Merge branch 'perf/urgent' into perf/core, to pick up fixes
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/Documentation/trace/events-msr.txt b/Documentation/trace/events-msr.txt
new file mode 100644
index 0000000..78c383b
--- /dev/null
+++ b/Documentation/trace/events-msr.txt
@@ -0,0 +1,37 @@
+
+The x86 kernel supports tracing most MSR (Model Specific Register) accesses.
+To see the definition of the MSRs on Intel systems please see the SDM
+at http://www.intel.com/sdm (Volume 3)
+
+Available trace points:
+
+/sys/kernel/debug/tracing/events/msr/
+
+Trace MSR reads
+
+read_msr
+
+msr: MSR number
+val: Value written
+failed: 1 if the access failed, otherwise 0
+
+
+Trace MSR writes
+
+write_msr
+
+msr: MSR number
+val: Value written
+failed: 1 if the access failed, otherwise 0
+
+
+Trace RDPMC in kernel
+
+rdpmc
+
+The trace data can be post processed with the postprocess/decode_msr.py script
+
+cat /sys/kernel/debug/tracing/trace | decode_msr.py /usr/src/linux/include/asm/msr-index.h
+
+to add symbolic MSR names.
+
diff --git a/Documentation/trace/postprocess/decode_msr.py b/Documentation/trace/postprocess/decode_msr.py
new file mode 100644
index 0000000..0ab40e0
--- /dev/null
+++ b/Documentation/trace/postprocess/decode_msr.py
@@ -0,0 +1,37 @@
+#!/usr/bin/python
+# add symbolic names to read_msr / write_msr in trace
+# decode_msr msr-index.h < trace
+import sys
+import re
+
+msrs = dict()
+
+with open(sys.argv[1] if len(sys.argv) > 1 else "msr-index.h", "r") as f:
+ for j in f:
+ m = re.match(r'#define (MSR_\w+)\s+(0x[0-9a-fA-F]+)', j)
+ if m:
+ msrs[int(m.group(2), 16)] = m.group(1)
+
+extra_ranges = (
+ ( "MSR_LASTBRANCH_%d_FROM_IP", 0x680, 0x69F ),
+ ( "MSR_LASTBRANCH_%d_TO_IP", 0x6C0, 0x6DF ),
+ ( "LBR_INFO_%d", 0xdc0, 0xddf ),
+)
+
+for j in sys.stdin:
+ m = re.search(r'(read|write)_msr:\s+([0-9a-f]+)', j)
+ if m:
+ r = None
+ num = int(m.group(2), 16)
+ if num in msrs:
+ r = msrs[num]
+ else:
+ for er in extra_ranges:
+ if er[1] <= num <= er[2]:
+ r = er[0] % (num - er[1],)
+ break
+ if r:
+ j = j.replace(" " + m.group(2), " " + r + "(" + m.group(2) + ")")
+ print j,
+
+
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index ae5fb83..3e86742 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -3,7 +3,6 @@
#include <linux/compiler.h>
#include <linux/types.h>
-#include <asm/processor.h>
#include <asm/alternative.h>
#include <asm/cmpxchg.h>
#include <asm/rmwcc.h>
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index a11c30b..a984111 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -3,7 +3,6 @@
#include <linux/compiler.h>
#include <linux/types.h>
-#include <asm/processor.h>
//#include <asm/cmpxchg.h>
/* An 64bit atomic type */
diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h
new file mode 100644
index 0000000..e1a4117
--- /dev/null
+++ b/arch/x86/include/asm/intel_pt.h
@@ -0,0 +1,10 @@
+#ifndef _ASM_X86_INTEL_PT_H
+#define _ASM_X86_INTEL_PT_H
+
+#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
+void cpu_emergency_stop_pt(void);
+#else
+static inline void cpu_emergency_stop_pt(void) {}
+#endif
+
+#endif /* _ASM_X86_INTEL_PT_H */
diff --git a/arch/x86/include/asm/msr-trace.h b/arch/x86/include/asm/msr-trace.h
new file mode 100644
index 0000000..7567225
--- /dev/null
+++ b/arch/x86/include/asm/msr-trace.h
@@ -0,0 +1,57 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM msr
+
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE msr-trace
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH asm/
+
+#if !defined(_TRACE_MSR_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MSR_H
+
+#include <linux/tracepoint.h>
+
+/*
+ * Tracing for x86 model specific registers. Directly maps to the
+ * RDMSR/WRMSR instructions.
+ */
+
+DECLARE_EVENT_CLASS(msr_trace_class,
+ TP_PROTO(unsigned msr, u64 val, int failed),
+ TP_ARGS(msr, val, failed),
+ TP_STRUCT__entry(
+ __field( unsigned, msr )
+ __field( u64, val )
+ __field( int, failed )
+ ),
+ TP_fast_assign(
+ __entry->msr = msr;
+ __entry->val = val;
+ __entry->failed = failed;
+ ),
+ TP_printk("%x, value %llx%s",
+ __entry->msr,
+ __entry->val,
+ __entry->failed ? " #GP" : "")
+);
+
+DEFINE_EVENT(msr_trace_class, read_msr,
+ TP_PROTO(unsigned msr, u64 val, int failed),
+ TP_ARGS(msr, val, failed)
+);
+
+DEFINE_EVENT(msr_trace_class, write_msr,
+ TP_PROTO(unsigned msr, u64 val, int failed),
+ TP_ARGS(msr, val, failed)
+);
+
+DEFINE_EVENT(msr_trace_class, rdpmc,
+ TP_PROTO(unsigned msr, u64 val, int failed),
+ TP_ARGS(msr, val, failed)
+);
+
+#endif /* _TRACE_MSR_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 77d8b28..fedd6e6 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -57,11 +57,34 @@
#define EAX_EDX_RET(val, low, high) "=A" (val)
#endif
+#ifdef CONFIG_TRACEPOINTS
+/*
+ * Be very careful with includes. This header is prone to include loops.
+ */
+#include <asm/atomic.h>
+#include <linux/tracepoint-defs.h>
+
+extern struct tracepoint __tracepoint_read_msr;
+extern struct tracepoint __tracepoint_write_msr;
+extern struct tracepoint __tracepoint_rdpmc;
+#define msr_tracepoint_active(t) static_key_false(&(t).key)
+extern void do_trace_write_msr(unsigned msr, u64 val, int failed);
+extern void do_trace_read_msr(unsigned msr, u64 val, int failed);
+extern void do_trace_rdpmc(unsigned msr, u64 val, int failed);
+#else
+#define msr_tracepoint_active(t) false
+static inline void do_trace_write_msr(unsigned msr, u64 val, int failed) {}
+static inline void do_trace_read_msr(unsigned msr, u64 val, int failed) {}
+static inline void do_trace_rdpmc(unsigned msr, u64 val, int failed) {}
+#endif
+
static inline unsigned long long native_read_msr(unsigned int msr)
{
DECLARE_ARGS(val, low, high);
asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr));
+ if (msr_tracepoint_active(__tracepoint_read_msr))
+ do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0);
return EAX_EDX_VAL(val, low, high);
}
@@ -78,6 +101,8 @@
_ASM_EXTABLE(2b, 3b)
: [err] "=r" (*err), EAX_EDX_RET(val, low, high)
: "c" (msr), [fault] "i" (-EIO));
+ if (msr_tracepoint_active(__tracepoint_read_msr))
+ do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err);
return EAX_EDX_VAL(val, low, high);
}
@@ -85,6 +110,8 @@
unsigned low, unsigned high)
{
asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory");
+ if (msr_tracepoint_active(__tracepoint_read_msr))
+ do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
}
/* Can be uninlined because referenced by paravirt */
@@ -102,6 +129,8 @@
: "c" (msr), "0" (low), "d" (high),
[fault] "i" (-EIO)
: "memory");
+ if (msr_tracepoint_active(__tracepoint_read_msr))
+ do_trace_write_msr(msr, ((u64)high << 32 | low), err);
return err;
}
@@ -160,6 +189,8 @@
DECLARE_ARGS(val, low, high);
asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter));
+ if (msr_tracepoint_active(__tracepoint_rdpmc))
+ do_trace_rdpmc(counter, EAX_EDX_VAL(val, low, high), 0);
return EAX_EDX_VAL(val, low, high);
}
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 09b1b0a..660458a 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -745,5 +745,14 @@
#undef __copy_from_user_overflow
#undef __copy_to_user_overflow
+/*
+ * We rely on the nested NMI work to allow atomic faults from the NMI path; the
+ * nested NMI paths are careful to preserve CR2.
+ *
+ * Caller must use pagefault_enable/disable, or run in interrupt context,
+ * and also do a uaccess_ok() check
+ */
+#define __copy_from_user_nmi __copy_from_user_inatomic
+
#endif /* _ASM_X86_UACCESS_H */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 2bf79d7..9dfbba5 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2250,12 +2250,19 @@
ss_base = get_segment_base(regs->ss);
fp = compat_ptr(ss_base + regs->bp);
+ pagefault_disable();
while (entry->nr < PERF_MAX_STACK_DEPTH) {
unsigned long bytes;
frame.next_frame = 0;
frame.return_address = 0;
- bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+ if (!access_ok(VERIFY_READ, fp, 8))
+ break;
+
+ bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4);
+ if (bytes != 0)
+ break;
+ bytes = __copy_from_user_nmi(&frame.return_address, fp+4, 4);
if (bytes != 0)
break;
@@ -2265,6 +2272,7 @@
perf_callchain_store(entry, cs_base + frame.return_address);
fp = compat_ptr(ss_base + frame.next_frame);
}
+ pagefault_enable();
return 1;
}
#else
@@ -2302,12 +2310,19 @@
if (perf_callchain_user32(regs, entry))
return;
+ pagefault_disable();
while (entry->nr < PERF_MAX_STACK_DEPTH) {
unsigned long bytes;
frame.next_frame = NULL;
frame.return_address = 0;
- bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+ if (!access_ok(VERIFY_READ, fp, 16))
+ break;
+
+ bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8);
+ if (bytes != 0)
+ break;
+ bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8);
if (bytes != 0)
break;
@@ -2315,8 +2330,9 @@
break;
perf_callchain_store(entry, frame.return_address);
- fp = frame.next_frame;
+ fp = (void __user *)frame.next_frame;
}
+ pagefault_enable();
}
/*
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index d0e35eb..799e6bd 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -14,17 +14,7 @@
#include <linux/perf_event.h>
-#if 0
-#undef wrmsrl
-#define wrmsrl(msr, val) \
-do { \
- unsigned int _msr = (msr); \
- u64 _val = (val); \
- trace_printk("wrmsrl(%x, %Lx)\n", (unsigned int)(_msr), \
- (unsigned long long)(_val)); \
- native_write_msr((_msr), (u32)(_val), (u32)(_val >> 32)); \
-} while (0)
-#endif
+/* To enable MSR tracing please use the generic trace points. */
/*
* | NHM/WSM | SNB |
@@ -318,6 +308,10 @@
#define INTEL_UEVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
+/* Constraint on specific umask bit only + event */
+#define INTEL_UBIT_EVENT_CONSTRAINT(c, n) \
+ EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|(c))
+
/* Like UEVENT_CONSTRAINT, but match flags too */
#define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index e2a4300..33b4b67 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -255,7 +255,7 @@
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */
- INTEL_UEVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
+ INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
EVENT_CONSTRAINT_END
};
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 659f01e..e2fad0c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -42,6 +42,13 @@
#define LBR_FAR_BIT 8 /* do not capture far branches */
#define LBR_CALL_STACK_BIT 9 /* enable call stack */
+/*
+ * Following bit only exists in Linux; we mask it out before writing it to
+ * the actual MSR. But it helps the constraint perf code to understand
+ * that this is a separate configuration.
+ */
+#define LBR_NO_INFO_BIT 63 /* don't read LBR_INFO. */
+
#define LBR_KERNEL (1 << LBR_KERNEL_BIT)
#define LBR_USER (1 << LBR_USER_BIT)
#define LBR_JCC (1 << LBR_JCC_BIT)
@@ -52,6 +59,7 @@
#define LBR_IND_JMP (1 << LBR_IND_JMP_BIT)
#define LBR_FAR (1 << LBR_FAR_BIT)
#define LBR_CALL_STACK (1 << LBR_CALL_STACK_BIT)
+#define LBR_NO_INFO (1ULL << LBR_NO_INFO_BIT)
#define LBR_PLM (LBR_KERNEL | LBR_USER)
@@ -152,7 +160,7 @@
* did not change.
*/
if (cpuc->lbr_sel)
- lbr_select = cpuc->lbr_sel->config;
+ lbr_select = cpuc->lbr_sel->config & x86_pmu.lbr_sel_mask;
if (!pmi)
wrmsrl(MSR_LBR_SELECT, lbr_select);
@@ -422,6 +430,7 @@
*/
static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
{
+ bool need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO);
unsigned long mask = x86_pmu.lbr_nr - 1;
int lbr_format = x86_pmu.intel_cap.lbr_format;
u64 tos = intel_pmu_lbr_tos();
@@ -442,7 +451,7 @@
rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
rdmsrl(x86_pmu.lbr_to + lbr_idx, to);
- if (lbr_format == LBR_FORMAT_INFO) {
+ if (lbr_format == LBR_FORMAT_INFO && need_info) {
u64 info;
rdmsrl(MSR_LBR_INFO_0 + lbr_idx, info);
@@ -590,6 +599,7 @@
if (v != LBR_IGN)
mask |= v;
}
+
reg = &event->hw.branch_reg;
reg->idx = EXTRA_REG_LBR;
@@ -600,6 +610,11 @@
*/
reg->config = mask ^ x86_pmu.lbr_sel_mask;
+ if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) &&
+ (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) &&
+ (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO))
+ reg->config |= LBR_NO_INFO;
+
return 0;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
index 868e119..c0bbd10 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -27,6 +27,7 @@
#include <asm/perf_event.h>
#include <asm/insn.h>
#include <asm/io.h>
+#include <asm/intel_pt.h>
#include "perf_event.h"
#include "intel_pt.h"
@@ -1122,6 +1123,14 @@
return 0;
}
+void cpu_emergency_stop_pt(void)
+{
+ struct pt *pt = this_cpu_ptr(&pt_ctx);
+
+ if (pt->handle.event)
+ pt_event_stop(pt->handle.event, PERF_EF_UPDATE);
+}
+
static __init int pt_init(void)
{
int ret, cpu, prior_warn = 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index ed446bd..fb5843d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -63,7 +63,7 @@
#define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */
#define NR_RAPL_DOMAINS 0x4
-static const char *rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
+static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
"pp0-core",
"package",
"dram",
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 2c1910f..58f3431 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -35,6 +35,7 @@
#include <asm/cpu.h>
#include <asm/reboot.h>
#include <asm/virtext.h>
+#include <asm/intel_pt.h>
/* Alignment required for elf header segment */
#define ELF_CORE_HEADER_ALIGN 4096
@@ -125,6 +126,11 @@
cpu_emergency_vmxoff();
cpu_emergency_svm_disable();
+ /*
+ * Disable Intel PT to stop its logging
+ */
+ cpu_emergency_stop_pt();
+
disable_local_APIC();
}
@@ -169,6 +175,11 @@
cpu_emergency_vmxoff();
cpu_emergency_svm_disable();
+ /*
+ * Disable Intel PT to stop its logging
+ */
+ cpu_emergency_stop_pt();
+
#ifdef CONFIG_X86_IO_APIC
/* Prevent crash_kexec() from deadlocking on ioapic_lock. */
ioapic_zap_locks();
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 4362373..004c861 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -1,6 +1,8 @@
#include <linux/module.h>
#include <linux/preempt.h>
#include <asm/msr.h>
+#define CREATE_TRACE_POINTS
+#include <asm/msr-trace.h>
struct msr *msrs_alloc(void)
{
@@ -108,3 +110,27 @@
{
return __flip_bit(msr, bit, false);
}
+
+#ifdef CONFIG_TRACEPOINTS
+void do_trace_write_msr(unsigned msr, u64 val, int failed)
+{
+ trace_write_msr(msr, val, failed);
+}
+EXPORT_SYMBOL(do_trace_write_msr);
+EXPORT_TRACEPOINT_SYMBOL(write_msr);
+
+void do_trace_read_msr(unsigned msr, u64 val, int failed)
+{
+ trace_read_msr(msr, val, failed);
+}
+EXPORT_SYMBOL(do_trace_read_msr);
+EXPORT_TRACEPOINT_SYMBOL(read_msr);
+
+void do_trace_rdpmc(unsigned counter, u64 val, int failed)
+{
+ trace_rdpmc(counter, val, failed);
+}
+EXPORT_SYMBOL(do_trace_rdpmc);
+EXPORT_TRACEPOINT_SYMBOL(rdpmc);
+
+#endif
diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h
new file mode 100644
index 0000000..e1ee97c
--- /dev/null
+++ b/include/linux/tracepoint-defs.h
@@ -0,0 +1,27 @@
+#ifndef TRACEPOINT_DEFS_H
+#define TRACEPOINT_DEFS_H 1
+
+/*
+ * File can be included directly by headers who only want to access
+ * tracepoint->key to guard out of line trace calls. Otherwise
+ * linux/tracepoint.h should be used.
+ */
+
+#include <linux/atomic.h>
+#include <linux/static_key.h>
+
+struct tracepoint_func {
+ void *func;
+ void *data;
+ int prio;
+};
+
+struct tracepoint {
+ const char *name; /* Tracepoint name */
+ struct static_key key;
+ void (*regfunc)(void);
+ void (*unregfunc)(void);
+ struct tracepoint_func __rcu *funcs;
+};
+
+#endif
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 696a339c..f7c732b 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -17,26 +17,12 @@
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/rcupdate.h>
-#include <linux/static_key.h>
+#include <linux/tracepoint-defs.h>
struct module;
struct tracepoint;
struct notifier_block;
-struct tracepoint_func {
- void *func;
- void *data;
- int prio;
-};
-
-struct tracepoint {
- const char *name; /* Tracepoint name */
- struct static_key key;
- void (*regfunc)(void);
- void (*unregfunc)(void);
- struct tracepoint_func __rcu *funcs;
-};
-
struct trace_enum_map {
const char *system;
const char *enum_string;
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index d801bb0..1afe962 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -171,6 +171,9 @@
PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT = 12, /* indirect jumps */
PERF_SAMPLE_BRANCH_CALL_SHIFT = 13, /* direct call */
+ PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT = 14, /* no flags */
+ PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT = 15, /* no cycles */
+
PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */
};
@@ -192,6 +195,9 @@
PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT,
PERF_SAMPLE_BRANCH_CALL = 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT,
+ PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT,
+ PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT,
+
PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
};
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 39cf4a4..c3d61b9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -126,6 +126,37 @@
return data.ret;
}
+static void event_function_call(struct perf_event *event,
+ int (*active)(void *),
+ void (*inactive)(void *),
+ void *data)
+{
+ struct perf_event_context *ctx = event->ctx;
+ struct task_struct *task = ctx->task;
+
+ if (!task) {
+ cpu_function_call(event->cpu, active, data);
+ return;
+ }
+
+again:
+ if (!task_function_call(task, active, data))
+ return;
+
+ raw_spin_lock_irq(&ctx->lock);
+ if (ctx->is_active) {
+ /*
+ * Reload the task pointer, it might have been changed by
+ * a concurrent perf_event_context_sched_out().
+ */
+ task = ctx->task;
+ raw_spin_unlock_irq(&ctx->lock);
+ goto again;
+ }
+ inactive(data);
+ raw_spin_unlock_irq(&ctx->lock);
+}
+
#define EVENT_OWNER_KERNEL ((void *) -1)
static bool is_kernel_event(struct perf_event *event)
@@ -1629,6 +1660,17 @@
bool detach_group;
};
+static void ___perf_remove_from_context(void *info)
+{
+ struct remove_event *re = info;
+ struct perf_event *event = re->event;
+ struct perf_event_context *ctx = event->ctx;
+
+ if (re->detach_group)
+ perf_group_detach(event);
+ list_del_event(event, ctx);
+}
+
/*
* Cross CPU call to remove a performance event
*
@@ -1656,7 +1698,6 @@
return 0;
}
-
/*
* Remove the event from a task's (or a CPU's) list of events.
*
@@ -1673,7 +1714,6 @@
static void perf_remove_from_context(struct perf_event *event, bool detach_group)
{
struct perf_event_context *ctx = event->ctx;
- struct task_struct *task = ctx->task;
struct remove_event re = {
.event = event,
.detach_group = detach_group,
@@ -1681,44 +1721,8 @@
lockdep_assert_held(&ctx->mutex);
- if (!task) {
- /*
- * Per cpu events are removed via an smp call. The removal can
- * fail if the CPU is currently offline, but in that case we
- * already called __perf_remove_from_context from
- * perf_event_exit_cpu.
- */
- cpu_function_call(event->cpu, __perf_remove_from_context, &re);
- return;
- }
-
-retry:
- if (!task_function_call(task, __perf_remove_from_context, &re))
- return;
-
- raw_spin_lock_irq(&ctx->lock);
- /*
- * If we failed to find a running task, but find the context active now
- * that we've acquired the ctx->lock, retry.
- */
- if (ctx->is_active) {
- raw_spin_unlock_irq(&ctx->lock);
- /*
- * Reload the task pointer, it might have been changed by
- * a concurrent perf_event_context_sched_out().
- */
- task = ctx->task;
- goto retry;
- }
-
- /*
- * Since the task isn't running, its safe to remove the event, us
- * holding the ctx->lock ensures the task won't get scheduled in.
- */
- if (detach_group)
- perf_group_detach(event);
- list_del_event(event, ctx);
- raw_spin_unlock_irq(&ctx->lock);
+ event_function_call(event, __perf_remove_from_context,
+ ___perf_remove_from_context, &re);
}
/*
@@ -2067,6 +2071,18 @@
ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
}
+static void ___perf_install_in_context(void *info)
+{
+ struct perf_event *event = info;
+ struct perf_event_context *ctx = event->ctx;
+
+ /*
+ * Since the task isn't running, its safe to add the event, us holding
+ * the ctx->lock ensures the task won't get scheduled in.
+ */
+ add_event_to_ctx(event, ctx);
+}
+
/*
* Cross CPU call to install and enable a performance event
*
@@ -2143,48 +2159,14 @@
struct perf_event *event,
int cpu)
{
- struct task_struct *task = ctx->task;
-
lockdep_assert_held(&ctx->mutex);
event->ctx = ctx;
if (event->cpu != -1)
event->cpu = cpu;
- if (!task) {
- /*
- * Per cpu events are installed via an smp call and
- * the install is always successful.
- */
- cpu_function_call(cpu, __perf_install_in_context, event);
- return;
- }
-
-retry:
- if (!task_function_call(task, __perf_install_in_context, event))
- return;
-
- raw_spin_lock_irq(&ctx->lock);
- /*
- * If we failed to find a running task, but find the context active now
- * that we've acquired the ctx->lock, retry.
- */
- if (ctx->is_active) {
- raw_spin_unlock_irq(&ctx->lock);
- /*
- * Reload the task pointer, it might have been changed by
- * a concurrent perf_event_context_sched_out().
- */
- task = ctx->task;
- goto retry;
- }
-
- /*
- * Since the task isn't running, its safe to add the event, us holding
- * the ctx->lock ensures the task won't get scheduled in.
- */
- add_event_to_ctx(event, ctx);
- raw_spin_unlock_irq(&ctx->lock);
+ event_function_call(event, __perf_install_in_context,
+ ___perf_install_in_context, event);
}
/*
@@ -4154,6 +4136,22 @@
u64 value;
};
+static void ___perf_event_period(void *info)
+{
+ struct period_event *pe = info;
+ struct perf_event *event = pe->event;
+ u64 value = pe->value;
+
+ if (event->attr.freq) {
+ event->attr.sample_freq = value;
+ } else {
+ event->attr.sample_period = value;
+ event->hw.sample_period = value;
+ }
+
+ local64_set(&event->hw.period_left, 0);
+}
+
static int __perf_event_period(void *info)
{
struct period_event *pe = info;
@@ -4190,8 +4188,6 @@
static int perf_event_period(struct perf_event *event, u64 __user *arg)
{
struct period_event pe = { .event = event, };
- struct perf_event_context *ctx = event->ctx;
- struct task_struct *task;
u64 value;
if (!is_sampling_event(event))
@@ -4206,34 +4202,10 @@
if (event->attr.freq && value > sysctl_perf_event_sample_rate)
return -EINVAL;
- task = ctx->task;
pe.value = value;
- if (!task) {
- cpu_function_call(event->cpu, __perf_event_period, &pe);
- return 0;
- }
-
-retry:
- if (!task_function_call(task, __perf_event_period, &pe))
- return 0;
-
- raw_spin_lock_irq(&ctx->lock);
- if (ctx->is_active) {
- raw_spin_unlock_irq(&ctx->lock);
- task = ctx->task;
- goto retry;
- }
-
- if (event->attr.freq) {
- event->attr.sample_freq = value;
- } else {
- event->attr.sample_period = value;
- event->hw.sample_period = value;
- }
-
- local64_set(&event->hw.period_left, 0);
- raw_spin_unlock_irq(&ctx->lock);
+ event_function_call(event, __perf_event_period,
+ ___perf_event_period, &pe);
return 0;
}
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
index 83c33a5b..d51e25a 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -16,6 +16,10 @@
#include <linux/kernel.h>
#include <linux/atomic.h>
+#ifdef CONFIG_X86
+#include <asm/processor.h> /* for boot_cpu_has below */
+#endif
+
#define TEST(bit, op, c_op, val) \
do { \
atomic##bit##_set(&v, v0); \
diff --git a/tools/Makefile b/tools/Makefile
index 7dc820a..0ba0df3 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -96,7 +96,7 @@
$(call descend,$(@:_install=),install)
selftests_install:
- $(call descend,testing/$(@:_clean=),install)
+ $(call descend,testing/$(@:_install=),install)
turbostat_install x86_energy_perf_policy_install:
$(call descend,power/x86/$(@:_install=),install)
diff --git a/tools/build/Makefile b/tools/build/Makefile
index a930362..0d5a0e3 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -25,7 +25,7 @@
MAKEFLAGS := --no-print-directory
build := -f $(srctree)/tools/build/Makefile.build dir=. obj
-all: fixdep
+all: $(OUTPUT)fixdep
clean:
$(call QUIET_CLEAN, fixdep)
diff --git a/tools/build/Makefile.include b/tools/build/Makefile.include
index 4e09ad6..be630be 100644
--- a/tools/build/Makefile.include
+++ b/tools/build/Makefile.include
@@ -4,7 +4,7 @@
fixdep:
else
fixdep:
- $(Q)$(MAKE) -C $(srctree)/tools/build fixdep
+ $(Q)$(MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= $(OUTPUT)fixdep
endif
.PHONY: fixdep
diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h
new file mode 100644
index 0000000..2e2f736c
--- /dev/null
+++ b/tools/include/linux/string.h
@@ -0,0 +1,11 @@
+#ifndef _TOOLS_LINUX_STRING_H_
+#define _TOOLS_LINUX_STRING_H_
+
+
+#include <linux/types.h> /* for size_t */
+
+void *memdup(const void *src, size_t len);
+
+int strtobool(const char *s, bool *res);
+
+#endif /* _LINUX_STRING_H_ */
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index a3caaf3..636e3dd 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -71,7 +71,17 @@
INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi
FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES)
+check_feat := 1
+NON_CHECK_FEAT_TARGETS := clean TAGS tags cscope help
+ifdef MAKECMDGOALS
+ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),)
+ check_feat := 0
+endif
+endif
+
+ifeq ($(check_feat),1)
include $(srctree)/tools/build/Makefile.feature
+endif
export prefix libdir src obj
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index a633105..5bdc6ea 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -83,3 +83,17 @@
log_buf[0] = 0;
return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
}
+
+int bpf_map_update_elem(int fd, void *key, void *value,
+ u64 flags)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.map_fd = fd;
+ attr.key = ptr_to_u64(key);
+ attr.value = ptr_to_u64(value);
+ attr.flags = flags;
+
+ return sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 854b736..a764655 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -20,4 +20,6 @@
u32 kern_version, char *log_buf,
size_t log_buf_sz);
+int bpf_map_update_elem(int fd, void *key, void *value,
+ u64 flags);
#endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e176bad..a298614 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -152,29 +152,36 @@
} *reloc_desc;
int nr_reloc;
- int fd;
+ struct {
+ int nr;
+ int *fds;
+ } instances;
+ bpf_program_prep_t preprocessor;
struct bpf_object *obj;
void *priv;
bpf_program_clear_priv_t clear_priv;
};
+struct bpf_map {
+ int fd;
+ char *name;
+ struct bpf_map_def def;
+ void *priv;
+ bpf_map_clear_priv_t clear_priv;
+};
+
static LIST_HEAD(bpf_objects_list);
struct bpf_object {
char license[64];
u32 kern_version;
- void *maps_buf;
- size_t maps_buf_sz;
struct bpf_program *programs;
size_t nr_programs;
- int *map_fds;
- /*
- * This field is required because maps_buf will be freed and
- * maps_buf_sz will be set to 0 after loaded.
- */
- size_t nr_map_fds;
+ struct bpf_map *maps;
+ size_t nr_maps;
+
bool loaded;
/*
@@ -206,10 +213,25 @@
static void bpf_program__unload(struct bpf_program *prog)
{
+ int i;
+
if (!prog)
return;
- zclose(prog->fd);
+ /*
+ * If the object is opened but the program was never loaded,
+ * it is possible that prog->instances.nr == -1.
+ */
+ if (prog->instances.nr > 0) {
+ for (i = 0; i < prog->instances.nr; i++)
+ zclose(prog->instances.fds[i]);
+ } else if (prog->instances.nr != -1) {
+ pr_warning("Internal error: instances.nr is %d\n",
+ prog->instances.nr);
+ }
+
+ prog->instances.nr = -1;
+ zfree(&prog->instances.fds);
}
static void bpf_program__exit(struct bpf_program *prog)
@@ -260,7 +282,8 @@
memcpy(prog->insns, data,
prog->insns_cnt * sizeof(struct bpf_insn));
prog->idx = idx;
- prog->fd = -1;
+ prog->instances.fds = NULL;
+ prog->instances.nr = -1;
return 0;
errout:
@@ -469,30 +492,81 @@
bpf_object__init_maps(struct bpf_object *obj, void *data,
size_t size)
{
- if (size == 0) {
+ size_t nr_maps;
+ int i;
+
+ nr_maps = size / sizeof(struct bpf_map_def);
+ if (!data || !nr_maps) {
pr_debug("%s doesn't need map definition\n",
obj->path);
return 0;
}
- obj->maps_buf = malloc(size);
- if (!obj->maps_buf) {
- pr_warning("malloc maps failed: %s\n", obj->path);
+ pr_debug("maps in %s: %zd bytes\n", obj->path, size);
+
+ obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
+ if (!obj->maps) {
+ pr_warning("alloc maps for object failed\n");
return -ENOMEM;
}
+ obj->nr_maps = nr_maps;
- obj->maps_buf_sz = size;
- memcpy(obj->maps_buf, data, size);
- pr_debug("maps in %s: %ld bytes\n", obj->path, (long)size);
+ for (i = 0; i < nr_maps; i++) {
+ struct bpf_map_def *def = &obj->maps[i].def;
+
+ /*
+ * fill all fd with -1 so won't close incorrect
+ * fd (fd=0 is stdin) when failure (zclose won't close
+ * negative fd)).
+ */
+ obj->maps[i].fd = -1;
+
+ /* Save map definition into obj->maps */
+ *def = ((struct bpf_map_def *)data)[i];
+ }
return 0;
}
+static void
+bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx)
+{
+ int i;
+ Elf_Data *symbols = obj->efile.symbols;
+
+ if (!symbols || maps_shndx < 0)
+ return;
+
+ for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+ GElf_Sym sym;
+ size_t map_idx;
+ const char *map_name;
+
+ if (!gelf_getsym(symbols, i, &sym))
+ continue;
+ if (sym.st_shndx != maps_shndx)
+ continue;
+
+ map_name = elf_strptr(obj->efile.elf,
+ obj->efile.ehdr.e_shstrndx,
+ sym.st_name);
+ map_idx = sym.st_value / sizeof(struct bpf_map_def);
+ if (map_idx >= obj->nr_maps) {
+ pr_warning("index of map \"%s\" is buggy: %zu > %zu\n",
+ map_name, map_idx, obj->nr_maps);
+ continue;
+ }
+ obj->maps[map_idx].name = strdup(map_name);
+ pr_debug("map %zu is \"%s\"\n", map_idx,
+ obj->maps[map_idx].name);
+ }
+}
+
static int bpf_object__elf_collect(struct bpf_object *obj)
{
Elf *elf = obj->efile.elf;
GElf_Ehdr *ep = &obj->efile.ehdr;
Elf_Scn *scn = NULL;
- int idx = 0, err = 0;
+ int idx = 0, err = 0, maps_shndx = -1;
/* Elf is corrupted/truncated, avoid calling elf_strptr. */
if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
@@ -542,10 +616,11 @@
err = bpf_object__init_kversion(obj,
data->d_buf,
data->d_size);
- else if (strcmp(name, "maps") == 0)
+ else if (strcmp(name, "maps") == 0) {
err = bpf_object__init_maps(obj, data->d_buf,
data->d_size);
- else if (sh.sh_type == SHT_SYMTAB) {
+ maps_shndx = idx;
+ } else if (sh.sh_type == SHT_SYMTAB) {
if (obj->efile.symbols) {
pr_warning("bpf: multiple SYMTAB in %s\n",
obj->path);
@@ -586,6 +661,9 @@
if (err)
goto out;
}
+
+ if (maps_shndx >= 0)
+ bpf_object__init_maps_name(obj, maps_shndx);
out:
return err;
}
@@ -668,37 +746,15 @@
bpf_object__create_maps(struct bpf_object *obj)
{
unsigned int i;
- size_t nr_maps;
- int *pfd;
- nr_maps = obj->maps_buf_sz / sizeof(struct bpf_map_def);
- if (!obj->maps_buf || !nr_maps) {
- pr_debug("don't need create maps for %s\n",
- obj->path);
- return 0;
- }
+ for (i = 0; i < obj->nr_maps; i++) {
+ struct bpf_map_def *def = &obj->maps[i].def;
+ int *pfd = &obj->maps[i].fd;
- obj->map_fds = malloc(sizeof(int) * nr_maps);
- if (!obj->map_fds) {
- pr_warning("realloc perf_bpf_map_fds failed\n");
- return -ENOMEM;
- }
- obj->nr_map_fds = nr_maps;
-
- /* fill all fd with -1 */
- memset(obj->map_fds, -1, sizeof(int) * nr_maps);
-
- pfd = obj->map_fds;
- for (i = 0; i < nr_maps; i++) {
- struct bpf_map_def def;
-
- def = *(struct bpf_map_def *)(obj->maps_buf +
- i * sizeof(struct bpf_map_def));
-
- *pfd = bpf_create_map(def.type,
- def.key_size,
- def.value_size,
- def.max_entries);
+ *pfd = bpf_create_map(def->type,
+ def->key_size,
+ def->value_size,
+ def->max_entries);
if (*pfd < 0) {
size_t j;
int err = *pfd;
@@ -706,22 +762,17 @@
pr_warning("failed to create map: %s\n",
strerror(errno));
for (j = 0; j < i; j++)
- zclose(obj->map_fds[j]);
- obj->nr_map_fds = 0;
- zfree(&obj->map_fds);
+ zclose(obj->maps[j].fd);
return err;
}
pr_debug("create map: fd=%d\n", *pfd);
- pfd++;
}
- zfree(&obj->maps_buf);
- obj->maps_buf_sz = 0;
return 0;
}
static int
-bpf_program__relocate(struct bpf_program *prog, int *map_fds)
+bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
{
int i;
@@ -741,7 +792,7 @@
return -LIBBPF_ERRNO__RELOC;
}
insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
- insns[insn_idx].imm = map_fds[map_idx];
+ insns[insn_idx].imm = obj->maps[map_idx].fd;
}
zfree(&prog->reloc_desc);
@@ -760,7 +811,7 @@
for (i = 0; i < obj->nr_programs; i++) {
prog = &obj->programs[i];
- err = bpf_program__relocate(prog, obj->map_fds);
+ err = bpf_program__relocate(prog, obj);
if (err) {
pr_warning("failed to relocate '%s'\n",
prog->section_name);
@@ -784,8 +835,7 @@
Elf_Data *data = obj->efile.reloc[i].data;
int idx = shdr->sh_info;
struct bpf_program *prog;
- size_t nr_maps = obj->maps_buf_sz /
- sizeof(struct bpf_map_def);
+ size_t nr_maps = obj->nr_maps;
if (shdr->sh_type != SHT_REL) {
pr_warning("internal error at %d\n", __LINE__);
@@ -860,13 +910,73 @@
bpf_program__load(struct bpf_program *prog,
char *license, u32 kern_version)
{
- int err, fd;
+ int err = 0, fd, i;
- err = load_program(prog->insns, prog->insns_cnt,
- license, kern_version, &fd);
- if (!err)
- prog->fd = fd;
+ if (prog->instances.nr < 0 || !prog->instances.fds) {
+ if (prog->preprocessor) {
+ pr_warning("Internal error: can't load program '%s'\n",
+ prog->section_name);
+ return -LIBBPF_ERRNO__INTERNAL;
+ }
+ prog->instances.fds = malloc(sizeof(int));
+ if (!prog->instances.fds) {
+ pr_warning("Not enough memory for BPF fds\n");
+ return -ENOMEM;
+ }
+ prog->instances.nr = 1;
+ prog->instances.fds[0] = -1;
+ }
+
+ if (!prog->preprocessor) {
+ if (prog->instances.nr != 1) {
+ pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
+ prog->section_name, prog->instances.nr);
+ }
+ err = load_program(prog->insns, prog->insns_cnt,
+ license, kern_version, &fd);
+ if (!err)
+ prog->instances.fds[0] = fd;
+ goto out;
+ }
+
+ for (i = 0; i < prog->instances.nr; i++) {
+ struct bpf_prog_prep_result result;
+ bpf_program_prep_t preprocessor = prog->preprocessor;
+
+ bzero(&result, sizeof(result));
+ err = preprocessor(prog, i, prog->insns,
+ prog->insns_cnt, &result);
+ if (err) {
+ pr_warning("Preprocessing the %dth instance of program '%s' failed\n",
+ i, prog->section_name);
+ goto out;
+ }
+
+ if (!result.new_insn_ptr || !result.new_insn_cnt) {
+ pr_debug("Skip loading the %dth instance of program '%s'\n",
+ i, prog->section_name);
+ prog->instances.fds[i] = -1;
+ if (result.pfd)
+ *result.pfd = -1;
+ continue;
+ }
+
+ err = load_program(result.new_insn_ptr,
+ result.new_insn_cnt,
+ license, kern_version, &fd);
+
+ if (err) {
+ pr_warning("Loading the %dth instance of program '%s' failed\n",
+ i, prog->section_name);
+ goto out;
+ }
+
+ if (result.pfd)
+ *result.pfd = fd;
+ prog->instances.fds[i] = fd;
+ }
+out:
if (err)
pr_warning("failed to load program '%s'\n",
prog->section_name);
@@ -970,10 +1080,8 @@
if (!obj)
return -EINVAL;
- for (i = 0; i < obj->nr_map_fds; i++)
- zclose(obj->map_fds[i]);
- zfree(&obj->map_fds);
- obj->nr_map_fds = 0;
+ for (i = 0; i < obj->nr_maps; i++)
+ zclose(obj->maps[i].fd);
for (i = 0; i < obj->nr_programs; i++)
bpf_program__unload(&obj->programs[i]);
@@ -1016,7 +1124,16 @@
bpf_object__elf_finish(obj);
bpf_object__unload(obj);
- zfree(&obj->maps_buf);
+ for (i = 0; i < obj->nr_maps; i++) {
+ zfree(&obj->maps[i].name);
+ if (obj->maps[i].clear_priv)
+ obj->maps[i].clear_priv(&obj->maps[i],
+ obj->maps[i].priv);
+ obj->maps[i].priv = NULL;
+ obj->maps[i].clear_priv = NULL;
+ }
+ zfree(&obj->maps);
+ obj->nr_maps = 0;
if (obj->programs && obj->nr_programs) {
for (i = 0; i < obj->nr_programs; i++)
@@ -1121,5 +1238,142 @@
int bpf_program__fd(struct bpf_program *prog)
{
- return prog->fd;
+ return bpf_program__nth_fd(prog, 0);
+}
+
+int bpf_program__set_prep(struct bpf_program *prog, int nr_instances,
+ bpf_program_prep_t prep)
+{
+ int *instances_fds;
+
+ if (nr_instances <= 0 || !prep)
+ return -EINVAL;
+
+ if (prog->instances.nr > 0 || prog->instances.fds) {
+ pr_warning("Can't set pre-processor after loading\n");
+ return -EINVAL;
+ }
+
+ instances_fds = malloc(sizeof(int) * nr_instances);
+ if (!instances_fds) {
+ pr_warning("alloc memory failed for fds\n");
+ return -ENOMEM;
+ }
+
+ /* fill all fd with -1 */
+ memset(instances_fds, -1, sizeof(int) * nr_instances);
+
+ prog->instances.nr = nr_instances;
+ prog->instances.fds = instances_fds;
+ prog->preprocessor = prep;
+ return 0;
+}
+
+int bpf_program__nth_fd(struct bpf_program *prog, int n)
+{
+ int fd;
+
+ if (n >= prog->instances.nr || n < 0) {
+ pr_warning("Can't get the %dth fd from program %s: only %d instances\n",
+ n, prog->section_name, prog->instances.nr);
+ return -EINVAL;
+ }
+
+ fd = prog->instances.fds[n];
+ if (fd < 0) {
+ pr_warning("%dth instance of program '%s' is invalid\n",
+ n, prog->section_name);
+ return -ENOENT;
+ }
+
+ return fd;
+}
+
+int bpf_map__get_fd(struct bpf_map *map)
+{
+ if (!map)
+ return -EINVAL;
+
+ return map->fd;
+}
+
+int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef)
+{
+ if (!map || !pdef)
+ return -EINVAL;
+
+ *pdef = map->def;
+ return 0;
+}
+
+const char *bpf_map__get_name(struct bpf_map *map)
+{
+ if (!map)
+ return NULL;
+ return map->name;
+}
+
+int bpf_map__set_private(struct bpf_map *map, void *priv,
+ bpf_map_clear_priv_t clear_priv)
+{
+ if (!map)
+ return -EINVAL;
+
+ if (map->priv) {
+ if (map->clear_priv)
+ map->clear_priv(map, map->priv);
+ }
+
+ map->priv = priv;
+ map->clear_priv = clear_priv;
+ return 0;
+}
+
+int bpf_map__get_private(struct bpf_map *map, void **ppriv)
+{
+ if (!map)
+ return -EINVAL;
+
+ if (ppriv)
+ *ppriv = map->priv;
+ return 0;
+}
+
+struct bpf_map *
+bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
+{
+ size_t idx;
+ struct bpf_map *s, *e;
+
+ if (!obj || !obj->maps)
+ return NULL;
+
+ s = obj->maps;
+ e = obj->maps + obj->nr_maps;
+
+ if (prev == NULL)
+ return s;
+
+ if ((prev < s) || (prev >= e)) {
+ pr_warning("error in %s: map handler doesn't belong to object\n",
+ __func__);
+ return NULL;
+ }
+
+ idx = (prev - obj->maps) + 1;
+ if (idx >= obj->nr_maps)
+ return NULL;
+ return &obj->maps[idx];
+}
+
+struct bpf_map *
+bpf_object__get_map_by_name(struct bpf_object *obj, const char *name)
+{
+ struct bpf_map *pos;
+
+ bpf_map__for_each(pos, obj) {
+ if (strcmp(pos->name, name) == 0)
+ return pos;
+ }
+ return NULL;
}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index c9a9aef..a51594c 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -88,6 +88,70 @@
int bpf_program__fd(struct bpf_program *prog);
+struct bpf_insn;
+
+/*
+ * Libbpf allows callers to adjust BPF programs before being loaded
+ * into kernel. One program in an object file can be transform into
+ * multiple variants to be attached to different code.
+ *
+ * bpf_program_prep_t, bpf_program__set_prep and bpf_program__nth_fd
+ * are APIs for this propose.
+ *
+ * - bpf_program_prep_t:
+ * It defines 'preprocessor', which is a caller defined function
+ * passed to libbpf through bpf_program__set_prep(), and will be
+ * called before program is loaded. The processor should adjust
+ * the program one time for each instances according to the number
+ * passed to it.
+ *
+ * - bpf_program__set_prep:
+ * Attachs a preprocessor to a BPF program. The number of instances
+ * whould be created is also passed through this function.
+ *
+ * - bpf_program__nth_fd:
+ * After the program is loaded, get resuling fds from bpf program for
+ * each instances.
+ *
+ * If bpf_program__set_prep() is not used, the program whould be loaded
+ * without adjustment during bpf_object__load(). The program has only
+ * one instance. In this case bpf_program__fd(prog) is equal to
+ * bpf_program__nth_fd(prog, 0).
+ */
+
+struct bpf_prog_prep_result {
+ /*
+ * If not NULL, load new instruction array.
+ * If set to NULL, don't load this instance.
+ */
+ struct bpf_insn *new_insn_ptr;
+ int new_insn_cnt;
+
+ /* If not NULL, result fd is set to it */
+ int *pfd;
+};
+
+/*
+ * Parameters of bpf_program_prep_t:
+ * - prog: The bpf_program being loaded.
+ * - n: Index of instance being generated.
+ * - insns: BPF instructions array.
+ * - insns_cnt:Number of instructions in insns.
+ * - res: Output parameter, result of transformation.
+ *
+ * Return value:
+ * - Zero: pre-processing success.
+ * - Non-zero: pre-processing, stop loading.
+ */
+typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n,
+ struct bpf_insn *insns, int insns_cnt,
+ struct bpf_prog_prep_result *res);
+
+int bpf_program__set_prep(struct bpf_program *prog, int nr_instance,
+ bpf_program_prep_t prep);
+
+int bpf_program__nth_fd(struct bpf_program *prog, int n);
+
/*
* We don't need __attribute__((packed)) now since it is
* unnecessary for 'bpf_map_def' because they are all aligned.
@@ -101,4 +165,28 @@
unsigned int max_entries;
};
+/*
+ * There is another 'struct bpf_map' in include/linux/map.h. However,
+ * it is not a uapi header so no need to consider name clash.
+ */
+struct bpf_map;
+struct bpf_map *
+bpf_object__get_map_by_name(struct bpf_object *obj, const char *name);
+
+struct bpf_map *
+bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
+#define bpf_map__for_each(pos, obj) \
+ for ((pos) = bpf_map__next(NULL, (obj)); \
+ (pos) != NULL; \
+ (pos) = bpf_map__next((pos), (obj)))
+
+int bpf_map__get_fd(struct bpf_map *map);
+int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef);
+const char *bpf_map__get_name(struct bpf_map *map);
+
+typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
+int bpf_map__set_private(struct bpf_map *map, void *priv,
+ bpf_map_clear_priv_t clear_priv);
+int bpf_map__get_private(struct bpf_map *map, void **ppriv);
+
#endif
diff --git a/tools/lib/string.c b/tools/lib/string.c
new file mode 100644
index 0000000..065e54f
--- /dev/null
+++ b/tools/lib/string.c
@@ -0,0 +1,62 @@
+/*
+ * linux/tools/lib/string.c
+ *
+ * Copied from linux/lib/string.c, where it is:
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * More specifically, the first copied function was strtobool, which
+ * was introduced by:
+ *
+ * d0f1fed29e6e ("Add a strtobool function matching semantics of existing in kernel equivalents")
+ * Author: Jonathan Cameron <jic23@cam.ac.uk>
+ */
+
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <linux/string.h>
+
+/**
+ * memdup - duplicate region of memory
+ *
+ * @src: memory region to duplicate
+ * @len: memory region length
+ */
+void *memdup(const void *src, size_t len)
+{
+ void *p = malloc(len);
+
+ if (p)
+ memcpy(p, src, len);
+
+ return p;
+}
+
+/**
+ * strtobool - convert common user inputs into boolean values
+ * @s: input string
+ * @res: result
+ *
+ * This routine returns 0 iff the first character is one of 'Yy1Nn0'.
+ * Otherwise it will return -EINVAL. Value pointed to by res is
+ * updated upon finding a match.
+ */
+int strtobool(const char *s, bool *res)
+{
+ switch (s[0]) {
+ case 'y':
+ case 'Y':
+ case '1':
+ *res = true;
+ break;
+ case 'n':
+ case 'N':
+ case '0':
+ *res = false;
+ break;
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 2a912df..68276f3 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -4968,13 +4968,12 @@
sizeof(long) != 8) {
char *p;
- ls = 2;
/* make %l into %ll */
- p = strchr(format, 'l');
- if (p)
+ if (ls == 1 && (p = strchr(format, 'l')))
memmove(p+1, p, strlen(p)+1);
else if (strcmp(format, "%p") == 0)
strcpy(format, "0x%llx");
+ ls = 2;
}
switch (ls) {
case -2:
diff --git a/tools/perf/Build b/tools/perf/Build
index 7223745..2c7aaf2 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -1,5 +1,6 @@
perf-y += builtin-bench.o
perf-y += builtin-annotate.o
+perf-y += builtin-config.o
perf-y += builtin-diff.o
perf-y += builtin-evlist.o
perf-y += builtin-help.o
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
new file mode 100644
index 0000000..b9ca1e3
--- /dev/null
+++ b/tools/perf/Documentation/perf-config.txt
@@ -0,0 +1,103 @@
+perf-config(1)
+==============
+
+NAME
+----
+perf-config - Get and set variables in a configuration file.
+
+SYNOPSIS
+--------
+[verse]
+'perf config' -l | --list
+
+DESCRIPTION
+-----------
+You can manage variables in a configuration file with this command.
+
+OPTIONS
+-------
+
+-l::
+--list::
+ Show current config variables, name and value, for all sections.
+
+CONFIGURATION FILE
+------------------
+
+The perf configuration file contains many variables to change various
+aspects of each of its tools, including output, disk usage, etc.
+The '$HOME/.perfconfig' file is used to store a per-user configuration.
+The file '$(sysconfdir)/perfconfig' can be used to
+store a system-wide default configuration.
+
+Syntax
+~~~~~~
+
+The file consist of sections. A section starts with its name
+surrounded by square brackets and continues till the next section
+begins. Each variable must be in a section, and have the form
+'name = value', for example:
+
+ [section]
+ name1 = value1
+ name2 = value2
+
+Section names are case sensitive and can contain any characters except
+newline (double quote `"` and backslash have to be escaped as `\"` and `\\`,
+respectively). Section headers can't span multiple lines.
+
+Example
+~~~~~~~
+
+Given a $HOME/.perfconfig like this:
+
+#
+# This is the config file, and
+# a '#' and ';' character indicates a comment
+#
+
+ [colors]
+ # Color variables
+ top = red, default
+ medium = green, default
+ normal = lightgray, default
+ selected = white, lightgray
+ code = blue, default
+ addr = magenta, default
+ root = white, blue
+
+ [tui]
+ # Defaults if linked with libslang
+ report = on
+ annotate = on
+ top = on
+
+ [buildid]
+ # Default, disable using /dev/null
+ dir = ~/.debug
+
+ [annotate]
+ # Defaults
+ hide_src_code = false
+ use_offset = true
+ jump_arrows = true
+ show_nr_jumps = false
+
+ [help]
+ # Format can be man, info, web or html
+ format = man
+ autocorrect = 0
+
+ [ui]
+ show-headers = true
+
+ [call-graph]
+ # fp (framepointer), dwarf
+ record-mode = fp
+ print-type = graph
+ order = caller
+ sort-key = function
+
+SEE ALSO
+--------
+linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 5ce8da1..dab99ed 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -170,17 +170,18 @@
Dump raw trace in ASCII.
-g::
---call-graph=<print_type,threshold[,print_limit],order,sort_key,branch>::
+--call-graph=<print_type,threshold[,print_limit],order,sort_key[,branch],value>::
Display call chains using type, min percent threshold, print limit,
- call order, sort key and branch. Note that ordering of parameters is not
- fixed so any parement can be given in an arbitraty order. One exception
- is the print_limit which should be preceded by threshold.
+ call order, sort key, optional branch and value. Note that ordering of
+ parameters is not fixed so any parement can be given in an arbitraty order.
+ One exception is the print_limit which should be preceded by threshold.
print_type can be either:
- flat: single column, linear exposure of call chains.
- graph: use a graph tree, displaying absolute overhead rates. (default)
- fractal: like graph, but displays relative rates. Each branch of
the tree is considered as a new profiled object.
+ - folded: call chains are displayed in a line, separated by semicolons
- none: disable call chain display.
threshold is a percentage value which specifies a minimum percent to be
@@ -204,6 +205,11 @@
- branch: include last branch information in callgraph when available.
Usually more convenient to use --branch-history for this.
+ value can be:
+ - percent: diplay overhead percent (default)
+ - period: display event period
+ - count: display event count
+
--children::
Accumulate callchain of children to parent entry so that then can
show up in the output. The output will have a new "Children" column
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 39c38cb..2562eac 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -22,6 +22,7 @@
tools/lib/bpf
tools/lib/hweight.c
tools/lib/rbtree.c
+tools/lib/string.c
tools/lib/symbol/kallsyms.c
tools/lib/symbol/kallsyms.h
tools/lib/util/find_next_bit.c
@@ -50,6 +51,7 @@
tools/include/linux/poison.h
tools/include/linux/rbtree.h
tools/include/linux/rbtree_augmented.h
+tools/include/linux/string.h
tools/include/linux/types.h
tools/include/linux/err.h
include/asm-generic/bitops/arch_hweight.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 0d19d54..929a32b 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -420,7 +420,7 @@
$(call QUIET_CLEAN, libtraceevent)
$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) O=$(OUTPUT) clean >/dev/null
-install-traceevent-plugins: $(LIBTRACEEVENT)
+install-traceevent-plugins: libtraceevent_plugins
$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) install_plugins
$(LIBAPI): fixdep FORCE
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index 7ed00f4..b48de2f 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -2,10 +2,10 @@
#define ARCH_TESTS_H
/* Tests */
-int test__rdpmc(void);
-int test__perf_time_to_tsc(void);
-int test__insn_x86(void);
-int test__intel_cqm_count_nmi_context(void);
+int test__rdpmc(int subtest);
+int test__perf_time_to_tsc(int subtest);
+int test__insn_x86(int subtest);
+int test__intel_cqm_count_nmi_context(int subtest);
#ifdef HAVE_DWARF_UNWIND_SUPPORT
struct thread;
diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c
index b6115df..08d9b2bc 100644
--- a/tools/perf/arch/x86/tests/insn-x86.c
+++ b/tools/perf/arch/x86/tests/insn-x86.c
@@ -171,7 +171,7 @@
* verbose (-v) option to see all the instructions and whether or not they
* decoded successfuly.
*/
-int test__insn_x86(void)
+int test__insn_x86(int subtest __maybe_unused)
{
int ret = 0;
diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
index d28c1b6..94e0cb7 100644
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -33,7 +33,7 @@
* the last read counter value to avoid triggering a WARN_ON_ONCE() in
* smp_call_function_many() caused by sending IPIs from NMI context.
*/
-int test__intel_cqm_count_nmi_context(void)
+int test__intel_cqm_count_nmi_context(int subtest __maybe_unused)
{
struct perf_evlist *evlist = NULL;
struct perf_evsel *evsel = NULL;
diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index 658cd20..a289aa8 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -35,7 +35,7 @@
* %0 is returned, otherwise %-1 is returned. If TSC conversion is not
* supported then then the test passes but " (not supported)" is printed.
*/
-int test__perf_time_to_tsc(void)
+int test__perf_time_to_tsc(int subtest __maybe_unused)
{
struct record_opts opts = {
.mmap_pages = UINT_MAX,
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index e768821..7bb0d13 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -149,7 +149,7 @@
return 0;
}
-int test__rdpmc(void)
+int test__rdpmc(int subtest __maybe_unused)
{
int status = 0;
int wret = 0;
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index ff63649f..4659703 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -5,6 +5,7 @@
libperf-y += perf_regs.o
libperf-$(CONFIG_DWARF) += dwarf-regs.o
+libperf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o
libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
new file mode 100644
index 0000000..427ea7a
--- /dev/null
+++ b/tools/perf/builtin-config.c
@@ -0,0 +1,66 @@
+/*
+ * builtin-config.c
+ *
+ * Copyright (C) 2015, Taeung Song <treeze.taeung@gmail.com>
+ *
+ */
+#include "builtin.h"
+
+#include "perf.h"
+
+#include "util/cache.h"
+#include "util/parse-options.h"
+#include "util/util.h"
+#include "util/debug.h"
+
+static const char * const config_usage[] = {
+ "perf config [options]",
+ NULL
+};
+
+enum actions {
+ ACTION_LIST = 1
+} actions;
+
+static struct option config_options[] = {
+ OPT_SET_UINT('l', "list", &actions,
+ "show current config variables", ACTION_LIST),
+ OPT_END()
+};
+
+static int show_config(const char *key, const char *value,
+ void *cb __maybe_unused)
+{
+ if (value)
+ printf("%s=%s\n", key, value);
+ else
+ printf("%s\n", key);
+
+ return 0;
+}
+
+int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+ int ret = 0;
+
+ argc = parse_options(argc, argv, config_options, config_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+
+ switch (actions) {
+ case ACTION_LIST:
+ if (argc) {
+ pr_err("Error: takes no arguments\n");
+ parse_options_usage(config_usage, config_options, "l", 1);
+ } else {
+ ret = perf_config(show_config, NULL);
+ if (ret < 0)
+ pr_err("Nothing configured, "
+ "please check your ~/.perfconfig file\n");
+ }
+ break;
+ default:
+ usage_with_options(config_usage, config_options);
+ }
+
+ return ret;
+}
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index f256fac..af5db88 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -45,7 +45,6 @@
struct perf_tool tool;
struct perf_session *session;
bool use_tui, use_gtk, use_stdio;
- bool hide_unresolved;
bool dont_use_callchains;
bool show_full_info;
bool show_threads;
@@ -146,7 +145,7 @@
struct hist_entry_iter iter = {
.evsel = evsel,
.sample = sample,
- .hide_unresolved = rep->hide_unresolved,
+ .hide_unresolved = symbol_conf.hide_unresolved,
.add_entry_cb = hist_iter__report_callback,
};
int ret = 0;
@@ -157,7 +156,7 @@
return -1;
}
- if (rep->hide_unresolved && al.sym == NULL)
+ if (symbol_conf.hide_unresolved && al.sym == NULL)
goto out_put;
if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
@@ -514,20 +513,26 @@
if (rep->cpu_list) {
ret = perf_session__cpu_bitmap(session, rep->cpu_list,
rep->cpu_bitmap);
- if (ret)
+ if (ret) {
+ ui__error("failed to set cpu bitmap\n");
return ret;
+ }
}
if (rep->show_threads)
perf_read_values_init(&rep->show_threads_values);
ret = report__setup_sample_type(rep);
- if (ret)
+ if (ret) {
+ /* report__setup_sample_type() already showed error message */
return ret;
+ }
ret = perf_session__process_events(session);
- if (ret)
+ if (ret) {
+ ui__error("failed to process sample\n");
return ret;
+ }
report__warn_kptr_restrict(rep);
@@ -625,7 +630,7 @@
return 0;
}
-#define CALLCHAIN_DEFAULT_OPT "graph,0.5,caller,function"
+#define CALLCHAIN_DEFAULT_OPT "graph,0.5,caller,function,percent"
const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n"
CALLCHAIN_REPORT_HELP
@@ -708,7 +713,7 @@
OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
"Only display entries with parent-match"),
OPT_CALLBACK_DEFAULT('g', "call-graph", &report,
- "print_type,threshold[,print_limit],order,sort_key[,branch]",
+ "print_type,threshold[,print_limit],order,sort_key[,branch],value",
report_callchain_help, &report_parse_callchain_opt,
callchain_default_opt),
OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
@@ -740,7 +745,7 @@
OPT_STRING_NOEMPTY('t', "field-separator", &symbol_conf.field_sep, "separator",
"separator for columns, no spaces will be added between "
"columns '.' is reserved."),
- OPT_BOOLEAN('U', "hide-unresolved", &report.hide_unresolved,
+ OPT_BOOLEAN('U', "hide-unresolved", &symbol_conf.hide_unresolved,
"Only display entries resolved to a symbol"),
OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
"Look for files with symbols relative to this directory"),
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 72b5deb..3c3f8d0 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -588,8 +588,17 @@
printf(" %-4s ", str);
}
-static void process_event(union perf_event *event, struct perf_sample *sample,
- struct perf_evsel *evsel, struct addr_location *al)
+struct perf_script {
+ struct perf_tool tool;
+ struct perf_session *session;
+ bool show_task_events;
+ bool show_mmap_events;
+ bool show_switch_events;
+};
+
+static void process_event(struct perf_script *script __maybe_unused, union perf_event *event,
+ struct perf_sample *sample, struct perf_evsel *evsel,
+ struct addr_location *al)
{
struct thread *thread = al->thread;
struct perf_event_attr *attr = &evsel->attr;
@@ -643,65 +652,33 @@
printf("\n");
}
-static int default_start_script(const char *script __maybe_unused,
- int argc __maybe_unused,
- const char **argv __maybe_unused)
-{
- return 0;
-}
-
-static int default_flush_script(void)
-{
- return 0;
-}
-
-static int default_stop_script(void)
-{
- return 0;
-}
-
-static int default_generate_script(struct pevent *pevent __maybe_unused,
- const char *outfile __maybe_unused)
-{
- return 0;
-}
-
-static struct scripting_ops default_scripting_ops = {
- .start_script = default_start_script,
- .flush_script = default_flush_script,
- .stop_script = default_stop_script,
- .process_event = process_event,
- .generate_script = default_generate_script,
-};
-
static struct scripting_ops *scripting_ops;
static void setup_scripting(void)
{
setup_perl_scripting();
setup_python_scripting();
-
- scripting_ops = &default_scripting_ops;
}
static int flush_scripting(void)
{
- return scripting_ops->flush_script();
+ return scripting_ops ? scripting_ops->flush_script() : 0;
}
static int cleanup_scripting(void)
{
pr_debug("\nperf script stopped\n");
- return scripting_ops->stop_script();
+ return scripting_ops ? scripting_ops->stop_script() : 0;
}
-static int process_sample_event(struct perf_tool *tool __maybe_unused,
+static int process_sample_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine)
{
+ struct perf_script *scr = container_of(tool, struct perf_script, tool);
struct addr_location al;
if (debug_mode) {
@@ -727,20 +704,16 @@
if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
goto out_put;
- scripting_ops->process_event(event, sample, evsel, &al);
+ if (scripting_ops)
+ scripting_ops->process_event(event, sample, evsel, &al);
+ else
+ process_event(scr, event, sample, evsel, &al);
+
out_put:
addr_location__put(&al);
return 0;
}
-struct perf_script {
- struct perf_tool tool;
- struct perf_session *session;
- bool show_task_events;
- bool show_mmap_events;
- bool show_switch_events;
-};
-
static int process_attr(struct perf_tool *tool, union perf_event *event,
struct perf_evlist **pevlist)
{
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e77880b..e74712d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -161,15 +161,32 @@
attr->inherit = !no_inherit;
- if (target__has_cpu(&target))
- return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
+ /*
+ * Some events get initialized with sample_(period/type) set,
+ * like tracepoints. Clear it up for counting.
+ */
+ attr->sample_period = 0;
+ attr->sample_type = 0;
- if (!target__has_task(&target) && perf_evsel__is_group_leader(evsel)) {
+ /*
+ * Disabling all counters initially, they will be enabled
+ * either manually by us or by kernel via enable_on_exec
+ * set later.
+ */
+ if (perf_evsel__is_group_leader(evsel)) {
attr->disabled = 1;
- if (!initial_delay)
+
+ /*
+ * In case of initial_delay we enable tracee
+ * events manually.
+ */
+ if (target__none(&target) && !initial_delay)
attr->enable_on_exec = 1;
}
+ if (target__has_cpu(&target))
+ return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
+
return perf_evsel__open_per_thread(evsel, evsel_list->threads);
}
@@ -244,18 +261,18 @@
print_counters(&rs, 0, NULL);
}
-static void handle_initial_delay(void)
+static void enable_counters(void)
{
- struct perf_evsel *counter;
-
- if (initial_delay) {
- const int ncpus = cpu_map__nr(evsel_list->cpus),
- nthreads = thread_map__nr(evsel_list->threads);
-
+ if (initial_delay)
usleep(initial_delay * 1000);
- evlist__for_each(evsel_list, counter)
- perf_evsel__enable(counter, ncpus, nthreads);
- }
+
+ /*
+ * We need to enable counters only if:
+ * - we don't have tracee (attaching to task or cpu)
+ * - we have initial delay configured
+ */
+ if (!target__none(&target) || initial_delay)
+ perf_evlist__enable(evsel_list);
}
static volatile int workload_exec_errno;
@@ -352,7 +369,7 @@
if (forks) {
perf_evlist__start_workload(evsel_list);
- handle_initial_delay();
+ enable_counters();
if (interval) {
while (!waitpid(child_pid, &status, WNOHANG)) {
@@ -371,7 +388,7 @@
if (WIFSIGNALED(status))
psignal(WTERMSIG(status), argv[0]);
} else {
- handle_initial_delay();
+ enable_counters();
while (!done) {
nanosleep(&ts, NULL);
if (interval)
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 3688ad2..3f871b5 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -17,6 +17,7 @@
extern int cmd_bench(int argc, const char **argv, const char *prefix);
extern int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
extern int cmd_buildid_list(int argc, const char **argv, const char *prefix);
+extern int cmd_config(int argc, const char **argv, const char *prefix);
extern int cmd_diff(int argc, const char **argv, const char *prefix);
extern int cmd_evlist(int argc, const char **argv, const char *prefix);
extern int cmd_help(int argc, const char **argv, const char *prefix);
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 00fcaf8..acc3ea7 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -9,6 +9,7 @@
perf-buildid-list mainporcelain common
perf-data mainporcelain common
perf-diff mainporcelain common
+perf-config mainporcelain common
perf-evlist mainporcelain common
perf-inject mainporcelain common
perf-kmem mainporcelain common
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index de89ec5..6eb9a95 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -318,6 +318,18 @@
CFLAGS += -DHAVE_LIBBPF_SUPPORT
$(call detected,CONFIG_LIBBPF)
endif
+
+ ifndef NO_DWARF
+ ifdef PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
+ CFLAGS += -DHAVE_BPF_PROLOGUE
+ $(call detected,CONFIG_BPF_PROLOGUE)
+ else
+ msg := $(warning BPF prologue is not supported by architecture $(ARCH), missing regs_query_register_offset());
+ endif
+ else
+ msg := $(warning DWARF support is off, BPF prologue is disabled);
+ endif
+
endif # NO_LIBBPF
endif # NO_LIBELF
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 3d4c7c0..4bee53c 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -39,6 +39,7 @@
static struct cmd_struct commands[] = {
{ "buildid-cache", cmd_buildid_cache, 0 },
{ "buildid-list", cmd_buildid_list, 0 },
+ { "config", cmd_config, 0 },
{ "diff", cmd_diff, 0 },
{ "evlist", cmd_evlist, 0 },
{ "help", cmd_help, 0 },
diff --git a/tools/perf/tests/.gitignore b/tools/perf/tests/.gitignore
index 489fc9f..bf016c4 100644
--- a/tools/perf/tests/.gitignore
+++ b/tools/perf/tests/.gitignore
@@ -1,2 +1,3 @@
llvm-src-base.c
llvm-src-kbuild.c
+llvm-src-prologue.c
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index f41ebf8..0ff8a97 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -31,7 +31,7 @@
perf-y += parse-no-sample-id-all.o
perf-y += kmod-path.o
perf-y += thread-map.o
-perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o
+perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o
perf-y += bpf.o
perf-y += topology.o
@@ -49,6 +49,13 @@
$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
$(Q)echo ';' >> $@
+$(OUTPUT)tests/llvm-src-prologue.c: tests/bpf-script-test-prologue.c
+ $(call rule_mkdir)
+ $(Q)echo '#include <tests/llvm.h>' > $@
+ $(Q)echo 'const char test_llvm__bpf_test_prologue_prog[] =' >> $@
+ $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
+ $(Q)echo ';' >> $@
+
ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64))
perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
endif
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 638875a..b66730eb9 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -153,7 +153,7 @@
return system(cmd);
}
-int test__attr(void)
+int test__attr(int subtest __maybe_unused)
{
struct stat st;
char path_perf[PATH_MAX];
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index a02b035..fb80c9e 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -111,7 +111,7 @@
return count;
}
-int test__bp_signal(void)
+int test__bp_signal(int subtest __maybe_unused)
{
struct sigaction sa;
long long count1, count2;
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
index e765377..89f92fa 100644
--- a/tools/perf/tests/bp_signal_overflow.c
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -58,7 +58,7 @@
#define EXECUTIONS 10000
#define THRESHOLD 100
-int test__bp_signal_overflow(void)
+int test__bp_signal_overflow(int subtest __maybe_unused)
{
struct perf_event_attr pe;
struct sigaction sa;
diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c
new file mode 100644
index 0000000..7230e62
--- /dev/null
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -0,0 +1,35 @@
+/*
+ * bpf-script-test-prologue.c
+ * Test BPF prologue
+ */
+#ifndef LINUX_VERSION_CODE
+# error Need LINUX_VERSION_CODE
+# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
+#endif
+#define SEC(NAME) __attribute__((section(NAME), used))
+
+#include <uapi/linux/fs.h>
+
+#define FMODE_READ 0x1
+#define FMODE_WRITE 0x2
+
+static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) =
+ (void *) 6;
+
+SEC("func=null_lseek file->f_mode offset orig")
+int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode,
+ unsigned long offset, unsigned long orig)
+{
+ if (err)
+ return 0;
+ if (f_mode & FMODE_WRITE)
+ return 0;
+ if (offset & 1)
+ return 0;
+ if (orig == SEEK_CUR)
+ return 0;
+ return 1;
+}
+
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index ec16f78..33689a0 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -19,6 +19,29 @@
return 0;
}
+#ifdef HAVE_BPF_PROLOGUE
+
+static int llseek_loop(void)
+{
+ int fds[2], i;
+
+ fds[0] = open("/dev/null", O_RDONLY);
+ fds[1] = open("/dev/null", O_RDWR);
+
+ if (fds[0] < 0 || fds[1] < 0)
+ return -1;
+
+ for (i = 0; i < NR_ITERS; i++) {
+ lseek(fds[i % 2], i, (i / 2) % 2 ? SEEK_CUR : SEEK_SET);
+ lseek(fds[(i + 1) % 2], i, (i / 2) % 2 ? SEEK_CUR : SEEK_SET);
+ }
+ close(fds[0]);
+ close(fds[1]);
+ return 0;
+}
+
+#endif
+
static struct {
enum test_llvm__testcase prog_id;
const char *desc;
@@ -37,6 +60,17 @@
&epoll_pwait_loop,
(NR_ITERS + 1) / 2,
},
+#ifdef HAVE_BPF_PROLOGUE
+ {
+ LLVM_TESTCASE_BPF_PROLOGUE,
+ "Test BPF prologue generation",
+ "[bpf_prologue_test]",
+ "fix kbuild first",
+ "check your vmlinux setting?",
+ &llseek_loop,
+ (NR_ITERS + 1) / 4,
+ },
+#endif
};
static int do_test(struct bpf_object *obj, int (*func)(void),
@@ -68,8 +102,7 @@
err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj);
if (err || list_empty(&parse_evlist.list)) {
pr_debug("Failed to add events selected by BPF\n");
- if (!err)
- return TEST_FAIL;
+ return TEST_FAIL;
}
snprintf(pid, sizeof(pid), "%d", getpid());
@@ -123,8 +156,10 @@
}
}
- if (count != expect)
+ if (count != expect) {
pr_debug("BPF filter result incorrect\n");
+ goto out_delete_evlist;
+ }
ret = TEST_OK;
@@ -146,7 +181,7 @@
return obj;
}
-static int __test__bpf(int index)
+static int __test__bpf(int idx)
{
int ret;
void *obj_buf;
@@ -154,54 +189,72 @@
struct bpf_object *obj;
ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
- bpf_testcase_table[index].prog_id,
+ bpf_testcase_table[idx].prog_id,
true);
if (ret != TEST_OK || !obj_buf || !obj_buf_sz) {
pr_debug("Unable to get BPF object, %s\n",
- bpf_testcase_table[index].msg_compile_fail);
- if (index == 0)
+ bpf_testcase_table[idx].msg_compile_fail);
+ if (idx == 0)
return TEST_SKIP;
else
return TEST_FAIL;
}
obj = prepare_bpf(obj_buf, obj_buf_sz,
- bpf_testcase_table[index].name);
+ bpf_testcase_table[idx].name);
if (!obj) {
ret = TEST_FAIL;
goto out;
}
ret = do_test(obj,
- bpf_testcase_table[index].target_func,
- bpf_testcase_table[index].expect_result);
+ bpf_testcase_table[idx].target_func,
+ bpf_testcase_table[idx].expect_result);
out:
bpf__clear();
return ret;
}
-int test__bpf(void)
+int test__bpf_subtest_get_nr(void)
{
- unsigned int i;
+ return (int)ARRAY_SIZE(bpf_testcase_table);
+}
+
+const char *test__bpf_subtest_get_desc(int i)
+{
+ if (i < 0 || i >= (int)ARRAY_SIZE(bpf_testcase_table))
+ return NULL;
+ return bpf_testcase_table[i].desc;
+}
+
+int test__bpf(int i)
+{
int err;
+ if (i < 0 || i >= (int)ARRAY_SIZE(bpf_testcase_table))
+ return TEST_FAIL;
+
if (geteuid() != 0) {
pr_debug("Only root can run BPF test\n");
return TEST_SKIP;
}
- for (i = 0; i < ARRAY_SIZE(bpf_testcase_table); i++) {
- err = __test__bpf(i);
-
- if (err != TEST_OK)
- return err;
- }
-
- return TEST_OK;
+ err = __test__bpf(i);
+ return err;
}
#else
-int test__bpf(void)
+int test__bpf_subtest_get_nr(void)
+{
+ return 0;
+}
+
+const char *test__bpf_subtest_get_desc(int i __maybe_unused)
+{
+ return NULL;
+}
+
+int test__bpf(int i __maybe_unused)
{
pr_debug("Skip BPF test because BPF support is not compiled\n");
return TEST_SKIP;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 80c442e..2b1ade1 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -160,6 +160,11 @@
{
.desc = "Test LLVM searching and compiling",
.func = test__llvm,
+ .subtest = {
+ .skip_if_fail = true,
+ .get_nr = test__llvm_subtest_get_nr,
+ .get_desc = test__llvm_subtest_get_desc,
+ },
},
{
.desc = "Test topology in session",
@@ -168,6 +173,11 @@
{
.desc = "Test BPF filter",
.func = test__bpf,
+ .subtest = {
+ .skip_if_fail = true,
+ .get_nr = test__bpf_subtest_get_nr,
+ .get_desc = test__bpf_subtest_get_desc,
+ },
},
{
.func = NULL,
@@ -203,7 +213,7 @@
return false;
}
-static int run_test(struct test *test)
+static int run_test(struct test *test, int subtest)
{
int status, err = -1, child = fork();
char sbuf[STRERR_BUFSIZE];
@@ -216,7 +226,19 @@
if (!child) {
pr_debug("test child forked, pid %d\n", getpid());
- err = test->func();
+ if (!verbose) {
+ int nullfd = open("/dev/null", O_WRONLY);
+ if (nullfd >= 0) {
+ close(STDERR_FILENO);
+ close(STDOUT_FILENO);
+
+ dup2(nullfd, STDOUT_FILENO);
+ dup2(STDOUT_FILENO, STDERR_FILENO);
+ close(nullfd);
+ }
+ }
+
+ err = test->func(subtest);
exit(err);
}
@@ -237,6 +259,40 @@
for (j = 0; j < ARRAY_SIZE(tests); j++) \
for (t = &tests[j][0]; t->func; t++)
+static int test_and_print(struct test *t, bool force_skip, int subtest)
+{
+ int err;
+
+ if (!force_skip) {
+ pr_debug("\n--- start ---\n");
+ err = run_test(t, subtest);
+ pr_debug("---- end ----\n");
+ } else {
+ pr_debug("\n--- force skipped ---\n");
+ err = TEST_SKIP;
+ }
+
+ if (!t->subtest.get_nr)
+ pr_debug("%s:", t->desc);
+ else
+ pr_debug("%s subtest %d:", t->desc, subtest);
+
+ switch (err) {
+ case TEST_OK:
+ pr_info(" Ok\n");
+ break;
+ case TEST_SKIP:
+ color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n");
+ break;
+ case TEST_FAIL:
+ default:
+ color_fprintf(stderr, PERF_COLOR_RED, " FAILED!\n");
+ break;
+ }
+
+ return err;
+}
+
static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
{
struct test *t;
@@ -264,21 +320,43 @@
continue;
}
- pr_debug("\n--- start ---\n");
- err = run_test(t);
- pr_debug("---- end ----\n%s:", t->desc);
+ if (!t->subtest.get_nr) {
+ test_and_print(t, false, -1);
+ } else {
+ int subn = t->subtest.get_nr();
+ /*
+ * minus 2 to align with normal testcases.
+ * For subtest we print additional '.x' in number.
+ * for example:
+ *
+ * 35: Test LLVM searching and compiling :
+ * 35.1: Basic BPF llvm compiling test : Ok
+ */
+ int subw = width > 2 ? width - 2 : width;
+ bool skip = false;
+ int subi;
- switch (err) {
- case TEST_OK:
- pr_info(" Ok\n");
- break;
- case TEST_SKIP:
- color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n");
- break;
- case TEST_FAIL:
- default:
- color_fprintf(stderr, PERF_COLOR_RED, " FAILED!\n");
- break;
+ if (subn <= 0) {
+ color_fprintf(stderr, PERF_COLOR_YELLOW,
+ " Skip (not compiled in)\n");
+ continue;
+ }
+ pr_info("\n");
+
+ for (subi = 0; subi < subn; subi++) {
+ int len = strlen(t->subtest.get_desc(subi));
+
+ if (subw < len)
+ subw = len;
+ }
+
+ for (subi = 0; subi < subn; subi++) {
+ pr_info("%2d.%1d: %-*s:", i, subi + 1, subw,
+ t->subtest.get_desc(subi));
+ err = test_and_print(t, skip, subi);
+ if (err != TEST_OK && t->subtest.skip_if_fail)
+ skip = true;
+ }
}
}
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index a767a64..313a48c 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -433,7 +433,6 @@
static int do_test_code_reading(bool try_kcore)
{
- struct machines machines;
struct machine *machine;
struct thread *thread;
struct record_opts opts = {
@@ -459,8 +458,7 @@
pid = getpid();
- machines__init(&machines);
- machine = &machines.host;
+ machine = machine__new_host();
ret = machine__create_kernel_maps(machine);
if (ret < 0) {
@@ -549,6 +547,13 @@
if (ret < 0) {
if (!excl_kernel) {
excl_kernel = true;
+ /*
+ * Both cpus and threads are now owned by evlist
+ * and will be freed by following perf_evlist__set_maps
+ * call. Getting refference to keep them alive.
+ */
+ cpu_map__get(cpus);
+ thread_map__get(threads);
perf_evlist__set_maps(evlist, NULL, NULL);
perf_evlist__delete(evlist);
evlist = NULL;
@@ -594,14 +599,13 @@
cpu_map__put(cpus);
thread_map__put(threads);
}
- machines__destroy_kernel_maps(&machines);
machine__delete_threads(machine);
- machines__exit(&machines);
+ machine__delete(machine);
return err;
}
-int test__code_reading(void)
+int test__code_reading(int subtest __maybe_unused)
{
int ret;
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index a218aea..dc673ff 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -110,7 +110,7 @@
return fd;
}
-int test__dso_data(void)
+int test__dso_data(int subtest __maybe_unused)
{
struct machine machine;
struct dso *dso;
@@ -245,7 +245,7 @@
return setrlimit(RLIMIT_NOFILE, &rlim);
}
-int test__dso_data_cache(void)
+int test__dso_data_cache(int subtest __maybe_unused)
{
struct machine machine;
long nr_end, nr = open_files_cnt();
@@ -302,7 +302,7 @@
return 0;
}
-int test__dso_data_reopen(void)
+int test__dso_data_reopen(int subtest __maybe_unused)
{
struct machine machine;
long nr_end, nr = open_files_cnt();
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 0722179..1c5c022 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -51,6 +51,12 @@
"krava_1",
"test__dwarf_unwind"
};
+ /*
+ * The funcs[MAX_STACK] array index, based on the
+ * callchain order setup.
+ */
+ int idx = callchain_param.order == ORDER_CALLER ?
+ MAX_STACK - *cnt - 1 : *cnt;
if (*cnt >= MAX_STACK) {
pr_debug("failed: crossed the max stack value %d\n", MAX_STACK);
@@ -63,8 +69,10 @@
return -1;
}
- pr_debug("got: %s 0x%" PRIx64 "\n", symbol, entry->ip);
- return strcmp((const char *) symbol, funcs[(*cnt)++]);
+ (*cnt)++;
+ pr_debug("got: %s 0x%" PRIx64 ", expecting %s\n",
+ symbol, entry->ip, funcs[idx]);
+ return strcmp((const char *) symbol, funcs[idx]);
}
__attribute__ ((noinline))
@@ -105,8 +113,16 @@
/* Any possible value should be 'thread' */
struct thread *thread = *(struct thread **)p1;
- if (global_unwind_retval == -INT_MAX)
+ if (global_unwind_retval == -INT_MAX) {
+ /* Call unwinder twice for both callchain orders. */
+ callchain_param.order = ORDER_CALLER;
+
global_unwind_retval = unwind_thread(thread);
+ if (!global_unwind_retval) {
+ callchain_param.order = ORDER_CALLEE;
+ global_unwind_retval = unwind_thread(thread);
+ }
+ }
return p1 - p2;
}
@@ -142,21 +158,23 @@
return krava_2(thread);
}
-int test__dwarf_unwind(void)
+int test__dwarf_unwind(int subtest __maybe_unused)
{
- struct machines machines;
struct machine *machine;
struct thread *thread;
int err = -1;
- machines__init(&machines);
-
- machine = machines__find(&machines, HOST_KERNEL_ID);
+ machine = machine__new_host();
if (!machine) {
pr_err("Could not get machine\n");
return -1;
}
+ if (machine__create_kernel_maps(machine)) {
+ pr_err("Failed to create kernel maps\n");
+ return -1;
+ }
+
callchain_param.record_mode = CALLCHAIN_DWARF;
if (init_live_machine(machine)) {
@@ -178,7 +196,6 @@
out:
machine__delete_threads(machine);
- machine__exit(machine);
- machines__exit(&machines);
+ machine__delete(machine);
return err;
}
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 3fa7159..2de4a4f 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -95,7 +95,7 @@
#define perf_evsel__name_array_test(names) \
__perf_evsel__name_array_test(names, ARRAY_SIZE(names))
-int test__perf_evsel__roundtrip_name_test(void)
+int test__perf_evsel__roundtrip_name_test(int subtest __maybe_unused)
{
int err = 0, ret = 0;
@@ -103,7 +103,8 @@
if (err)
ret = err;
- err = perf_evsel__name_array_test(perf_evsel__sw_names);
+ err = __perf_evsel__name_array_test(perf_evsel__sw_names,
+ PERF_COUNT_SW_DUMMY + 1);
if (err)
ret = err;
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 790e413..1984b3b 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -32,7 +32,7 @@
return ret;
}
-int test__perf_evsel__tp_sched_test(void)
+int test__perf_evsel__tp_sched_test(int subtest __maybe_unused)
{
struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch");
int ret = 0;
diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
index d24b837..c809463 100644
--- a/tools/perf/tests/fdarray.c
+++ b/tools/perf/tests/fdarray.c
@@ -25,7 +25,7 @@
return printed + fdarray__fprintf(fda, fp);
}
-int test__fdarray__filter(void)
+int test__fdarray__filter(int subtest __maybe_unused)
{
int nr_fds, expected_fd[2], fd, err = TEST_FAIL;
struct fdarray *fda = fdarray__new(5, 5);
@@ -103,7 +103,7 @@
return err;
}
-int test__fdarray__add(void)
+int test__fdarray__add(int subtest __maybe_unused)
{
int err = TEST_FAIL;
struct fdarray *fda = fdarray__new(2, 2);
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index ce80b27..46f453b 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -87,6 +87,11 @@
return NULL;
}
+ if (machine__create_kernel_maps(machine)) {
+ pr_debug("Not enough memory for machine setup\n");
+ goto out;
+ }
+
for (i = 0; i < ARRAY_SIZE(fake_threads); i++) {
struct thread *thread;
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 7ed73701..8292948 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -686,7 +686,7 @@
return err;
}
-int test__hists_cumulate(void)
+int test__hists_cumulate(int subtest __maybe_unused)
{
int err = TEST_FAIL;
struct machines machines;
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 818acf8..ccb5b49 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -104,7 +104,7 @@
return TEST_FAIL;
}
-int test__hists_filter(void)
+int test__hists_filter(int subtest __maybe_unused)
{
int err = TEST_FAIL;
struct machines machines;
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 8c102b0..6243e2b 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -274,7 +274,7 @@
return __validate_link(leader, 0) || __validate_link(other, 1);
}
-int test__hists_link(void)
+int test__hists_link(int subtest __maybe_unused)
{
int err = -1;
struct hists *hists, *first_hists;
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index adbebc8..248beec 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -576,7 +576,7 @@
return err;
}
-int test__hists_output(void)
+int test__hists_output(int subtest __maybe_unused)
{
int err = TEST_FAIL;
struct machines machines;
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index a2e2269..a337a6d 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -49,7 +49,7 @@
* when an event is disabled but a dummy software event is not disabled. If the
* test passes %0 is returned, otherwise %-1 is returned.
*/
-int test__keep_tracking(void)
+int test__keep_tracking(int subtest __maybe_unused)
{
struct record_opts opts = {
.mmap_pages = UINT_MAX,
diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c
index 08c433b..d2af781 100644
--- a/tools/perf/tests/kmod-path.c
+++ b/tools/perf/tests/kmod-path.c
@@ -49,7 +49,7 @@
#define M(path, c, e) \
TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e))
-int test__kmod_path__parse(void)
+int test__kmod_path__parse(int subtest __maybe_unused)
{
/* path alloc_name alloc_ext kmod comp name ext */
T("/xxxx/xxxx/x-x.ko", true , true , true, false, "[x_x]", NULL);
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index bc4cf50..06f45c1 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -44,13 +44,17 @@
.source = test_llvm__bpf_test_kbuild_prog,
.desc = "Test kbuild searching",
},
+ [LLVM_TESTCASE_BPF_PROLOGUE] = {
+ .source = test_llvm__bpf_test_prologue_prog,
+ .desc = "Compile source for BPF prologue generation test",
+ },
};
int
test_llvm__fetch_bpf_obj(void **p_obj_buf,
size_t *p_obj_buf_sz,
- enum test_llvm__testcase index,
+ enum test_llvm__testcase idx,
bool force)
{
const char *source;
@@ -59,11 +63,11 @@
char *tmpl_new = NULL, *clang_opt_new = NULL;
int err, old_verbose, ret = TEST_FAIL;
- if (index >= __LLVM_TESTCASE_MAX)
+ if (idx >= __LLVM_TESTCASE_MAX)
return TEST_FAIL;
- source = bpf_source_table[index].source;
- desc = bpf_source_table[index].desc;
+ source = bpf_source_table[idx].source;
+ desc = bpf_source_table[idx].desc;
perf_config(perf_config_cb, NULL);
@@ -127,44 +131,39 @@
return ret;
}
-int test__llvm(void)
+int test__llvm(int subtest)
{
- enum test_llvm__testcase i;
+ int ret;
+ void *obj_buf = NULL;
+ size_t obj_buf_sz = 0;
- for (i = 0; i < __LLVM_TESTCASE_MAX; i++) {
- int ret;
- void *obj_buf = NULL;
- size_t obj_buf_sz = 0;
+ if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX))
+ return TEST_FAIL;
- ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
- i, false);
+ ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
+ subtest, false);
- if (ret == TEST_OK) {
- ret = test__bpf_parsing(obj_buf, obj_buf_sz);
- if (ret != TEST_OK)
- pr_debug("Failed to parse test case '%s'\n",
- bpf_source_table[i].desc);
- }
- free(obj_buf);
-
- switch (ret) {
- case TEST_SKIP:
- return TEST_SKIP;
- case TEST_OK:
- break;
- default:
- /*
- * Test 0 is the basic LLVM test. If test 0
- * fail, the basic LLVM support not functional
- * so the whole test should fail. If other test
- * case fail, it can be fixed by adjusting
- * config so don't report error.
- */
- if (i == 0)
- return TEST_FAIL;
- else
- return TEST_SKIP;
+ if (ret == TEST_OK) {
+ ret = test__bpf_parsing(obj_buf, obj_buf_sz);
+ if (ret != TEST_OK) {
+ pr_debug("Failed to parse test case '%s'\n",
+ bpf_source_table[subtest].desc);
}
}
- return TEST_OK;
+ free(obj_buf);
+
+ return ret;
+}
+
+int test__llvm_subtest_get_nr(void)
+{
+ return __LLVM_TESTCASE_MAX;
+}
+
+const char *test__llvm_subtest_get_desc(int subtest)
+{
+ if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX))
+ return NULL;
+
+ return bpf_source_table[subtest].desc;
}
diff --git a/tools/perf/tests/llvm.h b/tools/perf/tests/llvm.h
index d91d8f4..5150b4d 100644
--- a/tools/perf/tests/llvm.h
+++ b/tools/perf/tests/llvm.h
@@ -6,10 +6,12 @@
extern const char test_llvm__bpf_base_prog[];
extern const char test_llvm__bpf_test_kbuild_prog[];
+extern const char test_llvm__bpf_test_prologue_prog[];
enum test_llvm__testcase {
LLVM_TESTCASE_BASE,
LLVM_TESTCASE_KBUILD,
+ LLVM_TESTCASE_BPF_PROLOGUE,
__LLVM_TESTCASE_MAX,
};
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 4495493..359e98f 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -16,7 +16,7 @@
* Then it checks if the number of syscalls reported as perf events by
* the kernel corresponds to the number of syscalls made.
*/
-int test__basic_mmap(void)
+int test__basic_mmap(int subtest __maybe_unused)
{
int err = -1;
union perf_event *event;
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 145050e..0c5ce44 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -149,7 +149,6 @@
static int mmap_events(synth_cb synth)
{
- struct machines machines;
struct machine *machine;
int err, i;
@@ -162,8 +161,7 @@
*/
TEST_ASSERT_VAL("failed to create threads", !threads_create());
- machines__init(&machines);
- machine = &machines.host;
+ machine = machine__new_host();
dump_trace = verbose > 1 ? 1 : 0;
@@ -203,7 +201,7 @@
}
machine__delete_threads(machine);
- machines__exit(&machines);
+ machine__delete(machine);
return err;
}
@@ -221,7 +219,7 @@
*
* by using all thread objects.
*/
-int test__mmap_thread_lookup(void)
+int test__mmap_thread_lookup(int subtest __maybe_unused)
{
/* perf_event__synthesize_threads synthesize */
TEST_ASSERT_VAL("failed with sythesizing all",
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index 2006485..53c2273 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -7,7 +7,7 @@
#include "debug.h"
#include "stat.h"
-int test__openat_syscall_event_on_all_cpus(void)
+int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused)
{
int err = -1, fd, cpu;
struct cpu_map *cpus;
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 5e811cd..eb99a105 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -6,7 +6,7 @@
#include "tests.h"
#include "debug.h"
-int test__syscall_openat_tp_fields(void)
+int test__syscall_openat_tp_fields(int subtest __maybe_unused)
{
struct record_opts opts = {
.target = {
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index 033b547..1184f9b 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -5,7 +5,7 @@
#include "debug.h"
#include "tests.h"
-int test__openat_syscall_event(void)
+int test__openat_syscall_event(int subtest __maybe_unused)
{
int err = -1, fd;
struct perf_evsel *evsel;
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 636d7b4..abe8849 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1765,7 +1765,7 @@
fprintf(stderr, " Warning: %s\n", msg);
}
-int test__parse_events(void)
+int test__parse_events(int subtest __maybe_unused)
{
int ret1, ret2 = 0;
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 2c63ea6..294c76b 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -67,7 +67,7 @@
*
* Return: %0 on success, %-1 if the test fails.
*/
-int test__parse_no_sample_id_all(void)
+int test__parse_no_sample_id_all(int subtest __maybe_unused)
{
int err;
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 7a228a2..9d5f0b5 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -32,7 +32,7 @@
return cpu;
}
-int test__PERF_RECORD(void)
+int test__PERF_RECORD(int subtest __maybe_unused)
{
struct record_opts opts = {
.target = {
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index faa04e9..1e2ba26 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -133,7 +133,7 @@
return &terms;
}
-int test__pmu(void)
+int test__pmu(int subtest __maybe_unused)
{
char *format = test_format_dir_get();
LIST_HEAD(formats);
diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c
index 7760277..7a52834 100644
--- a/tools/perf/tests/python-use.c
+++ b/tools/perf/tests/python-use.c
@@ -4,11 +4,12 @@
#include <stdio.h>
#include <stdlib.h>
+#include <linux/compiler.h>
#include "tests.h"
extern int verbose;
-int test__python_use(void)
+int test__python_use(int subtest __maybe_unused)
{
char *cmd;
int ret;
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 30c0218..5f23710 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -290,7 +290,7 @@
* checks sample format bits separately and together. If the test passes %0 is
* returned, otherwise %-1 is returned.
*/
-int test__sample_parsing(void)
+int test__sample_parsing(int subtest __maybe_unused)
{
const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
u64 sample_type;
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 5b83f56..36e8ce1 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -122,7 +122,7 @@
return err;
}
-int test__sw_clock_freq(void)
+int test__sw_clock_freq(int subtest __maybe_unused)
{
int ret;
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index a02af50..dfbd8d6 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -305,7 +305,7 @@
* evsel->system_wide and evsel->tracking flags (respectively) with other events
* sometimes enabled or disabled.
*/
-int test__switch_tracking(void)
+int test__switch_tracking(int subtest __maybe_unused)
{
const char *sched_switch = "sched:sched_switch";
struct switch_tracking switch_tracking = { .tids = NULL, };
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index add1638..2dfff7a 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -31,7 +31,7 @@
* if the number of exit event reported by the kernel is 1 or not
* in order to check the kernel returns correct number of event.
*/
-int test__task_exit(void)
+int test__task_exit(int subtest __maybe_unused)
{
int err = -1;
union perf_event *event;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 3c8734a..a0733aa 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -1,6 +1,8 @@
#ifndef TESTS_H
#define TESTS_H
+#include <stdbool.h>
+
#define TEST_ASSERT_VAL(text, cond) \
do { \
if (!(cond)) { \
@@ -26,48 +28,57 @@
struct test {
const char *desc;
- int (*func)(void);
+ int (*func)(int subtest);
+ struct {
+ bool skip_if_fail;
+ int (*get_nr)(void);
+ const char *(*get_desc)(int subtest);
+ } subtest;
};
/* Tests */
-int test__vmlinux_matches_kallsyms(void);
-int test__openat_syscall_event(void);
-int test__openat_syscall_event_on_all_cpus(void);
-int test__basic_mmap(void);
-int test__PERF_RECORD(void);
-int test__perf_evsel__roundtrip_name_test(void);
-int test__perf_evsel__tp_sched_test(void);
-int test__syscall_openat_tp_fields(void);
-int test__pmu(void);
-int test__attr(void);
-int test__dso_data(void);
-int test__dso_data_cache(void);
-int test__dso_data_reopen(void);
-int test__parse_events(void);
-int test__hists_link(void);
-int test__python_use(void);
-int test__bp_signal(void);
-int test__bp_signal_overflow(void);
-int test__task_exit(void);
-int test__sw_clock_freq(void);
-int test__code_reading(void);
-int test__sample_parsing(void);
-int test__keep_tracking(void);
-int test__parse_no_sample_id_all(void);
-int test__dwarf_unwind(void);
-int test__hists_filter(void);
-int test__mmap_thread_lookup(void);
-int test__thread_mg_share(void);
-int test__hists_output(void);
-int test__hists_cumulate(void);
-int test__switch_tracking(void);
-int test__fdarray__filter(void);
-int test__fdarray__add(void);
-int test__kmod_path__parse(void);
-int test__thread_map(void);
-int test__llvm(void);
-int test__bpf(void);
-int test_session_topology(void);
+int test__vmlinux_matches_kallsyms(int subtest);
+int test__openat_syscall_event(int subtest);
+int test__openat_syscall_event_on_all_cpus(int subtest);
+int test__basic_mmap(int subtest);
+int test__PERF_RECORD(int subtest);
+int test__perf_evsel__roundtrip_name_test(int subtest);
+int test__perf_evsel__tp_sched_test(int subtest);
+int test__syscall_openat_tp_fields(int subtest);
+int test__pmu(int subtest);
+int test__attr(int subtest);
+int test__dso_data(int subtest);
+int test__dso_data_cache(int subtest);
+int test__dso_data_reopen(int subtest);
+int test__parse_events(int subtest);
+int test__hists_link(int subtest);
+int test__python_use(int subtest);
+int test__bp_signal(int subtest);
+int test__bp_signal_overflow(int subtest);
+int test__task_exit(int subtest);
+int test__sw_clock_freq(int subtest);
+int test__code_reading(int subtest);
+int test__sample_parsing(int subtest);
+int test__keep_tracking(int subtest);
+int test__parse_no_sample_id_all(int subtest);
+int test__dwarf_unwind(int subtest);
+int test__hists_filter(int subtest);
+int test__mmap_thread_lookup(int subtest);
+int test__thread_mg_share(int subtest);
+int test__hists_output(int subtest);
+int test__hists_cumulate(int subtest);
+int test__switch_tracking(int subtest);
+int test__fdarray__filter(int subtest);
+int test__fdarray__add(int subtest);
+int test__kmod_path__parse(int subtest);
+int test__thread_map(int subtest);
+int test__llvm(int subtest);
+const char *test__llvm_subtest_get_desc(int subtest);
+int test__llvm_subtest_get_nr(void);
+int test__bpf(int subtest);
+const char *test__bpf_subtest_get_desc(int subtest);
+int test__bpf_subtest_get_nr(void);
+int test_session_topology(int subtest);
#if defined(__arm__) || defined(__aarch64__)
#ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index 138a0e3..2be02d3 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -4,7 +4,7 @@
#include "thread_map.h"
#include "debug.h"
-int test__thread_map(void)
+int test__thread_map(int subtest __maybe_unused)
{
struct thread_map *map;
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index 01fabb1..188b631 100644
--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -4,7 +4,7 @@
#include "map.h"
#include "debug.h"
-int test__thread_mg_share(void)
+int test__thread_mg_share(int subtest __maybe_unused)
{
struct machines machines;
struct machine *machine;
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index f5bb096..98fe69a 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -84,7 +84,7 @@
return 0;
}
-int test_session_topology(void)
+int test_session_topology(int subtest __maybe_unused)
{
char path[PATH_MAX];
struct cpu_map *map;
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index d677e01..f0bfc9e 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -18,7 +18,7 @@
#define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x))
-int test__vmlinux_matches_kallsyms(void)
+int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
{
int err = -1;
struct rb_node *nd;
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 81def6c3..ec33196 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -178,12 +178,51 @@
return n;
}
+static int callchain_node__count_flat_rows(struct callchain_node *node)
+{
+ struct callchain_list *chain;
+ char folded_sign = 0;
+ int n = 0;
+
+ list_for_each_entry(chain, &node->parent_val, list) {
+ if (!folded_sign) {
+ /* only check first chain list entry */
+ folded_sign = callchain_list__folded(chain);
+ if (folded_sign == '+')
+ return 1;
+ }
+ n++;
+ }
+
+ list_for_each_entry(chain, &node->val, list) {
+ if (!folded_sign) {
+ /* node->parent_val list might be empty */
+ folded_sign = callchain_list__folded(chain);
+ if (folded_sign == '+')
+ return 1;
+ }
+ n++;
+ }
+
+ return n;
+}
+
+static int callchain_node__count_folded_rows(struct callchain_node *node __maybe_unused)
+{
+ return 1;
+}
+
static int callchain_node__count_rows(struct callchain_node *node)
{
struct callchain_list *chain;
bool unfolded = false;
int n = 0;
+ if (callchain_param.mode == CHAIN_FLAT)
+ return callchain_node__count_flat_rows(node);
+ else if (callchain_param.mode == CHAIN_FOLDED)
+ return callchain_node__count_folded_rows(node);
+
list_for_each_entry(chain, &node->val, list) {
++n;
unfolded = chain->unfolded;
@@ -263,7 +302,7 @@
chain = list_entry(node->val.next, struct callchain_list, list);
chain->has_children = has_sibling;
- if (!list_empty(&node->val)) {
+ if (node->val.next != node->val.prev) {
chain = list_entry(node->val.prev, struct callchain_list, list);
chain->has_children = !RB_EMPTY_ROOT(&node->rb_root);
}
@@ -279,6 +318,9 @@
for (nd = rb_first(root); nd; nd = rb_next(nd)) {
struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
callchain_node__init_have_children(node, has_sibling);
+ if (callchain_param.mode == CHAIN_FLAT ||
+ callchain_param.mode == CHAIN_FOLDED)
+ callchain_node__make_parent_list(node);
}
}
@@ -577,6 +619,231 @@
#define LEVEL_OFFSET_STEP 3
+static int hist_browser__show_callchain_list(struct hist_browser *browser,
+ struct callchain_node *node,
+ struct callchain_list *chain,
+ unsigned short row, u64 total,
+ bool need_percent, int offset,
+ print_callchain_entry_fn print,
+ struct callchain_print_arg *arg)
+{
+ char bf[1024], *alloc_str;
+ const char *str;
+
+ if (arg->row_offset != 0) {
+ arg->row_offset--;
+ return 0;
+ }
+
+ alloc_str = NULL;
+ str = callchain_list__sym_name(chain, bf, sizeof(bf),
+ browser->show_dso);
+
+ if (need_percent) {
+ char buf[64];
+
+ callchain_node__scnprintf_value(node, buf, sizeof(buf),
+ total);
+
+ if (asprintf(&alloc_str, "%s %s", buf, str) < 0)
+ str = "Not enough memory!";
+ else
+ str = alloc_str;
+ }
+
+ print(browser, chain, str, offset, row, arg);
+
+ free(alloc_str);
+ return 1;
+}
+
+static int hist_browser__show_callchain_flat(struct hist_browser *browser,
+ struct rb_root *root,
+ unsigned short row, u64 total,
+ print_callchain_entry_fn print,
+ struct callchain_print_arg *arg,
+ check_output_full_fn is_output_full)
+{
+ struct rb_node *node;
+ int first_row = row, offset = LEVEL_OFFSET_STEP;
+ bool need_percent;
+
+ node = rb_first(root);
+ need_percent = node && rb_next(node);
+
+ while (node) {
+ struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
+ struct rb_node *next = rb_next(node);
+ struct callchain_list *chain;
+ char folded_sign = ' ';
+ int first = true;
+ int extra_offset = 0;
+
+ list_for_each_entry(chain, &child->parent_val, list) {
+ bool was_first = first;
+
+ if (first)
+ first = false;
+ else if (need_percent)
+ extra_offset = LEVEL_OFFSET_STEP;
+
+ folded_sign = callchain_list__folded(chain);
+
+ row += hist_browser__show_callchain_list(browser, child,
+ chain, row, total,
+ was_first && need_percent,
+ offset + extra_offset,
+ print, arg);
+
+ if (is_output_full(browser, row))
+ goto out;
+
+ if (folded_sign == '+')
+ goto next;
+ }
+
+ list_for_each_entry(chain, &child->val, list) {
+ bool was_first = first;
+
+ if (first)
+ first = false;
+ else if (need_percent)
+ extra_offset = LEVEL_OFFSET_STEP;
+
+ folded_sign = callchain_list__folded(chain);
+
+ row += hist_browser__show_callchain_list(browser, child,
+ chain, row, total,
+ was_first && need_percent,
+ offset + extra_offset,
+ print, arg);
+
+ if (is_output_full(browser, row))
+ goto out;
+
+ if (folded_sign == '+')
+ break;
+ }
+
+next:
+ if (is_output_full(browser, row))
+ break;
+ node = next;
+ }
+out:
+ return row - first_row;
+}
+
+static char *hist_browser__folded_callchain_str(struct hist_browser *browser,
+ struct callchain_list *chain,
+ char *value_str, char *old_str)
+{
+ char bf[1024];
+ const char *str;
+ char *new;
+
+ str = callchain_list__sym_name(chain, bf, sizeof(bf),
+ browser->show_dso);
+ if (old_str) {
+ if (asprintf(&new, "%s%s%s", old_str,
+ symbol_conf.field_sep ?: ";", str) < 0)
+ new = NULL;
+ } else {
+ if (value_str) {
+ if (asprintf(&new, "%s %s", value_str, str) < 0)
+ new = NULL;
+ } else {
+ if (asprintf(&new, "%s", str) < 0)
+ new = NULL;
+ }
+ }
+ return new;
+}
+
+static int hist_browser__show_callchain_folded(struct hist_browser *browser,
+ struct rb_root *root,
+ unsigned short row, u64 total,
+ print_callchain_entry_fn print,
+ struct callchain_print_arg *arg,
+ check_output_full_fn is_output_full)
+{
+ struct rb_node *node;
+ int first_row = row, offset = LEVEL_OFFSET_STEP;
+ bool need_percent;
+
+ node = rb_first(root);
+ need_percent = node && rb_next(node);
+
+ while (node) {
+ struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
+ struct rb_node *next = rb_next(node);
+ struct callchain_list *chain, *first_chain = NULL;
+ int first = true;
+ char *value_str = NULL, *value_str_alloc = NULL;
+ char *chain_str = NULL, *chain_str_alloc = NULL;
+
+ if (arg->row_offset != 0) {
+ arg->row_offset--;
+ goto next;
+ }
+
+ if (need_percent) {
+ char buf[64];
+
+ callchain_node__scnprintf_value(child, buf, sizeof(buf), total);
+ if (asprintf(&value_str, "%s", buf) < 0) {
+ value_str = (char *)"<...>";
+ goto do_print;
+ }
+ value_str_alloc = value_str;
+ }
+
+ list_for_each_entry(chain, &child->parent_val, list) {
+ chain_str = hist_browser__folded_callchain_str(browser,
+ chain, value_str, chain_str);
+ if (first) {
+ first = false;
+ first_chain = chain;
+ }
+
+ if (chain_str == NULL) {
+ chain_str = (char *)"Not enough memory!";
+ goto do_print;
+ }
+
+ chain_str_alloc = chain_str;
+ }
+
+ list_for_each_entry(chain, &child->val, list) {
+ chain_str = hist_browser__folded_callchain_str(browser,
+ chain, value_str, chain_str);
+ if (first) {
+ first = false;
+ first_chain = chain;
+ }
+
+ if (chain_str == NULL) {
+ chain_str = (char *)"Not enough memory!";
+ goto do_print;
+ }
+
+ chain_str_alloc = chain_str;
+ }
+
+do_print:
+ print(browser, first_chain, chain_str, offset, row++, arg);
+ free(value_str_alloc);
+ free(chain_str_alloc);
+
+next:
+ if (is_output_full(browser, row))
+ break;
+ node = next;
+ }
+
+ return row - first_row;
+}
+
static int hist_browser__show_callchain(struct hist_browser *browser,
struct rb_root *root, int level,
unsigned short row, u64 total,
@@ -595,15 +862,12 @@
while (node) {
struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
struct rb_node *next = rb_next(node);
- u64 cumul = callchain_cumul_hits(child);
struct callchain_list *chain;
char folded_sign = ' ';
int first = true;
int extra_offset = 0;
list_for_each_entry(chain, &child->val, list) {
- char bf[1024], *alloc_str;
- const char *str;
bool was_first = first;
if (first)
@@ -612,31 +876,16 @@
extra_offset = LEVEL_OFFSET_STEP;
folded_sign = callchain_list__folded(chain);
- if (arg->row_offset != 0) {
- arg->row_offset--;
- goto do_next;
- }
- alloc_str = NULL;
- str = callchain_list__sym_name(chain, bf, sizeof(bf),
- browser->show_dso);
+ row += hist_browser__show_callchain_list(browser, child,
+ chain, row, total,
+ was_first && need_percent,
+ offset + extra_offset,
+ print, arg);
- if (was_first && need_percent) {
- double percent = cumul * 100.0 / total;
-
- if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
- str = "Not enough memory!";
- else
- str = alloc_str;
- }
-
- print(browser, chain, str, offset + extra_offset, row, arg);
-
- free(alloc_str);
-
- if (is_output_full(browser, ++row))
+ if (is_output_full(browser, row))
goto out;
-do_next:
+
if (folded_sign == '+')
break;
}
@@ -847,10 +1096,22 @@
total = entry->stat.period;
}
- printed += hist_browser__show_callchain(browser,
+ if (callchain_param.mode == CHAIN_FLAT) {
+ printed += hist_browser__show_callchain_flat(browser,
+ &entry->sorted_chain, row, total,
+ hist_browser__show_callchain_entry, &arg,
+ hist_browser__check_output_full);
+ } else if (callchain_param.mode == CHAIN_FOLDED) {
+ printed += hist_browser__show_callchain_folded(browser,
+ &entry->sorted_chain, row, total,
+ hist_browser__show_callchain_entry, &arg,
+ hist_browser__check_output_full);
+ } else {
+ printed += hist_browser__show_callchain(browser,
&entry->sorted_chain, 1, row, total,
hist_browser__show_callchain_entry, &arg,
hist_browser__check_output_full);
+ }
if (arg.is_current_entry)
browser->he_selection = entry;
@@ -1802,10 +2063,9 @@
SLang_reset_tty();
SLang_init_tty(0, 0, 0);
- if (min_pcnt) {
+ if (min_pcnt)
browser->min_pcnt = min_pcnt;
- hist_browser__update_nr_entries(browser);
- }
+ hist_browser__update_nr_entries(browser);
browser->pstack = pstack__new(3);
if (browser->pstack == NULL)
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 4b3585e..4677172 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -89,8 +89,8 @@
perf_gtk__hpp_color_overhead_acc;
}
-static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
- GtkTreeIter *parent, int col, u64 total)
+static void perf_gtk__add_callchain_flat(struct rb_root *root, GtkTreeStore *store,
+ GtkTreeIter *parent, int col, u64 total)
{
struct rb_node *nd;
bool has_single_node = (rb_first(root) == rb_last(root));
@@ -100,13 +100,132 @@
struct callchain_list *chain;
GtkTreeIter iter, new_parent;
bool need_new_parent;
- double percent;
- u64 hits, child_total;
node = rb_entry(nd, struct callchain_node, rb_node);
- hits = callchain_cumul_hits(node);
- percent = 100.0 * hits / total;
+ new_parent = *parent;
+ need_new_parent = !has_single_node;
+
+ callchain_node__make_parent_list(node);
+
+ list_for_each_entry(chain, &node->parent_val, list) {
+ char buf[128];
+
+ gtk_tree_store_append(store, &iter, &new_parent);
+
+ callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
+ gtk_tree_store_set(store, &iter, 0, buf, -1);
+
+ callchain_list__sym_name(chain, buf, sizeof(buf), false);
+ gtk_tree_store_set(store, &iter, col, buf, -1);
+
+ if (need_new_parent) {
+ /*
+ * Only show the top-most symbol in a callchain
+ * if it's not the only callchain.
+ */
+ new_parent = iter;
+ need_new_parent = false;
+ }
+ }
+
+ list_for_each_entry(chain, &node->val, list) {
+ char buf[128];
+
+ gtk_tree_store_append(store, &iter, &new_parent);
+
+ callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
+ gtk_tree_store_set(store, &iter, 0, buf, -1);
+
+ callchain_list__sym_name(chain, buf, sizeof(buf), false);
+ gtk_tree_store_set(store, &iter, col, buf, -1);
+
+ if (need_new_parent) {
+ /*
+ * Only show the top-most symbol in a callchain
+ * if it's not the only callchain.
+ */
+ new_parent = iter;
+ need_new_parent = false;
+ }
+ }
+ }
+}
+
+static void perf_gtk__add_callchain_folded(struct rb_root *root, GtkTreeStore *store,
+ GtkTreeIter *parent, int col, u64 total)
+{
+ struct rb_node *nd;
+
+ for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+ struct callchain_node *node;
+ struct callchain_list *chain;
+ GtkTreeIter iter;
+ char buf[64];
+ char *str, *str_alloc = NULL;
+ bool first = true;
+
+ node = rb_entry(nd, struct callchain_node, rb_node);
+
+ callchain_node__make_parent_list(node);
+
+ list_for_each_entry(chain, &node->parent_val, list) {
+ char name[1024];
+
+ callchain_list__sym_name(chain, name, sizeof(name), false);
+
+ if (asprintf(&str, "%s%s%s",
+ first ? "" : str_alloc,
+ first ? "" : symbol_conf.field_sep ?: "; ",
+ name) < 0)
+ return;
+
+ first = false;
+ free(str_alloc);
+ str_alloc = str;
+ }
+
+ list_for_each_entry(chain, &node->val, list) {
+ char name[1024];
+
+ callchain_list__sym_name(chain, name, sizeof(name), false);
+
+ if (asprintf(&str, "%s%s%s",
+ first ? "" : str_alloc,
+ first ? "" : symbol_conf.field_sep ?: "; ",
+ name) < 0)
+ return;
+
+ first = false;
+ free(str_alloc);
+ str_alloc = str;
+ }
+
+ gtk_tree_store_append(store, &iter, parent);
+
+ callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
+ gtk_tree_store_set(store, &iter, 0, buf, -1);
+
+ gtk_tree_store_set(store, &iter, col, str, -1);
+
+ free(str_alloc);
+ }
+}
+
+static void perf_gtk__add_callchain_graph(struct rb_root *root, GtkTreeStore *store,
+ GtkTreeIter *parent, int col, u64 total)
+{
+ struct rb_node *nd;
+ bool has_single_node = (rb_first(root) == rb_last(root));
+
+ for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+ struct callchain_node *node;
+ struct callchain_list *chain;
+ GtkTreeIter iter, new_parent;
+ bool need_new_parent;
+ u64 child_total;
+
+ node = rb_entry(nd, struct callchain_node, rb_node);
new_parent = *parent;
need_new_parent = !has_single_node && (node->val_nr > 1);
@@ -116,7 +235,7 @@
gtk_tree_store_append(store, &iter, &new_parent);
- scnprintf(buf, sizeof(buf), "%5.2f%%", percent);
+ callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
gtk_tree_store_set(store, &iter, 0, buf, -1);
callchain_list__sym_name(chain, buf, sizeof(buf), false);
@@ -138,11 +257,22 @@
child_total = total;
/* Now 'iter' contains info of the last callchain_list */
- perf_gtk__add_callchain(&node->rb_root, store, &iter, col,
- child_total);
+ perf_gtk__add_callchain_graph(&node->rb_root, store, &iter, col,
+ child_total);
}
}
+static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
+ GtkTreeIter *parent, int col, u64 total)
+{
+ if (callchain_param.mode == CHAIN_FLAT)
+ perf_gtk__add_callchain_flat(root, store, parent, col, total);
+ else if (callchain_param.mode == CHAIN_FOLDED)
+ perf_gtk__add_callchain_folded(root, store, parent, col, total);
+ else
+ perf_gtk__add_callchain_graph(root, store, parent, col, total);
+}
+
static void on_row_activated(GtkTreeView *view, GtkTreePath *path,
GtkTreeViewColumn *col __maybe_unused,
gpointer user_data __maybe_unused)
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index dfcbc90..7ebc661 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -34,10 +34,10 @@
return ret;
}
-static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
+static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
+ struct callchain_list *chain,
int depth, int depth_mask, int period,
- u64 total_samples, u64 hits,
- int left_margin)
+ u64 total_samples, int left_margin)
{
int i;
size_t ret = 0;
@@ -50,10 +50,9 @@
else
ret += fprintf(fp, " ");
if (!period && i == depth - 1) {
- double percent;
-
- percent = hits * 100.0 / total_samples;
- ret += percent_color_fprintf(fp, "--%2.2f%%-- ", percent);
+ ret += fprintf(fp, "--");
+ ret += callchain_node__fprintf_value(node, fp, total_samples);
+ ret += fprintf(fp, "--");
} else
ret += fprintf(fp, "%s", " ");
}
@@ -82,13 +81,14 @@
int depth_mask, int left_margin)
{
struct rb_node *node, *next;
- struct callchain_node *child;
+ struct callchain_node *child = NULL;
struct callchain_list *chain;
int new_depth_mask = depth_mask;
u64 remaining;
size_t ret = 0;
int i;
uint entries_printed = 0;
+ int cumul_count = 0;
remaining = total_samples;
@@ -100,6 +100,7 @@
child = rb_entry(node, struct callchain_node, rb_node);
cumul = callchain_cumul_hits(child);
remaining -= cumul;
+ cumul_count += callchain_cumul_counts(child);
/*
* The depth mask manages the output of pipes that show
@@ -120,10 +121,9 @@
left_margin);
i = 0;
list_for_each_entry(chain, &child->val, list) {
- ret += ipchain__fprintf_graph(fp, chain, depth,
+ ret += ipchain__fprintf_graph(fp, child, chain, depth,
new_depth_mask, i++,
total_samples,
- cumul,
left_margin);
}
@@ -143,14 +143,23 @@
if (callchain_param.mode == CHAIN_GRAPH_REL &&
remaining && remaining != total_samples) {
+ struct callchain_node rem_node = {
+ .hit = remaining,
+ };
if (!rem_sq_bracket)
return ret;
+ if (callchain_param.value == CCVAL_COUNT && child && child->parent) {
+ rem_node.count = child->parent->children_count - cumul_count;
+ if (rem_node.count <= 0)
+ return ret;
+ }
+
new_depth_mask &= ~(1 << (depth - 1));
- ret += ipchain__fprintf_graph(fp, &rem_hits, depth,
+ ret += ipchain__fprintf_graph(fp, &rem_node, &rem_hits, depth,
new_depth_mask, 0, total_samples,
- remaining, left_margin);
+ left_margin);
}
return ret;
@@ -243,13 +252,63 @@
struct rb_node *rb_node = rb_first(tree);
while (rb_node) {
- double percent;
+ chain = rb_entry(rb_node, struct callchain_node, rb_node);
+
+ ret += fprintf(fp, " ");
+ ret += callchain_node__fprintf_value(chain, fp, total_samples);
+ ret += fprintf(fp, "\n");
+ ret += __callchain__fprintf_flat(fp, chain, total_samples);
+ ret += fprintf(fp, "\n");
+ if (++entries_printed == callchain_param.print_limit)
+ break;
+
+ rb_node = rb_next(rb_node);
+ }
+
+ return ret;
+}
+
+static size_t __callchain__fprintf_folded(FILE *fp, struct callchain_node *node)
+{
+ const char *sep = symbol_conf.field_sep ?: ";";
+ struct callchain_list *chain;
+ size_t ret = 0;
+ char bf[1024];
+ bool first;
+
+ if (!node)
+ return 0;
+
+ ret += __callchain__fprintf_folded(fp, node->parent);
+
+ first = (ret == 0);
+ list_for_each_entry(chain, &node->val, list) {
+ if (chain->ip >= PERF_CONTEXT_MAX)
+ continue;
+ ret += fprintf(fp, "%s%s", first ? "" : sep,
+ callchain_list__sym_name(chain,
+ bf, sizeof(bf), false));
+ first = false;
+ }
+
+ return ret;
+}
+
+static size_t callchain__fprintf_folded(FILE *fp, struct rb_root *tree,
+ u64 total_samples)
+{
+ size_t ret = 0;
+ u32 entries_printed = 0;
+ struct callchain_node *chain;
+ struct rb_node *rb_node = rb_first(tree);
+
+ while (rb_node) {
chain = rb_entry(rb_node, struct callchain_node, rb_node);
- percent = chain->hit * 100.0 / total_samples;
- ret = percent_color_fprintf(fp, " %6.2f%%\n", percent);
- ret += __callchain__fprintf_flat(fp, chain, total_samples);
+ ret += callchain_node__fprintf_value(chain, fp, total_samples);
+ ret += fprintf(fp, " ");
+ ret += __callchain__fprintf_folded(fp, chain);
ret += fprintf(fp, "\n");
if (++entries_printed == callchain_param.print_limit)
break;
@@ -278,6 +337,9 @@
case CHAIN_FLAT:
return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
break;
+ case CHAIN_FOLDED:
+ return callchain__fprintf_folded(fp, &he->sorted_chain, total_samples);
+ break;
case CHAIN_NONE:
break;
default:
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 591b3fe..0513dd5 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -21,6 +21,7 @@
libperf-y += perf_regs.o
libperf-y += path.o
libperf-y += rbtree.o
+libperf-y += libstring.o
libperf-y += bitmap.o
libperf-y += hweight.o
libperf-y += run-command.o
@@ -88,6 +89,7 @@
libperf-y += parse-regs-options.o
libperf-$(CONFIG_LIBBPF) += bpf-loader.o
+libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
libperf-$(CONFIG_LIBELF) += symbol-elf.o
libperf-$(CONFIG_LIBELF) += probe-file.o
libperf-$(CONFIG_LIBELF) += probe-event.o
@@ -138,6 +140,7 @@
CFLAGS_find_next_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_rbtree.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_parse-events.o += -Wno-redundant-decls
@@ -153,6 +156,10 @@
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
+$(OUTPUT)util/libstring.o: ../lib/string.c FORCE
+ $(call rule_mkdir)
+ $(call if_changed_dep,cc_o_c)
+
$(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 1dd1949..b795b69 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -65,6 +65,11 @@
name++;
+#ifdef __arm__
+ if (strchr(name, '+'))
+ return -1;
+#endif
+
tok = strchr(name, '>');
if (tok == NULL)
return -1;
@@ -246,7 +251,11 @@
return -1;
target = ++s;
+#ifdef __arm__
+ comment = strchr(s, ';');
+#else
comment = strchr(s, '#');
+#endif
if (comment != NULL)
s = comment - 1;
@@ -354,6 +363,20 @@
{ .name = "addq", .ops = &mov_ops, },
{ .name = "addw", .ops = &mov_ops, },
{ .name = "and", .ops = &mov_ops, },
+#ifdef __arm__
+ { .name = "b", .ops = &jump_ops, }, // might also be a call
+ { .name = "bcc", .ops = &jump_ops, },
+ { .name = "bcs", .ops = &jump_ops, },
+ { .name = "beq", .ops = &jump_ops, },
+ { .name = "bge", .ops = &jump_ops, },
+ { .name = "bgt", .ops = &jump_ops, },
+ { .name = "bhi", .ops = &jump_ops, },
+ { .name = "bl", .ops = &call_ops, },
+ { .name = "blt", .ops = &jump_ops, },
+ { .name = "bls", .ops = &jump_ops, },
+ { .name = "blx", .ops = &call_ops, },
+ { .name = "bne", .ops = &jump_ops, },
+#endif
{ .name = "bts", .ops = &mov_ops, },
{ .name = "call", .ops = &call_ops, },
{ .name = "callq", .ops = &call_ops, },
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 4c50411..540a7ef 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -5,11 +5,15 @@
* Copyright (C) 2015 Huawei Inc.
*/
+#include <linux/bpf.h>
#include <bpf/libbpf.h>
#include <linux/err.h>
+#include <linux/string.h>
#include "perf.h"
#include "debug.h"
#include "bpf-loader.h"
+#include "bpf-prologue.h"
+#include "llvm-utils.h"
#include "probe-event.h"
#include "probe-finder.h" // for MAX_PROBES
#include "llvm-utils.h"
@@ -32,6 +36,10 @@
struct bpf_prog_priv {
struct perf_probe_event pev;
+ bool need_prologue;
+ struct bpf_insn *insns_buf;
+ int nr_types;
+ int *type_mapping;
};
static bool libbpf_initialized;
@@ -106,10 +114,178 @@
struct bpf_prog_priv *priv = _priv;
cleanup_perf_probe_events(&priv->pev, 1);
+ zfree(&priv->insns_buf);
+ zfree(&priv->type_mapping);
free(priv);
}
static int
+prog_config__exec(const char *value, struct perf_probe_event *pev)
+{
+ pev->uprobes = true;
+ pev->target = strdup(value);
+ if (!pev->target)
+ return -ENOMEM;
+ return 0;
+}
+
+static int
+prog_config__module(const char *value, struct perf_probe_event *pev)
+{
+ pev->uprobes = false;
+ pev->target = strdup(value);
+ if (!pev->target)
+ return -ENOMEM;
+ return 0;
+}
+
+static int
+prog_config__bool(const char *value, bool *pbool, bool invert)
+{
+ int err;
+ bool bool_value;
+
+ if (!pbool)
+ return -EINVAL;
+
+ err = strtobool(value, &bool_value);
+ if (err)
+ return err;
+
+ *pbool = invert ? !bool_value : bool_value;
+ return 0;
+}
+
+static int
+prog_config__inlines(const char *value,
+ struct perf_probe_event *pev __maybe_unused)
+{
+ return prog_config__bool(value, &probe_conf.no_inlines, true);
+}
+
+static int
+prog_config__force(const char *value,
+ struct perf_probe_event *pev __maybe_unused)
+{
+ return prog_config__bool(value, &probe_conf.force_add, false);
+}
+
+static struct {
+ const char *key;
+ const char *usage;
+ const char *desc;
+ int (*func)(const char *, struct perf_probe_event *);
+} bpf_prog_config_terms[] = {
+ {
+ .key = "exec",
+ .usage = "exec=<full path of file>",
+ .desc = "Set uprobe target",
+ .func = prog_config__exec,
+ },
+ {
+ .key = "module",
+ .usage = "module=<module name> ",
+ .desc = "Set kprobe module",
+ .func = prog_config__module,
+ },
+ {
+ .key = "inlines",
+ .usage = "inlines=[yes|no] ",
+ .desc = "Probe at inline symbol",
+ .func = prog_config__inlines,
+ },
+ {
+ .key = "force",
+ .usage = "force=[yes|no] ",
+ .desc = "Forcibly add events with existing name",
+ .func = prog_config__force,
+ },
+};
+
+static int
+do_prog_config(const char *key, const char *value,
+ struct perf_probe_event *pev)
+{
+ unsigned int i;
+
+ pr_debug("config bpf program: %s=%s\n", key, value);
+ for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++)
+ if (strcmp(key, bpf_prog_config_terms[i].key) == 0)
+ return bpf_prog_config_terms[i].func(value, pev);
+
+ pr_debug("BPF: ERROR: invalid program config option: %s=%s\n",
+ key, value);
+
+ pr_debug("\nHint: Valid options are:\n");
+ for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++)
+ pr_debug("\t%s:\t%s\n", bpf_prog_config_terms[i].usage,
+ bpf_prog_config_terms[i].desc);
+ pr_debug("\n");
+
+ return -BPF_LOADER_ERRNO__PROGCONF_TERM;
+}
+
+static const char *
+parse_prog_config_kvpair(const char *config_str, struct perf_probe_event *pev)
+{
+ char *text = strdup(config_str);
+ char *sep, *line;
+ const char *main_str = NULL;
+ int err = 0;
+
+ if (!text) {
+ pr_debug("No enough memory: dup config_str failed\n");
+ return ERR_PTR(-ENOMEM);
+ }
+
+ line = text;
+ while ((sep = strchr(line, ';'))) {
+ char *equ;
+
+ *sep = '\0';
+ equ = strchr(line, '=');
+ if (!equ) {
+ pr_warning("WARNING: invalid config in BPF object: %s\n",
+ line);
+ pr_warning("\tShould be 'key=value'.\n");
+ goto nextline;
+ }
+ *equ = '\0';
+
+ err = do_prog_config(line, equ + 1, pev);
+ if (err)
+ break;
+nextline:
+ line = sep + 1;
+ }
+
+ if (!err)
+ main_str = config_str + (line - text);
+ free(text);
+
+ return err ? ERR_PTR(err) : main_str;
+}
+
+static int
+parse_prog_config(const char *config_str, struct perf_probe_event *pev)
+{
+ int err;
+ const char *main_str = parse_prog_config_kvpair(config_str, pev);
+
+ if (IS_ERR(main_str))
+ return PTR_ERR(main_str);
+
+ err = parse_perf_probe_command(main_str, pev);
+ if (err < 0) {
+ pr_debug("bpf: '%s' is not a valid config string\n",
+ config_str);
+ /* parse failed, don't need clear pev. */
+ return -BPF_LOADER_ERRNO__CONFIG;
+ }
+ return 0;
+}
+
+static int
config_bpf_program(struct bpf_program *prog)
{
struct perf_probe_event *pev = NULL;
@@ -117,6 +293,10 @@
const char *config_str;
int err;
+ /* Initialize per-program probing setting */
+ probe_conf.no_inlines = false;
+ probe_conf.force_add = false;
+
config_str = bpf_program__title(prog, false);
if (IS_ERR(config_str)) {
pr_debug("bpf: unable to get title for program\n");
@@ -131,13 +311,9 @@
pev = &priv->pev;
pr_debug("bpf: config program '%s'\n", config_str);
- err = parse_perf_probe_command(config_str, pev);
- if (err < 0) {
- pr_debug("bpf: '%s' is not a valid config string\n",
- config_str);
- err = -BPF_LOADER_ERRNO__CONFIG;
+ err = parse_prog_config(config_str, pev);
+ if (err)
goto errout;
- }
if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) {
pr_debug("bpf: '%s': group for event is set and not '%s'.\n",
@@ -197,6 +373,220 @@
return err;
}
+static int
+preproc_gen_prologue(struct bpf_program *prog, int n,
+ struct bpf_insn *orig_insns, int orig_insns_cnt,
+ struct bpf_prog_prep_result *res)
+{
+ struct probe_trace_event *tev;
+ struct perf_probe_event *pev;
+ struct bpf_prog_priv *priv;
+ struct bpf_insn *buf;
+ size_t prologue_cnt = 0;
+ int i, err;
+
+ err = bpf_program__get_private(prog, (void **)&priv);
+ if (err || !priv)
+ goto errout;
+
+ pev = &priv->pev;
+
+ if (n < 0 || n >= priv->nr_types)
+ goto errout;
+
+ /* Find a tev belongs to that type */
+ for (i = 0; i < pev->ntevs; i++) {
+ if (priv->type_mapping[i] == n)
+ break;
+ }
+
+ if (i >= pev->ntevs) {
+ pr_debug("Internal error: prologue type %d not found\n", n);
+ return -BPF_LOADER_ERRNO__PROLOGUE;
+ }
+
+ tev = &pev->tevs[i];
+
+ buf = priv->insns_buf;
+ err = bpf__gen_prologue(tev->args, tev->nargs,
+ buf, &prologue_cnt,
+ BPF_MAXINSNS - orig_insns_cnt);
+ if (err) {
+ const char *title;
+
+ title = bpf_program__title(prog, false);
+ if (!title)
+ title = "[unknown]";
+
+ pr_debug("Failed to generate prologue for program %s\n",
+ title);
+ return err;
+ }
+
+ memcpy(&buf[prologue_cnt], orig_insns,
+ sizeof(struct bpf_insn) * orig_insns_cnt);
+
+ res->new_insn_ptr = buf;
+ res->new_insn_cnt = prologue_cnt + orig_insns_cnt;
+ res->pfd = NULL;
+ return 0;
+
+errout:
+ pr_debug("Internal error in preproc_gen_prologue\n");
+ return -BPF_LOADER_ERRNO__PROLOGUE;
+}
+
+/*
+ * compare_tev_args is reflexive, transitive and antisymmetric.
+ * I can proof it but this margin is too narrow to contain.
+ */
+static int compare_tev_args(const void *ptev1, const void *ptev2)
+{
+ int i, ret;
+ const struct probe_trace_event *tev1 =
+ *(const struct probe_trace_event **)ptev1;
+ const struct probe_trace_event *tev2 =
+ *(const struct probe_trace_event **)ptev2;
+
+ ret = tev2->nargs - tev1->nargs;
+ if (ret)
+ return ret;
+
+ for (i = 0; i < tev1->nargs; i++) {
+ struct probe_trace_arg *arg1, *arg2;
+ struct probe_trace_arg_ref *ref1, *ref2;
+
+ arg1 = &tev1->args[i];
+ arg2 = &tev2->args[i];
+
+ ret = strcmp(arg1->value, arg2->value);
+ if (ret)
+ return ret;
+
+ ref1 = arg1->ref;
+ ref2 = arg2->ref;
+
+ while (ref1 && ref2) {
+ ret = ref2->offset - ref1->offset;
+ if (ret)
+ return ret;
+
+ ref1 = ref1->next;
+ ref2 = ref2->next;
+ }
+
+ if (ref1 || ref2)
+ return ref2 ? 1 : -1;
+ }
+
+ return 0;
+}
+
+/*
+ * Assign a type number to each tevs in a pev.
+ * mapping is an array with same slots as tevs in that pev.
+ * nr_types will be set to number of types.
+ */
+static int map_prologue(struct perf_probe_event *pev, int *mapping,
+ int *nr_types)
+{
+ int i, type = 0;
+ struct probe_trace_event **ptevs;
+
+ size_t array_sz = sizeof(*ptevs) * pev->ntevs;
+
+ ptevs = malloc(array_sz);
+ if (!ptevs) {
+ pr_debug("No ehough memory: alloc ptevs failed\n");
+ return -ENOMEM;
+ }
+
+ pr_debug("In map_prologue, ntevs=%d\n", pev->ntevs);
+ for (i = 0; i < pev->ntevs; i++)
+ ptevs[i] = &pev->tevs[i];
+
+ qsort(ptevs, pev->ntevs, sizeof(*ptevs),
+ compare_tev_args);
+
+ for (i = 0; i < pev->ntevs; i++) {
+ int n;
+
+ n = ptevs[i] - pev->tevs;
+ if (i == 0) {
+ mapping[n] = type;
+ pr_debug("mapping[%d]=%d\n", n, type);
+ continue;
+ }
+
+ if (compare_tev_args(ptevs + i, ptevs + i - 1) == 0)
+ mapping[n] = type;
+ else
+ mapping[n] = ++type;
+
+ pr_debug("mapping[%d]=%d\n", n, mapping[n]);
+ }
+ free(ptevs);
+ *nr_types = type + 1;
+
+ return 0;
+}
+
+static int hook_load_preprocessor(struct bpf_program *prog)
+{
+ struct perf_probe_event *pev;
+ struct bpf_prog_priv *priv;
+ bool need_prologue = false;
+ int err, i;
+
+ err = bpf_program__get_private(prog, (void **)&priv);
+ if (err || !priv) {
+ pr_debug("Internal error when hook preprocessor\n");
+ return -BPF_LOADER_ERRNO__INTERNAL;
+ }
+
+ pev = &priv->pev;
+ for (i = 0; i < pev->ntevs; i++) {
+ struct probe_trace_event *tev = &pev->tevs[i];
+
+ if (tev->nargs > 0) {
+ need_prologue = true;
+ break;
+ }
+ }
+
+ /*
+ * Since all tevs don't have argument, we don't need generate
+ * prologue.
+ */
+ if (!need_prologue) {
+ priv->need_prologue = false;
+ return 0;
+ }
+
+ priv->need_prologue = true;
+ priv->insns_buf = malloc(sizeof(struct bpf_insn) * BPF_MAXINSNS);
+ if (!priv->insns_buf) {
+ pr_debug("No enough memory: alloc insns_buf failed\n");
+ return -ENOMEM;
+ }
+
+ priv->type_mapping = malloc(sizeof(int) * pev->ntevs);
+ if (!priv->type_mapping) {
+ pr_debug("No enough memory: alloc type_mapping failed\n");
+ return -ENOMEM;
+ }
+ memset(priv->type_mapping, -1,
+ sizeof(int) * pev->ntevs);
+
+ err = map_prologue(pev, priv->type_mapping, &priv->nr_types);
+ if (err)
+ return err;
+
+ err = bpf_program__set_prep(prog, priv->nr_types,
+ preproc_gen_prologue);
+ return err;
+}
+
int bpf__probe(struct bpf_object *obj)
{
int err = 0;
@@ -231,6 +621,18 @@
pr_debug("bpf_probe: failed to apply perf probe events");
goto out;
}
+
+ /*
+ * After probing, let's consider prologue, which
+ * adds program fetcher to BPF programs.
+ *
+ * hook_load_preprocessorr() hooks pre-processor
+ * to bpf_program, let it generate prologue
+ * dynamically during loading.
+ */
+ err = hook_load_preprocessor(prog);
+ if (err)
+ goto out;
}
out:
return err < 0 ? err : 0;
@@ -314,7 +716,14 @@
for (i = 0; i < pev->ntevs; i++) {
tev = &pev->tevs[i];
- fd = bpf_program__fd(prog);
+ if (priv->need_prologue) {
+ int type = priv->type_mapping[i];
+
+ fd = bpf_program__nth_fd(prog, type);
+ } else {
+ fd = bpf_program__fd(prog);
+ }
+
if (fd < 0) {
pr_debug("bpf: failed to get file descriptor\n");
return fd;
@@ -340,6 +749,10 @@
[ERRCODE_OFFSET(EVENTNAME)] = "No event name found in config string",
[ERRCODE_OFFSET(INTERNAL)] = "BPF loader internal error",
[ERRCODE_OFFSET(COMPILE)] = "Error when compiling BPF scriptlet",
+ [ERRCODE_OFFSET(PROGCONF_TERM)] = "Invalid program config term in config string",
+ [ERRCODE_OFFSET(PROLOGUE)] = "Failed to generate prologue",
+ [ERRCODE_OFFSET(PROLOGUE2BIG)] = "Prologue too big for program",
+ [ERRCODE_OFFSET(PROLOGUEOOB)] = "Offset out of bound for prologue",
};
static int
@@ -420,7 +833,11 @@
int err, char *buf, size_t size)
{
bpf__strerror_head(err, buf, size);
- bpf__strerror_entry(EEXIST, "Probe point exist. Try use 'perf probe -d \"*\"'");
+ case BPF_LOADER_ERRNO__PROGCONF_TERM: {
+ scnprintf(buf, size, "%s (add -v to see detail)", emsg);
+ break;
+ }
+ bpf__strerror_entry(EEXIST, "Probe point exist. Try 'perf probe -d \"*\"' and set 'force=yes'");
bpf__strerror_entry(EACCES, "You need to be root");
bpf__strerror_entry(EPERM, "You need to be root, and /proc/sys/kernel/kptr_restrict should be 0");
bpf__strerror_entry(ENOENT, "You need to check probing points in BPF file");
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 9caf3ae..6fdc045 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -20,6 +20,10 @@
BPF_LOADER_ERRNO__EVENTNAME, /* Event name is missing */
BPF_LOADER_ERRNO__INTERNAL, /* BPF loader internal error */
BPF_LOADER_ERRNO__COMPILE, /* Error when compiling BPF scriptlet */
+ BPF_LOADER_ERRNO__PROGCONF_TERM,/* Invalid program config term in config string */
+ BPF_LOADER_ERRNO__PROLOGUE, /* Failed to generate prologue */
+ BPF_LOADER_ERRNO__PROLOGUE2BIG, /* Prologue too big for program */
+ BPF_LOADER_ERRNO__PROLOGUEOOB, /* Offset out of bound for prologue */
__BPF_LOADER_ERRNO__END,
};
diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c
new file mode 100644
index 0000000..6cdbee1
--- /dev/null
+++ b/tools/perf/util/bpf-prologue.c
@@ -0,0 +1,455 @@
+/*
+ * bpf-prologue.c
+ *
+ * Copyright (C) 2015 He Kuang <hekuang@huawei.com>
+ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015 Huawei Inc.
+ */
+
+#include <bpf/libbpf.h>
+#include "perf.h"
+#include "debug.h"
+#include "bpf-loader.h"
+#include "bpf-prologue.h"
+#include "probe-finder.h"
+#include <dwarf-regs.h>
+#include <linux/filter.h>
+
+#define BPF_REG_SIZE 8
+
+#define JMP_TO_ERROR_CODE -1
+#define JMP_TO_SUCCESS_CODE -2
+#define JMP_TO_USER_CODE -3
+
+struct bpf_insn_pos {
+ struct bpf_insn *begin;
+ struct bpf_insn *end;
+ struct bpf_insn *pos;
+};
+
+static inline int
+pos_get_cnt(struct bpf_insn_pos *pos)
+{
+ return pos->pos - pos->begin;
+}
+
+static int
+append_insn(struct bpf_insn new_insn, struct bpf_insn_pos *pos)
+{
+ if (!pos->pos)
+ return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
+
+ if (pos->pos + 1 >= pos->end) {
+ pr_err("bpf prologue: prologue too long\n");
+ pos->pos = NULL;
+ return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
+ }
+
+ *(pos->pos)++ = new_insn;
+ return 0;
+}
+
+static int
+check_pos(struct bpf_insn_pos *pos)
+{
+ if (!pos->pos || pos->pos >= pos->end)
+ return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
+ return 0;
+}
+
+/* Give it a shorter name */
+#define ins(i, p) append_insn((i), (p))
+
+/*
+ * Give a register name (in 'reg'), generate instruction to
+ * load register into an eBPF register rd:
+ * 'ldd target_reg, offset(ctx_reg)', where:
+ * ctx_reg is pre initialized to pointer of 'struct pt_regs'.
+ */
+static int
+gen_ldx_reg_from_ctx(struct bpf_insn_pos *pos, int ctx_reg,
+ const char *reg, int target_reg)
+{
+ int offset = regs_query_register_offset(reg);
+
+ if (offset < 0) {
+ pr_err("bpf: prologue: failed to get register %s\n",
+ reg);
+ return offset;
+ }
+ ins(BPF_LDX_MEM(BPF_DW, target_reg, ctx_reg, offset), pos);
+
+ return check_pos(pos);
+}
+
+/*
+ * Generate a BPF_FUNC_probe_read function call.
+ *
+ * src_base_addr_reg is a register holding base address,
+ * dst_addr_reg is a register holding dest address (on stack),
+ * result is:
+ *
+ * *[dst_addr_reg] = *([src_base_addr_reg] + offset)
+ *
+ * Arguments of BPF_FUNC_probe_read:
+ * ARG1: ptr to stack (dest)
+ * ARG2: size (8)
+ * ARG3: unsafe ptr (src)
+ */
+static int
+gen_read_mem(struct bpf_insn_pos *pos,
+ int src_base_addr_reg,
+ int dst_addr_reg,
+ long offset)
+{
+ /* mov arg3, src_base_addr_reg */
+ if (src_base_addr_reg != BPF_REG_ARG3)
+ ins(BPF_MOV64_REG(BPF_REG_ARG3, src_base_addr_reg), pos);
+ /* add arg3, #offset */
+ if (offset)
+ ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG3, offset), pos);
+
+ /* mov arg2, #reg_size */
+ ins(BPF_ALU64_IMM(BPF_MOV, BPF_REG_ARG2, BPF_REG_SIZE), pos);
+
+ /* mov arg1, dst_addr_reg */
+ if (dst_addr_reg != BPF_REG_ARG1)
+ ins(BPF_MOV64_REG(BPF_REG_ARG1, dst_addr_reg), pos);
+
+ /* Call probe_read */
+ ins(BPF_EMIT_CALL(BPF_FUNC_probe_read), pos);
+ /*
+ * Error processing: if read fail, goto error code,
+ * will be relocated. Target should be the start of
+ * error processing code.
+ */
+ ins(BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, JMP_TO_ERROR_CODE),
+ pos);
+
+ return check_pos(pos);
+}
+
+/*
+ * Each arg should be bare register. Fetch and save them into argument
+ * registers (r3 - r5).
+ *
+ * BPF_REG_1 should have been initialized with pointer to
+ * 'struct pt_regs'.
+ */
+static int
+gen_prologue_fastpath(struct bpf_insn_pos *pos,
+ struct probe_trace_arg *args, int nargs)
+{
+ int i, err = 0;
+
+ for (i = 0; i < nargs; i++) {
+ err = gen_ldx_reg_from_ctx(pos, BPF_REG_1, args[i].value,
+ BPF_PROLOGUE_START_ARG_REG + i);
+ if (err)
+ goto errout;
+ }
+
+ return check_pos(pos);
+errout:
+ return err;
+}
+
+/*
+ * Slow path:
+ * At least one argument has the form of 'offset($rx)'.
+ *
+ * Following code first stores them into stack, then loads all of then
+ * to r2 - r5.
+ * Before final loading, the final result should be:
+ *
+ * low address
+ * BPF_REG_FP - 24 ARG3
+ * BPF_REG_FP - 16 ARG2
+ * BPF_REG_FP - 8 ARG1
+ * BPF_REG_FP
+ * high address
+ *
+ * For each argument (described as: offn(...off2(off1(reg)))),
+ * generates following code:
+ *
+ * r7 <- fp
+ * r7 <- r7 - stack_offset // Ideal code should initialize r7 using
+ * // fp before generating args. However,
+ * // eBPF won't regard r7 as stack pointer
+ * // if it is generated by minus 8 from
+ * // another stack pointer except fp.
+ * // This is why we have to set r7
+ * // to fp for each variable.
+ * r3 <- value of 'reg'-> generated using gen_ldx_reg_from_ctx()
+ * (r7) <- r3 // skip following instructions for bare reg
+ * r3 <- r3 + off1 . // skip if off1 == 0
+ * r2 <- 8 \
+ * r1 <- r7 |-> generated by gen_read_mem()
+ * call probe_read /
+ * jnei r0, 0, err ./
+ * r3 <- (r7)
+ * r3 <- r3 + off2 . // skip if off2 == 0
+ * r2 <- 8 \ // r2 may be broken by probe_read, so set again
+ * r1 <- r7 |-> generated by gen_read_mem()
+ * call probe_read /
+ * jnei r0, 0, err ./
+ * ...
+ */
+static int
+gen_prologue_slowpath(struct bpf_insn_pos *pos,
+ struct probe_trace_arg *args, int nargs)
+{
+ int err, i;
+
+ for (i = 0; i < nargs; i++) {
+ struct probe_trace_arg *arg = &args[i];
+ const char *reg = arg->value;
+ struct probe_trace_arg_ref *ref = NULL;
+ int stack_offset = (i + 1) * -8;
+
+ pr_debug("prologue: fetch arg %d, base reg is %s\n",
+ i, reg);
+
+ /* value of base register is stored into ARG3 */
+ err = gen_ldx_reg_from_ctx(pos, BPF_REG_CTX, reg,
+ BPF_REG_ARG3);
+ if (err) {
+ pr_err("prologue: failed to get offset of register %s\n",
+ reg);
+ goto errout;
+ }
+
+ /* Make r7 the stack pointer. */
+ ins(BPF_MOV64_REG(BPF_REG_7, BPF_REG_FP), pos);
+ /* r7 += -8 */
+ ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, stack_offset), pos);
+ /*
+ * Store r3 (base register) onto stack
+ * Ensure fp[offset] is set.
+ * fp is the only valid base register when storing
+ * into stack. We are not allowed to use r7 as base
+ * register here.
+ */
+ ins(BPF_STX_MEM(BPF_DW, BPF_REG_FP, BPF_REG_ARG3,
+ stack_offset), pos);
+
+ ref = arg->ref;
+ while (ref) {
+ pr_debug("prologue: arg %d: offset %ld\n",
+ i, ref->offset);
+ err = gen_read_mem(pos, BPF_REG_3, BPF_REG_7,
+ ref->offset);
+ if (err) {
+ pr_err("prologue: failed to generate probe_read function call\n");
+ goto errout;
+ }
+
+ ref = ref->next;
+ /*
+ * Load previous result into ARG3. Use
+ * BPF_REG_FP instead of r7 because verifier
+ * allows FP based addressing only.
+ */
+ if (ref)
+ ins(BPF_LDX_MEM(BPF_DW, BPF_REG_ARG3,
+ BPF_REG_FP, stack_offset), pos);
+ }
+ }
+
+ /* Final pass: read to registers */
+ for (i = 0; i < nargs; i++)
+ ins(BPF_LDX_MEM(BPF_DW, BPF_PROLOGUE_START_ARG_REG + i,
+ BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos);
+
+ ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos);
+
+ return check_pos(pos);
+errout:
+ return err;
+}
+
+static int
+prologue_relocate(struct bpf_insn_pos *pos, struct bpf_insn *error_code,
+ struct bpf_insn *success_code, struct bpf_insn *user_code)
+{
+ struct bpf_insn *insn;
+
+ if (check_pos(pos))
+ return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
+
+ for (insn = pos->begin; insn < pos->pos; insn++) {
+ struct bpf_insn *target;
+ u8 class = BPF_CLASS(insn->code);
+ u8 opcode;
+
+ if (class != BPF_JMP)
+ continue;
+ opcode = BPF_OP(insn->code);
+ if (opcode == BPF_CALL)
+ continue;
+
+ switch (insn->off) {
+ case JMP_TO_ERROR_CODE:
+ target = error_code;
+ break;
+ case JMP_TO_SUCCESS_CODE:
+ target = success_code;
+ break;
+ case JMP_TO_USER_CODE:
+ target = user_code;
+ break;
+ default:
+ pr_err("bpf prologue: internal error: relocation failed\n");
+ return -BPF_LOADER_ERRNO__PROLOGUE;
+ }
+
+ insn->off = target - (insn + 1);
+ }
+ return 0;
+}
+
+int bpf__gen_prologue(struct probe_trace_arg *args, int nargs,
+ struct bpf_insn *new_prog, size_t *new_cnt,
+ size_t cnt_space)
+{
+ struct bpf_insn *success_code = NULL;
+ struct bpf_insn *error_code = NULL;
+ struct bpf_insn *user_code = NULL;
+ struct bpf_insn_pos pos;
+ bool fastpath = true;
+ int err = 0, i;
+
+ if (!new_prog || !new_cnt)
+ return -EINVAL;
+
+ if (cnt_space > BPF_MAXINSNS)
+ cnt_space = BPF_MAXINSNS;
+
+ pos.begin = new_prog;
+ pos.end = new_prog + cnt_space;
+ pos.pos = new_prog;
+
+ if (!nargs) {
+ ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0),
+ &pos);
+
+ if (check_pos(&pos))
+ goto errout;
+
+ *new_cnt = pos_get_cnt(&pos);
+ return 0;
+ }
+
+ if (nargs > BPF_PROLOGUE_MAX_ARGS) {
+ pr_warning("bpf: prologue: %d arguments are dropped\n",
+ nargs - BPF_PROLOGUE_MAX_ARGS);
+ nargs = BPF_PROLOGUE_MAX_ARGS;
+ }
+
+ /* First pass: validation */
+ for (i = 0; i < nargs; i++) {
+ struct probe_trace_arg_ref *ref = args[i].ref;
+
+ if (args[i].value[0] == '@') {
+ /* TODO: fetch global variable */
+ pr_err("bpf: prologue: global %s%+ld not support\n",
+ args[i].value, ref ? ref->offset : 0);
+ return -ENOTSUP;
+ }
+
+ while (ref) {
+ /* fastpath is true if all args has ref == NULL */
+ fastpath = false;
+
+ /*
+ * Instruction encodes immediate value using
+ * s32, ref->offset is long. On systems which
+ * can't fill long in s32, refuse to process if
+ * ref->offset too large (or small).
+ */
+#ifdef __LP64__
+#define OFFSET_MAX ((1LL << 31) - 1)
+#define OFFSET_MIN ((1LL << 31) * -1)
+ if (ref->offset > OFFSET_MAX ||
+ ref->offset < OFFSET_MIN) {
+ pr_err("bpf: prologue: offset out of bound: %ld\n",
+ ref->offset);
+ return -BPF_LOADER_ERRNO__PROLOGUEOOB;
+ }
+#endif
+ ref = ref->next;
+ }
+ }
+ pr_debug("prologue: pass validation\n");
+
+ if (fastpath) {
+ /* If all variables are registers... */
+ pr_debug("prologue: fast path\n");
+ err = gen_prologue_fastpath(&pos, args, nargs);
+ if (err)
+ goto errout;
+ } else {
+ pr_debug("prologue: slow path\n");
+
+ /* Initialization: move ctx to a callee saved register. */
+ ins(BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1), &pos);
+
+ err = gen_prologue_slowpath(&pos, args, nargs);
+ if (err)
+ goto errout;
+ /*
+ * start of ERROR_CODE (only slow pass needs error code)
+ * mov r2 <- 1 // r2 is error number
+ * mov r3 <- 0 // r3, r4... should be touched or
+ * // verifier would complain
+ * mov r4 <- 0
+ * ...
+ * goto usercode
+ */
+ error_code = pos.pos;
+ ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 1),
+ &pos);
+
+ for (i = 0; i < nargs; i++)
+ ins(BPF_ALU64_IMM(BPF_MOV,
+ BPF_PROLOGUE_START_ARG_REG + i,
+ 0),
+ &pos);
+ ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_USER_CODE),
+ &pos);
+ }
+
+ /*
+ * start of SUCCESS_CODE:
+ * mov r2 <- 0
+ * goto usercode // skip
+ */
+ success_code = pos.pos;
+ ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0), &pos);
+
+ /*
+ * start of USER_CODE:
+ * Restore ctx to r1
+ */
+ user_code = pos.pos;
+ if (!fastpath) {
+ /*
+ * Only slow path needs restoring of ctx. In fast path,
+ * register are loaded directly from r1.
+ */
+ ins(BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX), &pos);
+ err = prologue_relocate(&pos, error_code, success_code,
+ user_code);
+ if (err)
+ goto errout;
+ }
+
+ err = check_pos(&pos);
+ if (err)
+ goto errout;
+
+ *new_cnt = pos_get_cnt(&pos);
+ return 0;
+errout:
+ return err;
+}
diff --git a/tools/perf/util/bpf-prologue.h b/tools/perf/util/bpf-prologue.h
new file mode 100644
index 0000000..d94cbea
--- /dev/null
+++ b/tools/perf/util/bpf-prologue.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright (C) 2015, He Kuang <hekuang@huawei.com>
+ * Copyright (C) 2015, Huawei Inc.
+ */
+#ifndef __BPF_PROLOGUE_H
+#define __BPF_PROLOGUE_H
+
+#include <linux/compiler.h>
+#include <linux/filter.h>
+#include "probe-event.h"
+
+#define BPF_PROLOGUE_MAX_ARGS 3
+#define BPF_PROLOGUE_START_ARG_REG BPF_REG_3
+#define BPF_PROLOGUE_FETCH_RESULT_REG BPF_REG_2
+
+#ifdef HAVE_BPF_PROLOGUE
+int bpf__gen_prologue(struct probe_trace_arg *args, int nargs,
+ struct bpf_insn *new_prog, size_t *new_cnt,
+ size_t cnt_space);
+#else
+static inline int
+bpf__gen_prologue(struct probe_trace_arg *args __maybe_unused,
+ int nargs __maybe_unused,
+ struct bpf_insn *new_prog __maybe_unused,
+ size_t *new_cnt,
+ size_t cnt_space __maybe_unused)
+{
+ if (!new_cnt)
+ return -EINVAL;
+ *new_cnt = 0;
+ return -ENOTSUP;
+}
+#endif
+#endif /* __BPF_PROLOGUE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 735ad48..564377d 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -44,6 +44,10 @@
callchain_param.mode = CHAIN_GRAPH_REL;
return 0;
}
+ if (!strncmp(value, "folded", strlen(value))) {
+ callchain_param.mode = CHAIN_FOLDED;
+ return 0;
+ }
return -1;
}
@@ -79,6 +83,23 @@
return -1;
}
+static int parse_callchain_value(const char *value)
+{
+ if (!strncmp(value, "percent", strlen(value))) {
+ callchain_param.value = CCVAL_PERCENT;
+ return 0;
+ }
+ if (!strncmp(value, "period", strlen(value))) {
+ callchain_param.value = CCVAL_PERIOD;
+ return 0;
+ }
+ if (!strncmp(value, "count", strlen(value))) {
+ callchain_param.value = CCVAL_COUNT;
+ return 0;
+ }
+ return -1;
+}
+
static int
__parse_callchain_report_opt(const char *arg, bool allow_record_opt)
{
@@ -102,7 +123,8 @@
if (!parse_callchain_mode(tok) ||
!parse_callchain_order(tok) ||
- !parse_callchain_sort_key(tok)) {
+ !parse_callchain_sort_key(tok) ||
+ !parse_callchain_value(tok)) {
/* parsing ok - move on to the next */
try_stack_size = false;
goto next;
@@ -218,6 +240,7 @@
switch (mode) {
case CHAIN_FLAT:
+ case CHAIN_FOLDED:
if (rnode->hit < chain->hit)
p = &(*p)->rb_left;
else
@@ -267,6 +290,7 @@
sort_chain_flat(struct rb_root *rb_root, struct callchain_root *root,
u64 min_hit, struct callchain_param *param __maybe_unused)
{
+ *rb_root = RB_ROOT;
__sort_chain_flat(rb_root, &root->node, min_hit);
}
@@ -338,6 +362,7 @@
param->sort = sort_chain_graph_rel;
break;
case CHAIN_FLAT:
+ case CHAIN_FOLDED:
param->sort = sort_chain_flat;
break;
case CHAIN_NONE:
@@ -363,6 +388,7 @@
}
new->parent = parent;
INIT_LIST_HEAD(&new->val);
+ INIT_LIST_HEAD(&new->parent_val);
if (inherit_children) {
struct rb_node *n;
@@ -431,6 +457,8 @@
new->children_hit = 0;
new->hit = period;
+ new->children_count = 0;
+ new->count = 1;
return new;
}
@@ -478,6 +506,9 @@
parent->children_hit = callchain_cumul_hits(new);
new->val_nr = parent->val_nr - idx_local;
parent->val_nr = idx_local;
+ new->count = parent->count;
+ new->children_count = parent->children_count;
+ parent->children_count = callchain_cumul_counts(new);
/* create a new child for the new branch if any */
if (idx_total < cursor->nr) {
@@ -488,6 +519,8 @@
parent->hit = 0;
parent->children_hit += period;
+ parent->count = 0;
+ parent->children_count += 1;
node = callchain_cursor_current(cursor);
new = add_child(parent, cursor, period);
@@ -510,6 +543,7 @@
rb_insert_color(&new->rb_node_in, &parent->rb_root_in);
} else {
parent->hit = period;
+ parent->count = 1;
}
}
@@ -556,6 +590,7 @@
inc_children_hit:
root->children_hit += period;
+ root->children_count++;
}
static int
@@ -608,6 +643,7 @@
/* we match 100% of the path, increment the hit */
if (matches == root->val_nr && cursor->pos == cursor->nr) {
root->hit += period;
+ root->count++;
return 0;
}
@@ -799,12 +835,72 @@
return bf;
}
+char *callchain_node__scnprintf_value(struct callchain_node *node,
+ char *bf, size_t bfsize, u64 total)
+{
+ double percent = 0.0;
+ u64 period = callchain_cumul_hits(node);
+ unsigned count = callchain_cumul_counts(node);
+
+ if (callchain_param.mode == CHAIN_FOLDED) {
+ period = node->hit;
+ count = node->count;
+ }
+
+ switch (callchain_param.value) {
+ case CCVAL_PERIOD:
+ scnprintf(bf, bfsize, "%"PRIu64, period);
+ break;
+ case CCVAL_COUNT:
+ scnprintf(bf, bfsize, "%u", count);
+ break;
+ case CCVAL_PERCENT:
+ default:
+ if (total)
+ percent = period * 100.0 / total;
+ scnprintf(bf, bfsize, "%.2f%%", percent);
+ break;
+ }
+ return bf;
+}
+
+int callchain_node__fprintf_value(struct callchain_node *node,
+ FILE *fp, u64 total)
+{
+ double percent = 0.0;
+ u64 period = callchain_cumul_hits(node);
+ unsigned count = callchain_cumul_counts(node);
+
+ if (callchain_param.mode == CHAIN_FOLDED) {
+ period = node->hit;
+ count = node->count;
+ }
+
+ switch (callchain_param.value) {
+ case CCVAL_PERIOD:
+ return fprintf(fp, "%"PRIu64, period);
+ case CCVAL_COUNT:
+ return fprintf(fp, "%u", count);
+ case CCVAL_PERCENT:
+ default:
+ if (total)
+ percent = period * 100.0 / total;
+ return percent_color_fprintf(fp, "%.2f%%", percent);
+ }
+ return 0;
+}
+
static void free_callchain_node(struct callchain_node *node)
{
struct callchain_list *list, *tmp;
struct callchain_node *child;
struct rb_node *n;
+ list_for_each_entry_safe(list, tmp, &node->parent_val, list) {
+ list_del(&list->list);
+ free(list);
+ }
+
list_for_each_entry_safe(list, tmp, &node->val, list) {
list_del(&list->list);
free(list);
@@ -828,3 +924,41 @@
free_callchain_node(&root->node);
}
+
+int callchain_node__make_parent_list(struct callchain_node *node)
+{
+ struct callchain_node *parent = node->parent;
+ struct callchain_list *chain, *new;
+ LIST_HEAD(head);
+
+ while (parent) {
+ list_for_each_entry_reverse(chain, &parent->val, list) {
+ new = malloc(sizeof(*new));
+ if (new == NULL)
+ goto out;
+ *new = *chain;
+ new->has_children = false;
+ list_add_tail(&new->list, &head);
+ }
+ parent = parent->parent;
+ }
+
+ list_for_each_entry_safe_reverse(chain, new, &head, list)
+ list_move_tail(&chain->list, &node->parent_val);
+
+ if (!list_empty(&node->parent_val)) {
+ chain = list_first_entry(&node->parent_val, struct callchain_list, list);
+ chain->has_children = rb_prev(&node->rb_node) || rb_next(&node->rb_node);
+
+ chain = list_first_entry(&node->val, struct callchain_list, list);
+ chain->has_children = false;
+ }
+ return 0;
+
+out:
+ list_for_each_entry_safe(chain, new, &head, list) {
+ list_del(&chain->list);
+ free(chain);
+ }
+ return -ENOMEM;
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index fce8161..8ac8f043 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -24,12 +24,13 @@
#define CALLCHAIN_RECORD_HELP CALLCHAIN_HELP RECORD_MODE_HELP RECORD_SIZE_HELP
#define CALLCHAIN_REPORT_HELP \
- HELP_PAD "print_type:\tcall graph printing style (graph|flat|fractal|none)\n" \
+ HELP_PAD "print_type:\tcall graph printing style (graph|flat|fractal|folded|none)\n" \
HELP_PAD "threshold:\tminimum call graph inclusion threshold (<percent>)\n" \
HELP_PAD "print_limit:\tmaximum number of call graph entry (<number>)\n" \
HELP_PAD "order:\t\tcall graph order (caller|callee)\n" \
HELP_PAD "sort_key:\tcall graph sort key (function|address)\n" \
- HELP_PAD "branch:\t\tinclude last branch info to call graph (branch)\n"
+ HELP_PAD "branch:\t\tinclude last branch info to call graph (branch)\n" \
+ HELP_PAD "value:\t\tcall graph value (percent|period|count)\n"
enum perf_call_graph_mode {
CALLCHAIN_NONE,
@@ -43,7 +44,8 @@
CHAIN_NONE,
CHAIN_FLAT,
CHAIN_GRAPH_ABS,
- CHAIN_GRAPH_REL
+ CHAIN_GRAPH_REL,
+ CHAIN_FOLDED,
};
enum chain_order {
@@ -54,11 +56,14 @@
struct callchain_node {
struct callchain_node *parent;
struct list_head val;
+ struct list_head parent_val;
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;
+ unsigned int count;
+ unsigned int children_count;
u64 hit;
u64 children_hit;
};
@@ -78,6 +83,12 @@
CCKEY_ADDRESS
};
+enum chain_value {
+ CCVAL_PERCENT,
+ CCVAL_PERIOD,
+ CCVAL_COUNT,
+};
+
struct callchain_param {
bool enabled;
enum perf_call_graph_mode record_mode;
@@ -90,6 +101,7 @@
bool order_set;
enum chain_key key;
bool branch_callstack;
+ enum chain_value value;
};
extern struct callchain_param callchain_param;
@@ -131,6 +143,7 @@
static inline void callchain_init(struct callchain_root *root)
{
INIT_LIST_HEAD(&root->node.val);
+ INIT_LIST_HEAD(&root->node.parent_val);
root->node.parent = NULL;
root->node.hit = 0;
@@ -144,6 +157,11 @@
return node->hit + node->children_hit;
}
+static inline unsigned callchain_cumul_counts(struct callchain_node *node)
+{
+ return node->count + node->children_count;
+}
+
int callchain_register_param(struct callchain_param *param);
int callchain_append(struct callchain_root *root,
struct callchain_cursor *cursor,
@@ -229,7 +247,12 @@
char *callchain_list__sym_name(struct callchain_list *cl,
char *bf, size_t bfsize, bool show_dso);
+char *callchain_node__scnprintf_value(struct callchain_node *node,
+ char *bf, size_t bfsize, u64 total);
+int callchain_node__fprintf_value(struct callchain_node *node,
+ FILE *fp, u64 total);
void free_callchain(struct callchain_root *root);
+int callchain_node__make_parent_list(struct callchain_node *node);
#endif /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 425df5c..e8e9a9d 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1243,6 +1243,8 @@
if (dso != NULL) {
__dsos__add(dsos, dso);
dso__set_basename(dso);
+ /* Put dso here because __dsos_add already got it */
+ dso__put(dso);
}
return dso;
}
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d139219..d1b6c20 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -336,20 +336,12 @@
void perf_evlist__disable(struct perf_evlist *evlist)
{
- int cpu, thread;
struct perf_evsel *pos;
- int nr_cpus = cpu_map__nr(evlist->cpus);
- int nr_threads;
- for (cpu = 0; cpu < nr_cpus; cpu++) {
- evlist__for_each(evlist, pos) {
- if (!perf_evsel__is_group_leader(pos) || !pos->fd)
- continue;
- nr_threads = perf_evlist__nr_threads(evlist, pos);
- for (thread = 0; thread < nr_threads; thread++)
- ioctl(FD(pos, cpu, thread),
- PERF_EVENT_IOC_DISABLE, 0);
- }
+ evlist__for_each(evlist, pos) {
+ if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+ continue;
+ perf_evsel__disable(pos);
}
evlist->enabled = false;
@@ -357,20 +349,12 @@
void perf_evlist__enable(struct perf_evlist *evlist)
{
- int cpu, thread;
struct perf_evsel *pos;
- int nr_cpus = cpu_map__nr(evlist->cpus);
- int nr_threads;
- for (cpu = 0; cpu < nr_cpus; cpu++) {
- evlist__for_each(evlist, pos) {
- if (!perf_evsel__is_group_leader(pos) || !pos->fd)
- continue;
- nr_threads = perf_evlist__nr_threads(evlist, pos);
- for (thread = 0; thread < nr_threads; thread++)
- ioctl(FD(pos, cpu, thread),
- PERF_EVENT_IOC_ENABLE, 0);
- }
+ evlist__for_each(evlist, pos) {
+ if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+ continue;
+ perf_evsel__enable(pos);
}
evlist->enabled = true;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 397fb4e..47f0330 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -981,13 +981,26 @@
return -1;
}
-int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads)
+int perf_evsel__enable(struct perf_evsel *evsel)
{
+ int nthreads = thread_map__nr(evsel->threads);
+ int ncpus = cpu_map__nr(evsel->cpus);
+
return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
PERF_EVENT_IOC_ENABLE,
0);
}
+int perf_evsel__disable(struct perf_evsel *evsel)
+{
+ int nthreads = thread_map__nr(evsel->threads);
+ int ncpus = cpu_map__nr(evsel->cpus);
+
+ return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
+ PERF_EVENT_IOC_DISABLE,
+ 0);
+}
+
int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
{
if (ncpus == 0 || nthreads == 0)
@@ -1192,6 +1205,7 @@
bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
+ bit_name(WEIGHT),
{ .name = NULL, }
};
#undef bit_name
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 0e49bd7..5ded1fc 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -227,7 +227,8 @@
const char *op, const char *filter);
int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
const char *filter);
-int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads);
+int perf_evsel__enable(struct perf_evsel *evsel);
+int perf_evsel__disable(struct perf_evsel *evsel);
int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
struct cpu_map *cpus);
diff --git a/tools/perf/util/exec_cmd.c b/tools/perf/util/exec_cmd.c
index 7adf4ad..1099e92 100644
--- a/tools/perf/util/exec_cmd.c
+++ b/tools/perf/util/exec_cmd.c
@@ -9,17 +9,17 @@
static const char *argv_exec_path;
static const char *argv0_path;
-const char *system_path(const char *path)
+char *system_path(const char *path)
{
static const char *prefix = PREFIX;
struct strbuf d = STRBUF_INIT;
if (is_absolute_path(path))
- return path;
+ return strdup(path);
strbuf_addf(&d, "%s/%s", prefix, path);
path = strbuf_detach(&d, NULL);
- return path;
+ return (char *)path;
}
const char *perf_extract_argv0_path(const char *argv0)
@@ -52,17 +52,16 @@
/* Returns the highest-priority, location to look for perf programs. */
-const char *perf_exec_path(void)
+char *perf_exec_path(void)
{
- const char *env;
+ char *env;
if (argv_exec_path)
- return argv_exec_path;
+ return strdup(argv_exec_path);
env = getenv(EXEC_PATH_ENVIRONMENT);
- if (env && *env) {
- return env;
- }
+ if (env && *env)
+ return strdup(env);
return system_path(PERF_EXEC_PATH);
}
@@ -83,9 +82,11 @@
{
const char *old_path = getenv("PATH");
struct strbuf new_path = STRBUF_INIT;
+ char *tmp = perf_exec_path();
- add_path(&new_path, perf_exec_path());
+ add_path(&new_path, tmp);
add_path(&new_path, argv0_path);
+ free(tmp);
if (old_path)
strbuf_addstr(&new_path, old_path);
diff --git a/tools/perf/util/exec_cmd.h b/tools/perf/util/exec_cmd.h
index bc4b915..48b4175 100644
--- a/tools/perf/util/exec_cmd.h
+++ b/tools/perf/util/exec_cmd.h
@@ -3,10 +3,11 @@
extern void perf_set_argv_exec_path(const char *exec_path);
extern const char *perf_extract_argv0_path(const char *path);
-extern const char *perf_exec_path(void);
extern void setup_path(void);
extern int execv_perf_cmd(const char **argv); /* NULL terminated */
extern int execl_perf_cmd(const char *cmd, ...);
-extern const char *system_path(const char *path);
+/* perf_exec_path and system_path return malloc'd string, caller must free it */
+extern char *perf_exec_path(void);
+extern char *system_path(const char *path);
#endif /* __PERF_EXEC_CMD_H */
diff --git a/tools/perf/util/help.c b/tools/perf/util/help.c
index 86c37c4..fa1fc4a 100644
--- a/tools/perf/util/help.c
+++ b/tools/perf/util/help.c
@@ -159,7 +159,7 @@
struct cmdnames *other_cmds)
{
const char *env_path = getenv("PATH");
- const char *exec_path = perf_exec_path();
+ char *exec_path = perf_exec_path();
if (exec_path) {
list_commands_in_dir(main_cmds, exec_path, prefix);
@@ -187,6 +187,7 @@
sizeof(*other_cmds->names), cmdname_compare);
uniq(other_cmds);
}
+ free(exec_path);
exclude_cmds(other_cmds, main_cmds);
}
@@ -203,13 +204,14 @@
longest = other_cmds->names[i]->len;
if (main_cmds->cnt) {
- const char *exec_path = perf_exec_path();
+ char *exec_path = perf_exec_path();
printf("available %s in '%s'\n", title, exec_path);
printf("----------------");
mput_char('-', strlen(title) + strlen(exec_path));
putchar('\n');
pretty_print_string_list(main_cmds, longest);
putchar('\n');
+ free(exec_path);
}
if (other_cmds->cnt) {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 4fd37d6..6e8e0ee 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -924,9 +924,6 @@
int64_t cmp = 0;
perf_hpp__for_each_sort_list(fmt) {
- if (perf_hpp__should_skip(fmt))
- continue;
-
cmp = fmt->cmp(fmt, left, right);
if (cmp)
break;
@@ -942,9 +939,6 @@
int64_t cmp = 0;
perf_hpp__for_each_sort_list(fmt) {
- if (perf_hpp__should_skip(fmt))
- continue;
-
cmp = fmt->collapse(fmt, left, right);
if (cmp)
break;
diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h
deleted file mode 100644
index 6f19c54..0000000
--- a/tools/perf/util/include/linux/string.h
+++ /dev/null
@@ -1,3 +0,0 @@
-#include <string.h>
-
-void *memdup(const void *src, size_t len);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 8b303ff..bfc289c 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -122,6 +122,7 @@
void machine__exit(struct machine *machine)
{
+ machine__destroy_kernel_maps(machine);
map_groups__exit(&machine->kmaps);
dsos__exit(&machine->dsos);
machine__exit_vdso(machine);
@@ -560,11 +561,29 @@
return 0;
}
+static void dso__adjust_kmod_long_name(struct dso *dso, const char *filename)
+{
+ const char *dup_filename;
+
+ if (!filename || !dso || !dso->long_name)
+ return;
+ if (dso->long_name[0] != '[')
+ return;
+ if (!strchr(filename, '/'))
+ return;
+
+ dup_filename = strdup(filename);
+ if (!dup_filename)
+ return;
+
+ dso__set_long_name(dso, dup_filename, true);
+}
+
struct map *machine__findnew_module_map(struct machine *machine, u64 start,
const char *filename)
{
struct map *map = NULL;
- struct dso *dso;
+ struct dso *dso = NULL;
struct kmod_path m;
if (kmod_path__parse_name(&m, filename))
@@ -572,8 +591,15 @@
map = map_groups__find_by_name(&machine->kmaps, MAP__FUNCTION,
m.name);
- if (map)
+ if (map) {
+ /*
+ * If the map's dso is an offline module, give dso__load()
+ * a chance to find the file path of that module by fixing
+ * long_name.
+ */
+ dso__adjust_kmod_long_name(map->dso, filename);
goto out;
+ }
dso = machine__findnew_module_dso(machine, &m, filename);
if (dso == NULL)
@@ -585,7 +611,11 @@
map_groups__insert(&machine->kmaps, map);
+ /* Put the map here because map_groups__insert alread got it */
+ map__put(map);
out:
+ /* put the dso here, corresponding to machine__findnew_module_dso */
+ dso__put(dso);
free(m.name);
return map;
}
@@ -788,6 +818,7 @@
kmap->ref_reloc_sym = NULL;
}
+ map__put(machine->vmlinux_maps[type]);
machine->vmlinux_maps[type] = NULL;
}
}
@@ -1084,11 +1115,14 @@
struct dso *kernel = machine__get_kernel(machine);
const char *name;
u64 addr = machine__get_running_kernel_start(machine, &name);
- if (!addr)
+ int ret;
+
+ if (!addr || kernel == NULL)
return -1;
- if (kernel == NULL ||
- __machine__create_kernel_maps(machine, kernel) < 0)
+ ret = __machine__create_kernel_maps(machine, kernel);
+ dso__put(kernel);
+ if (ret < 0)
return -1;
if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
@@ -1609,6 +1643,8 @@
}
}
+ if (symbol_conf.hide_unresolved && al.sym == NULL)
+ return 0;
return callchain_cursor_append(&callchain_cursor, al.addr, al.map, al.sym);
}
@@ -1863,6 +1899,9 @@
static int unwind_entry(struct unwind_entry *entry, void *arg)
{
struct callchain_cursor *cursor = arg;
+
+ if (symbol_conf.hide_unresolved && entry->sym == NULL)
+ return 0;
return callchain_cursor_append(cursor, entry->ip,
entry->map, entry->sym);
}
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index afc6b56..93d9f1c 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -26,8 +26,8 @@
static inline int is_anon_memory(const char *filename)
{
return !strcmp(filename, "//anon") ||
- !strcmp(filename, "/dev/zero (deleted)") ||
- !strcmp(filename, "/anon_hugepage (deleted)");
+ !strncmp(filename, "/dev/zero", sizeof("/dev/zero") - 1) ||
+ !strncmp(filename, "/anon_hugepage", sizeof("/anon_hugepage") - 1);
}
static inline int is_no_dso_memory(const char *filename)
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index e48d9da..6fc8cd7 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -124,6 +124,10 @@
.symbol = "dummy",
.alias = "",
},
+ [PERF_COUNT_SW_BPF_OUTPUT] = {
+ .symbol = "bpf-output",
+ .alias = "",
+ },
};
#define __PERF_EVENT_FIELD(config, name) \
@@ -1879,7 +1883,7 @@
for (i = 0; i < max; i++, syms++) {
- if (event_glob != NULL &&
+ if (event_glob != NULL && syms->symbol != NULL &&
!(strglobmatch(syms->symbol, event_glob) ||
(syms->alias && strglobmatch(syms->alias, event_glob))))
continue;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 03875f9..93996ec 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2326,8 +2326,11 @@
goto out;
if (!allow_suffix) {
- pr_warning("Error: event \"%s\" already exists. "
- "(Use -f to force duplicates.)\n", buf);
+ pr_warning("Error: event \"%s\" already exists.\n"
+ " Hint: Remove existing event by 'perf probe -d'\n"
+ " or force duplicates by 'perf probe -f'\n"
+ " or set 'force=yes' in BPF source.\n",
+ buf);
ret = -EEXIST;
goto out;
}
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 05012bb..2be10fb 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -654,6 +654,7 @@
static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
{
Dwarf_Attribute fb_attr;
+ Dwarf_Frame *frame = NULL;
size_t nops;
int ret;
@@ -686,11 +687,11 @@
#if _ELFUTILS_PREREQ(0, 142)
} else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
pf->cfi != NULL) {
- Dwarf_Frame *frame;
if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 ||
dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) {
pr_warning("Failed to get call frame on 0x%jx\n",
(uintmax_t)pf->addr);
+ free(frame);
return -ENOENT;
}
#endif
@@ -699,7 +700,8 @@
/* Call finder's callback handler */
ret = pf->callback(sc_die, pf);
- /* *pf->fb_ops will be cached in libdw. Don't free it. */
+ /* Since *pf->fb_ops can be a part of frame. we should free it here. */
+ free(frame);
pf->fb_ops = NULL;
return ret;
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index fc8781d..7f7e072 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -342,22 +342,6 @@
return s;
}
-/**
- * memdup - duplicate region of memory
- * @src: memory region to duplicate
- * @len: memory region length
- */
-void *memdup(const void *src, size_t len)
-{
- void *p;
-
- p = malloc(len);
- if (p)
- memcpy(p, src, len);
-
- return p;
-}
-
char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints)
{
/*
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 475d88d..53f1996 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1042,6 +1042,8 @@
}
curr_dso->symtab_type = dso->symtab_type;
map_groups__insert(kmaps, curr_map);
+ /* kmaps already got it */
+ map__put(curr_map);
dsos__add(&map->groups->machine->dsos, curr_dso);
dso__set_loaded(curr_dso, map->type);
} else
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index cd08027..d51abd2 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1860,24 +1860,44 @@
zfree(&vmlinux_path);
}
+static const char * const vmlinux_paths[] = {
+ "vmlinux",
+ "/boot/vmlinux"
+};
+
+static const char * const vmlinux_paths_upd[] = {
+ "/boot/vmlinux-%s",
+ "/usr/lib/debug/boot/vmlinux-%s",
+ "/lib/modules/%s/build/vmlinux",
+ "/usr/lib/debug/lib/modules/%s/vmlinux",
+ "/usr/lib/debug/boot/vmlinux-%s.debug"
+};
+
+static int vmlinux_path__add(const char *new_entry)
+{
+ vmlinux_path[vmlinux_path__nr_entries] = strdup(new_entry);
+ if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
+ return -1;
+ ++vmlinux_path__nr_entries;
+
+ return 0;
+}
+
static int vmlinux_path__init(struct perf_env *env)
{
struct utsname uts;
char bf[PATH_MAX];
char *kernel_version;
+ unsigned int i;
- vmlinux_path = malloc(sizeof(char *) * 6);
+ vmlinux_path = malloc(sizeof(char *) * (ARRAY_SIZE(vmlinux_paths) +
+ ARRAY_SIZE(vmlinux_paths_upd)));
if (vmlinux_path == NULL)
return -1;
- vmlinux_path[vmlinux_path__nr_entries] = strdup("vmlinux");
- if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
- goto out_fail;
- ++vmlinux_path__nr_entries;
- vmlinux_path[vmlinux_path__nr_entries] = strdup("/boot/vmlinux");
- if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
- goto out_fail;
- ++vmlinux_path__nr_entries;
+ for (i = 0; i < ARRAY_SIZE(vmlinux_paths); i++)
+ if (vmlinux_path__add(vmlinux_paths[i]) < 0)
+ goto out_fail;
/* only try kernel version if no symfs was given */
if (symbol_conf.symfs[0] != 0)
@@ -1892,28 +1912,11 @@
kernel_version = uts.release;
}
- snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", kernel_version);
- vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
- if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
- goto out_fail;
- ++vmlinux_path__nr_entries;
- snprintf(bf, sizeof(bf), "/usr/lib/debug/boot/vmlinux-%s",
- kernel_version);
- vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
- if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
- goto out_fail;
- ++vmlinux_path__nr_entries;
- snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", kernel_version);
- vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
- if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
- goto out_fail;
- ++vmlinux_path__nr_entries;
- snprintf(bf, sizeof(bf), "/usr/lib/debug/lib/modules/%s/vmlinux",
- kernel_version);
- vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
- if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
- goto out_fail;
- ++vmlinux_path__nr_entries;
+ for (i = 0; i < ARRAY_SIZE(vmlinux_paths_upd); i++) {
+ snprintf(bf, sizeof(bf), vmlinux_paths_upd[i], kernel_version);
+ if (vmlinux_path__add(bf) < 0)
+ goto out_fail;
+ }
return 0;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index dcd786e..857f707 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -108,7 +108,8 @@
show_hist_headers,
branch_callstack,
has_filter,
- show_ref_callgraph;
+ show_ref_callgraph,
+ hide_unresolved;
const char *vmlinux_name,
*kallsyms_name,
*source_prefix,
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 2dcfe9a..db8142b 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -11,6 +11,7 @@
#include <linux/types.h>
#include "event.h"
#include "perf_regs.h"
+#include "callchain.h"
static char *debuginfo_path;
@@ -52,25 +53,28 @@
return __report_module(&al, ip, ui);
}
+/*
+ * Store all entries within entries array,
+ * we will process it after we finish unwind.
+ */
static int entry(u64 ip, struct unwind_info *ui)
{
- struct unwind_entry e;
+ struct unwind_entry *e = &ui->entries[ui->idx++];
struct addr_location al;
if (__report_module(&al, ip, ui))
return -1;
- e.ip = ip;
- e.map = al.map;
- e.sym = al.sym;
+ e->ip = ip;
+ e->map = al.map;
+ e->sym = al.sym;
pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
al.sym ? al.sym->name : "''",
ip,
al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
-
- return ui->cb(&e, ui->arg);
+ return 0;
}
static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
@@ -168,7 +172,7 @@
struct perf_sample *data,
int max_stack)
{
- struct unwind_info ui = {
+ struct unwind_info *ui, ui_buf = {
.sample = data,
.thread = thread,
.machine = thread->mg->machine,
@@ -177,35 +181,54 @@
.max_stack = max_stack,
};
Dwarf_Word ip;
- int err = -EINVAL;
+ int err = -EINVAL, i;
if (!data->user_regs.regs)
return -EINVAL;
- ui.dwfl = dwfl_begin(&offline_callbacks);
- if (!ui.dwfl)
+ ui = zalloc(sizeof(ui_buf) + sizeof(ui_buf.entries[0]) * max_stack);
+ if (!ui)
+ return -ENOMEM;
+
+ *ui = ui_buf;
+
+ ui->dwfl = dwfl_begin(&offline_callbacks);
+ if (!ui->dwfl)
goto out;
err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
if (err)
goto out;
- err = report_module(ip, &ui);
+ err = report_module(ip, ui);
if (err)
goto out;
- if (!dwfl_attach_state(ui.dwfl, EM_NONE, thread->tid, &callbacks, &ui))
+ if (!dwfl_attach_state(ui->dwfl, EM_NONE, thread->tid, &callbacks, ui))
goto out;
- err = dwfl_getthread_frames(ui.dwfl, thread->tid, frame_callback, &ui);
+ err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui);
- if (err && !ui.max_stack)
+ if (err && !ui->max_stack)
err = 0;
+ /*
+ * Display what we got based on the order setup.
+ */
+ for (i = 0; i < ui->idx && !err; i++) {
+ int j = i;
+
+ if (callchain_param.order == ORDER_CALLER)
+ j = ui->idx - i - 1;
+
+ err = ui->entries[j].ip ? ui->cb(&ui->entries[j], ui->arg) : 0;
+ }
+
out:
if (err)
pr_debug("unwind: failed with '%s'\n", dwfl_errmsg(-1));
- dwfl_end(ui.dwfl);
+ dwfl_end(ui->dwfl);
+ free(ui);
return 0;
}
diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h
index 417a142..5832866 100644
--- a/tools/perf/util/unwind-libdw.h
+++ b/tools/perf/util/unwind-libdw.h
@@ -16,6 +16,8 @@
unwind_entry_cb_t cb;
void *arg;
int max_stack;
+ int idx;
+ struct unwind_entry entries[];
};
#endif /* __PERF_UNWIND_LIBDW_H */
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index c83832b..3c258a0 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -614,23 +614,48 @@
static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
void *arg, int max_stack)
{
+ u64 val;
+ unw_word_t ips[max_stack];
unw_addr_space_t addr_space;
unw_cursor_t c;
- int ret;
+ int ret, i = 0;
- addr_space = thread__priv(ui->thread);
- if (addr_space == NULL)
- return -1;
-
- ret = unw_init_remote(&c, addr_space, ui);
+ ret = perf_reg_value(&val, &ui->sample->user_regs, PERF_REG_IP);
if (ret)
- display_error(ret);
+ return ret;
- while (!ret && (unw_step(&c) > 0) && max_stack--) {
- unw_word_t ip;
+ ips[i++] = (unw_word_t) val;
- unw_get_reg(&c, UNW_REG_IP, &ip);
- ret = ip ? entry(ip, ui->thread, cb, arg) : 0;
+ /*
+ * If we need more than one entry, do the DWARF
+ * unwind itself.
+ */
+ if (max_stack - 1 > 0) {
+ addr_space = thread__priv(ui->thread);
+ if (addr_space == NULL)
+ return -1;
+
+ ret = unw_init_remote(&c, addr_space, ui);
+ if (ret)
+ display_error(ret);
+
+ while (!ret && (unw_step(&c) > 0) && i < max_stack) {
+ unw_get_reg(&c, UNW_REG_IP, &ips[i]);
+ ++i;
+ }
+
+ max_stack = i;
+ }
+
+ /*
+ * Display what we got based on the order setup.
+ */
+ for (i = 0; i < max_stack && !ret; i++) {
+ int j = i;
+
+ if (callchain_param.order == ORDER_CALLER)
+ j = max_stack - i - 1;
+ ret = ips[j] ? entry(ips[j], ui->thread, cb, arg) : 0;
}
return ret;
@@ -640,24 +665,17 @@
struct thread *thread,
struct perf_sample *data, int max_stack)
{
- u64 ip;
struct unwind_info ui = {
.sample = data,
.thread = thread,
.machine = thread->mg->machine,
};
- int ret;
if (!data->user_regs.regs)
return -EINVAL;
- ret = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
- if (ret)
- return ret;
+ if (max_stack <= 0)
+ return -EINVAL;
- ret = entry(ip, thread, cb, arg);
- if (ret)
- return -ENOMEM;
-
- return --max_stack > 0 ? get_entries(&ui, cb, arg, max_stack) : 0;
+ return get_entries(&ui, cb, arg, max_stack);
}
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 47b1e36..75759ae 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -21,7 +21,8 @@
.mode = CHAIN_GRAPH_ABS,
.min_percent = 0.5,
.order = ORDER_CALLEE,
- .key = CCKEY_FUNCTION
+ .key = CCKEY_FUNCTION,
+ .value = CCVAL_PERCENT,
};
/*