creat(to, mode);
if (tofd < 0)
goto out_close_from;
@@ -121,6 +124,11 @@
return err;
}
+int copyfile(const char *from, const char *to)
+{
+ return copyfile_mode(from, to, 0755);
+}
+
unsigned long convert_unit(unsigned long value, char *unit)
{
*unit = ' ';
@@ -204,7 +212,7 @@
}
/* Obtain a backtrace and print it to stdout. */
-#ifdef BACKTRACE_SUPPORT
+#ifdef HAVE_BACKTRACE_SUPPORT
void dump_stack(void)
{
void *array[16];
@@ -361,3 +369,47 @@
*ptime = time_sec * NSEC_PER_SEC + time_nsec;
return 0;
}
+
+unsigned long parse_tag_value(const char *str, struct parse_tag *tags)
+{
+ struct parse_tag *i = tags;
+
+ while (i->tag) {
+ char *s;
+
+ s = strchr(str, i->tag);
+ if (s) {
+ unsigned long int value;
+ char *endptr;
+
+ value = strtoul(str, &endptr, 10);
+ if (s != endptr)
+ break;
+
+ if (value > ULONG_MAX / i->mult)
+ break;
+ value *= i->mult;
+ return value;
+ }
+ i++;
+ }
+
+ return (unsigned long) -1;
+}
+
+int filename__read_int(const char *filename, int *value)
+{
+ char line[64];
+ int fd = open(filename, O_RDONLY), err = -1;
+
+ if (fd < 0)
+ return -1;
+
+ if (read(fd, line, sizeof(line)) > 0) {
+ *value = atoi(line);
+ err = 0;
+ }
+
+ close(fd);
+ return err;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index a535359..c8f362d 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -128,6 +128,8 @@
#endif
#endif
+#define PERF_GTK_DSO "libperf-gtk.so"
+
/* General helper functions */
extern void usage(const char *err) NORETURN;
extern void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2)));
@@ -241,6 +243,7 @@
int mkdir_p(char *path, mode_t mode);
int copyfile(const char *from, const char *to);
+int copyfile_mode(const char *from, const char *to, mode_t mode);
s64 perf_atoll(const char *str);
char **argv_split(const char *str, int *argcp);
@@ -270,6 +273,13 @@
return (n != 0 && ((n & (n - 1)) == 0));
}
+static inline unsigned next_pow2(unsigned x)
+{
+ if (!x)
+ return 1;
+ return 1ULL << (32 - __builtin_clz(x - 1));
+}
+
size_t hex_width(u64 v);
int hex2u64(const char *ptr, u64 *val);
@@ -281,4 +291,20 @@
extern unsigned int page_size;
void get_term_dimensions(struct winsize *ws);
+
+struct parse_tag {
+ char tag;
+ int mult;
+};
+
+unsigned long parse_tag_value(const char *str, struct parse_tag *tags);
+
+#define SRCLINE_UNKNOWN ((char *) "??:0")
+
+struct dso;
+
+char *get_srcline(struct dso *dso, unsigned long addr);
+void free_srcline(char *srcline);
+
+int filename__read_int(const char *filename, int *value);
#endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 0d0506d..ee76544 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -59,21 +59,22 @@
QUIET_SUBDIR1 =
ifneq ($(findstring $(MAKEFLAGS),s),s)
-ifneq ($(V),1)
- QUIET_CC = @echo ' ' CC $@;
- QUIET_AR = @echo ' ' AR $@;
- QUIET_LINK = @echo ' ' LINK $@;
- QUIET_MKDIR = @echo ' ' MKDIR $@;
- QUIET_GEN = @echo ' ' GEN $@;
+ ifneq ($(V),1)
+ QUIET_CC = @echo ' CC '$@;
+ QUIET_AR = @echo ' AR '$@;
+ QUIET_LINK = @echo ' LINK '$@;
+ QUIET_MKDIR = @echo ' MKDIR '$@;
+ QUIET_GEN = @echo ' GEN '$@;
QUIET_SUBDIR0 = +@subdir=
- QUIET_SUBDIR1 = ;$(NO_SUBDIR) echo ' ' SUBDIR $$subdir; \
+ QUIET_SUBDIR1 = ;$(NO_SUBDIR) \
+ echo ' SUBDIR '$$subdir; \
$(MAKE) $(PRINT_DIR) -C $$subdir
- QUIET_FLEX = @echo ' ' FLEX $@;
- QUIET_BISON = @echo ' ' BISON $@;
+ QUIET_FLEX = @echo ' FLEX '$@;
+ QUIET_BISON = @echo ' BISON '$@;
descend = \
- +@echo ' ' DESCEND $(1); \
+ +@echo ' DESCEND '$(1); \
mkdir -p $(OUTPUT)$(1) && \
$(MAKE) $(COMMAND_O) subdir=$(if $(subdir),$(subdir)/$(1),$(1)) $(PRINT_DIR) -C $(1) $(2)
-endif
+ endif
endif
